Merge git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Marcelo Tosatti.

* git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86 emulator: use stack size attribute to mask rsp in stack ops
  KVM: MMU: Fix mmu_shrink() so that it can free mmu pages as intended
  ppc: e500_tlb memset clears nothing
  KVM: PPC: Add cache flush on page map
  KVM: PPC: Book3S HV: Fix incorrect branch in H_CEDE code
  KVM: x86: update KVM_SAVE_MSRS_BEGIN to correct value

10 files changed, 64 insertions, 23 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 50ea12f..a8bf5c6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -33,6 +33,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/processor.h>
 #include <asm/page.h>
+#include <asm/cacheflush.h>
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 0124937..e006f0b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -219,4 +219,16 @@ void kvmppc_claim_lpid(long lpid);
 void kvmppc_free_lpid(long lpid);
 void kvmppc_init_lpid(unsigned long nr_lpids);
 
+static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
+{
+	/* Clear i-cache for new pages */
+	struct page *page;
+	page = pfn_to_page(pfn);
+	if (!test_bit(PG_arch_1, &page->flags)) {
+		flush_dcache_icache_page(page);
+		set_bit(PG_arch_1, &page->flags);
+	}
+}
+
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index f922c29..837f13e 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -211,6 +211,9 @@ next_pteg:
 		pteg1 |= PP_RWRX;
 	}
 
+	if (orig_pte->may_execute)
+		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
+
 	local_irq_disable();
 
 	if (pteg[rr]) {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 10fc8ec..0688b6b 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -126,6 +126,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	if (!orig_pte->may_execute)
 		rflags |= HPTE_R_N;
+	else
+		kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
 
 	hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5a84c8d..44b72fe 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1421,13 +1421,13 @@ _GLOBAL(kvmppc_h_cede)
 	sync			/* order setting ceded vs. testing prodded */
 	lbz	r5,VCPU_PRODDED(r3)
 	cmpwi	r5,0
-	bne	1f
+	bne	kvm_cede_prodded
 	li	r0,0		/* set trap to 0 to say hcall is handled */
 	stw	r0,VCPU_TRAP(r3)
 	li	r0,H_SUCCESS
 	std	r0,VCPU_GPR(R3)(r3)
 BEGIN_FTR_SECTION
-	b	2f		/* just send it up to host on 970 */
+	b	kvm_cede_exit	/* just send it up to host on 970 */
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 
 	/*
@@ -1446,7 +1446,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	or	r4,r4,r0
 	PPC_POPCNTW(R7,R4)
 	cmpw	r7,r8
-	bge	2f
+	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
 	li	r0,1
@@ -1555,7 +1555,8 @@ kvm_end_cede:
 	b	hcall_real_fallback
 
 	/* cede when already previously prodded case */
-1:	li	r0,0
+kvm_cede_prodded:
+	li	r0,0
 	stb	r0,VCPU_PRODDED(r3)
 	sync			/* order testing prodded vs. clearing ceded */
 	stb	r0,VCPU_CEDED(r3)
@@ -1563,7 +1564,8 @@ kvm_end_cede:
 	blr
 
 	/* we've ceded but we want to give control to the host */
-2:	li	r3,H_TOO_HARD
+kvm_cede_exit:
+	li	r3,H_TOO_HARD
 	blr
 
 secondary_too_late:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index c510fc9..a2b6671 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -322,11 +322,11 @@ static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	if (vcpu_e500->g2h_tlb1_map)
-		memset(vcpu_e500->g2h_tlb1_map,
-		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries, 0);
+		memset(vcpu_e500->g2h_tlb1_map, 0,
+		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
 	if (vcpu_e500->h2g_tlb1_rmap)
-		memset(vcpu_e500->h2g_tlb1_rmap,
-		       sizeof(unsigned int) * host_tlb_params[1].entries, 0);
+		memset(vcpu_e500->h2g_tlb1_rmap, 0,
+		       sizeof(unsigned int) * host_tlb_params[1].entries);
 }
 
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -539,6 +539,9 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
 				ref, gvaddr, stlbe);
+
+	/* Clear i-cache for new pages */
+	kvmppc_mmu_flush_icache(pfn);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index baaafde..fbdad0e 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -469,6 +469,7 @@ void flush_dcache_icache_page(struct page *page)
 	__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
 #endif
 }
+EXPORT_SYMBOL(flush_dcache_icache_page);
 
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97d9a99..a3b57a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg)
 	return address_mask(ctxt, reg);
 }
 
+static void masked_increment(ulong *reg, ulong mask, int inc)
+{
+	assign_masked(reg, *reg + inc, mask);
+}
+
 static inline void
 register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
 {
+	ulong mask;
+
 	if (ctxt->ad_bytes == sizeof(unsigned long))
-		*reg += inc;
+		mask = ~0UL;
 	else
-		*reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt));
+		mask = ad_mask(ctxt);
+	masked_increment(reg, mask, inc);
+}
+
+static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
+{
+	masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc);
 }
 
 static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes)
 {
 	struct segmented_address addr;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes);
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	rsp_increment(ctxt, -bytes);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 
 	return segmented_write(ctxt, addr, data, bytes);
@@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt,
 	int rc;
 	struct segmented_address addr;
 
-	addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+	addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
 	addr.seg = VCPU_SREG_SS;
 	rc = segmented_read(ctxt, addr, dest, len);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len);
+	rsp_increment(ctxt, len);
 	return rc;
 }
 
@@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
 
 	while (reg >= VCPU_REGS_RAX) {
 		if (reg == VCPU_REGS_RSP) {
-			register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP],
-							ctxt->op_bytes);
+			rsp_increment(ctxt, ctxt->op_bytes);
 			--reg;
 		}
 
@@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val);
+	rsp_increment(ctxt, ctxt->src.val);
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01ca004..7fbd0d2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4113,16 +4113,21 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 		LIST_HEAD(invalid_list);
 
 		/*
+		 * Never scan more than sc->nr_to_scan VM instances.
+		 * Will not hit this condition practically since we do not try
+		 * to shrink more than one VM and it is very unlikely to see
+		 * !n_used_mmu_pages so many times.
+		 */
+		if (!nr_to_scan--)
+			break;
+		/*
 		 * n_used_mmu_pages is accessed without holding kvm->mmu_lock
 		 * here. We may skip a VM instance errorneosly, but we do not
 		 * want to shrink a VM that only started to populate its MMU
 		 * anyway.
 		 */
-		if (kvm->arch.n_used_mmu_pages > 0) {
-			if (!nr_to_scan--)
-				break;
+		if (!kvm->arch.n_used_mmu_pages)
 			continue;
-		}
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 42bce48..dce75b76 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,