From bf998156d24bcb127318ad5bf531ac3bdfcd6449 Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Mon, 31 May 2010 14:28:19 +0800
Subject: KVM: Avoid killing userspace through guest SRAO MCE on unmapped pages

In common cases, guest SRAO MCE will cause corresponding poisoned page
be un-mapped and SIGBUS be sent to QEMU-KVM, then QEMU-KVM will relay
the MCE to guest OS.

But it is reported that if the poisoned page is accessed in guest
after unmapping and before MCE is relayed to guest OS, userspace will
be killed.

The reason is as follows. Because poisoned page has been un-mapped,
guest access will cause guest exit and kvm_mmu_page_fault will be
called. kvm_mmu_page_fault can not get the poisoned page for fault
address, so kernel and user space MMIO processing is tried in turn. In
user MMIO processing, poisoned page is accessed again, then userspace
is killed by force_sig_info.

To fix the bug, kvm_mmu_page_fault send HWPOISON signal to QEMU-KVM
and do not try kernel and user space MMIO processing for poisoned
page.

[xiao: fix warning introduced by avi]

Reported-by: Max Asbock <masbock@linux.vnet.ibm.com>
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 include/linux/kvm_host.h | 1 +
 include/linux/mm.h       | 8 ++++++++
 2 files changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7cb116afa1cd..a0e019769f5d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -266,6 +266,7 @@ extern pfn_t bad_pfn;
 
 int is_error_page(struct page *page);
 int is_error_pfn(pfn_t pfn);
+int is_hwpoison_pfn(pfn_t pfn);
 int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a2b48041b910..7a9ab7db1975 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1465,6 +1465,14 @@ extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
 extern atomic_long_t mce_bad_pages;
 extern int soft_offline_page(struct page *page, int flags);
+#ifdef CONFIG_MEMORY_FAILURE
+int is_hwpoison_address(unsigned long addr);
+#else
+static inline int is_hwpoison_address(unsigned long addr)
+{
+	return 0;
+}
+#endif
 
 extern void dump_page(struct page *page);
 
-- 
cgit v1.2.3


From d94e1dc9af60e3431a586c3edfbe42d8a0d3932b Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 3 May 2010 16:54:48 +0300
Subject: KVM: Get rid of KVM_REQ_KICK

KVM_REQ_KICK poisons vcpu->requests by having a bit set during normal
operation.  This causes the fast path check for a clear vcpu->requests
to fail all the time, triggering tons of atomic operations.

Fix by replacing KVM_REQ_KICK with a vcpu->guest_mode atomic.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/x86.c       | 17 ++++++++++-------
 include/linux/kvm_host.h |  1 +
 2 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 63c87adcec48..fc5611b4007f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4604,13 +4604,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
 
-	local_irq_disable();
+	atomic_set(&vcpu->guest_mode, 1);
+	smp_wmb();
 
-	clear_bit(KVM_REQ_KICK, &vcpu->requests);
-	smp_mb__after_clear_bit();
+	local_irq_disable();
 
-	if (vcpu->requests || need_resched() || signal_pending(current)) {
-		set_bit(KVM_REQ_KICK, &vcpu->requests);
+	if (!atomic_read(&vcpu->guest_mode) || vcpu->requests
+	    || need_resched() || signal_pending(current)) {
+		atomic_set(&vcpu->guest_mode, 0);
+		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
 		r = 1;
@@ -4655,7 +4657,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (hw_breakpoint_active())
 		hw_breakpoint_restore();
 
-	set_bit(KVM_REQ_KICK, &vcpu->requests);
+	atomic_set(&vcpu->guest_mode, 0);
+	smp_wmb();
 	local_irq_enable();
 
 	++vcpu->stat.exits;
@@ -5580,7 +5583,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 
 	me = get_cpu();
 	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (!test_and_set_bit(KVM_REQ_KICK, &vcpu->requests))
+		if (atomic_xchg(&vcpu->guest_mode, 0))
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a0e019769f5d..2c62319727ef 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -81,6 +81,7 @@ struct kvm_vcpu {
 	int vcpu_id;
 	struct mutex mutex;
 	int   cpu;
+	atomic_t guest_mode;
 	struct kvm_run *run;
 	unsigned long requests;
 	unsigned long guest_debug;
-- 
cgit v1.2.3


From 2acf923e38fb6a4ce0c57115decbb38d334902ac Mon Sep 17 00:00:00 2001
From: Dexuan Cui <dexuan.cui@intel.com>
Date: Thu, 10 Jun 2010 11:27:12 +0800
Subject: KVM: VMX: Enable XSAVE/XRSTOR for guest

This patch enable guest to use XSAVE/XRSTOR instructions.

We assume that host_xcr0 would use all possible bits that OS supported.

And we loaded xcr0 in the same way we handled fpu - do it as late as we can.

Signed-off-by: Dexuan Cui <dexuan.cui@intel.com>
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   2 +
 arch/x86/include/asm/vmx.h      |   1 +
 arch/x86/kvm/kvm_cache_regs.h   |   6 ++
 arch/x86/kvm/vmx.c              |  13 ++++
 arch/x86/kvm/x86.c              | 130 +++++++++++++++++++++++++++++++++++++---
 include/linux/kvm_host.h        |   2 +-
 6 files changed, 146 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0cd0f2923af5..91631b8b2090 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -302,6 +302,7 @@ struct kvm_vcpu_arch {
 	} update_pte;
 
 	struct fpu guest_fpu;
+	u64 xcr0;
 
 	gva_t mmio_fault_cr2;
 	struct kvm_pio_request pio;
@@ -605,6 +606,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
+int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 96a5886d384e..9f0cbd987d50 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -267,6 +267,7 @@ enum vmcs_field {
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD		54
+#define EXIT_REASON_XSETBV		55
 
 /*
  * Interruption-information format
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index d2a98f8f9af5..6491ac8e755b 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -71,4 +71,10 @@ static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
 	return kvm_read_cr4_bits(vcpu, ~0UL);
 }
 
