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

Pull more kvm updates from Paolo Bonzini:
 "ARM:
   - Full debug support for arm64
   - Active state switching for timer interrupts
   - Lazy FP/SIMD save/restore for arm64
   - Generic ARMv8 target

  PPC:
   - Book3S: A few bug fixes
   - Book3S: Allow micro-threading on POWER8

  x86:
   - Compiler warnings

  Generic:
   - Adaptive polling for guest halt"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (49 commits)
  kvm: irqchip: fix memory leak
  kvm: move new trace event outside #ifdef CONFIG_KVM_ASYNC_PF
  KVM: trace kvm_halt_poll_ns grow/shrink
  KVM: dynamic halt-polling
  KVM: make halt_poll_ns per-vCPU
  Silence compiler warning in arch/x86/kvm/emulate.c
  kvm: compile process_smi_save_seg_64() only for x86_64
  KVM: x86: avoid uninitialized variable warning
  KVM: PPC: Book3S: Fix typo in top comment about locking
  KVM: PPC: Book3S: Fix size of the PSPB register
  KVM: PPC: Book3S HV: Exit on H_DOORBELL if HOST_IPI is set
  KVM: PPC: Book3S HV: Fix race in starting secondary threads
  KVM: PPC: Book3S: correct width in XER handling
  KVM: PPC: Book3S HV: Fix preempted vcore stolen time calculation
  KVM: PPC: Book3S HV: Fix preempted vcore list locking
  KVM: PPC: Book3S HV: Implement H_CLEAR_REF and H_CLEAR_MOD
  KVM: PPC: Book3S HV: Fix bug in dirty page tracking
  KVM: PPC: Book3S HV: Fix race in reading change bit when removing HPTE
  KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
  KVM: PPC: Book3S HV: Make use of unused threads when running guests
  ...

1 files changed, 218 insertions, 399 deletions

diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 10915aaf0b01..37c89ea2c572 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -230,199 +230,52 @@
 	stp	x24, x25, [x3, #160]
 .endm
 
