Merge remote-tracking branch 'upstream/master' into queue

Merge reason:

From: Alexander Graf <agraf@suse.de>

"Just recently this really important patch got pulled into Linus' tree for 3.9:

commit 1674400aaee5b466c595a8fc310488263ce888c7
Author: Anton Blanchard <anton <at> samba.org>
Date:   Tue Mar 12 01:51:51 2013 +0000

Without that commit, I can not boot my G5, thus I can't run automated tests on it against my queue.

Could you please merge kvm/next against linus/master, so that I can base my trees against that?"

* upstream/master: (653 commits)
  PCI: Use ROM images from firmware only if no other ROM source available
  sparc: remove unused "config BITS"
  sparc: delete "if !ULTRA_HAS_POPULATION_COUNT"
  KVM: Fix bounds checking in ioapic indirect register reads (CVE-2013-1798)
  KVM: x86: Convert MSR_KVM_SYSTEM_TIME to use gfn_to_hva_cache functions (CVE-2013-1797)
  KVM: x86: fix for buffer overflow in handling of MSR_KVM_SYSTEM_TIME (CVE-2013-1796)
  arm64: Kconfig.debug: Remove unused CONFIG_DEBUG_ERRORS
  arm64: Do not select GENERIC_HARDIRQS_NO_DEPRECATED
  inet: limit length of fragment queue hash table bucket lists
  qeth: Fix scatter-gather regression
  qeth: Fix invalid router settings handling
  qeth: delay feature trace
  sgy-cts1000: Remove __dev* attributes
  KVM: x86: fix deadlock in clock-in-progress request handling
  KVM: allow host header to be included even for !CONFIG_KVM
  hwmon: (lm75) Fix tcn75 prefix
  hwmon: (lm75.h) Update header inclusion
  MAINTAINERS: Remove Mark M. Hoffman
  xfs: ensure we capture IO errors correctly
  xfs: fix xfs_iomap_eof_prealloc_initial_size type
  ...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

10 files changed, 82 insertions, 45 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a4f24f5b1218..70c0f3da0476 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -112,7 +112,7 @@ config X86
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
 	select HAVE_IRQ_TIME_ACCOUNTING
-	select HAVE_VIRT_TO_BUS
+	select VIRT_TO_BUS
 	select MODULES_USE_ELF_REL if X86_32
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 5b5e9cb774b5..653668d140f9 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -14,13 +14,29 @@
  * analysis of kexec-tools; if other broken bootloaders initialize a
  * different set of fields we will need to figure out how to disambiguate.
  *
+ * Note: efi_info is commonly left uninitialized, but that field has a
+ * private magic, so it is better to leave it unchanged.
  */
 static void sanitize_boot_params(struct boot_params *boot_params)
 {
+	/* 
+	 * IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear
+	 * this field.  The purpose of this field is to guarantee
+	 * compliance with the x86 boot spec located in
+	 * Documentation/x86/boot.txt .  That spec says that the
+	 * *whole* structure should be cleared, after which only the
+	 * portion defined by struct setup_header (boot_params->hdr)
+	 * should be copied in.
+	 *
+	 * If you're having an issue because the sentinel is set, you
+	 * need to change the whole structure to be cleared, not this
+	 * (or any other) individual field, or you will soon have
+	 * problems again.
+	 */
 	if (boot_params->sentinel) {
-		/*fields in boot_params are not valid, clear them */
+		/* fields in boot_params are left uninitialized, clear them */
 		memset(&boot_params->olpc_ofw_header, 0,
-		       (char *)&boot_params->alt_mem_k -
+		       (char *)&boot_params->efi_info -
 			(char *)&boot_params->olpc_ofw_header);
 		memset(&boot_params->kbd_status, 0,
 		       (char *)&boot_params->hdr -
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3f205c6cde59..b5a64621d5af 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -414,8 +414,8 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
+	struct gfn_to_hva_cache pv_time;
+	bool pv_time_enabled;
 	/* set guest stopped flag in pvclock flags field */
 	bool pvclock_set_guest_stopped_request;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a4f2ee..b05a575d56f4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -729,3 +729,13 @@ void intel_ds_init(void)
 		}
 	}
 }
+
+void perf_restore_debug_store(void)
+{
+	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 84d32855f65c..90d8cc930f5e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -171,9 +171,15 @@ static struct resource bss_resource = {
 
 #ifdef CONFIG_X86_32
 /* cpu data as detected by the assembly code in head.S */
-struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 new_cpu_data __cpuinitdata = {
+	.wp_works_ok = -1,
+	.fdiv_bug = -1,
+};
 /* common cpu data for all cpus */
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+struct cpuinfo_x86 boot_cpu_data __read_mostly = {
+	.wp_works_ok = -1,
+	.fdiv_bug = -1,
+};
 EXPORT_SYMBOL(boot_cpu_data);
 
 unsigned int def_to_bigsmp;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a6ceaedc396a..9f190a2a00e9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1365,9 +1365,8 @@ static inline void mwait_play_dead(void)
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int highest_cstate = 0;
 	unsigned int highest_subcstate = 0;
-	int i;
 	void *mwait_ptr;
-	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
+	int i;
 