+static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
+{
+	return (kvm_register_read(vcpu, VCPU_REGS_RAX) & -1u)
+		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
+}
+
 #endif
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 26ba61d6af8c..864a1b6d155a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -37,6 +37,8 @@
 #include <asm/vmx.h>
 #include <asm/virtext.h>
 #include <asm/mce.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
 
 #include "trace.h"
 
@@ -3390,6 +3392,16 @@ static int handle_wbinvd(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_xsetbv(struct kvm_vcpu *vcpu)
+{
+	u64 new_bv = kvm_read_edx_eax(vcpu);
+	u32 index = kvm_register_read(vcpu, VCPU_REGS_RCX);
+
+	if (kvm_set_xcr(vcpu, index, new_bv) == 0)
+		skip_emulated_instruction(vcpu);
+	return 1;
+}
+
 static int handle_apic_access(struct kvm_vcpu *vcpu)
 {
 	return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
@@ -3668,6 +3680,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
+	[EXIT_REASON_XSETBV]                  = handle_xsetbv,
 	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
 	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
 	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b08c0052e332..b5e644701cc1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -65,6 +65,7 @@
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE	\
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR	\
+			  | X86_CR4_OSXSAVE \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
@@ -150,6 +151,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+u64 __read_mostly host_xcr0;
+
+static inline u32 bit(int bitno)
+{
+	return 1 << (bitno & 31);
+}
+
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
@@ -474,6 +482,61 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
+int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
+{
+	u64 xcr0;
+
+	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
+	if (index != XCR_XFEATURE_ENABLED_MASK)
+		return 1;
+	xcr0 = xcr;
+	if (kvm_x86_ops->get_cpl(vcpu) != 0)
+		return 1;
+	if (!(xcr0 & XSTATE_FP))
+		return 1;
+	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
+		return 1;
+	if (xcr0 & ~host_xcr0)
+		return 1;
+	vcpu->arch.xcr0 = xcr0;
+	vcpu->guest_xcr0_loaded = 0;
+	return 0;
+}
+
+int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
+{
+	if (__kvm_set_xcr(vcpu, index, xcr)) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_set_xcr);
+
+static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
+}
+
+static void update_cpuid(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	if (!best)
+		return;
+
+	/* Update OSXSAVE bit */
+	if (cpu_has_xsave && best->function == 0x1) {
+		best->ecx &= ~(bit(X86_FEATURE_OSXSAVE));
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
+			best->ecx |= bit(X86_FEATURE_OSXSAVE);
+	}
+}
+
 int __kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
@@ -482,6 +545,9 @@ int __kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
+		return 1;
+
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
@@ -498,6 +564,9 @@ int __kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if ((cr4 ^ old_cr4) & pdptr_bits)
 		kvm_mmu_reset_context(vcpu);
 
+	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
+		update_cpuid(vcpu);
+
 	return 0;
 }
 
@@ -666,11 +735,6 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 }
 EXPORT_SYMBOL_GPL(kvm_get_dr);
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 /*
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
@@ -1814,6 +1878,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 	r = 0;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	update_cpuid(vcpu);
 
 out_free:
 	vfree(cpuid_entries);
@@ -1837,6 +1902,7 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 	vcpu->arch.cpuid_nent = cpuid->nent;
 	kvm_apic_set_version(vcpu);
 	kvm_x86_ops->cpuid_update(vcpu);
+	update_cpuid(vcpu);
 	return 0;
 
 out:
@@ -1917,7 +1983,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
 		0 /* Reserved, DCA */ | F(XMM4_1) |
 		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
-		0 /* Reserved, XSAVE, OSXSAVE */;
+		0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */;
 	/* cpuid 0x80000001.ecx */
 	const u32 kvm_supported_word6_x86_features =
 		F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
@@ -1932,7 +1998,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	switch (function) {
 	case 0:
-		entry->eax = min(entry->eax, (u32)0xb);
+		entry->eax = min(entry->eax, (u32)0xd);
 		break;
 	case 1:
 		entry->edx &= kvm_supported_word0_x86_features;
@@ -1990,6 +2056,20 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
+	case 0xd: {
+		int i;
+
+		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+		for (i = 1; *nent < maxnent; ++i) {
+			if (entry[i - 1].eax == 0 && i != 2)
+				break;
+			do_cpuid_1_ent(&entry[i], function, i);
+			entry[i].flags |=
+			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+			++*nent;
+		}
+		break;
+	}
 	case KVM_CPUID_SIGNATURE: {
 		char signature[12] = "KVMKVMKVM\0\0";
 		u32 *sigptr = (u32 *)signature;
@@ -4125,6 +4205,9 @@ int kvm_arch_init(void *opaque)
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);
 
+	if (cpu_has_xsave)
+		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+
 	return 0;
 
 out:
@@ -4523,6 +4606,25 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
+			!vcpu->guest_xcr0_loaded) {
+		/* kvm_set_xcr() also depends on this */
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
+		vcpu->guest_xcr0_loaded = 1;
+	}
+}
+
+static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->guest_xcr0_loaded) {
+		if (vcpu->arch.xcr0 != host_xcr0)
+			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
+		vcpu->guest_xcr0_loaded = 0;
+	}
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -4568,6 +4670,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
+	kvm_load_guest_xcr0(vcpu);
 
 	atomic_set(&vcpu->guest_mode, 1);
 	smp_wmb();
@@ -5124,6 +5227,11 @@ int fx_init(struct kvm_vcpu *vcpu)
 
 	fpu_finit(&vcpu->arch.guest_fpu);
 
+	/*
+	 * Ensure guest xcr0 is valid for loading
+	 */
+	vcpu->arch.xcr0 = XSTATE_FP;
+
 	vcpu->arch.cr0 |= X86_CR0_ET;
 
 	return 0;
@@ -5140,6 +5248,12 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_fpu_loaded)
 		return;
 