-.macro save_debug
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	mrs	x26, id_aa64dfr0_el1
-	ubfx	x24, x26, #12, #4	// Extract BRPs
-	ubfx	x25, x26, #20, #4	// Extract WRPs
-	mov	w26, #15
-	sub	w24, w26, w24		// How many BPs to skip
-	sub	w25, w26, w25		// How many WPs to skip
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
-1:
-	mrs	x20, dbgbcr15_el1
-	mrs	x19, dbgbcr14_el1
-	mrs	x18, dbgbcr13_el1
-	mrs	x17, dbgbcr12_el1
-	mrs	x16, dbgbcr11_el1
-	mrs	x15, dbgbcr10_el1
-	mrs	x14, dbgbcr9_el1
-	mrs	x13, dbgbcr8_el1
-	mrs	x12, dbgbcr7_el1
-	mrs	x11, dbgbcr6_el1
-	mrs	x10, dbgbcr5_el1
-	mrs	x9, dbgbcr4_el1
-	mrs	x8, dbgbcr3_el1
-	mrs	x7, dbgbcr2_el1
-	mrs	x6, dbgbcr1_el1
-	mrs	x5, dbgbcr0_el1
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
-
-1:
-	str	x20, [x3, #(15 * 8)]
-	str	x19, [x3, #(14 * 8)]
-	str	x18, [x3, #(13 * 8)]
-	str	x17, [x3, #(12 * 8)]
-	str	x16, [x3, #(11 * 8)]
-	str	x15, [x3, #(10 * 8)]
-	str	x14, [x3, #(9 * 8)]
-	str	x13, [x3, #(8 * 8)]
-	str	x12, [x3, #(7 * 8)]
-	str	x11, [x3, #(6 * 8)]
-	str	x10, [x3, #(5 * 8)]
-	str	x9, [x3, #(4 * 8)]
-	str	x8, [x3, #(3 * 8)]
-	str	x7, [x3, #(2 * 8)]
-	str	x6, [x3, #(1 * 8)]
-	str	x5, [x3, #(0 * 8)]
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
+.macro save_debug type
+	// x4: pointer to register set
+	// x5: number of registers to skip
+	// x6..x22 trashed
+
+	adr	x22, 1f
+	add	x22, x22, x5, lsl #2
+	br	x22
 1:
-	mrs	x20, dbgbvr15_el1
-	mrs	x19, dbgbvr14_el1
-	mrs	x18, dbgbvr13_el1
-	mrs	x17, dbgbvr12_el1
-	mrs	x16, dbgbvr11_el1
-	mrs	x15, dbgbvr10_el1
-	mrs	x14, dbgbvr9_el1
-	mrs	x13, dbgbvr8_el1
-	mrs	x12, dbgbvr7_el1
-	mrs	x11, dbgbvr6_el1
-	mrs	x10, dbgbvr5_el1
-	mrs	x9, dbgbvr4_el1
-	mrs	x8, dbgbvr3_el1
-	mrs	x7, dbgbvr2_el1
-	mrs	x6, dbgbvr1_el1
-	mrs	x5, dbgbvr0_el1
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
-
-1:
-	str	x20, [x3, #(15 * 8)]
-	str	x19, [x3, #(14 * 8)]
-	str	x18, [x3, #(13 * 8)]
-	str	x17, [x3, #(12 * 8)]
-	str	x16, [x3, #(11 * 8)]
-	str	x15, [x3, #(10 * 8)]
-	str	x14, [x3, #(9 * 8)]
-	str	x13, [x3, #(8 * 8)]
-	str	x12, [x3, #(7 * 8)]
-	str	x11, [x3, #(6 * 8)]
-	str	x10, [x3, #(5 * 8)]
-	str	x9, [x3, #(4 * 8)]
-	str	x8, [x3, #(3 * 8)]
-	str	x7, [x3, #(2 * 8)]
-	str	x6, [x3, #(1 * 8)]
-	str	x5, [x3, #(0 * 8)]
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	mrs	x20, dbgwcr15_el1
-	mrs	x19, dbgwcr14_el1
-	mrs	x18, dbgwcr13_el1
-	mrs	x17, dbgwcr12_el1
-	mrs	x16, dbgwcr11_el1
-	mrs	x15, dbgwcr10_el1
-	mrs	x14, dbgwcr9_el1
-	mrs	x13, dbgwcr8_el1
