summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/virtual/kvm/cpuid.txt4
-rw-r--r--Documentation/virtual/kvm/hypercalls.txt14
-rw-r--r--arch/mips/kvm/kvm_locore.S969
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_64_vio.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv.c2
-rw-r--r--arch/x86/include/asm/kvm_host.h5
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h1
-rw-r--r--arch/x86/kvm/cpuid.c3
-rw-r--r--arch/x86/kvm/lapic.c5
-rw-r--r--arch/x86/kvm/mmu.c4
-rw-r--r--arch/x86/kvm/vmx.c1
-rw-r--r--arch/x86/kvm/x86.c85
-rw-r--r--include/uapi/linux/kvm.h1
-rw-r--r--include/uapi/linux/kvm_para.h1
-rw-r--r--virt/kvm/kvm_main.c46
16 files changed, 592 insertions, 553 deletions
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 83afe65d496..22ff659bc0f 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -43,6 +43,10 @@ KVM_FEATURE_CLOCKSOURCE2 || 3 || kvmclock available at msrs
KVM_FEATURE_ASYNC_PF || 4 || async pf can be enabled by
|| || writing to msr 0x4b564d02
------------------------------------------------------------------------------
+KVM_FEATURE_PV_UNHALT || 7 || guest checks this feature bit
+ || || before enabling paravirtualized
+ || || spinlock support.
+------------------------------------------------------------------------------
KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side
|| || per-cpu warps are expected in
|| || kvmclock.
diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virtual/kvm/hypercalls.txt
index ea113b5d87a..022198e389d 100644
--- a/Documentation/virtual/kvm/hypercalls.txt
+++ b/Documentation/virtual/kvm/hypercalls.txt
@@ -64,3 +64,17 @@ Purpose: To enable communication between the hypervisor and guest there is a
shared page that contains parts of supervisor visible register state.
The guest can map this shared page to access its supervisor register through
memory using this hypercall.
+
+5. KVM_HC_KICK_CPU
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to wakeup a vcpu from HLT state
+Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest
+kernel mode for an event to occur (ex: a spinlock to become available) can
+execute HLT instruction once it has busy-waited for more than a threshold
+time-interval. Execution of HLT instruction would cause the hypervisor to put
+the vcpu to sleep until occurence of an appropriate event. Another vcpu of the
+same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
+specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
+is used in the hypercall for future use.
diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S
index dca2aa66599..bbace092ad0 100644
--- a/arch/mips/kvm/kvm_locore.S
+++ b/arch/mips/kvm/kvm_locore.S
@@ -1,13 +1,13 @@
/*
-* This file is subject to the terms and conditions of the GNU General Public
-* License. See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Main entry point for the guest, exception handling.
-*
-* Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Main entry point for the guest, exception handling.
+ *
+ * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
#include <asm/asm.h>
#include <asm/asmmacro.h>
@@ -55,195 +55,193 @@
* a0: run
* a1: vcpu
*/
+ .set noreorder
+ .set noat
FEXPORT(__kvm_mips_vcpu_run)
- .set push
- .set noreorder
- .set noat
-
- /* k0/k1 not being used in host kernel context */
- addiu k1,sp, -PT_SIZE
- LONG_S $0, PT_R0(k1)
- LONG_S $1, PT_R1(k1)
- LONG_S $2, PT_R2(k1)
- LONG_S $3, PT_R3(k1)
-
- LONG_S $4, PT_R4(k1)
- LONG_S $5, PT_R5(k1)
- LONG_S $6, PT_R6(k1)
- LONG_S $7, PT_R7(k1)
-
- LONG_S $8, PT_R8(k1)
- LONG_S $9, PT_R9(k1)
- LONG_S $10, PT_R10(k1)
- LONG_S $11, PT_R11(k1)
- LONG_S $12, PT_R12(k1)
- LONG_S $13, PT_R13(k1)
- LONG_S $14, PT_R14(k1)
- LONG_S $15, PT_R15(k1)
- LONG_S $16, PT_R16(k1)
- LONG_S $17, PT_R17(k1)
-
- LONG_S $18, PT_R18(k1)
- LONG_S $19, PT_R19(k1)
- LONG_S $20, PT_R20(k1)
- LONG_S $21, PT_R21(k1)
- LONG_S $22, PT_R22(k1)
- LONG_S $23, PT_R23(k1)
- LONG_S $24, PT_R24(k1)
- LONG_S $25, PT_R25(k1)
+ /* k0/k1 not being used in host kernel context */
+ INT_ADDIU k1, sp, -PT_SIZE
+ LONG_S $0, PT_R0(k1)
+ LONG_S $1, PT_R1(k1)
+ LONG_S $2, PT_R2(k1)
+ LONG_S $3, PT_R3(k1)
+
+ LONG_S $4, PT_R4(k1)
+ LONG_S $5, PT_R5(k1)
+ LONG_S $6, PT_R6(k1)
+ LONG_S $7, PT_R7(k1)
+
+ LONG_S $8, PT_R8(k1)
+ LONG_S $9, PT_R9(k1)
+ LONG_S $10, PT_R10(k1)
+ LONG_S $11, PT_R11(k1)
+ LONG_S $12, PT_R12(k1)
+ LONG_S $13, PT_R13(k1)
+ LONG_S $14, PT_R14(k1)
+ LONG_S $15, PT_R15(k1)
+ LONG_S $16, PT_R16(k1)
+ LONG_S $17, PT_R17(k1)
+
+ LONG_S $18, PT_R18(k1)
+ LONG_S $19, PT_R19(k1)
+ LONG_S $20, PT_R20(k1)
+ LONG_S $21, PT_R21(k1)
+ LONG_S $22, PT_R22(k1)
