Merge branch 'timers/urgent' into x86/xen
Conflicts:
arch/x86/kernel/process_32.c
arch/x86/kernel/process_64.c
Manual merge:
arch/x86/kernel/smpboot.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1c7d39f..9983bc3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -344,31 +344,15 @@
/*
* The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6, unfortunately, that's not true in practice because
+ * family >= 6; unfortunately, that's not true in practice because
* of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect. Hence, probe for it based on first
- * principles.
+ * are not easy to detect. In the latter case it doesn't even *fail*
+ * reliably, so probing for it doesn't even work. Disable it completely
+ * unless we can find a reliable way to detect all the broken cases.
*/
static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
{
- const u32 nopl_signature = 0x888c53b1; /* Random number */
- u32 has_nopl = nopl_signature;
-
clear_cpu_cap(c, X86_FEATURE_NOPL);
- if (c->x86 >= 6) {
- asm volatile("\n"
- "1: .byte 0x0f,0x1f,0xc0\n" /* nopl %eax */
- "2:\n"
- " .section .fixup,\"ax\"\n"
- "3: xor %0,%0\n"
- " jmp 2b\n"
- " .previous\n"
- _ASM_EXTABLE(1b,3b)
- : "+a" (has_nopl));
-
- if (has_nopl == nopl_signature)
- set_cpu_cap(c, X86_FEATURE_NOPL);
- }
}
static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index f2d43bc..ff7d3b0 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -139,6 +139,7 @@
if (PageHighMem(pg)) {
data = ioremap_cache(pa_data, sizeof(*data));
if (!data) {
+ kfree(node);
error = -ENXIO;
goto err_dir;
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7fc4d5b..876e918 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -246,6 +246,14 @@
return 1;
}
+static cpumask_t c1e_mask = CPU_MASK_NONE;
+static int c1e_detected;
+
+void c1e_remove_cpu(int cpu)
+{
+ cpu_clear(cpu, c1e_mask);
+}
+
/*
* C1E aware idle routine. We check for C1E active in the interrupt
* pending message MSR. If we detect C1E, then we handle it the same
@@ -253,9 +261,6 @@
*/
static void c1e_idle(void)
{
- static cpumask_t c1e_mask = CPU_MASK_NONE;
- static int c1e_detected;
-
if (need_resched())
return;
@@ -265,8 +270,10 @@
rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
if (lo & K8_INTP_C1E_ACTIVE_MASK) {
c1e_detected = 1;
- mark_tsc_unstable("TSC halt in C1E");
- printk(KERN_INFO "System has C1E enabled\n");
+ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+ mark_tsc_unstable("TSC halt in AMD C1E");
+ printk(KERN_INFO "System has AMD C1E enabled\n");
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E);
}
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 362d4e7..9838f25 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -670,6 +670,10 @@
parse_early_param();
+#ifdef CONFIG_X86_64
+ check_efer();
+#endif
+
#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
/*
* Must be before kernel pagetables are setup
@@ -738,7 +742,6 @@
#else
num_physpages = max_pfn;
- check_efer();
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 66b04e5..06f1407 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -52,6 +52,7 @@
#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
+#include <asm/idle.h>
#include <asm/smp.h>
#include <asm/trampoline.h>
#include <asm/cpu.h>
@@ -1414,6 +1415,7 @@
idle_task_exit();
reset_lazy_tlbstate();
irq_ctx_exit(raw_smp_processor_id());
+ c1e_remove_cpu(raw_smp_processor_id());
mb();
/* Ack it */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 0bfe2bd..3da2508 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -711,6 +711,10 @@
u64 *spte;
int young = 0;
+ /* always return old for EPT */
+ if (!shadow_accessed_mask)
+ return 0;
+
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
int _young;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e2ee264..8233b86 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -62,6 +62,7 @@
module_param(npt, int, S_IRUGO);
static void kvm_reput_irq(struct vcpu_svm *svm);
+static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
{
@@ -878,6 +879,10 @@
static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+ unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
+
+ if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
+ force_new_asid(vcpu);
vcpu->arch.cr4 = cr4;
if (!npt_enabled)
@@ -1027,6 +1032,13 @@
KVMTRACE_3D(TDP_FAULT, &svm->vcpu, error_code,
(u32)fault_address, (u32)(fault_address >> 32),
handler);
+ /*
+ * FIXME: Tis shouldn't be necessary here, but there is a flush
+ * missing in the MMU code. Until we find this bug, flush the
+ * complete TLB here on an NPF
+ */
+ if (npt_enabled)
+ svm_flush_tlb(&svm->vcpu);
if (event_injection)
kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2a69773..7041cc5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3301,8 +3301,7 @@
kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
VMX_EPT_WRITABLE_MASK |
VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
- kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK,
- VMX_EPT_FAKE_DIRTY_MASK, 0ull,
+ kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
VMX_EPT_EXECUTABLE_MASK);
kvm_enable_tdp();
} else
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 425a134..23e8373 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -370,8 +370,6 @@
#define VMX_EPT_READABLE_MASK 0x1ull
#define VMX_EPT_WRITABLE_MASK 0x2ull
#define VMX_EPT_EXECUTABLE_MASK 0x4ull
-#define VMX_EPT_FAKE_ACCESSED_MASK (1ull << 62)
-#define VMX_EPT_FAKE_DIRTY_MASK (1ull << 63)
#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index d37f293..60ec1d0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -458,11 +458,7 @@
{
pgd_t *pgd_base = swapper_pg_dir;
- paravirt_pagetable_setup_start(pgd_base);
-
permanent_kmaps_init(pgd_base);
-
- paravirt_pagetable_setup_done(pgd_base);
}
#ifdef CONFIG_ACPI_SLEEP
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b6acc3a..d679010 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -42,7 +42,7 @@
e820.nr_map = 0;
- e820_add_region(0, PFN_PHYS(max_pfn), E820_RAM);
+ e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
/*
* Even though this is normal, usable memory under Xen, reserve