-	mrs	x12, dbgwcr7_el1
-	mrs	x11, dbgwcr6_el1
-	mrs	x10, dbgwcr5_el1
-	mrs	x9, dbgwcr4_el1
-	mrs	x8, dbgwcr3_el1
-	mrs	x7, dbgwcr2_el1
-	mrs	x6, dbgwcr1_el1
-	mrs	x5, dbgwcr0_el1
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-
-1:
-	str	x20, [x3, #(15 * 8)]
-	str	x19, [x3, #(14 * 8)]
-	str	x18, [x3, #(13 * 8)]
-	str	x17, [x3, #(12 * 8)]
-	str	x16, [x3, #(11 * 8)]
-	str	x15, [x3, #(10 * 8)]
-	str	x14, [x3, #(9 * 8)]
-	str	x13, [x3, #(8 * 8)]
-	str	x12, [x3, #(7 * 8)]
-	str	x11, [x3, #(6 * 8)]
-	str	x10, [x3, #(5 * 8)]
-	str	x9, [x3, #(4 * 8)]
-	str	x8, [x3, #(3 * 8)]
-	str	x7, [x3, #(2 * 8)]
-	str	x6, [x3, #(1 * 8)]
-	str	x5, [x3, #(0 * 8)]
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	mrs	x20, dbgwvr15_el1
-	mrs	x19, dbgwvr14_el1
-	mrs	x18, dbgwvr13_el1
-	mrs	x17, dbgwvr12_el1
-	mrs	x16, dbgwvr11_el1
-	mrs	x15, dbgwvr10_el1
-	mrs	x14, dbgwvr9_el1
-	mrs	x13, dbgwvr8_el1
-	mrs	x12, dbgwvr7_el1
-	mrs	x11, dbgwvr6_el1
-	mrs	x10, dbgwvr5_el1
-	mrs	x9, dbgwvr4_el1
-	mrs	x8, dbgwvr3_el1
-	mrs	x7, dbgwvr2_el1
-	mrs	x6, dbgwvr1_el1
-	mrs	x5, dbgwvr0_el1
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-
+	mrs	x21, \type\()15_el1
+	mrs	x20, \type\()14_el1
+	mrs	x19, \type\()13_el1
+	mrs	x18, \type\()12_el1
+	mrs	x17, \type\()11_el1
+	mrs	x16, \type\()10_el1
+	mrs	x15, \type\()9_el1
+	mrs	x14, \type\()8_el1
+	mrs	x13, \type\()7_el1
+	mrs	x12, \type\()6_el1
+	mrs	x11, \type\()5_el1
+	mrs	x10, \type\()4_el1
+	mrs	x9, \type\()3_el1
+	mrs	x8, \type\()2_el1
+	mrs	x7, \type\()1_el1
+	mrs	x6, \type\()0_el1
+
+	adr	x22, 1f
+	add	x22, x22, x5, lsl #2
+	br	x22
 1:
-	str	x20, [x3, #(15 * 8)]
-	str	x19, [x3, #(14 * 8)]
-	str	x18, [x3, #(13 * 8)]
-	str	x17, [x3, #(12 * 8)]
-	str	x16, [x3, #(11 * 8)]
-	str	x15, [x3, #(10 * 8)]
-	str	x14, [x3, #(9 * 8)]
-	str	x13, [x3, #(8 * 8)]
-	str	x12, [x3, #(7 * 8)]
-	str	x11, [x3, #(6 * 8)]
-	str	x10, [x3, #(5 * 8)]
-	str	x9, [x3, #(4 * 8)]
-	str	x8, [x3, #(3 * 8)]
-	str	x7, [x3, #(2 * 8)]
-	str	x6, [x3, #(1 * 8)]
-	str	x5, [x3, #(0 * 8)]
-
-	mrs	x21, mdccint_el1
-	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+	str	x21, [x4, #(15 * 8)]
+	str	x20, [x4, #(14 * 8)]
+	str	x19, [x4, #(13 * 8)]
+	str	x18, [x4, #(12 * 8)]
+	str	x17, [x4, #(11 * 8)]
+	str	x16, [x4, #(10 * 8)]
+	str	x15, [x4, #(9 * 8)]
+	str	x14, [x4, #(8 * 8)]
+	str	x13, [x4, #(7 * 8)]
+	str	x12, [x4, #(6 * 8)]
+	str	x11, [x4, #(5 * 8)]
+	str	x10, [x4, #(4 * 8)]
+	str	x9, [x4, #(3 * 8)]
+	str	x8, [x4, #(2 * 8)]
+	str	x7, [x4, #(1 * 8)]
+	str	x6, [x4, #(0 * 8)]
 .endm
 