+ LONG_S $23, PT_R23(k1)
+ LONG_S $24, PT_R24(k1)
+ LONG_S $25, PT_R25(k1)
/* XXXKYMA k0/k1 not saved, not being used if we got here through an ioctl() */
- LONG_S $28, PT_R28(k1)
- LONG_S $29, PT_R29(k1)
- LONG_S $30, PT_R30(k1)
- LONG_S $31, PT_R31(k1)
+ LONG_S $28, PT_R28(k1)
+ LONG_S $29, PT_R29(k1)
+ LONG_S $30, PT_R30(k1)
+ LONG_S $31, PT_R31(k1)
- /* Save hi/lo */
- mflo v0
- LONG_S v0, PT_LO(k1)
- mfhi v1
- LONG_S v1, PT_HI(k1)
+ /* Save hi/lo */
+ mflo v0
+ LONG_S v0, PT_LO(k1)
+ mfhi v1
+ LONG_S v1, PT_HI(k1)
/* Save host status */
- mfc0 v0, CP0_STATUS
- LONG_S v0, PT_STATUS(k1)
+ mfc0 v0, CP0_STATUS
+ LONG_S v0, PT_STATUS(k1)
/* Save host ASID, shove it into the BVADDR location */
- mfc0 v1,CP0_ENTRYHI
- andi v1, 0xff
- LONG_S v1, PT_HOST_ASID(k1)
+ mfc0 v1, CP0_ENTRYHI
+ andi v1, 0xff
+ LONG_S v1, PT_HOST_ASID(k1)
- /* Save DDATA_LO, will be used to store pointer to vcpu */
- mfc0 v1, CP0_DDATA_LO
- LONG_S v1, PT_HOST_USERLOCAL(k1)
+ /* Save DDATA_LO, will be used to store pointer to vcpu */
+ mfc0 v1, CP0_DDATA_LO
+ LONG_S v1, PT_HOST_USERLOCAL(k1)
- /* DDATA_LO has pointer to vcpu */
- mtc0 a1,CP0_DDATA_LO
+ /* DDATA_LO has pointer to vcpu */
+ mtc0 a1, CP0_DDATA_LO
- /* Offset into vcpu->arch */
- addiu k1, a1, VCPU_HOST_ARCH
+ /* Offset into vcpu->arch */
+ INT_ADDIU k1, a1, VCPU_HOST_ARCH
- /* Save the host stack to VCPU, used for exception processing when we exit from the Guest */
- LONG_S sp, VCPU_HOST_STACK(k1)
+ /*
+ * Save the host stack to VCPU, used for exception processing
+ * when we exit from the Guest
+ */
+ LONG_S sp, VCPU_HOST_STACK(k1)
- /* Save the kernel gp as well */
- LONG_S gp, VCPU_HOST_GP(k1)
+ /* Save the kernel gp as well */
+ LONG_S gp, VCPU_HOST_GP(k1)
/* Setup status register for running the guest in UM, interrupts are disabled */
- li k0,(ST0_EXL | KSU_USER| ST0_BEV)
- mtc0 k0,CP0_STATUS
- ehb
-
- /* load up the new EBASE */
- LONG_L k0, VCPU_GUEST_EBASE(k1)
- mtc0 k0,CP0_EBASE
-
- /* Now that the new EBASE has been loaded, unset BEV, set interrupt mask as it was
- * but make sure that timer interrupts are enabled
- */
- li k0,(ST0_EXL | KSU_USER | ST0_IE)
- andi v0, v0, ST0_IM
- or k0, k0, v0
- mtc0 k0,CP0_STATUS
- ehb
+ li k0, (ST0_EXL | KSU_USER | ST0_BEV)
+ mtc0 k0, CP0_STATUS
+ ehb
+
+ /* load up the new EBASE */
+ LONG_L k0, VCPU_GUEST_EBASE(k1)
+ mtc0 k0, CP0_EBASE
+
+ /*
+ * Now that the new EBASE has been loaded, unset BEV, set
+ * interrupt mask as it was but make sure that timer interrupts
+ * are enabled
+ */
+ li k0, (ST0_EXL | KSU_USER | ST0_IE)
+ andi v0, v0, ST0_IM
+ or k0, k0, v0
+ mtc0 k0, CP0_STATUS
+ ehb
/* Set Guest EPC */
- LONG_L t0, VCPU_PC(k1)
- mtc0 t0, CP0_EPC
+ LONG_L t0, VCPU_PC(k1)
+ mtc0 t0, CP0_EPC
FEXPORT(__kvm_mips_load_asid)
- /* Set the ASID for the Guest Kernel */
- sll t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */
- /* addresses shift to 0x80000000 */
- bltz t0, 1f /* If kernel */
- addiu t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */
- addiu t1, k1, VCPU_GUEST_USER_ASID /* else user */
+ /* Set the ASID for the Guest Kernel */
+ INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */
+ /* addresses shift to 0x80000000 */
+ bltz t0, 1f /* If kernel */
+ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */
+ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */
1:
- /* t1: contains the base of the ASID array, need to get the cpu id */
- LONG_L t2, TI_CPU($28) /* smp_processor_id */
- sll t2, t2, 2 /* x4 */
- addu t3, t1, t2
- LONG_L k0, (t3)
- andi k0, k0, 0xff
- mtc0 k0,CP0_ENTRYHI
- ehb
-
- /* Disable RDHWR access */
- mtc0 zero, CP0_HWRENA
-
- /* Now load up the Guest Context from VCPU */
- LONG_L $1, VCPU_R1(k1)
- LONG_L $2, VCPU_R2(k1)
- LONG_L $3, VCPU_R3(k1)
-
- LONG_L $4, VCPU_R4(k1)
- LONG_L $5, VCPU_R5(k1)
- LONG_L $6, VCPU_R6(k1)
- LONG_L $7, VCPU_R7(k1)
-
- LONG_L $8, VCPU_R8(k1)
- LONG_L $9, VCPU_R9(k1)
- LONG_L $10, VCPU_R10(k1)
- LONG_L $11, VCPU_R11(k1)
- LONG_L $12, VCPU_R12(k1)
- LONG_L $13, VCPU_R13(k1)
- LONG_L $14, VCPU_R14(k1)
- LONG_L $15, VCPU_R15(k1)
- LONG_L $16, VCPU_R16(k1)
- LONG_L $17, VCPU_R17(k1)
- LONG_L $18, VCPU_R18(k1)
- LONG_L $19, VCPU_R19(k1)
- LONG_L $20, VCPU_R20(k1)
- LONG_L $21, VCPU_R21(k1)
- LONG_L $22, VCPU_R22(k1)
- LONG_L $23, VCPU_R23(k1)
- LONG_L $24, VCPU_R24(k1)
- LONG_L $25, VCPU_R25(k1)
-
- /* k0/k1 loaded up later */
-
- LONG_L $28, VCPU_R28(k1)
- LONG_L $29, VCPU_R29(k1)
- LONG_L $30, VCPU_R30(k1)
- LONG_L $31, VCPU_R31(k1)
-
- /* Restore hi/lo */
- LONG_L k0, VCPU_LO(k1)
- mtlo k0
-
- LONG_L k0, VCPU_HI(k1)
- mthi k0