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d3c478742e2c..2aaba814f1c8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1411,25 +1411,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	unsigned long flags, this_tsc_khz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
-	void *shared_kaddr;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp, host_tsc;
-	struct pvclock_vcpu_time_info *guest_hv_clock;
+	struct pvclock_vcpu_time_info guest_hv_clock;
 	u8 pvclock_flags;
 	bool use_master_clock;
 
 	kernel_ns = 0;
 	host_tsc = 0;
 
-	/* Keep irq disabled to prevent changes to the clock */
-	local_irq_save(flags);
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
-	if (unlikely(this_tsc_khz == 0)) {
-		local_irq_restore(flags);
-		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
-		return 1;
-	}
-
 	/*
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
@@ -1441,6 +1431,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		kernel_ns = ka->master_kernel_ns;
 	}
 	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	/* Keep irq disabled to prevent changes to the clock */
+	local_irq_save(flags);
+	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	if (unlikely(this_tsc_khz == 0)) {
+		local_irq_restore(flags);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
+		return 1;
+	}
 	if (!use_master_clock) {
 		host_tsc = native_read_tsc();
 		kernel_ns = get_kernel_ns();
@@ -1468,7 +1467,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->time_page)
+	if (!vcpu->pv_time_enabled)
 		return 0;
 
 	/*
@@ -1530,12 +1529,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	vcpu->hv_clock.version += 2;
 
-	shared_kaddr = kmap_atomic(vcpu->time_page);
-
-	guest_hv_clock = shared_kaddr + vcpu->time_offset;
+	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+		&guest_hv_clock, sizeof(guest_hv_clock))))
+		return 0;
 
 	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-	pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+	pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
 
 	if (vcpu->pvclock_set_guest_stopped_request) {
 		pvclock_flags |= PVCLOCK_GUEST_STOPPED;
@@ -1548,12 +1547,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	vcpu->hv_clock.flags = pvclock_flags;
 
-	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-	       sizeof(vcpu->hv_clock));
-
-	kunmap_atomic(shared_kaddr);
-
-	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
 	return 0;
 }
 
@@ -1842,10 +1838,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	vcpu->arch.pv_time_enabled = false;
 }
 
 static void accumulate_steal_time(struct kvm_vcpu *vcpu)
@@ -1952,6 +1945,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
+		u64 gpa_offset;
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
@@ -1961,14 +1955,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		/* ...but clean it before doing the actual write */
-		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.time_page =
-				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		/* Check that the address is 32-byte aligned. */
+		if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
+			break;
 
-		if (is_error_page(vcpu->arch.time_page))
-			vcpu->arch.time_page = NULL;
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		     &vcpu->arch.pv_time, data & ~1ULL))
+			vcpu->arch.pv_time_enabled = false;
+		else
+			vcpu->arch.pv_time_enabled = true;
 
 		break;
 	}
@@ -2972,7 +2969,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
  */
 static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->arch.time_page)
+	if (!vcpu->arch.pv_time_enabled)
 		return -EINVAL;
 	vcpu->arch.pvclock_set_guest_stopped_request = true;
 	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -6740,6 +6737,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_wbinvd_dirty_mask;
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
+	vcpu->arch.pv_time_enabled = false;
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4903a03ae876..59b7fc453277 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -410,9 +410,8 @@ void __init init_mem_mapping(void)
 	/* the ISA range is always mapped regardless of memory holes */
 	init_memory_mapping(0, ISA_END_ADDRESS);
 
-	/* xen has big range in reserved near end of ram, skip it at first */
-	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE,
-			 PAGE_SIZE);
+	/* xen has big range in reserved near end of ram, skip it at first.*/
+	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE);
 	real_end = addr + PMD_SIZE;
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2610bd93c896..657438858e83 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -563,6 +563,13 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 	if (base > __pa(high_memory-1))
 		return 0;
 
+	/*
+	 * some areas in the middle of the kernel identity range
+	 * are not mapped, like the PCI space.
+	 */
+	if (!page_is_ram(base >> PAGE_SHIFT))
+		return 0;
+
 	id_sz = (__pa(high_memory-1) <= base + size) ?
 				__pa(high_memory) - base :
 				size;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 120cee1c3f8d..3c68768d7a75 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -228,6 +229,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	do_fpu_end();
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
+	perf_restore_debug_store();
 }
 
 /* Needed by apm.c */