MIPS: KVM: Fix modular KVM under QEMU

Copy __kvm_mips_vcpu_run() into unmapped memory, so that we can never
get a TLB refill exception in it when KVM is built as a module.

This was observed to happen with the host MIPS kernel running under
QEMU, due to a not entirely transparent optimisation in the QEMU TLB
handling where TLB entries replaced with TLBWR are copied to a separate
part of the TLB array. Code in those pages continue to be executable,
but those mappings persist only until the next ASID switch, even if they
are marked global.

An ASID switch happens in __kvm_mips_vcpu_run() at exception level after
switching to the guest exception base. Subsequent TLB mapped kernel
instructions just prior to switching to the guest trigger a TLB refill
exception, which enters the guest exception handlers without updating
EPC. This appears as a guest triggered TLB refill on a host kernel
mapped (host KSeg2) address, which is not handled correctly as user
(guest) mode accesses to kernel (host) segments always generate address
error exceptions.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: kvm@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: <stable@vger.kernel.org> # 3.10.x-
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 6733ac575da4fd13d7cee0e06e4e45e0c2d9b0a6..2d5bb133d11a520f73f4a53aaa1620e670cd79c2 100644 (file)
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -338,6 +338,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE        64
 struct kvm_vcpu_arch {
        void *host_ebase, *guest_ebase;
+       int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
        unsigned long host_stack;
        unsigned long host_gp;
 

diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h
index 4ab4bdfad703e5f19ed1f2db2c10bbece179f259..2143884709e4761ca440cab2944709f1e85661f5 100644 (file)
--- a/arch/mips/kvm/interrupt.h
+++ b/arch/mips/kvm/interrupt.h
@@ -28,6 +28,7 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char __kvm_mips_vcpu_run_end[];
 extern char mips32_exception[], mips32_exceptionEnd[];
 extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 

diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 3ef03009de5f65fa4807cac71bb9749baaa63ab7..828fcfc1cd7fe9037dc70c1828d4630ac9839c33 100644 (file)
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 
        /* Jump to guest */
        eret
+EXPORT(__kvm_mips_vcpu_run_end)
 
 VECTOR(MIPSX(exception), unknown)
 /* Find out what mode we came from and jump to the proper handler. */

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index dc052fb5c7a2f80cdc20b7bf282b0cb09fc30a2e..44da5259f39027e9bd8d0e6584c864997d3388e9 100644 (file)
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
        memcpy(gebase + offset, mips32_GuestException,
               mips32_GuestExceptionEnd - mips32_GuestException);
 
+#ifdef MODULE
+       offset += mips32_GuestExceptionEnd - mips32_GuestException;
+       memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run,
+              __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run);
+       vcpu->arch.vcpu_run = gebase + offset;
+#else
+       vcpu->arch.vcpu_run = __kvm_mips_vcpu_run;
+#endif
+
        /* Invalidate the icache for these ranges */
        local_flush_icache_range((unsigned long)gebase,
                                (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
@@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
        /* Disable hardware page table walking while in guest */
        htw_stop();
 
-       r = __kvm_mips_vcpu_run(run, vcpu);
+       r = vcpu->arch.vcpu_run(run, vcpu);
 
        /* Re-enable HTW before enabling interrupts */
        htw_start();