+ /* t1: contains the base of the ASID array, need to get the cpu id */
+ LONG_L t2, TI_CPU($28) /* smp_processor_id */
+ INT_SLL t2, t2, 2 /* x4 */
+ REG_ADDU t3, t1, t2
+ LONG_L k0, (t3)
+ andi k0, k0, 0xff
+ mtc0 k0, CP0_ENTRYHI
+ ehb
+
+ /* Disable RDHWR access */
+ mtc0 zero, CP0_HWRENA
+
+ /* Now load up the Guest Context from VCPU */
+ LONG_L $1, VCPU_R1(k1)
+ LONG_L $2, VCPU_R2(k1)
+ LONG_L $3, VCPU_R3(k1)
+
+ LONG_L $4, VCPU_R4(k1)
+ LONG_L $5, VCPU_R5(k1)
+ LONG_L $6, VCPU_R6(k1)
+ LONG_L $7, VCPU_R7(k1)
+
+ LONG_L $8, VCPU_R8(k1)
+ LONG_L $9, VCPU_R9(k1)
+ LONG_L $10, VCPU_R10(k1)
+ LONG_L $11, VCPU_R11(k1)
+ LONG_L $12, VCPU_R12(k1)
+ LONG_L $13, VCPU_R13(k1)
+ LONG_L $14, VCPU_R14(k1)
+ LONG_L $15, VCPU_R15(k1)
+ LONG_L $16, VCPU_R16(k1)
+ LONG_L $17, VCPU_R17(k1)
+ LONG_L $18, VCPU_R18(k1)
+ LONG_L $19, VCPU_R19(k1)
+ LONG_L $20, VCPU_R20(k1)
+ LONG_L $21, VCPU_R21(k1)
+ LONG_L $22, VCPU_R22(k1)
+ LONG_L $23, VCPU_R23(k1)
+ LONG_L $24, VCPU_R24(k1)
+ LONG_L $25, VCPU_R25(k1)
+
+ /* k0/k1 loaded up later */
+
+ LONG_L $28, VCPU_R28(k1)
+ LONG_L $29, VCPU_R29(k1)
+ LONG_L $30, VCPU_R30(k1)
+ LONG_L $31, VCPU_R31(k1)
+
+ /* Restore hi/lo */
+ LONG_L k0, VCPU_LO(k1)
+ mtlo k0
+
+ LONG_L k0, VCPU_HI(k1)
+ mthi k0
FEXPORT(__kvm_mips_load_k0k1)
/* Restore the guest's k0/k1 registers */
- LONG_L k0, VCPU_R26(k1)
- LONG_L k1, VCPU_R27(k1)
+ LONG_L k0, VCPU_R26(k1)
+ LONG_L k1, VCPU_R27(k1)
- /* Jump to guest */
+ /* Jump to guest */
eret
- .set pop
VECTOR(MIPSX(exception), unknown)
/*
* Find out what mode we came from and jump to the proper handler.
*/
- .set push
- .set noat
- .set noreorder
- mtc0 k0, CP0_ERROREPC #01: Save guest k0
- ehb #02:
-
- mfc0 k0, CP0_EBASE #02: Get EBASE
- srl k0, k0, 10 #03: Get rid of CPUNum
- sll k0, k0, 10 #04
- LONG_S k1, 0x3000(k0) #05: Save k1 @ offset 0x3000
- addiu k0, k0, 0x2000 #06: Exception handler is installed @ offset 0x2000
- j k0 #07: jump to the function
- nop #08: branch delay slot
- .set push
+ mtc0 k0, CP0_ERROREPC #01: Save guest k0
+ ehb #02:
+
+ mfc0 k0, CP0_EBASE #02: Get EBASE
+ INT_SRL k0, k0, 10 #03: Get rid of CPUNum
+ INT_SLL k0, k0, 10 #04
+ LONG_S k1, 0x3000(k0) #05: Save k1 @ offset 0x3000
+ INT_ADDIU k0, k0, 0x2000 #06: Exception handler is installed @ offset 0x2000
+ j k0 #07: jump to the function
+ nop #08: branch delay slot
VECTOR_END(MIPSX(exceptionEnd))
.end MIPSX(exception)
@@ -253,329 +251,327 @@ VECTOR_END(MIPSX(exceptionEnd))
*
*/
NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
- .set push
- .set noat
- .set noreorder
-
- /* Get the VCPU pointer from DDTATA_LO */
- mfc0 k1, CP0_DDATA_LO
- addiu k1, k1, VCPU_HOST_ARCH
-
- /* Start saving Guest context to VCPU */
- LONG_S $0, VCPU_R0(k1)
- LONG_S $1, VCPU_R1(k1)
- LONG_S $2, VCPU_R2(k1)
- LONG_S $3, VCPU_R3(k1)
- LONG_S $4, VCPU_R4(k1)
- LONG_S $5, VCPU_R5(k1)
- LONG_S $6, VCPU_R6(k1)
- LONG_S $7, VCPU_R7(k1)
- LONG_S $8, VCPU_R8(k1)
- LONG_S $9, VCPU_R9(k1)
- LONG_S $10, VCPU_R10(k1)
- LONG_S $11, VCPU_R11(k1)
- LONG_S $12, VCPU_R12(k1)
- LONG_S $13, VCPU_R13(k1)
- LONG_S $14, VCPU_R14(k1)
- LONG_S $15, VCPU_R15(k1)
- LONG_S $16, VCPU_R16(k1)
- LONG_S $17,VCPU_R17(k1)
- LONG_S $18, VCPU_R18(k1)
- LONG_S $19, VCPU_R19(k1)
- LONG_S $20, VCPU_R20(k1)
- LONG_S $21, VCPU_R21(k1)
- LONG_S $22, VCPU_R22(k1)
- LONG_S $23, VCPU_R23(k1)
- LONG_S $24, VCPU_R24(k1)
- LONG_S $25, VCPU_R25(k1)
-
- /* Guest k0/k1 saved later */
-
- LONG_S $28, VCPU_R28(k1)
- LONG_S $29, VCPU_R29(k1)
- LONG_S $30, VCPU_R30(k1)
- LONG_S $31, VCPU_R31(k1)
-
- /* We need to save hi/lo and restore them on
- * the way out
- */
- mfhi t0
- LONG_S t0, VCPU_HI(k1)
-
- mflo t0
- LONG_S t0, VCPU_LO(k1)
-
- /* Finally save guest k0/k1 to VCPU */
- mfc0 t0, CP0_ERROREPC
- LONG_S t0, VCPU_R26(k1)
-
- /* Get GUEST k1 and save it in VCPU */
- la t1, ~0x2ff
- mfc0 t0, CP0_EBASE
- and t0, t0, t1
- LONG_L t0, 0x3000(t0)
- LONG_S t0, VCPU_R27(k1)
-
- /* Now that context has been saved, we can use other registers */
-
- /* Restore vcpu */
- mfc0 a1, CP0_DDATA_LO
- move s1, a1
-
- /* Restore run (vcpu->run) */
- LONG_L a0, VCPU_RUN(a1)
- /* Save pointer to run in s0, will be saved by the compiler */
- move s0, a0
-
-
- /* Save Host level EPC, BadVaddr and Cause to VCPU, useful to process the exception */
- mfc0 k0,CP0_EPC
- LONG_S k0, VCPU_PC(k1)
-
- mfc0 k0, CP0_BADVADDR
- LONG_S k0, VCPU_HOST_CP0_BADVADDR(k1)
-
- mfc0 k0, CP0_CAUSE
- LONG_S k0, VCPU_HOST_CP0_CAUSE(k1)
-
- mfc0 k0, CP0_ENTRYHI
- LONG_S k0, VCPU_HOST_ENTRYHI(k1)
-
- /* Now restore the host state just enough to run the handlers */
-
- /* Swtich EBASE to the one used by Linux */
- /* load up the host EBASE */