 .macro restore_sysregs
@@ -467,195 +320,52 @@
 	msr	mdscr_el1,	x25
 .endm
 
-.macro restore_debug
-	// x2: base address for cpu context
-	// x3: tmp register
-
-	mrs	x26, id_aa64dfr0_el1
-	ubfx	x24, x26, #12, #4	// Extract BRPs
-	ubfx	x25, x26, #20, #4	// Extract WRPs
-	mov	w26, #15
-	sub	w24, w26, w24		// How many BPs to skip
-	sub	w25, w26, w25		// How many WPs to skip
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+.macro restore_debug type
+	// x4: pointer to register set
+	// x5: number of registers to skip
+	// x6..x22 trashed
 
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
-1:
-	ldr	x20, [x3, #(15 * 8)]
-	ldr	x19, [x3, #(14 * 8)]
-	ldr	x18, [x3, #(13 * 8)]
-	ldr	x17, [x3, #(12 * 8)]
-	ldr	x16, [x3, #(11 * 8)]
-	ldr	x15, [x3, #(10 * 8)]
-	ldr	x14, [x3, #(9 * 8)]
-	ldr	x13, [x3, #(8 * 8)]
-	ldr	x12, [x3, #(7 * 8)]
-	ldr	x11, [x3, #(6 * 8)]
-	ldr	x10, [x3, #(5 * 8)]
-	ldr	x9, [x3, #(4 * 8)]
-	ldr	x8, [x3, #(3 * 8)]
-	ldr	x7, [x3, #(2 * 8)]
-	ldr	x6, [x3, #(1 * 8)]
-	ldr	x5, [x3, #(0 * 8)]
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
+	adr	x22, 1f
+	add	x22, x22, x5, lsl #2
+	br	x22
 1:
-	msr	dbgbcr15_el1, x20
-	msr	dbgbcr14_el1, x19
-	msr	dbgbcr13_el1, x18
-	msr	dbgbcr12_el1, x17
-	msr	dbgbcr11_el1, x16
-	msr	dbgbcr10_el1, x15
-	msr	dbgbcr9_el1, x14
-	msr	dbgbcr8_el1, x13
-	msr	dbgbcr7_el1, x12
-	msr	dbgbcr6_el1, x11
-	msr	dbgbcr5_el1, x10
-	msr	dbgbcr4_el1, x9
-	msr	dbgbcr3_el1, x8
-	msr	dbgbcr2_el1, x7
-	msr	dbgbcr1_el1, x6
-	msr	dbgbcr0_el1, x5
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
+	ldr	x21, [x4, #(15 * 8)]
+	ldr	x20, [x4, #(14 * 8)]
+	ldr	x19, [x4, #(13 * 8)]
+	ldr	x18, [x4, #(12 * 8)]
+	ldr	x17, [x4, #(11 * 8)]
+	ldr	x16, [x4, #(10 * 8)]
+	ldr	x15, [x4, #(9 * 8)]
+	ldr	x14, [x4, #(8 * 8)]
+	ldr	x13, [x4, #(7 * 8)]
+	ldr	x12, [x4, #(6 * 8)]
+	ldr	x11, [x4, #(5 * 8)]
+	ldr	x10, [x4, #(4 * 8)]
+	ldr	x9, [x4, #(3 * 8)]
+	ldr	x8, [x4, #(2 * 8)]
+	ldr	x7, [x4, #(1 * 8)]
+	ldr	x6, [x4, #(0 * 8)]
+
+	adr	x22, 1f
+	add	x22, x22, x5, lsl #2
+	br	x22
 1:
-	ldr	x20, [x3, #(15 * 8)]
-	ldr	x19, [x3, #(14 * 8)]
-	ldr	x18, [x3, #(13 * 8)]
-	ldr	x17, [x3, #(12 * 8)]
-	ldr	x16, [x3, #(11 * 8)]
-	ldr	x15, [x3, #(10 * 8)]
-	ldr	x14, [x3, #(9 * 8)]
-	ldr	x13, [x3, #(8 * 8)]
-	ldr	x12, [x3, #(7 * 8)]
-	ldr	x11, [x3, #(6 * 8)]
-	ldr	x10, [x3, #(5 * 8)]
-	ldr	x9, [x3, #(4 * 8)]
-	ldr	x8, [x3, #(3 * 8)]
-	ldr	x7, [x3, #(2 * 8)]
-	ldr	x6, [x3, #(1 * 8)]
-	ldr	x5, [x3, #(0 * 8)]
-
-	adr	x26, 1f
-	add	x26, x26, x24, lsl #2
-	br	x26
-1:
-	msr	dbgbvr15_el1, x20
-	msr	dbgbvr14_el1, x19
-	msr	dbgbvr13_el1, x18
-	msr	dbgbvr12_el1, x17
-	msr	dbgbvr11_el1, x16
-	msr	dbgbvr10_el1, x15
