Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Small release overall.

  x86:
   - miscellaneous fixes
   - AVIC support (local APIC virtualization, AMD version)

  s390:
   - polling for interrupts after a VCPU goes to halted state is now
     enabled for s390
   - use hardware provided information about facility bits that do not
     need any hypervisor activity, and other fixes for cpu models and
     facilities
   - improve perf output
   - floating interrupt controller improvements.

  MIPS:
   - miscellaneous fixes

  PPC:
   - bugfixes only

  ARM:
   - 16K page size support
   - generic firmware probing layer for timer and GIC

  Christoffer Dall (KVM-ARM maintainer) says:
    "There are a few changes in this pull request touching things
     outside KVM, but they should all carry the necessary acks and it
     made the merge process much easier to do it this way."

  though actually the irqchip maintainers' acks didn't make it into the
  patches.  Marc Zyngier, who is both irqchip and KVM-ARM maintainer,
  later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more
  formally and for documentation purposes')"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits)
  KVM: MTRR: remove MSR 0x2f8
  KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same
  svm: Manage vcpu load/unload when enable AVIC
  svm: Do not intercept CR8 when enable AVIC
  svm: Do not expose x2APIC when enable AVIC
  KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore
  svm: Add VMEXIT handlers for AVIC
  svm: Add interrupt injection via AVIC
  KVM: x86: Detect and Initialize AVIC support
  svm: Introduce new AVIC VMCB registers
  KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick
  KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks
  KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks
  KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg
  KVM: x86: Misc LAPIC changes to expose helper functions
  KVM: shrink halt polling even more for invalid wakeups
  KVM: s390: set halt polling to 80 microseconds
  KVM: halt_polling: provide a way to qualify wakeups during poll
  KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts
  kvm: Conditionally register IRQ bypass consumer
  ...

1 files changed, 50 insertions, 35 deletions

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 1b3dc9df5257..2cdb6b551ac6 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -85,32 +85,37 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1	((1 << 31) | (1 << 23))
-#define TCR_EL2_TBI	(1 << 20)
-#define TCR_EL2_PS	(7 << 16)
-#define TCR_EL2_PS_40B	(2 << 16)
-#define TCR_EL2_TG0	(1 << 14)
-#define TCR_EL2_SH0	(3 << 12)
-#define TCR_EL2_ORGN0	(3 << 10)
-#define TCR_EL2_IRGN0	(3 << 8)
-#define TCR_EL2_T0SZ	0x3f
-#define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
-			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
+#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_TBI		(1 << 20)
+#define TCR_EL2_PS_SHIFT	16
+#define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
+#define TCR_EL2_PS_40B		(2 << TCR_EL2_PS_SHIFT)
+#define TCR_EL2_TG0_MASK	TCR_TG0_MASK
+#define TCR_EL2_SH0_MASK	TCR_SH0_MASK
+#define TCR_EL2_ORGN0_MASK	TCR_ORGN0_MASK
+#define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
+#define TCR_EL2_T0SZ_MASK	0x3f
+#define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_RES1		(1 << 31)
-#define VTCR_EL2_PS_MASK	(7 << 16)
-#define VTCR_EL2_TG0_MASK	(1 << 14)
-#define VTCR_EL2_TG0_4K		(0 << 14)
-#define VTCR_EL2_TG0_64K	(1 << 14)
-#define VTCR_EL2_SH0_MASK	(3 << 12)
-#define VTCR_EL2_SH0_INNER	(3 << 12)
-#define VTCR_EL2_ORGN0_MASK	(3 << 10)
-#define VTCR_EL2_ORGN0_WBWA	(1 << 10)
-#define VTCR_EL2_IRGN0_MASK	(3 << 8)
-#define VTCR_EL2_IRGN0_WBWA	(1 << 8)
-#define VTCR_EL2_SL0_MASK	(3 << 6)
-#define VTCR_EL2_SL0_LVL1	(1 << 6)
+#define VTCR_EL2_HD		(1 << 22)
+#define VTCR_EL2_HA		(1 << 21)
+#define VTCR_EL2_PS_MASK	TCR_EL2_PS_MASK
+#define VTCR_EL2_TG0_MASK	TCR_TG0_MASK
+#define VTCR_EL2_TG0_4K		TCR_TG0_4K
+#define VTCR_EL2_TG0_16K	TCR_TG0_16K
+#define VTCR_EL2_TG0_64K	TCR_TG0_64K
+#define VTCR_EL2_SH0_MASK	TCR_SH0_MASK
+#define VTCR_EL2_SH0_INNER	TCR_SH0_INNER
+#define VTCR_EL2_ORGN0_MASK	TCR_ORGN0_MASK
+#define VTCR_EL2_ORGN0_WBWA	TCR_ORGN0_WBWA
+#define VTCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
+#define VTCR_EL2_IRGN0_WBWA	TCR_IRGN0_WBWA
+#define VTCR_EL2_SL0_SHIFT	6
+#define VTCR_EL2_SL0_MASK	(3 << VTCR_EL2_SL0_SHIFT)
+#define VTCR_EL2_SL0_LVL1	(1 << VTCR_EL2_SL0_SHIFT)
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 #define VTCR_EL2_VS_SHIFT	19
@@ -126,35 +131,45 @@
  * (see hyp-init.S).
  *
  * Note that when using 4K pages, we concatenate two first level page tables
- * together.
+ * together. With 16K pages, we concatenate 16 first level page tables.
  *
  * The magic numbers used for VTTBR_X in this patch can be found in Tables
  * D4-23 and D4-25 in ARM DDI 0487A.b.
  */
+
+#define VTCR_EL2_T0SZ_IPA	VTCR_EL2_T0SZ_40B
+#define VTCR_EL2_COMMON_BITS	(VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
+				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
+
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
- * 40bits input  (T0SZ = 24)
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
-				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
-#define VTTBR_X		(38 - VTCR_EL2_T0SZ_40B)
-#else
+#define VTCR_EL2_TGRAN_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SL0_LVL1)
+#define VTTBR_X_TGRAN_MAGIC		38
+#elif defined(CONFIG_ARM64_16K_PAGES)
+/*
+ * Stage2 translation configuration:
+ * 16kB pages (TG0 = 2)
+ * 2 level page tables (SL = 1)
+ */
+#define VTCR_EL2_TGRAN_FLAGS		(VTCR_EL2_TG0_16K | VTCR_EL2_SL0_LVL1)
+#define VTTBR_X_TGRAN_MAGIC		42
+#else	/* 4K */
 /*
  * Stage2 translation configuration:
- * 40bits input  (T0SZ = 24)
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
-				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_RES1)
-#define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_TGRAN_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SL0_LVL1)
+#define VTTBR_X_TGRAN_MAGIC		37
 #endif
 
+#define VTCR_EL2_FLAGS			(VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
+#define VTTBR_X				(VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
+
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
 #define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
 #define VTTBR_VMID_SHIFT  (UL(48))