- mfc0 v0, CP0_STATUS
-
- .set at
- or k0, v0, ST0_BEV
- .set noat
-
- mtc0 k0, CP0_STATUS
- ehb
-
- LONG_L k0, VCPU_HOST_EBASE(k1)
- mtc0 k0,CP0_EBASE
-
-
- /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
- .set at
- and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
- or v0, v0, ST0_CU0
- .set noat
- mtc0 v0, CP0_STATUS
- ehb
-
- /* Load up host GP */
- LONG_L gp, VCPU_HOST_GP(k1)
-
- /* Need a stack before we can jump to "C" */
- LONG_L sp, VCPU_HOST_STACK(k1)
-
- /* Saved host state */
- addiu sp,sp, -PT_SIZE
+ /* Get the VCPU pointer from DDTATA_LO */
+ mfc0 k1, CP0_DDATA_LO
+ INT_ADDIU k1, k1, VCPU_HOST_ARCH
+
+ /* Start saving Guest context to VCPU */
+ LONG_S $0, VCPU_R0(k1)
+ LONG_S $1, VCPU_R1(k1)
+ LONG_S $2, VCPU_R2(k1)
+ LONG_S $3, VCPU_R3(k1)
+ LONG_S $4, VCPU_R4(k1)
+ LONG_S $5, VCPU_R5(k1)
+ LONG_S $6, VCPU_R6(k1)
+ LONG_S $7, VCPU_R7(k1)
+ LONG_S $8, VCPU_R8(k1)
+ LONG_S $9, VCPU_R9(k1)
+ LONG_S $10, VCPU_R10(k1)
+ LONG_S $11, VCPU_R11(k1)
+ LONG_S $12, VCPU_R12(k1)
+ LONG_S $13, VCPU_R13(k1)
+ LONG_S $14, VCPU_R14(k1)
+ LONG_S $15, VCPU_R15(k1)
+ LONG_S $16, VCPU_R16(k1)
+ LONG_S $17, VCPU_R17(k1)
+ LONG_S $18, VCPU_R18(k1)
+ LONG_S $19, VCPU_R19(k1)
+ LONG_S $20, VCPU_R20(k1)
+ LONG_S $21, VCPU_R21(k1)
+ LONG_S $22, VCPU_R22(k1)
+ LONG_S $23, VCPU_R23(k1)
+ LONG_S $24, VCPU_R24(k1)
+ LONG_S $25, VCPU_R25(k1)
+
+ /* Guest k0/k1 saved later */
+
+ LONG_S $28, VCPU_R28(k1)
+ LONG_S $29, VCPU_R29(k1)
+ LONG_S $30, VCPU_R30(k1)
+ LONG_S $31, VCPU_R31(k1)
+
+ /* We need to save hi/lo and restore them on
+ * the way out
+ */
+ mfhi t0
+ LONG_S t0, VCPU_HI(k1)
+
+ mflo t0
+ LONG_S t0, VCPU_LO(k1)
+
+ /* Finally save guest k0/k1 to VCPU */
+ mfc0 t0, CP0_ERROREPC
+ LONG_S t0, VCPU_R26(k1)
+
+ /* Get GUEST k1 and save it in VCPU */
+ PTR_LI t1, ~0x2ff
+ mfc0 t0, CP0_EBASE
+ and t0, t0, t1
+ LONG_L t0, 0x3000(t0)
+ LONG_S t0, VCPU_R27(k1)
+
+ /* Now that context has been saved, we can use other registers */
+
+ /* Restore vcpu */
+ mfc0 a1, CP0_DDATA_LO
+ move s1, a1
+
+ /* Restore run (vcpu->run) */
+ LONG_L a0, VCPU_RUN(a1)
+ /* Save pointer to run in s0, will be saved by the compiler */
+ move s0, a0
+
+ /* Save Host level EPC, BadVaddr and Cause to VCPU, useful to
+ * process the exception */
+ mfc0 k0,CP0_EPC
+ LONG_S k0, VCPU_PC(k1)
+
+ mfc0 k0, CP0_BADVADDR
+ LONG_S k0, VCPU_HOST_CP0_BADVADDR(k1)
+
+ mfc0 k0, CP0_CAUSE
+ LONG_S k0, VCPU_HOST_CP0_CAUSE(k1)
+
+ mfc0 k0, CP0_ENTRYHI
+ LONG_S k0, VCPU_HOST_ENTRYHI(k1)
+
+ /* Now restore the host state just enough to run the handlers */
+
+ /* Swtich EBASE to the one used by Linux */
+ /* load up the host EBASE */
+ mfc0 v0, CP0_STATUS
+
+ .set at
+ or k0, v0, ST0_BEV
+ .set noat
+
+ mtc0 k0, CP0_STATUS
+ ehb
+
+ LONG_L k0, VCPU_HOST_EBASE(k1)
+ mtc0 k0,CP0_EBASE
+
- /* XXXKYMA do we need to load the host ASID, maybe not because the
- * kernel entries are marked GLOBAL, need to verify
- */
+ /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
+ .set at
+ and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
+ or v0, v0, ST0_CU0
+ .set noat
+ mtc0 v0, CP0_STATUS
+ ehb
+
+ /* Load up host GP */
+ LONG_L gp, VCPU_HOST_GP(k1)
+
+ /* Need a stack before we can jump to "C" */
+ LONG_L sp, VCPU_HOST_STACK(k1)
+
+ /* Saved host state */
+ INT_ADDIU sp, sp, -PT_SIZE
- /* Restore host DDATA_LO */
- LONG_L k0, PT_HOST_USERLOCAL(sp)
- mtc0 k0, CP0_DDATA_LO
+ /* XXXKYMA do we need to load the host ASID, maybe not because the
+ * kernel entries are marked GLOBAL, need to verify
+ */
- /* Restore RDHWR access */
- la k0, 0x2000000F
- mtc0 k0, CP0_HWRENA
+ /* Restore host DDATA_LO */
+ LONG_L k0, PT_HOST_USERLOCAL(sp)
+ mtc0 k0, CP0_DDATA_LO
- /* Jump to handler */
+ /* Restore RDHWR access */
+ PTR_LI k0, 0x2000000F
+ mtc0 k0, CP0_HWRENA
+
+ /* Jump to handler */
FEXPORT(__kvm_mips_jump_to_handler)
- /* XXXKYMA: not sure if this is safe, how large is the stack?? */
- /* Now jump to the kvm_mips_handle_exit() to see if we can deal with this in the kernel */
- la t9,kvm_mips_handle_exit
- jalr.hb t9
- addiu sp,sp, -CALLFRAME_SIZ /* BD Slot */
-
- /* Return from handler Make sure interrupts are disabled */
- di
- ehb
-
- /* XXXKYMA: k0/k1 could have been blown away if we processed an exception
- * while we were handling the exception from the guest, reload k1
- */
- move k1, s1
- addiu k1, k1, VCPU_HOST_ARCH
-
- /* Check return value, should tell us if we are returning to the host (handle I/O etc)
- * or resuming the guest
- */
- andi t0, v0, RESUME_HOST
- bnez t0, __kvm_mips_return_to_host
- nop
+ /* XXXKYMA: not sure if this is safe, how large is the stack??