+	/*
+	 * Restore all possible states in the guest,
+	 * and assume host would use all available bits.
+	 * Guest xcr0 would be loaded later.
+	 */
+	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	unlazy_fpu(current);
 	fpu_restore_checking(&vcpu->arch.guest_fpu);
@@ -5148,6 +5262,8 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
+	kvm_put_guest_xcr0(vcpu);
+
 	if (!vcpu->guest_fpu_loaded)
 		return;
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c62319727ef..2d96555cd4ed 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -88,7 +88,7 @@ struct kvm_vcpu {
 	int srcu_idx;
 
 	int fpu_active;
-	int guest_fpu_loaded;
+	int guest_fpu_loaded, guest_xcr0_loaded;
 	wait_queue_head_t wq;
 	int sigset_active;
 	sigset_t sigset;
-- 
cgit v1.2.3


From 2d5b5a665508c60577c1088e0405850a965b6795 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Sun, 13 Jun 2010 17:29:39 +0800
Subject: KVM: x86: XSAVE/XRSTOR live migration support

This patch enable save/restore of xsave state.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 Documentation/kvm/api.txt    |  74 +++++++++++++++++++++++
 arch/x86/include/asm/kvm.h   |  22 +++++++
 arch/x86/include/asm/xsave.h |   7 ++-
 arch/x86/kvm/x86.c           | 139 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/kvm.h          |  12 ++++
 5 files changed, 252 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 159b4efe1b0e..ffba03f55bdf 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -922,6 +922,80 @@ Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
 as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
 is vcpu 0.
 
+4.41 KVM_GET_XSAVE
+
+Capability: KVM_CAP_XSAVE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xsave (out)
+Returns: 0 on success, -1 on error
+
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+This ioctl would copy current vcpu's xsave struct to the userspace.
+
+4.42 KVM_SET_XSAVE
+
+Capability: KVM_CAP_XSAVE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xsave (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+This ioctl would copy userspace's xsave struct to the kernel.
+
+4.43 KVM_GET_XCRS
+
+Capability: KVM_CAP_XCRS
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xcrs (out)
+Returns: 0 on success, -1 on error
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
+This ioctl would copy current vcpu's xcrs to the userspace.
+
+4.44 KVM_SET_XCRS
+
+Capability: KVM_CAP_XCRS
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xcrs (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
+This ioctl would set vcpu's xcr to the value userspace specified.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index ff90055c7f0b..4d8dcbdfc120 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -22,6 +22,8 @@
 #define __KVM_HAVE_XEN_HVM
 #define __KVM_HAVE_VCPU_EVENTS
 #define __KVM_HAVE_DEBUGREGS
+#define __KVM_HAVE_XSAVE
+#define __KVM_HAVE_XCRS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -299,4 +301,24 @@ struct kvm_debugregs {
 	__u64 reserved[9];
 };
 
+/* for KVM_CAP_XSAVE */
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+#define KVM_MAX_XCRS	16
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 29ee4e4c64cf..32c36668fa7b 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -13,8 +13,11 @@
 
 #define FXSAVE_SIZE	512
 
-#define XSTATE_YMM_SIZE 256
-#define XSTATE_YMM_OFFSET (512 + 64)
+#define XSAVE_HDR_SIZE	    64
+#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE	    256
+#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /*
  * These are the features that the OS can handle currently.
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 795999e1ac19..0c8dc9614e7d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1680,6 +1680,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
+	case KVM_CAP_XSAVE:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1703,6 +1704,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MCE:
 		r = KVM_MAX_MCE_BANKS;
 		break;
+	case KVM_CAP_XCRS:
+		r = cpu_has_xsave;
+		break;
 	default:
 		r = 0;
 		break;
@@ -2355,6 +2359,77 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+					 struct kvm_xsave *guest_xsave)
+{
+	if (cpu_has_xsave)
+		memcpy(guest_xsave->region,
+			&vcpu->arch.guest_fpu.state->xsave,
+			sizeof(struct xsave_struct));
+	else {
+		memcpy(guest_xsave->region,
+			&vcpu->arch.guest_fpu.state->fxsave,
+			sizeof(struct i387_fxsave_struct));
+		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
+			XSTATE_FPSSE;
+	}
+}
+
+static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
+					struct kvm_xsave *guest_xsave)
+{
+	u64 xstate_bv =
+		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+
+	if (cpu_has_xsave)
+		memcpy(&vcpu->arch.guest_fpu.state->xsave,
+			guest_xsave->region, sizeof(struct xsave_struct));
+	else {
+		if (xstate_bv & ~XSTATE_FPSSE)
+			return -EINVAL;
+		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
+			guest_xsave->region, sizeof(struct i387_fxsave_struct));
+	}
+	return 0;
+}
+
+static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
+					struct kvm_xcrs *guest_xcrs)
+{
+	if (!cpu_has_xsave) {
+		guest_xcrs->nr_xcrs = 0;
+		return;
+	}
+
+	guest_xcrs->nr_xcrs = 1;
+	guest_xcrs->flags = 0;
+	guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
+	guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
+}
+
+static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
+				       struct kvm_xcrs *guest_xcrs)
+{
+	int i, r = 0;
+
+	if (!cpu_has_xsave)
+		return -EINVAL;
+
+	if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
+		return -EINVAL;
+
+	for (i = 0; i < guest_xcrs->nr_xcrs; i++)
+		/* Only support XCR0 currently */
+		if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
+			r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
+				guest_xcrs->xcrs[0].value);
+			break;
+		}
+	if (r)
+		r = -EINVAL;
+	return r;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -2556,6 +2631,70 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
 		break;
 	}
+	case KVM_GET_XSAVE: {
+		struct kvm_xsave *xsave;
+
+		xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!xsave)
+			break;
+
+		kvm_vcpu_ioctl_x86_get_xsave(vcpu, xsave);
+
+		r = -EFAULT;
+		if (copy_to_user(argp, xsave, sizeof(struct kvm_xsave)))
+			break;
+		r = 0;
+		break;
+	}
+	case KVM_SET_XSAVE: {
+		struct kvm_xsave *xsave;
+
+		xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!xsave)
+			break;
+
+		r = -EFAULT;
+		if (copy_from_user(xsave, argp, sizeof(struct kvm_xsave)))
+			break;
+
+		r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, xsave);
+		break;
+	}
+	case KVM_GET_XCRS: {
+		struct kvm_xcrs *xcrs;
+
+		xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!xcrs)
+			break;
+
+		kvm_vcpu_ioctl_x86_get_xcrs(vcpu, xcrs);
+
+		r = -EFAULT;
+		if (copy_to_user(argp, xcrs,
+				 sizeof(struct kvm_xcrs)))
+			break;
+		r = 0;
+		break;
+	}
+	case KVM_SET_XCRS: {
+		struct kvm_xcrs *xcrs;
+
+		xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!xcrs)
+			break;
+
+		r = -EFAULT;
+		if (copy_from_user(xcrs, argp,
+				   sizeof(struct kvm_xcrs)))
+			break;
+
+		r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, xcrs);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 23ea02253900..6fd40f540a8e 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -524,6 +524,12 @@ struct kvm_enable_cap {
 #define KVM_CAP_PPC_OSI 52
 #define KVM_CAP_PPC_UNSET_IRQ 53
 #define KVM_CAP_ENABLE_CAP 54
+#ifdef __KVM_HAVE_XSAVE
+#define KVM_CAP_XSAVE 55
+#endif
+#ifdef __KVM_HAVE_XCRS
+#define KVM_CAP_XCRS 56
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -714,6 +720,12 @@ struct kvm_clock_data {
 #define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
 #define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
 #define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)
+/* Available with KVM_CAP_XSAVE */
+#define KVM_GET_XSAVE		  _IOR(KVMIO,  0xa4, struct kvm_xsave)
+#define KVM_SET_XSAVE		  _IOW(KVMIO,  0xa5, struct kvm_xsave)
+/* Available with KVM_CAP_XCRS */
+#define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
+#define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 
-- 
cgit v1.2.3