-	msr	dbgbvr9_el1, x14
-	msr	dbgbvr8_el1, x13
-	msr	dbgbvr7_el1, x12
-	msr	dbgbvr6_el1, x11
-	msr	dbgbvr5_el1, x10
-	msr	dbgbvr4_el1, x9
-	msr	dbgbvr3_el1, x8
-	msr	dbgbvr2_el1, x7
-	msr	dbgbvr1_el1, x6
-	msr	dbgbvr0_el1, x5
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	ldr	x20, [x3, #(15 * 8)]
-	ldr	x19, [x3, #(14 * 8)]
-	ldr	x18, [x3, #(13 * 8)]
-	ldr	x17, [x3, #(12 * 8)]
-	ldr	x16, [x3, #(11 * 8)]
-	ldr	x15, [x3, #(10 * 8)]
-	ldr	x14, [x3, #(9 * 8)]
-	ldr	x13, [x3, #(8 * 8)]
-	ldr	x12, [x3, #(7 * 8)]
-	ldr	x11, [x3, #(6 * 8)]
-	ldr	x10, [x3, #(5 * 8)]
-	ldr	x9, [x3, #(4 * 8)]
-	ldr	x8, [x3, #(3 * 8)]
-	ldr	x7, [x3, #(2 * 8)]
-	ldr	x6, [x3, #(1 * 8)]
-	ldr	x5, [x3, #(0 * 8)]
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	msr	dbgwcr15_el1, x20
-	msr	dbgwcr14_el1, x19
-	msr	dbgwcr13_el1, x18
-	msr	dbgwcr12_el1, x17
-	msr	dbgwcr11_el1, x16
-	msr	dbgwcr10_el1, x15
-	msr	dbgwcr9_el1, x14
-	msr	dbgwcr8_el1, x13
-	msr	dbgwcr7_el1, x12
-	msr	dbgwcr6_el1, x11
-	msr	dbgwcr5_el1, x10
-	msr	dbgwcr4_el1, x9
-	msr	dbgwcr3_el1, x8
-	msr	dbgwcr2_el1, x7
-	msr	dbgwcr1_el1, x6
-	msr	dbgwcr0_el1, x5
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	ldr	x20, [x3, #(15 * 8)]
-	ldr	x19, [x3, #(14 * 8)]
-	ldr	x18, [x3, #(13 * 8)]
-	ldr	x17, [x3, #(12 * 8)]
-	ldr	x16, [x3, #(11 * 8)]
-	ldr	x15, [x3, #(10 * 8)]
-	ldr	x14, [x3, #(9 * 8)]
-	ldr	x13, [x3, #(8 * 8)]
-	ldr	x12, [x3, #(7 * 8)]
-	ldr	x11, [x3, #(6 * 8)]
-	ldr	x10, [x3, #(5 * 8)]
-	ldr	x9, [x3, #(4 * 8)]
-	ldr	x8, [x3, #(3 * 8)]
-	ldr	x7, [x3, #(2 * 8)]
-	ldr	x6, [x3, #(1 * 8)]
-	ldr	x5, [x3, #(0 * 8)]
-
-	adr	x26, 1f
-	add	x26, x26, x25, lsl #2
-	br	x26
-1:
-	msr	dbgwvr15_el1, x20
-	msr	dbgwvr14_el1, x19
-	msr	dbgwvr13_el1, x18
-	msr	dbgwvr12_el1, x17
-	msr	dbgwvr11_el1, x16
-	msr	dbgwvr10_el1, x15
-	msr	dbgwvr9_el1, x14
-	msr	dbgwvr8_el1, x13
-	msr	dbgwvr7_el1, x12
-	msr	dbgwvr6_el1, x11
-	msr	dbgwvr5_el1, x10
-	msr	dbgwvr4_el1, x9
-	msr	dbgwvr3_el1, x8
-	msr	dbgwvr2_el1, x7
-	msr	dbgwvr1_el1, x6
-	msr	dbgwvr0_el1, x5
-
-	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
-	msr	mdccint_el1, x21
+	msr	\type\()15_el1, x21
+	msr	\type\()14_el1, x20
+	msr	\type\()13_el1, x19
+	msr	\type\()12_el1, x18
+	msr	\type\()11_el1, x17
+	msr	\type\()10_el1, x16
+	msr	\type\()9_el1, x15
+	msr	\type\()8_el1, x14
+	msr	\type\()7_el1, x13
+	msr	\type\()6_el1, x12
+	msr	\type\()5_el1, x11
+	msr	\type\()4_el1, x10
+	msr	\type\()3_el1, x9
+	msr	\type\()2_el1, x8
+	msr	\type\()1_el1, x7
+	msr	\type\()0_el1, x6
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -675,6 +385,14 @@
 	tbz	\tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
 .endm
 