+ * Now jump to the kvm_mips_handle_exit() to see if we can deal
+ * with this in the kernel */
+ PTR_LA t9, kvm_mips_handle_exit
+ jalr.hb t9
+ INT_ADDIU sp, sp, -CALLFRAME_SIZ /* BD Slot */
+
+ /* Return from handler Make sure interrupts are disabled */
+ di
+ ehb
+
+ /* XXXKYMA: k0/k1 could have been blown away if we processed
+ * an exception while we were handling the exception from the
+ * guest, reload k1
+ */
+
+ move k1, s1
+ INT_ADDIU k1, k1, VCPU_HOST_ARCH
+
+ /* Check return value, should tell us if we are returning to the
+ * host (handle I/O etc)or resuming the guest
+ */
+ andi t0, v0, RESUME_HOST
+ bnez t0, __kvm_mips_return_to_host
+ nop
__kvm_mips_return_to_guest:
- /* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */
- mtc0 s1, CP0_DDATA_LO
-
- /* Load up the Guest EBASE to minimize the window where BEV is set */
- LONG_L t0, VCPU_GUEST_EBASE(k1)
-
- /* Switch EBASE back to the one used by KVM */
- mfc0 v1, CP0_STATUS
- .set at
- or k0, v1, ST0_BEV
- .set noat
- mtc0 k0, CP0_STATUS
- ehb
- mtc0 t0,CP0_EBASE
-
- /* Setup status register for running guest in UM */
- .set at
- or v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
- and v1, v1, ~ST0_CU0
- .set noat
- mtc0 v1, CP0_STATUS
- ehb
+ /* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */
+ mtc0 s1, CP0_DDATA_LO
+ /* Load up the Guest EBASE to minimize the window where BEV is set */
+ LONG_L t0, VCPU_GUEST_EBASE(k1)
+
+ /* Switch EBASE back to the one used by KVM */
+ mfc0 v1, CP0_STATUS
+ .set at
+ or k0, v1, ST0_BEV
+ .set noat
+ mtc0 k0, CP0_STATUS
+ ehb
+ mtc0 t0, CP0_EBASE
+
+ /* Setup status register for running guest in UM */
+ .set at
+ or v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
+ and v1, v1, ~ST0_CU0
+ .set noat
+ mtc0 v1, CP0_STATUS
+ ehb
/* Set Guest EPC */
- LONG_L t0, VCPU_PC(k1)
- mtc0 t0, CP0_EPC
-
- /* Set the ASID for the Guest Kernel */
- sll t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */
- /* addresses shift to 0x80000000 */
- bltz t0, 1f /* If kernel */
- addiu t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */
- addiu t1, k1, VCPU_GUEST_USER_ASID /* else user */
+ LONG_L t0, VCPU_PC(k1)
+ mtc0 t0, CP0_EPC
+
+ /* Set the ASID for the Guest Kernel */
+ INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */
+ /* addresses shift to 0x80000000 */
+ bltz t0, 1f /* If kernel */
+ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */
+ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */
1:
- /* t1: contains the base of the ASID array, need to get the cpu id */
- LONG_L t2, TI_CPU($28) /* smp_processor_id */
- sll t2, t2, 2 /* x4 */
- addu t3, t1, t2
- LONG_L k0, (t3)
- andi k0, k0, 0xff
- mtc0 k0,CP0_ENTRYHI
- ehb
-
- /* Disable RDHWR access */
- mtc0 zero, CP0_HWRENA
-
- /* load the guest context from VCPU and return */
- LONG_L $0, VCPU_R0(k1)
- LONG_L $1, VCPU_R1(k1)
- LONG_L $2, VCPU_R2(k1)
- LONG_L $3, VCPU_R3(k1)
- LONG_L $4, VCPU_R4(k1)
- LONG_L $5, VCPU_R5(k1)
- LONG_L $6, VCPU_R6(k1)
- LONG_L $7, VCPU_R7(k1)
- LONG_L $8, VCPU_R8(k1)
- LONG_L $9, VCPU_R9(k1)
- LONG_L $10, VCPU_R10(k1)
- LONG_L $11, VCPU_R11(k1)
- LONG_L $12, VCPU_R12(k1)
- LONG_L $13, VCPU_R13(k1)
- LONG_L $14, VCPU_R14(k1)
- LONG_L $15, VCPU_R15(k1)
- LONG_L $16, VCPU_R16(k1)
- LONG_L $17, VCPU_R17(k1)
- LONG_L $18, VCPU_R18(k1)
- LONG_L $19, VCPU_R19(k1)
- LONG_L $20, VCPU_R20(k1)
- LONG_L $21, VCPU_R21(k1)
- LONG_L $22, VCPU_R22(k1)
- LONG_L $23, VCPU_R23(k1)
- LONG_L $24, VCPU_R24(k1)
- LONG_L $25, VCPU_R25(k1)
-
- /* $/k1 loaded later */
- LONG_L $28, VCPU_R28(k1)
- LONG_L $29, VCPU_R29(k1)
- LONG_L $30, VCPU_R30(k1)
- LONG_L $31, VCPU_R31(k1)
+ /* t1: contains the base of the ASID array, need to get the cpu id */
+ LONG_L t2, TI_CPU($28) /* smp_processor_id */
+ INT_SLL t2, t2, 2 /* x4 */
+ REG_ADDU t3, t1, t2
+ LONG_L k0, (t3)
+ andi k0, k0, 0xff
+ mtc0 k0,CP0_ENTRYHI
+ ehb
+
+ /* Disable RDHWR access */
+ mtc0 zero, CP0_HWRENA
+
+ /* load the guest context from VCPU and return */
+ LONG_L $0, VCPU_R0(k1)
+ LONG_L $1, VCPU_R1(k1)
+ LONG_L $2, VCPU_R2(k1)
+ LONG_L $3, VCPU_R3(k1)
+ LONG_L $4, VCPU_R4(k1)
+ LONG_L $5, VCPU_R5(k1)
+ LONG_L $6, VCPU_R6(k1)
+ LONG_L $7, VCPU_R7(k1)
+ LONG_L $8, VCPU_R8(k1)
+ LONG_L $9, VCPU_R9(k1)
+ LONG_L $10, VCPU_R10(k1)
+ LONG_L $11, VCPU_R11(k1)
+ LONG_L $12, VCPU_R12(k1)
+ LONG_L $13, VCPU_R13(k1)
+ LONG_L $14, VCPU_R14(k1)
+ LONG_L $15, VCPU_R15(k1)
+ LONG_L $16, VCPU_R16(k1)
+ LONG_L $17, VCPU_R17(k1)
+ LONG_L $18, VCPU_R18(k1)
+ LONG_L $19, VCPU_R19(k1)
+ LONG_L $20, VCPU_R20(k1)
+ LONG_L $21, VCPU_R21(k1)
+ LONG_L $22, VCPU_R22(k1)
+ LONG_L $23, VCPU_R23(k1)
+ LONG_L $24, VCPU_R24(k1)
+ LONG_L $25, VCPU_R25(k1)
+
+ /* $/k1 loaded later */
+ LONG_L $28, VCPU_R28(k1)
+ LONG_L $29, VCPU_R29(k1)
+ LONG_L $30, VCPU_R30(k1)
+ LONG_L $31, VCPU_R31(k1)
FEXPORT(__kvm_mips_skip_guest_restore)
- LONG_L k0, VCPU_HI(k1)
- mthi k0
+ LONG_L k0, VCPU_HI(k1)
+ mthi k0
- LONG_L k0, VCPU_LO(k1)
- mtlo k0
+ LONG_L k0, VCPU_LO(k1)
+ mtlo k0
- LONG_L k0, VCPU_R26(k1)
- LONG_L k1, VCPU_R27(k1)
+ LONG_L k0, VCPU_R26(k1)
+ LONG_L k1, VCPU_R27(k1)
- eret
+ eret
__kvm_mips_return_to_host:
- /* EBASE is already pointing to Linux */
- LONG_L k1, VCPU_HOST_STACK(k1)
