KVM: PPC: Implement MMIO emulation support for Book3S HV guests
This provides the low-level support for MMIO emulation in Book3S HV
guests. When the guest tries to map a page which is not covered by
any memslot, that page is taken to be an MMIO emulation page. Instead
of inserting a valid HPTE, we insert an HPTE that has the valid bit
clear but another hypervisor software-use bit set, which we call
HPTE_V_ABSENT, to indicate that this is an absent page. An
absent page is treated much like a valid page as far as guest hcalls
(H_ENTER, H_REMOVE, H_READ etc.) are concerned, except of course that
an absent HPTE doesn't need to be invalidated with tlbie since it
was never valid as far as the hardware is concerned.
When the guest accesses a page for which there is an absent HPTE, it
will take a hypervisor data storage interrupt (HDSI) since we now set
the VPM1 bit in the LPCR. Our HDSI handler for HPTE-not-present faults
looks up the hash table and if it finds an absent HPTE mapping the
requested virtual address, will switch to kernel mode and handle the
fault in kvmppc_book3s_hv_page_fault(), which at present just calls
kvmppc_hv_emulate_mmio() to set up the MMIO emulation.
This is based on an earlier patch by Benjamin Herrenschmidt, but since
heavily reworked.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5c8b261..d07b64d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -601,6 +601,28 @@
stw r12,VCPU_TRAP(r9)
+ /* Save HEIR (HV emulation assist reg) in last_inst
+ if this is an HEI (HV emulation interrupt, e40) */
+ li r3,KVM_INST_FETCH_FAILED
+BEGIN_FTR_SECTION
+ cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
+ bne 11f
+ mfspr r3,SPRN_HEIR
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+11: stw r3,VCPU_LAST_INST(r9)
+
+ /* these are volatile across C function calls */
+ mfctr r3
+ mfxer r4
+ std r3, VCPU_CTR(r9)
+ stw r4, VCPU_XER(r9)
+
+BEGIN_FTR_SECTION
+ /* If this is a page table miss then see if it's theirs or ours */
+ cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+ beq kvmppc_hdsi
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
/* See if this is a leftover HDEC interrupt */
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
bne 2f
@@ -608,7 +630,7 @@
cmpwi r3,0
bge ignore_hdec
2:
- /* See if this is something we can handle in real mode */
+ /* See if this is an hcall we can handle in real mode */
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
@@ -624,6 +646,7 @@
1:
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+nohpte_cont:
hcall_real_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
/* Save DEC */
mfspr r5,SPRN_DEC
@@ -632,36 +655,21 @@
add r5,r5,r6
std r5,VCPU_DEC_EXPIRES(r9)
- /* Save HEIR (HV emulation assist reg) in last_inst
- if this is an HEI (HV emulation interrupt, e40) */
- li r3,-1
-BEGIN_FTR_SECTION
- cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
- bne 11f
- mfspr r3,SPRN_HEIR
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-11: stw r3,VCPU_LAST_INST(r9)
-
/* Save more register state */
- mfxer r5
mfdar r6
mfdsisr r7
- mfctr r8
-
- stw r5, VCPU_XER(r9)
std r6, VCPU_DAR(r9)
stw r7, VCPU_DSISR(r9)
- std r8, VCPU_CTR(r9)
- /* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */
BEGIN_FTR_SECTION
+ /* don't overwrite fault_dar/fault_dsisr if HDSI */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
beq 6f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-7: std r6, VCPU_FAULT_DAR(r9)
+ std r6, VCPU_FAULT_DAR(r9)
stw r7, VCPU_FAULT_DSISR(r9)
/* Save guest CTRL register, set runlatch to 1 */
- mfspr r6,SPRN_CTRLF
+6: mfspr r6,SPRN_CTRLF
stw r6,VCPU_CTRL(r9)
andi. r0,r6,1
bne 4f
@@ -1094,9 +1102,84 @@
mtspr SPRN_HSRR1, r7
ba 0x500
-6: mfspr r6,SPRN_HDAR
- mfspr r7,SPRN_HDSISR
- b 7b
+/*
+ * Check whether an HDSI is an HPTE not found fault or something else.
+ * If it is an HPTE not found fault that is due to the guest accessing
+ * a page that they have mapped but which we have paged out, then
+ * we continue on with the guest exit path. In all other cases,
+ * reflect the HDSI to the guest as a DSI.
+ */
+kvmppc_hdsi:
+ mfspr r4, SPRN_HDAR
+ mfspr r6, SPRN_HDSISR
+ /* HPTE not found fault? */
+ andis. r0, r6, DSISR_NOHPTE@h
+ beq 1f /* if not, send it to the guest */
+ andi. r0, r11, MSR_DR /* data relocation enabled? */
+ beq 3f
+ clrrdi r0, r4, 28
+ PPC_SLBFEE_DOT(r5, r0) /* if so, look up SLB */
+ bne 1f /* if no SLB entry found */
+4: std r4, VCPU_FAULT_DAR(r9)
+ stw r6, VCPU_FAULT_DSISR(r9)
+
+ /* Search the hash table. */
+ mr r3, r9 /* vcpu pointer */
+ bl .kvmppc_hpte_hv_fault
+ ld r9, HSTATE_KVM_VCPU(r13)
+ ld r10, VCPU_PC(r9)
+ ld r11, VCPU_MSR(r9)
+ li r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+ cmpdi r3, 0 /* retry the instruction */
+ beq 6f
+ cmpdi r3, -1 /* handle in kernel mode */
+ beq nohpte_cont
+ cmpdi r3, -2 /* MMIO emulation; need instr word */
+ beq 2f
+
+ /* Synthesize a DSI for the guest */
+ ld r4, VCPU_FAULT_DAR(r9)
+ mr r6, r3
+1: mtspr SPRN_DAR, r4
+ mtspr SPRN_DSISR, r6
+ mtspr SPRN_SRR0, r10
+ mtspr SPRN_SRR1, r11
+ li r10, BOOK3S_INTERRUPT_DATA_STORAGE
+ li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
+ rotldi r11, r11, 63
+6: ld r7, VCPU_CTR(r9)
+ lwz r8, VCPU_XER(r9)
+ mtctr r7
+ mtxer r8
+ mr r4, r9
+ b fast_guest_return
+
+3: ld r5, VCPU_KVM(r9) /* not relocated, use VRMA */
+ ld r5, KVM_VRMA_SLB_V(r5)
+ b 4b
+
+ /* If this is for emulated MMIO, load the instruction word */
+2: li r8, KVM_INST_FETCH_FAILED /* In case lwz faults */
+
+ /* Set guest mode to 'jump over instruction' so if lwz faults
+ * we'll just continue at the next IP. */
+ li r0, KVM_GUEST_MODE_SKIP
+ stb r0, HSTATE_IN_GUEST(r13)
+
+ /* Do the access with MSR:DR enabled */
+ mfmsr r3
+ ori r4, r3, MSR_DR /* Enable paging for data */
+ mtmsrd r4
+ lwz r8, 0(r10)
+ mtmsrd r3
+
+ /* Store the result */
+ stw r8, VCPU_LAST_INST(r9)
+
+ /* Unset guest mode. */
+ li r0, KVM_GUEST_MODE_NONE
+ stb r0, HSTATE_IN_GUEST(r13)
+ b nohpte_cont
/*
* Try to handle an hcall in real mode.