From a1f4d39500ad8ed61825eff061debff42386ab5b Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 21 Jun 2010 11:44:20 +0300
Subject: KVM: Remove memory alias support

As advertised in feature-removal-schedule.txt.  Equivalent support is provided
by overlapping memory regions.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/feature-removal-schedule.txt |  11 ---
 Documentation/kvm/api.txt                  |  12 +--
 arch/ia64/kvm/kvm-ia64.c                   |   5 --
 arch/powerpc/kvm/powerpc.c                 |   5 --
 arch/s390/kvm/kvm-s390.c                   |   5 --
 arch/x86/include/asm/kvm_host.h            |  21 -----
 arch/x86/kvm/mmu.c                         |  17 +---
 arch/x86/kvm/paging_tmpl.h                 |   3 +-
 arch/x86/kvm/x86.c                         | 125 -----------------------------
 arch/x86/kvm/x86.h                         |   7 --
 include/linux/kvm.h                        |   1 +
 include/linux/kvm_host.h                   |   6 --
 virt/kvm/kvm_main.c                        |  18 +----
 13 files changed, 11 insertions(+), 225 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 1571c0c83dba..ad1e90dd2780 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -538,17 +538,6 @@ Who:	Jan Kiszka <jan.kiszka@web.de>
 
 ----------------------------
 
-What:	KVM memory aliases support
-When:	July 2010
-Why:	Memory aliasing support is used for speeding up guest vga access
-	through the vga windows.
-
-	Modern userspace no longer uses this feature, so it's just bitrotted
-	code and can be removed with no impact.
-Who:	Avi Kivity <avi@redhat.com>
-
-----------------------------
-
 What:	xtime, wall_to_monotonic
 When:	2.6.36+
 Files:	kernel/time/timekeeping.c include/linux/time.h
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index ffba03f55bdf..7e415943a11e 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -226,17 +226,7 @@ Type: vm ioctl
 Parameters: struct kvm_memory_alias (in)
 Returns: 0 (success), -1 (error)
 
-struct kvm_memory_alias {
-	__u32 slot;  /* this has a different namespace than memory slots */
-	__u32 flags;
-	__u64 guest_phys_addr;
-	__u64 memory_size;
-	__u64 target_phys_addr;
-};
-
-Defines a guest physical address space region as an alias to another
-region.  Useful for aliased address, for example the VGA low memory
-window. Should not be used with userspace memory.
+This ioctl is obsolete and has been removed.
 
 4.9 KVM_RUN
 
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 91760e80e268..bd510beb43af 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1946,11 +1946,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return vcpu->arch.timer_fired;
 }
 
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	return gfn;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) ||
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b5ebdfbed20b..72a4ad86ee91 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -36,11 +36,6 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	return gfn;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
 	return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 08a3b35d30be..4fe68650535c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -723,11 +723,6 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 }
 
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	return gfn;
-}
-
 static int __init kvm_s390_init(void)
 {
 	int ret;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2ec2e27a403e..a57cdeacc4d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -69,8 +69,6 @@
 
 #define IOPL_SHIFT 12
 
-#define KVM_ALIAS_SLOTS 4
-
 #define KVM_PERMILLE_MMU_PAGES 20
 #define KVM_MIN_ALLOC_MMU_PAGES 64
 #define KVM_MMU_HASH_SHIFT 10
@@ -362,24 +360,7 @@ struct kvm_vcpu_arch {
 	u64 hv_vapic;
 };
 
-struct kvm_mem_alias {
-	gfn_t base_gfn;
-	unsigned long npages;
-	gfn_t target_gfn;
-#define KVM_ALIAS_INVALID     1UL
-	unsigned long flags;
-};
-
-#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION
-
-struct kvm_mem_aliases {
-	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
-	int naliases;
-};
-
 struct kvm_arch {
-	struct kvm_mem_aliases *aliases;
-
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_alloc_mmu_pages;
@@ -655,8 +636,6 @@ void kvm_disable_tdp(void);
 int complete_pio(struct kvm_vcpu *vcpu);
 bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
-struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn);
-
 static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 {
 	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8c2f580956d9..c5501bc10106 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -434,9 +434,7 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn)
 	int *write_count;
 	int i;
 
-	gfn = unalias_gfn(kvm, gfn);
-
-	slot = gfn_to_memslot_unaliased(kvm, gfn);
+	slot = gfn_to_memslot(kvm, gfn);
 	for (i = PT_DIRECTORY_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
 		write_count   = slot_largepage_idx(gfn, slot, i);
@@ -450,8 +448,7 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
 	int *write_count;
 	int i;
 