- addiu k1,k1, -PT_SIZE
-
- /* Restore host DDATA_LO */
- LONG_L k0, PT_HOST_USERLOCAL(k1)
- mtc0 k0, CP0_DDATA_LO
-
- /* Restore host ASID */
- LONG_L k0, PT_HOST_ASID(sp)
- andi k0, 0xff
- mtc0 k0,CP0_ENTRYHI
- ehb
-
- /* Load context saved on the host stack */
- LONG_L $0, PT_R0(k1)
- LONG_L $1, PT_R1(k1)
-
- /* r2/v0 is the return code, shift it down by 2 (arithmetic) to recover the err code */
- sra k0, v0, 2
- move $2, k0
-
- LONG_L $3, PT_R3(k1)
- LONG_L $4, PT_R4(k1)
- LONG_L $5, PT_R5(k1)
- LONG_L $6, PT_R6(k1)
- LONG_L $7, PT_R7(k1)
- LONG_L $8, PT_R8(k1)
- LONG_L $9, PT_R9(k1)
- LONG_L $10, PT_R10(k1)
- LONG_L $11, PT_R11(k1)
- LONG_L $12, PT_R12(k1)
- LONG_L $13, PT_R13(k1)
- LONG_L $14, PT_R14(k1)
- LONG_L $15, PT_R15(k1)
- LONG_L $16, PT_R16(k1)
- LONG_L $17, PT_R17(k1)
- LONG_L $18, PT_R18(k1)
- LONG_L $19, PT_R19(k1)
- LONG_L $20, PT_R20(k1)
- LONG_L $21, PT_R21(k1)
- LONG_L $22, PT_R22(k1)
- LONG_L $23, PT_R23(k1)
- LONG_L $24, PT_R24(k1)
- LONG_L $25, PT_R25(k1)
-
- /* Host k0/k1 were not saved */
-
- LONG_L $28, PT_R28(k1)
- LONG_L $29, PT_R29(k1)
- LONG_L $30, PT_R30(k1)
-
- LONG_L k0, PT_HI(k1)
- mthi k0
-
- LONG_L k0, PT_LO(k1)
- mtlo k0
-
- /* Restore RDHWR access */
- la k0, 0x2000000F
- mtc0 k0, CP0_HWRENA
-
-
- /* Restore RA, which is the address we will return to */
- LONG_L ra, PT_R31(k1)
- j ra
- nop
-
- .set pop
+ /* EBASE is already pointing to Linux */
+ LONG_L k1, VCPU_HOST_STACK(k1)
+ INT_ADDIU k1,k1, -PT_SIZE
+
+ /* Restore host DDATA_LO */
+ LONG_L k0, PT_HOST_USERLOCAL(k1)
+ mtc0 k0, CP0_DDATA_LO
+
+ /* Restore host ASID */
+ LONG_L k0, PT_HOST_ASID(sp)
+ andi k0, 0xff
+ mtc0 k0,CP0_ENTRYHI
+ ehb
+
+ /* Load context saved on the host stack */
+ LONG_L $0, PT_R0(k1)
+ LONG_L $1, PT_R1(k1)
+
+ /* r2/v0 is the return code, shift it down by 2 (arithmetic)
+ * to recover the err code */
+ INT_SRA k0, v0, 2
+ move $2, k0
+
+ LONG_L $3, PT_R3(k1)
+ LONG_L $4, PT_R4(k1)
+ LONG_L $5, PT_R5(k1)
+ LONG_L $6, PT_R6(k1)
+ LONG_L $7, PT_R7(k1)
+ LONG_L $8, PT_R8(k1)
+ LONG_L $9, PT_R9(k1)
+ LONG_L $10, PT_R10(k1)
+ LONG_L $11, PT_R11(k1)
+ LONG_L $12, PT_R12(k1)
+ LONG_L $13, PT_R13(k1)
+ LONG_L $14, PT_R14(k1)
+ LONG_L $15, PT_R15(k1)
+ LONG_L $16, PT_R16(k1)
+ LONG_L $17, PT_R17(k1)
+ LONG_L $18, PT_R18(k1)
+ LONG_L $19, PT_R19(k1)
+ LONG_L $20, PT_R20(k1)
+ LONG_L $21, PT_R21(k1)
+ LONG_L $22, PT_R22(k1)
+ LONG_L $23, PT_R23(k1)
+ LONG_L $24, PT_R24(k1)
+ LONG_L $25, PT_R25(k1)
+
+ /* Host k0/k1 were not saved */
+
+ LONG_L $28, PT_R28(k1)
+ LONG_L $29, PT_R29(k1)
+ LONG_L $30, PT_R30(k1)
+
+ LONG_L k0, PT_HI(k1)
+ mthi k0
+
+ LONG_L k0, PT_LO(k1)
+ mtlo k0
+
+ /* Restore RDHWR access */
+ PTR_LI k0, 0x2000000F
+ mtc0 k0, CP0_HWRENA
+
+
+ /* Restore RA, which is the address we will return to */
+ LONG_L ra, PT_R31(k1)
+ j ra
+ nop
+
VECTOR_END(MIPSX(GuestExceptionEnd))
.end MIPSX(GuestException)
@@ -627,24 +623,23 @@ MIPSX(exceptions):
#define HW_SYNCI_Step $1
LEAF(MIPSX(SyncICache))
- .set push
+ .set push
.set mips32r2
- beq a1, zero, 20f
- nop
- addu a1, a0, a1
- rdhwr v0, HW_SYNCI_Step
- beq v0, zero, 20f
- nop
-
+ beq a1, zero, 20f
+ nop
+ REG_ADDU a1, a0, a1
+ rdhwr v0, HW_SYNCI_Step
+ beq v0, zero, 20f
+ nop
10:
- synci 0(a0)
- addu a0, a0, v0
- sltu v1, a0, a1
- bne v1, zero, 10b
- nop
- sync
+ synci 0(a0)
+ REG_ADDU a0, a0, v0
+ sltu v1, a0, a1
+ bne v1, zero, 10b
+ nop
+ sync
20:
- jr.hb ra
- nop
- .set pop
+ jr.hb ra
+ nop
+ .set pop
END(MIPSX(SyncICache))
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index b7a1911d108..043eec8461e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1579,7 +1579,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
ctx->first_pass = 1;
rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
- ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
+ ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC);
if (ret < 0) {
kvm_put_kvm(kvm);
return ret;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b2d3f3b2de7..54cf9bc94da 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -136,7 +136,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
mutex_unlock(&kvm->lock);
return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
- stt, O_RDWR);
+ stt, O_RDWR | O_CLOEXEC);
fail:
if (stt) {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8aadd237d45..b0ee3bc9ca7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1564,7 +1564,7 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
if (!ri)
return -ENOMEM;
- fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR);
+ fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC);
if (fd < 0)
kvm_release_rma(ri);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c0efd16bdfa..c76ff74a98f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -516,6 +516,11 @@ struct kvm_vcpu_arch {
/* set at EPT violation at this point */
unsigned long exit_qualification;
+
+ /* pv related host specific info */
+ struct {
+ bool pv_unhalted;
+ } pv;
};
struct kvm_lpage_info {
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 06fdbd987e9..94dc8ca434e 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -23,6 +23,7 @@
#define KVM_FEATURE_ASYNC_PF 4
#define KVM_FEATURE_STEAL_TIME 5
