Merge 4.4.168 into android-4.4-p

Changes in 4.4.168
	ipv6: Check available headroom in ip6_xmit() even without options
	net: 8139cp: fix a BUG triggered by changing mtu with network traffic
	net: phy: don't allow __set_phy_supported to add unsupported modes
	net: Prevent invalid access to skb->prev in __qdisc_drop_all
	rtnetlink: ndo_dflt_fdb_dump() only work for ARPHRD_ETHER devices
	tcp: fix NULL ref in tail loss probe
	tun: forbid iface creation with rtnl ops
	neighbour: Avoid writing before skb->head in neigh_hh_output()
	ARM: OMAP2+: prm44xx: Fix section annotation on omap44xx_prm_enable_io_wakeup
	ARM: OMAP1: ams-delta: Fix possible use of uninitialized field
	sysv: return 'err' instead of 0 in __sysv_write_inode
	s390/cpum_cf: Reject request for sampling in event initialization
	hwmon: (ina2xx) Fix current value calculation
	ASoC: dapm: Recalculate audio map forcely when card instantiated
	hwmon: (w83795) temp4_type has writable permission
	Btrfs: send, fix infinite loop due to directory rename dependencies
	ASoC: omap-mcpdm: Add pm_qos handling to avoid under/overruns with CPU_IDLE
	ASoC: omap-dmic: Add pm_qos handling to avoid overruns with CPU_IDLE
	exportfs: do not read dentry after free
	bpf: fix check of allowed specifiers in bpf_trace_printk
	USB: omap_udc: use devm_request_irq()
	USB: omap_udc: fix crashes on probe error and module removal
	USB: omap_udc: fix omap_udc_start() on 15xx machines
	USB: omap_udc: fix USB gadget functionality on Palm Tungsten E
	KVM: x86: fix empty-body warnings
	net: thunderx: fix NULL pointer dereference in nic_remove
	ixgbe: recognize 1000BaseLX SFP modules as 1Gbps
	net: hisilicon: remove unexpected free_netdev
	drm/ast: fixed reading monitor EDID not stable issue
	xen: xlate_mmu: add missing header to fix 'W=1' warning
	fscache: fix race between enablement and dropping of object
	fscache, cachefiles: remove redundant variable 'cache'
	ocfs2: fix deadlock caused by ocfs2_defrag_extent()
	hfs: do not free node before using
	hfsplus: do not free node before using
	debugobjects: avoid recursive calls with kmemleak
	ocfs2: fix potential use after free
	pstore: Convert console write to use ->write_buf
	ALSA: pcm: remove SNDRV_PCM_IOCTL1_INFO internal command
	KVM: nVMX: fix msr bitmaps to prevent L2 from accessing L0 x2APIC
	KVM: nVMX: mark vmcs12 pages dirty on L2 exit
	KVM: nVMX: Eliminate vmcs02 pool
	KVM: VMX: introduce alloc_loaded_vmcs
	KVM: VMX: make MSR bitmaps per-VCPU
	KVM/x86: Add IBPB support
	KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES
	KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
	KVM/SVM: Allow direct access to MSR_IA32_SPEC_CTRL
	KVM/x86: Remove indirect MSR op calls from SPEC_CTRL
	x86: reorganize SMAP handling in user space accesses
	x86: fix SMAP in 32-bit environments
	x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec
	x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end}
	x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec
	x86/bugs, KVM: Support the combination of guest and host IBRS
	x86/KVM/VMX: Expose SPEC_CTRL Bit(2) to the guest
	KVM: SVM: Move spec control call after restore of GS
	x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL
	x86/speculation: Use synthetic bits for IBRS/IBPB/STIBP
	KVM: SVM: Implement VIRT_SPEC_CTRL support for SSBD
	bpf: support 8-byte metafield access
	bpf/verifier: Add spi variable to check_stack_write()
	bpf/verifier: Pass instruction index to check_mem_access() and check_xadd()
	bpf: Prevent memory disambiguation attack
	wil6210: missing length check in wmi_set_ie
	posix-timers: Sanitize overrun handling
	mm/hugetlb.c: don't call region_abort if region_chg fails
	hugetlbfs: fix offset overflow in hugetlbfs mmap
	hugetlbfs: check for pgoff value overflow
	hugetlbfs: fix bug in pgoff overflow checking
	swiotlb: clean up reporting
	sr: pass down correctly sized SCSI sense buffer
	mm: remove write/force parameters from __get_user_pages_locked()
	mm: remove write/force parameters from __get_user_pages_unlocked()
	mm/nommu.c: Switch __get_user_pages_unlocked() to use __get_user_pages()
	mm: replace get_user_pages_unlocked() write/force parameters with gup_flags
	mm: replace get_user_pages_locked() write/force parameters with gup_flags
	mm: replace get_vaddr_frames() write/force parameters with gup_flags
	mm: replace get_user_pages() write/force parameters with gup_flags
	mm: replace __access_remote_vm() write parameter with gup_flags
	mm: replace access_remote_vm() write parameter with gup_flags
	proc: don't use FOLL_FORCE for reading cmdline and environment
	proc: do not access cmdline nor environ from file-backed areas
	media: dvb-frontends: fix i2c access helpers for KASAN
	matroxfb: fix size of memcpy
	staging: speakup: Replace strncpy with memcpy
	rocker: fix rocker_tlv_put_* functions for KASAN
	selftests: Move networking/timestamping from Documentation
	Linux 4.4.168