-	gfn = unalias_gfn(kvm, gfn);
-	slot = gfn_to_memslot_unaliased(kvm, gfn);
+	slot = gfn_to_memslot(kvm, gfn);
 	for (i = PT_DIRECTORY_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
 		write_count   = slot_largepage_idx(gfn, slot, i);
@@ -467,8 +464,7 @@ static int has_wrprotected_page(struct kvm *kvm,
 	struct kvm_memory_slot *slot;
 	int *largepage_idx;
 
-	gfn = unalias_gfn(kvm, gfn);
-	slot = gfn_to_memslot_unaliased(kvm, gfn);
+	slot = gfn_to_memslot(kvm, gfn);
 	if (slot) {
 		largepage_idx = slot_largepage_idx(gfn, slot, level);
 		return *largepage_idx;
@@ -521,7 +517,6 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 
 /*
  * Take gfn and return the reverse mapping to it.
- * Note: gfn must be unaliased before this function get called
  */
 
 static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
@@ -561,7 +556,6 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	if (!is_rmap_spte(*spte))
 		return count;
-	gfn = unalias_gfn(vcpu->kvm, gfn);
 	sp = page_header(__pa(spte));
 	kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
@@ -698,7 +692,6 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn)
 	u64 *spte;
 	int i, write_protected = 0;
 
-	gfn = unalias_gfn(kvm, gfn);
 	rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL);
 
 	spte = rmap_next(kvm, rmapp, NULL);
@@ -885,7 +878,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	sp = page_header(__pa(spte));
 
-	gfn = unalias_gfn(vcpu->kvm, gfn);
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
 	kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
@@ -3510,8 +3502,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
 		if (sp->unsync)
 			continue;
 
-		gfn = unalias_gfn(vcpu->kvm, sp->gfn);
-		slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn);
+		slot = gfn_to_memslot(vcpu->kvm, sp->gfn);
 		rmapp = &slot->rmap[gfn - slot->base_gfn];
 
 		spte = rmap_next(vcpu->kvm, rmapp, NULL);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 863920f649fb..a21a86ef9e20 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -576,7 +576,6 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
- * - Alias changes zap the entire shadow cache.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			    bool clear_unsync)
@@ -611,7 +610,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			return -EINVAL;
 
 		gfn = gpte_to_gfn(gpte);
-		if (unalias_gfn(vcpu->kvm, gfn) != sp->gfns[i] ||
+		if (gfn != sp->gfns[i] ||
 		      !is_present_gpte(gpte) || !(gpte & PT_ACCESSED_MASK)) {
 			u64 nonpresent;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8e60b6c9c0b0..62596d373a49 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2740,115 +2740,6 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
 	return kvm->arch.n_alloc_mmu_pages;
 }
 
-gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn)
-{
-	int i;
-	struct kvm_mem_alias *alias;
-	struct kvm_mem_aliases *aliases;
-
-	aliases = kvm_aliases(kvm);
-
-	for (i = 0; i < aliases->naliases; ++i) {
-		alias = &aliases->aliases[i];
-		if (alias->flags & KVM_ALIAS_INVALID)
-			continue;
-		if (gfn >= alias->base_gfn
-		    && gfn < alias->base_gfn + alias->npages)
-			return alias->target_gfn + gfn - alias->base_gfn;
-	}
-	return gfn;
-}
-
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	int i;
-	struct kvm_mem_alias *alias;
-	struct kvm_mem_aliases *aliases;
-
-	aliases = kvm_aliases(kvm);
-
-	for (i = 0; i < aliases->naliases; ++i) {
-		alias = &aliases->aliases[i];
-		if (gfn >= alias->base_gfn
-		    && gfn < alias->base_gfn + alias->npages)
-			return alias->target_gfn + gfn - alias->base_gfn;
-	}
-	return gfn;
-}
-
-/*
- * Set a new alias region.  Aliases map a portion of physical memory into
- * another portion.  This is useful for memory windows, for example the PC
- * VGA region.
- */
-static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
-					 struct kvm_memory_alias *alias)
-{
-	int r, n;
-	struct kvm_mem_alias *p;
-	struct kvm_mem_aliases *aliases, *old_aliases;
-
-	r = -EINVAL;
-	/* General sanity checks */
-	if (alias->memory_size & (PAGE_SIZE - 1))
-		goto out;
-	if (alias->guest_phys_addr & (PAGE_SIZE - 1))
-		goto out;
-	if (alias->slot >= KVM_ALIAS_SLOTS)
-		goto out;
-	if (alias->guest_phys_addr + alias->memory_size
-	    < alias->guest_phys_addr)
-		goto out;
-	if (alias->target_phys_addr + alias->memory_size
-	    < alias->target_phys_addr)
-		goto out;
-
-	r = -ENOMEM;
-	aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
-	if (!aliases)
-		goto out;
-
-	mutex_lock(&kvm->slots_lock);
-
-	/* invalidate any gfn reference in case of deletion/shrinking */
-	memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
-	aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID;
-	old_aliases = kvm->arch.aliases;
-	rcu_assign_pointer(kvm->arch.aliases, aliases);
-	synchronize_srcu_expedited(&kvm->srcu);
-	kvm_mmu_zap_all(kvm);
-	kfree(old_aliases);
-
-	r = -ENOMEM;
-	aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
-	if (!aliases)
-		goto out_unlock;
-
-	memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
-
-	p = &aliases->aliases[alias->slot];
-	p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
-	p->npages = alias->memory_size >> PAGE_SHIFT;
-	p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;
-	p->flags &= ~(KVM_ALIAS_INVALID);
-
-	for (n = KVM_ALIAS_SLOTS; n > 0; --n)
-		if (aliases->aliases[n - 1].npages)
-			break;
-	aliases->naliases = n;
-
-	old_aliases = kvm->arch.aliases;
-	rcu_assign_pointer(kvm->arch.aliases, aliases);
-	synchronize_srcu_expedited(&kvm->srcu);
-	kfree(old_aliases);
-	r = 0;
-
-out_unlock:
-	mutex_unlock(&kvm->slots_lock);
-out:
-	return r;
-}
-
 static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 {
 	int r;
@@ -3056,7 +2947,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	union {
 		struct kvm_pit_state ps;
 		struct kvm_pit_state2 ps2;
-		struct kvm_memory_alias alias;
 		struct kvm_pit_config pit_config;
 	} u;
 