#define KVM_FEATURE_PV_EOI 6
+#define KVM_FEATURE_PV_UNHALT 7
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cb..b110fe6c03d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -413,7 +413,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
(1 << KVM_FEATURE_CLOCKSOURCE2) |
(1 << KVM_FEATURE_ASYNC_PF) |
(1 << KVM_FEATURE_PV_EOI) |
- (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+ (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+ (1 << KVM_FEATURE_PV_UNHALT);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c98f0544232..5439117d5c4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -689,7 +689,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
break;
case APIC_DM_REMRD:
- apic_debug("Ignoring delivery mode 3\n");
+ result = 1;
+ vcpu->arch.pv.pv_unhalted = 1;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_SMI:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9651c993758..6e2d2c8f230 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2781,7 +2781,7 @@ exit:
return ret;
}
-static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code)
+static bool page_fault_can_be_fast(u32 error_code)
{
/*
* Do not fix the mmio spte with invalid generation number which
@@ -2834,7 +2834,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
bool ret = false;
u64 spte = 0ull;
- if (!page_fault_can_be_fast(vcpu, error_code))
+ if (!page_fault_can_be_fast(error_code))
return false;
walk_shadow_page_lockless_begin(vcpu);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 57b4e129891..1f1da43ff2a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5485,6 +5485,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
if (err == EMULATE_USER_EXIT) {
+ ++vcpu->stat.mmio_exits;
ret = 0;
goto out;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 668f19aee6c..e5ca72a5cdb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1447,6 +1447,29 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
#endif
}
+static void kvm_gen_update_masterclock(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm_arch *ka = &kvm->arch;
+
+ spin_lock(&ka->pvclock_gtod_sync_lock);
+ kvm_make_mclock_inprogress_request(kvm);
+ /* no guest entries from this point */
+ pvclock_update_vm_gtod_copy(kvm);
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+
+ /* guest entries allowed */
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+#endif
+}
+
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags, this_tsc_khz;
@@ -3796,6 +3819,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
delta = user_ns.clock - now_ns;
local_irq_enable();
kvm->arch.kvmclock_offset = delta;
+ kvm_gen_update_masterclock(kvm);
break;
}
case KVM_GET_CLOCK: {
@@ -5122,9 +5146,10 @@ restart:
inject_emulated_exception(vcpu);
r = EMULATE_DONE;
} else if (vcpu->arch.pio.count) {
- if (!vcpu->arch.pio.in)
+ if (!vcpu->arch.pio.in) {
+ /* FIXME: return into emulator if single-stepping. */
vcpu->arch.pio.count = 0;
- else {
+ } else {
writeback = false;
vcpu->arch.complete_userspace_io = complete_emulated_pio;
}
@@ -5588,6 +5613,23 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
return 1;
}
+/*
+ * kvm_pv_kick_cpu_op: Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
+{
+ struct kvm_lapic_irq lapic_irq;
+
+ lapic_irq.shorthand = 0;
+ lapic_irq.dest_mode = 0;
+ lapic_irq.dest_id = apicid;
+
+ lapic_irq.delivery_mode = APIC_DM_REMRD;
+ kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL);
+}
+
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
@@ -5621,6 +5663,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
case KVM_HC_VAPIC_POLL_IRQ:
ret = 0;
break;
+ case KVM_HC_KICK_CPU:
+ kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+ ret = 0;
+ break;
default:
ret = -KVM_ENOSYS;
break;
@@ -5782,29 +5828,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
-static void kvm_gen_update_masterclock(struct kvm *kvm)
-{
-#ifdef CONFIG_X86_64
- int i;
- struct kvm_vcpu *vcpu;
- struct kvm_arch *ka = &kvm->arch;
-
- spin_lock(&ka->pvclock_gtod_sync_lock);
- kvm_make_mclock_inprogress_request(kvm);
- /* no guest entries from this point */
- pvclock_update_vm_gtod_copy(kvm);
-
- kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
-
- /* guest entries allowed */
- kvm_for_each_vcpu(i, vcpu, kvm)
- clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
-#endif
-}
-
static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
{
u64 eoi_exit_bitmap[4];
@@ -6043,6 +6066,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
kvm_apic_accept_events(vcpu);
switch(vcpu->arch.mp_state) {
case KVM_MP_STATE_HALTED:
+ vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
case KVM_MP_STATE_RUNNABLE:
@@ -6154,6 +6178,8 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
+
+ /* FIXME: return into emulator if single-stepping. */
if (vcpu->mmio_is_write)
return 1;
vcpu->mmio_read_completed = 1;
@@ -6342,7 +6368,12 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
kvm_apic_accept_events(vcpu);
- mp_state->mp_state = vcpu->arch.mp_state;
+ if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+ vcpu->arch.pv.pv_unhalted)
+ mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+ else
+ mp_state->mp_state = vcpu->arch.mp_state;