+/*
+ * Branch to target if CPTR_EL2.TFP bit is set (VFP/SIMD trapping enabled)
+ */
+.macro skip_fpsimd_state tmp, target
+	mrs	\tmp, cptr_el2
+	tbnz	\tmp, #CPTR_EL2_TFP_SHIFT, \target
+.endm
+
 .macro compute_debug_state target
 	// Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
 	// is set, we do a full save/restore cycle and disable trapping.
@@ -713,10 +431,12 @@
 	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
 	mrs	x4, dacr32_el2
 	mrs	x5, ifsr32_el2
-	mrs	x6, fpexc32_el2
 	stp	x4, x5, [x3]
-	str	x6, [x3, #16]
 
+	skip_fpsimd_state x8, 3f
+	mrs	x6, fpexc32_el2
+	str	x6, [x3, #16]
+3:
 	skip_debug_state x8, 2f
 	mrs	x7, dbgvcr32_el2
 	str	x7, [x3, #24]
@@ -743,10 +463,8 @@
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
 	ldp	x4, x5, [x3]
-	ldr	x6, [x3, #16]
 	msr	dacr32_el2, x4
 	msr	ifsr32_el2, x5
-	msr	fpexc32_el2, x6
 
 	skip_debug_state x8, 2f
 	ldr	x7, [x3, #24]
@@ -763,31 +481,35 @@
 
 .macro activate_traps
 	ldr     x2, [x0, #VCPU_HCR_EL2]
+
+	/*
+	 * We are about to set CPTR_EL2.TFP to trap all floating point
+	 * register accesses to EL2, however, the ARM ARM clearly states that
+	 * traps are only taken to EL2 if the operation would not otherwise
+	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 */
+	tbnz	x2, #HCR_RW_SHIFT, 99f // open code skip_32bit_state
+	mov	x3, #(1 << 30)
+	msr	fpexc32_el2, x3
+	isb
+99:
 	msr     hcr_el2, x2
 	mov	x2, #CPTR_EL2_TTA
+	orr     x2, x2, #CPTR_EL2_TFP
 	msr	cptr_el2, x2
 
 	mov	x2, #(1 << 15)	// Trap CP15 Cr=15
 	msr	hstr_el2, x2
 
-	mrs	x2, mdcr_el2
-	and	x2, x2, #MDCR_EL2_HPMN_MASK
-	orr	x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
-	orr	x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
-
-	// Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
-	// if not dirty.
-	ldr	x3, [x0, #VCPU_DEBUG_FLAGS]
-	tbnz	x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
-	orr	x2, x2,  #MDCR_EL2_TDA
-1:
+	// Monitor Debug Config - see kvm_arm_setup_debug()
+	ldr	x2, [x0, #VCPU_MDCR_EL2]
 	msr	mdcr_el2, x2
 .endm
 
 .macro deactivate_traps
 	mov	x2, #HCR_RW
 	msr	hcr_el2, x2
-	msr	cptr_el2, xzr
 	msr	hstr_el2, xzr
 
 	mrs	x2, mdcr_el2
@@ -900,21 +622,101 @@ __restore_sysregs:
 	restore_sysregs
 	ret
 
+/* Save debug state */
 __save_debug:
-	save_debug
+	// x2: ptr to CPU context
+	// x3: ptr to debug reg struct
+	// x4/x5/x6-22/x24-26: trashed
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	mov	x5, x24
+	add	x4, x3, #DEBUG_BCR
+	save_debug dbgbcr
+	add	x4, x3, #DEBUG_BVR
+	save_debug dbgbvr
+
+	mov	x5, x25
+	add	x4, x3, #DEBUG_WCR
+	save_debug dbgwcr
+	add	x4, x3, #DEBUG_WVR
+	save_debug dbgwvr
+
+	mrs	x21, mdccint_el1
+	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
 	ret
 
+/* Restore debug state */
 __restore_debug:
-	restore_debug
+	// x2: ptr to CPU context
+	// x3: ptr to debug reg struct
+	// x4/x5/x6-22/x24-26: trashed
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	mov	x5, x24
+	add	x4, x3, #DEBUG_BCR
+	restore_debug dbgbcr
+	add	x4, x3, #DEBUG_BVR
+	restore_debug dbgbvr
+
+	mov	x5, x25
+	add	x4, x3, #DEBUG_WCR
+	restore_debug dbgwcr
+	add	x4, x3, #DEBUG_WVR
+	restore_debug dbgwvr
+
+	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+	msr	mdccint_el1, x21
+
 	ret
 