@@ -3101,14 +2991,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_GET_NR_MMU_PAGES:
 		r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
 		break;
-	case KVM_SET_MEMORY_ALIAS:
-		r = -EFAULT;
-		if (copy_from_user(&u.alias, argp, sizeof(struct kvm_memory_alias)))
-			goto out;
-		r = kvm_vm_ioctl_set_memory_alias(kvm, &u.alias);
-		if (r)
-			goto out;
-		break;
 	case KVM_CREATE_IRQCHIP: {
 		struct kvm_pic *vpic;
 
@@ -5559,12 +5441,6 @@ struct  kvm *kvm_arch_create_vm(void)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
-	if (!kvm->arch.aliases) {
-		kfree(kvm);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
@@ -5622,7 +5498,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
 	cleanup_srcu_struct(&kvm->srcu);
-	kfree(kvm->arch.aliases);
 	kfree(kvm);
 }
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f4b54458285b..b7a404722d2b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -65,13 +65,6 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
-static inline struct kvm_mem_aliases *kvm_aliases(struct kvm *kvm)
-{
-	return rcu_dereference_check(kvm->arch.aliases,
-			srcu_read_lock_held(&kvm->srcu)
-			|| lockdep_is_held(&kvm->slots_lock));
-}
-
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 6fd40f540a8e..636fc381c897 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -619,6 +619,7 @@ struct kvm_clock_data {
  */
 #define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
+/* KVM_SET_MEMORY_ALIAS is obsolete: */
 #define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO,  0x43, struct kvm_memory_alias)
 #define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
 #define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2d96555cd4ed..240e460777bc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -286,8 +286,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				int user_alloc);
 void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
-gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn);
 
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
@@ -564,10 +562,6 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se
 }
 #endif
 
-#ifndef KVM_ARCH_HAS_UNALIAS_INSTANTIATION
-#define unalias_gfn_instantiation unalias_gfn
-#endif
-
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 
 #define KVM_MAX_IRQ_ROUTES 1024
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 84a090644d9d..65417e3d8462 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -841,7 +841,7 @@ int kvm_is_error_hva(unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 
-struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
 	struct kvm_memslots *slots = kvm_memslots(kvm);
@@ -855,20 +855,13 @@ struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(gfn_to_memslot_unaliased);
-
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
-{
-	gfn = unalias_gfn(kvm, gfn);
-	return gfn_to_memslot_unaliased(kvm, gfn);
-}
+EXPORT_SYMBOL_GPL(gfn_to_memslot);
 
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 
-	gfn = unalias_gfn_instantiation(kvm, gfn);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
 		struct kvm_memory_slot *memslot = &slots->memslots[i];
 
@@ -913,7 +906,6 @@ int memslot_id(struct kvm *kvm, gfn_t gfn)
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *memslot = NULL;
 
-	gfn = unalias_gfn(kvm, gfn);
 	for (i = 0; i < slots->nmemslots; ++i) {
 		memslot = &slots->memslots[i];
 
@@ -934,8 +926,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *slot;
 
-	gfn = unalias_gfn_instantiation(kvm, gfn);
-	slot = gfn_to_memslot_unaliased(kvm, gfn);
+	slot = gfn_to_memslot(kvm, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return bad_hva();
 	return gfn_to_hva_memslot(slot, gfn);
@@ -1202,8 +1193,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot;
 
-	gfn = unalias_gfn(kvm, gfn);
-	memslot = gfn_to_memslot_unaliased(kvm, gfn);
+	memslot = gfn_to_memslot(kvm, gfn);
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
-- 
cgit v1.2.3


From a8eeb04a44dd6dc4c8158953d9bae48849c9a188 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 10 May 2010 12:34:53 +0300
Subject: KVM: Add mini-API for vcpu->requests

Makes it a little more readable and hackable.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/lapic.c     |  2 +-
 arch/x86/kvm/mmu.c       |  6 +++---
 arch/x86/kvm/svm.c       |  2 +-
 arch/x86/kvm/timer.c     |  2 +-
 arch/x86/kvm/vmx.c       |  2 +-
 arch/x86/kvm/x86.c       | 27 +++++++++++++--------------
 include/linux/kvm_host.h | 15 +++++++++++++++
 virt/kvm/kvm_main.c      |  4 ++--
 8 files changed, 37 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 49573c78c24b..77d8c0f4817d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -534,7 +534,7 @@ static void __report_tpr_access(struct kvm_lapic *apic, bool write)
 	struct kvm_vcpu *vcpu = apic->vcpu;
 	struct kvm_run *run = vcpu->run;
 
-	set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests);
+	kvm_make_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu);
 	run->tpr_access.rip = kvm_rip_read(vcpu);
 	run->tpr_access.is_write = write;
 }
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index c5501bc10106..690a7fc58c17 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1378,7 +1378,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 
 		mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 		if (sp->unsync_children) {
-			set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
 			kvm_mmu_mark_parents_unsync(sp);
 		} else if (sp->unsync)
 			kvm_mmu_mark_parents_unsync(sp);
@@ -2131,7 +2131,7 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
 	int ret = 0;
 
 	if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
-		set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		ret = 1;
 	}
 
@@ -2329,7 +2329,7 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu)
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.tlb_flush;
-	set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
+	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 }
 
 static void paging_new_cr3(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f7a6fdcf8ef3..587b99d37d44 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1494,7 +1494,7 @@ static void svm_handle_mce(struct vcpu_svm *svm)
 		 */
 		pr_err("KVM: Guest triggered AMD Erratum 383\n");
 