+
return 0;
}
@@ -6863,6 +6894,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
BUG_ON(vcpu->kvm == NULL);
kvm = vcpu->kvm;
+ vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.emulate_ctxt.ops = &emulate_ops;
if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -7200,6 +7232,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
!vcpu->arch.apf.halted)
|| !list_empty_careful(&vcpu->async_pf.done)
|| kvm_apic_has_events(vcpu)
+ || vcpu->arch.pv.pv_unhalted
|| atomic_read(&vcpu->arch.nmi_queued) ||
(kvm_arch_interrupt_allowed(vcpu) &&
kvm_cpu_has_interrupt(vcpu));
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index acccd08be6c..99c25338ede 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -667,6 +667,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_PPC_RTAS 91
#define KVM_CAP_IRQ_XICS 92
#define KVM_CAP_ARM_EL1_32BIT 93
+#define KVM_CAP_SPAPR_MULTITCE 94
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index cea2c5c72d2..2841f86eae0 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -19,6 +19,7 @@
#define KVM_HC_MMU_OP 2
#define KVM_HC_FEATURES 3
#define KVM_HC_PPC_MAP_MAGIC_PAGE 4
+#define KVM_HC_KICK_CPU 5
/*
* hypercalls use architecture specific
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c6c8bbea174..bf040c4e02b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -102,28 +102,8 @@ static bool largepages_enabled = true;
bool kvm_is_mmio_pfn(pfn_t pfn)
{
- if (pfn_valid(pfn)) {
- int reserved;
- struct page *tail = pfn_to_page(pfn);
- struct page *head = compound_trans_head(tail);
- reserved = PageReserved(head);
- if (head != tail) {
- /*
- * "head" is not a dangling pointer
- * (compound_trans_head takes care of that)
- * but the hugepage may have been splitted
- * from under us (and we may not hold a
- * reference count on the head page so it can
- * be reused before we run PageReferenced), so
- * we've to check PageTail before returning
- * what we just read.
- */
- smp_rmb();
- if (PageTail(tail))
- return reserved;
- }
- return PageReserved(tail);
- }
+ if (pfn_valid(pfn))
+ return PageReserved(pfn_to_page(pfn));
return true;
}
@@ -1896,7 +1876,7 @@ static struct file_operations kvm_vcpu_fops = {
*/
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
- return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR);
+ return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
/*
@@ -2305,7 +2285,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
return ret;
}
- ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR);
+ ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
if (ret < 0) {
ops->destroy(dev);
return ret;
@@ -2589,7 +2569,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
return r;
}
#endif
- r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+ r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
if (r < 0)
kvm_put_kvm(kvm);
@@ -2815,8 +2795,8 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
kfree(bus);
}
-static inline int __kvm_io_bus_sort_cmp(const struct kvm_io_range *r1,
- const struct kvm_io_range *r2)
+static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
+ const struct kvm_io_range *r2)
{
if (r1->addr < r2->addr)
return -1;
@@ -2827,7 +2807,7 @@ static inline int __kvm_io_bus_sort_cmp(const struct kvm_io_range *r1,
static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
{
- return __kvm_io_bus_sort_cmp(p1, p2);
+ return kvm_io_bus_cmp(p1, p2);
}
static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
@@ -2863,7 +2843,7 @@ static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
off = range - bus->range;
- while (off > 0 && __kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0)
+ while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0)
off--;
return off;
@@ -2879,7 +2859,7 @@ static int __kvm_io_bus_write(struct kvm_io_bus *bus,
return -EOPNOTSUPP;
while (idx < bus->dev_count &&
- __kvm_io_bus_sort_cmp(range, &bus->range[idx]) == 0) {
+ kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
if (!kvm_iodevice_write(bus->range[idx].dev, range->addr,
range->len, val))
return idx;
@@ -2923,7 +2903,7 @@ int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
/* First try the device referenced by cookie. */
if ((cookie >= 0) && (cookie < bus->dev_count) &&
- (__kvm_io_bus_sort_cmp(&range, &bus->range[cookie]) == 0))
+ (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len,
val))
return cookie;
@@ -2945,7 +2925,7 @@ static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
return -EOPNOTSUPP;
while (idx < bus->dev_count &&
- __kvm_io_bus_sort_cmp(range, &bus->range[idx]) == 0) {
+ kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
if (!kvm_iodevice_read(bus->range[idx].dev, range->addr,
range->len, val))
return idx;
@@ -2989,7 +2969,7 @@ int kvm_io_bus_read_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
/* First try the device referenced by cookie. */
if ((cookie >= 0) && (cookie < bus->dev_count) &&
- (__kvm_io_bus_sort_cmp(&range, &bus->range[cookie]) == 0))
+ (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
if (!kvm_iodevice_read(bus->range[cookie].dev, addr, len,
val))
return cookie;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-05 03:21:54 +0000