Change-Id: Icd04a723739ae5e38258a2f6b0aee875f306a0bc
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

1 files changed, 141 insertions, 2 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index df7827a981dd..ecdf724da371 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -37,6 +37,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
+#include <asm/microcode.h>
 #include <asm/spec-ctrl.h>
 
 #include <asm/virtext.h>
@@ -147,6 +148,14 @@ struct vcpu_svm {
 		u64 gs_base;
 	} host;
 
+	u64 spec_ctrl;
+	/*
+	 * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
+	 * translated into the appropriate L2_CFG bits on the host to
+	 * perform speculative control.
+	 */
+	u64 virt_spec_ctrl;
+
 	u32 *msrpm;
 
 	ulong nmi_iret_rip;
@@ -182,6 +191,8 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_CSTAR,				.always = true  },
 	{ .index = MSR_SYSCALL_MASK,			.always = true  },
 #endif
+	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
+	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@@ -411,6 +422,7 @@ struct svm_cpu_data {
 	struct kvm_ldttss_desc *tss_desc;
 
 	struct page *save_area;
+	struct vmcb *current_vmcb;
 };
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
@@ -762,6 +774,25 @@ static bool valid_msr_intercept(u32 index)
 	return false;
 }
 
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
+{
+	u8 bit_write;
+	unsigned long tmp;
+	u32 offset;
+	u32 *msrpm;
+
+	msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
+				      to_svm(vcpu)->msrpm;
+
+	offset    = svm_msrpm_offset(msr);
+	bit_write = 2 * (msr & 0x0f) + 1;
+	tmp       = msrpm[offset];
+
+	BUG_ON(offset == MSR_INVALID);
+
+	return !!test_bit(bit_write,  &tmp);
+}
+
 static void set_msr_interception(u32 *msrpm, unsigned msr,
 				 int read, int write)
 {
@@ -1120,6 +1151,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	u32 dummy;
 	u32 eax = 1;
 
+	svm->spec_ctrl = 0;
+	svm->virt_spec_ctrl = 0;
+
 	if (!init_event) {
 		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
 					   MSR_IA32_APICBASE_ENABLE;
@@ -1210,11 +1244,17 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So do a full IBPB now.
+	 */
+	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
@@ -1239,6 +1279,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
 		}
 	}
+	if (sd->current_vmcb != svm->vmcb) {
+		sd->current_vmcb = svm->vmcb;
+		indirect_branch_prediction_barrier();
+	}
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3051,6 +3095,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_VM_CR:
 		msr_info->data = svm->nested.vm_cr_msr;
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		msr_info->data = svm->spec_ctrl;
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		msr_info->data = svm->virt_spec_ctrl;
+		break;
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = 0x01000065;
 		break;
@@ -3125,6 +3183,59 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr);
 		break;
+	case MSR_IA32_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_spec_ctrl(vcpu))
+			return 1;
+
+		/* The STIBP bit doesn't fault even if it's not advertised */
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+			return 1;
+
+		svm->spec_ctrl = data;
+
+		if (!data)
+			break;
+
+		/*
+		 * For non-nested:
+		 * When it's written (to non-zero) for the first time, pass
+		 * it through.
+		 *
+		 * For nested:
+		 * The handling of the MSR bitmap for L2 guests is done in
+		 * nested_svm_vmrun_msrpm.
+		 * We update the L1 MSR bit as well since it will end up
+		 * touching the MSR anyway now.
+		 */
+		set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		break;
+	case MSR_IA32_PRED_CMD:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_ibpb(vcpu))
+			return 1;
+
+		if (data & ~PRED_CMD_IBPB)
+			return 1;
+
+		if (!data)
+			break;
+
+		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+		if (is_guest_mode(vcpu))
+			break;
+		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		break;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		if (!msr->host_initiated &&
+		    !guest_cpuid_has_virt_ssbd(vcpu))
+			return 1;
+
+		if (data & ~SPEC_CTRL_SSBD)
+			return 1;
+
+		svm->virt_spec_ctrl = data;
+		break;
 	case MSR_STAR:
 		svm->vmcb->save.star = data;
 		break;
@@ -3811,6 +3922,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	local_irq_enable();
 
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
 		"mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
@@ -3915,6 +4034,26 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 #endif
 
+	/*
+	 * We do not use IBRS in the kernel. If this vCPU has used the
+	 * SPEC_CTRL MSR it may have left it on; save the value and
+	 * turn it off. This is much more efficient than blindly adding
+	 * it to the atomic save/restore list. Especially as the former
+	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
+	 *
+	 * For non-nested case:
+	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 *
+	 * For nested case:
+	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
+	 * save it.
+	 */
+	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+
+	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
+
 	reload_tss(vcpu);
 
 	local_irq_disable();
@@ -4015,7 +4154,7 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_high_real_mode_segbase(void)
+static bool svm_has_emulated_msr(int index)
 {
 	return true;
 }
@@ -4299,7 +4438,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
-	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
+	.has_emulated_msr = svm_has_emulated_msr,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,