-		set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests);
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, &svm->vcpu);
 
 		return;
 	}
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
index 564548fbb3d6..e16a0dbe74d8 100644
--- a/arch/x86/kvm/timer.c
+++ b/arch/x86/kvm/timer.c
@@ -32,7 +32,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
 		atomic_inc(&ktimer->pending);
 		/* FIXME: this code should not know anything about vcpus */
-		set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
 	}
 
 	if (waitqueue_active(q))
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 345a35470511..661c6e199b4a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -899,7 +899,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		unsigned long sysenter_esp;
 
 		kvm_migrate_timers(vcpu);
-		set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		local_irq_disable();
 		list_add(&vmx->local_vcpus_link,
 			 &per_cpu(vcpus_on_cpu, cpu));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9be6e4e5e8ee..7ef44107a14a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -296,7 +296,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 	prev_nr = vcpu->arch.exception.nr;
 	if (prev_nr == DF_VECTOR) {
 		/* triple fault -> shutdown */
-		set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		return;
 	}
 	class1 = exception_class(prev_nr);
@@ -948,7 +948,7 @@ static int kvm_request_guest_time_update(struct kvm_vcpu *v)
 
 	if (!vcpu->time_page)
 		return 0;
-	set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
+	kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
 	return 1;
 }
 
@@ -2253,7 +2253,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
 			printk(KERN_DEBUG "kvm: set_mce: "
 			       "injects mce exception while "
 			       "previous one is in progress!\n");
-			set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 			return 0;
 		}
 		if (banks[1] & MCI_STATUS_VAL)
@@ -4617,7 +4617,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		vcpu->run->request_interrupt_window;
 
 	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 
 	r = kvm_mmu_reload(vcpu);
@@ -4625,26 +4625,25 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto out;
 
 	if (vcpu->requests) {
-		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
+		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
 			__kvm_migrate_timers(vcpu);
-		if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests))
+		if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu))
 			kvm_write_guest_time(vcpu);
-		if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests))
+		if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
 			kvm_mmu_sync_roots(vcpu);
-		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
 			kvm_x86_ops->tlb_flush(vcpu);
-		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
-				       &vcpu->requests)) {
+		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
 			goto out;
 		}
-		if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
+		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 			r = 0;
 			goto out;
 		}
-		if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+		if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) {
 			vcpu->fpu_active = 0;
 			kvm_x86_ops->fpu_deactivate(vcpu);
 		}
@@ -4773,7 +4772,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 			kvm_vcpu_block(vcpu);
 			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-			if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
+			if (kvm_check_request(KVM_REQ_UNHALT, vcpu))
 			{
 				switch(vcpu->arch.mp_state) {
 				case KVM_MP_STATE_HALTED:
@@ -5255,7 +5254,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	vcpu->guest_fpu_loaded = 0;
 	fpu_save_init(&vcpu->arch.guest_fpu);
 	++vcpu->stat.fpu_reload;
-	set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
+	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
 	trace_kvm_fpu(0);
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 240e460777bc..c8a9d628898e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -624,5 +624,20 @@ static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 
 #endif
 
+static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
+{
+	set_bit(req, &vcpu->requests);
+}
+
+static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu)
+{
+	return test_and_set_bit(req, &vcpu->requests);
+}
+
+static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
+{
+	return test_and_clear_bit(req, &vcpu->requests);
+}
+
 #endif
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 65417e3d8462..5bd2f34ba576 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -145,7 +145,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 	raw_spin_lock(&kvm->requests_lock);
 	me = smp_processor_id();
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (test_and_set_bit(req, &vcpu->requests))
+		if (kvm_make_check_request(req, vcpu))
 			continue;
 		cpu = vcpu->cpu;
 		if (cpus != NULL && cpu != -1 && cpu != me)
@@ -1212,7 +1212,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_arch_vcpu_runnable(vcpu)) {
-			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
+			kvm_make_request(KVM_REQ_UNHALT, vcpu);
 			break;
 		}
 		if (kvm_cpu_has_pending_timer(vcpu))
-- 
cgit v1.2.3


From 0719837c0832a7b305e42327caa7d330462360ea Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 10 May 2010 13:08:26 +0300
Subject: KVM: Reduce atomic operations on vcpu->requests

Usually the vcpu->requests bitmap is sparse, so a test_and_clear_bit() for
each request generates a large number of unneeded atomics if a bit is set.

Replace with a separate test/clear sequence.  This is safe since there is
no clear_bit() outside the vcpu thread.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 include/linux/kvm_host.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c8a9d628898e..e820eb579108 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -636,7 +636,12 @@ static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu)
 
 static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 {
-	return test_and_clear_bit(req, &vcpu->requests);
+	if (test_bit(req, &vcpu->requests)) {
+		clear_bit(req, &vcpu->requests);
+		return true;
+	} else {
+		return false;
+	}
 }
 
 #endif
-- 
cgit v1.2.3


From e36d96f7cfaa71870c407131eb4fbd38ea285c01 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 21 Jun 2010 10:56:36 +0300
Subject: KVM: Keep slot ID in memory slot structure

May be used for distinguishing between internal and user slots, or for sorting
slots in size order.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 include/linux/kvm_host.h | 1 +
 virt/kvm/kvm_main.c      | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e820eb579108..e796326f3646 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -124,6 +124,7 @@ struct kvm_memory_slot {
 	} *lpage_info[KVM_NR_PAGE_SIZES - 1];
 	unsigned long userspace_addr;
 	int user_alloc;
+	int id;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5bd2f34ba576..74f731920945 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -570,6 +570,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	new = old = *memslot;
 
+	new.id = mem->slot;
 	new.base_gfn = base_gfn;
 	new.npages = npages;
 	new.flags = mem->flags;
-- 
cgit v1.2.3


From 5689cc53fa9d09b5bf41b1b1a7c90bd6c112ab40 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <joerg.roedel@amd.com>
Date: Thu, 1 Jul 2010 16:00:12 +0200
Subject: KVM: Use u64 for frame data types

For 32bit machines where the physical address width is
larger than the virtual address width the frame number types
in KVM may overflow. Fix this by changing them to u64.