 __save_fpsimd:
+	skip_fpsimd_state x3, 1f
 	save_fpsimd
-	ret
+1:	ret
 
 __restore_fpsimd:
+	skip_fpsimd_state x3, 1f
 	restore_fpsimd
-	ret
+1:	ret
+
+switch_to_guest_fpsimd:
+	push	x4, lr
+
+	mrs	x2, cptr_el2
+	bic	x2, x2, #CPTR_EL2_TFP
+	msr	cptr_el2, x2
+	isb
+
+	mrs	x0, tpidr_el2
+
+	ldr	x2, [x0, #VCPU_HOST_CONTEXT]
+	kern_hyp_va x2
+	bl __save_fpsimd
+
+	add	x2, x0, #VCPU_CONTEXT
+	bl __restore_fpsimd
+
+	skip_32bit_state x3, 1f
+	ldr	x4, [x2, #CPU_SYSREG_OFFSET(FPEXC32_EL2)]
+	msr	fpexc32_el2, x4
+1:
+	pop	x4, lr
+	pop	x2, x3
+	pop	x0, x1
+
+	eret
 
 /*
  * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu);
@@ -936,10 +738,10 @@ ENTRY(__kvm_vcpu_run)
 	kern_hyp_va x2
 
 	save_host_regs
-	bl __save_fpsimd
 	bl __save_sysregs
 
 	compute_debug_state 1f
+	add	x3, x0, #VCPU_HOST_DEBUG_STATE
 	bl	__save_debug
 1:
 	activate_traps
@@ -952,9 +754,10 @@ ENTRY(__kvm_vcpu_run)
 	add	x2, x0, #VCPU_CONTEXT
 
 	bl __restore_sysregs
-	bl __restore_fpsimd
 
 	skip_debug_state x3, 1f
+	ldr	x3, [x0, #VCPU_DEBUG_PTR]
+	kern_hyp_va x3
 	bl	__restore_debug
 1:
 	restore_guest_32bit_state
@@ -975,6 +778,8 @@ __kvm_vcpu_return:
 	bl __save_sysregs
 
 	skip_debug_state x3, 1f
+	ldr	x3, [x0, #VCPU_DEBUG_PTR]
+	kern_hyp_va x3
 	bl	__save_debug
 1:
 	save_guest_32bit_state
@@ -991,12 +796,15 @@ __kvm_vcpu_return:
 
 	bl __restore_sysregs
 	bl __restore_fpsimd
+	/* Clear FPSIMD and Trace trapping */
+	msr     cptr_el2, xzr
 
 	skip_debug_state x3, 1f
 	// Clear the dirty flag for the next run, as all the state has
 	// already been saved. Note that we nuke the whole 64bit word.
 	// If we ever add more flags, we'll have to be more careful...
 	str	xzr, [x0, #VCPU_DEBUG_FLAGS]
+	add	x3, x0, #VCPU_HOST_DEBUG_STATE
 	bl	__restore_debug
 1:
 	restore_host_regs
@@ -1199,6 +1007,11 @@ el1_trap:
 	 * x1: ESR
 	 * x2: ESR_EC
 	 */
+
+	/* Guest accessed VFP/SIMD registers, save host, restore Guest */
+	cmp	x2, #ESR_ELx_EC_FP_ASIMD
+	b.eq	switch_to_guest_fpsimd
+
 	cmp	x2, #ESR_ELx_EC_DABT_LOW
 	mov	x0, #ESR_ELx_EC_IABT_LOW
 	ccmp	x2, x0, #4, ne
@@ -1293,4 +1106,10 @@ ENTRY(__kvm_hyp_vector)
 	ventry	el1_error_invalid		// Error 32-bit EL1
 ENDPROC(__kvm_hyp_vector)
 
+
+ENTRY(__kvm_get_mdcr_el2)
+	mrs	x0, mdcr_el2
+	ret
+ENDPROC(__kvm_get_mdcr_el2)
+
 	.popsection