[sfr: fix build on 32-bit ppc]

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/kvm/44x_tlb.c | 3 ++-
 include/linux/kvm_types.h  | 4 ++--
 virt/kvm/iommu.c           | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 812312542e50..9b9b5cdea840 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -316,7 +316,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	gfn = gpaddr >> PAGE_SHIFT;
 	new_page = gfn_to_page(vcpu->kvm, gfn);
 	if (is_error_page(new_page)) {
-		printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
+		printk(KERN_ERR "Couldn't get guest page for gfn %llx!\n",
+			(unsigned long long)gfn);
 		kvm_release_page_clean(new_page);
 		return;
 	}
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index fb46efbeabec..7ac0d4eee430 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -32,11 +32,11 @@
 
 typedef unsigned long  gva_t;
 typedef u64            gpa_t;
-typedef unsigned long  gfn_t;
+typedef u64            gfn_t;
 
 typedef unsigned long  hva_t;
 typedef u64            hpa_t;
-typedef unsigned long  hfn_t;
+typedef u64            hfn_t;
 
 typedef hfn_t pfn_t;
 
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 779559552ce7..62a9caf0563c 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -108,7 +108,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 			      get_order(page_size), flags);
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
-			       "iommu failed to map pfn=%lx\n", pfn);
+			       "iommu failed to map pfn=%llx\n", pfn);
 			goto unmap_pages;
 		}
 
-- 
cgit v1.2.3


From edba23e51578f7cb6781461568489fc1825db4ac Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Wed, 7 Jul 2010 20:16:45 +0300
Subject: KVM: Return EFAULT from kvm ioctl when guest accesses bad area

Currently if guest access address that belongs to memory slot but is not
backed up by page or page is read only KVM treats it like MMIO access.
Remove that capability. It was never part of the interface and should
not be relied upon.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/mmu.c       |  4 +++-
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 28 ++++++++++++++++++++++++----
 3 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d8d48329cb82..89d7a2cae53b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2078,7 +2078,9 @@ static int kvm_handle_bad_page(struct kvm *kvm, gfn_t gfn, pfn_t pfn)
 	if (is_hwpoison_pfn(pfn)) {
 		kvm_send_hwpoison_signal(kvm, gfn);
 		return 0;
-	}
+	} else if (is_fault_pfn(pfn))
+		return -EFAULT;
+
 	return 1;
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e796326f3646..8055067b6bec 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -269,6 +269,7 @@ extern pfn_t bad_pfn;
 int is_error_page(struct page *page);
 int is_error_pfn(pfn_t pfn);
 int is_hwpoison_pfn(pfn_t pfn);
+int is_fault_pfn(pfn_t pfn);
 int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 630d1224f187..b78b794c1039 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -96,6 +96,9 @@ static bool largepages_enabled = true;
 static struct page *hwpoison_page;
 static pfn_t hwpoison_pfn;
 
+static struct page *fault_page;
+static pfn_t fault_pfn;
+
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
@@ -815,13 +818,13 @@ EXPORT_SYMBOL_GPL(kvm_disable_largepages);
 
 int is_error_page(struct page *page)
 {
-	return page == bad_page || page == hwpoison_page;
+	return page == bad_page || page == hwpoison_page || page == fault_page;
 }
 EXPORT_SYMBOL_GPL(is_error_page);
 
 int is_error_pfn(pfn_t pfn)
 {
-	return pfn == bad_pfn || pfn == hwpoison_pfn;
+	return pfn == bad_pfn || pfn == hwpoison_pfn || pfn == fault_pfn;
 }
 EXPORT_SYMBOL_GPL(is_error_pfn);
 
@@ -831,6 +834,12 @@ int is_hwpoison_pfn(pfn_t pfn)
 }
 EXPORT_SYMBOL_GPL(is_hwpoison_pfn);
 
+int is_fault_pfn(pfn_t pfn)
+{
+	return pfn == fault_pfn;
+}
+EXPORT_SYMBOL_GPL(is_fault_pfn);
+
 static inline unsigned long bad_hva(void)
 {
 	return PAGE_OFFSET;
@@ -959,8 +968,8 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr)
 		if (vma == NULL || addr < vma->vm_start ||
 		    !(vma->vm_flags & VM_PFNMAP)) {
 			up_read(&current->mm->mmap_sem);
-			get_page(bad_page);
-			return page_to_pfn(bad_page);
+			get_page(fault_page);
+			return page_to_pfn(fault_page);
 		}
 
 		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
@@ -2226,6 +2235,15 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 	hwpoison_pfn = page_to_pfn(hwpoison_page);
 
+	fault_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+
+	if (fault_page == NULL) {
+		r = -ENOMEM;
+		goto out_free_0;
+	}
+
+	fault_pfn = page_to_pfn(fault_page);
+
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
@@ -2298,6 +2316,8 @@ out_free_1:
 out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
+	if (fault_page)
+		__free_page(fault_page);
 	if (hwpoison_page)
 		__free_page(hwpoison_page);
 	__free_page(bad_page);
-- 
cgit v1.2.3


From 4a994358b919c3b14de61be5e30d9edc9089ba3f Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Sun, 11 Jul 2010 15:32:23 +0300
Subject: KVM: Convert mask notifiers to use irqchip/pin instead of gsi

Devices register mask notifier using gsi, but irqchip knows about
irqchip/pin, so conversion from irqchip/pin to gsi should be done before
looking for mask notifier to call.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 include/linux/kvm_host.h |  3 ++-
 virt/kvm/ioapic.c        |  2 +-
 virt/kvm/irq_comm.c      | 12 ++++++++----
 3 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8055067b6bec..c13cc48697aa 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -447,7 +447,8 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 				    struct kvm_irq_mask_notifier *kimn);
 void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn);
-void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask);
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask);
 
 #ifdef __KVM_HAVE_IOAPIC
 void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 1149c60b198f..0b9df8303dcf 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -152,7 +152,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		update_handled_vectors(ioapic);
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
-			kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after);
+			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 06cf61e729d2..369e38010ad5 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -279,15 +279,19 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 	synchronize_rcu();
 }
 
-void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+			     bool mask)
 {
 	struct kvm_irq_mask_notifier *kimn;
 	struct hlist_node *n;
+	int gsi;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link)
-		if (kimn->irq == irq)
-			kimn->func(kimn, mask);
+	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link)
+			if (kimn->irq == gsi)
+				kimn->func(kimn, mask);
 	rcu_read_unlock();
 }
 
-- 
cgit v1.2.3