Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Avi Kivity:
"Highlights include
- full big real mode emulation on pre-Westmere Intel hosts (can be
disabled with emulate_invalid_guest_state=0)
- relatively small ppc and s390 updates
- PCID/INVPCID support in guests
- EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
interrupt intensive workloads)
- Lockless write faults during live migration
- EPT accessed/dirty bits support for new Intel processors"
Fix up conflicts in:
- Documentation/virtual/kvm/api.txt:
Stupid subchapter numbering, added next to each other.
- arch/powerpc/kvm/booke_interrupts.S:
PPC asm changes clashing with the KVM fixes
- arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:
Duplicated commits through the kvm tree and the s390 tree, with
subsequent edits in the KVM tree.
* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
KVM: fix race with level interrupts
x86, hyper: fix build with !CONFIG_KVM_GUEST
Revert "apic: fix kvm build on UP without IOAPIC"
KVM guest: switch to apic_set_eoi_write, apic_write
apic: add apic_set_eoi_write for PV use
KVM: VMX: Implement PCID/INVPCID for guests with EPT
KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
KVM: PPC: Critical interrupt emulation support
KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
KVM: PPC: bookehv64: Add support for std/ld emulation.
booke: Added crit/mc exception handler for e500v2
booke/bookehv: Add host crit-watchdog exception support
KVM: MMU: document mmu-lock and fast page fault
KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
KVM: MMU: trace fast page fault
KVM: MMU: fast path of handling guest page fault
KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
KVM: MMU: fold tlb flush judgement into mmu_spte_update
...
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index 976835d..bf2c06c 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -153,6 +153,8 @@
#define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
#define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
+extern bool epapr_paravirt_enabled;
+extern u32 epapr_hypercall_start[];
/*
* We use "uintptr_t" to define a register because it's guaranteed to be a
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 0554ab0..e45c494 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -34,6 +34,8 @@
extern void timer_interrupt(struct pt_regs *);
extern void performance_monitor_exception(struct pt_regs *regs);
+extern void WatchdogException(struct pt_regs *regs);
+extern void unknown_exception(struct pt_regs *regs);
#ifdef CONFIG_PPC64
#include <asm/paca.h>
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b0c08b1..0dd1d86 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -36,11 +36,8 @@
#define SPAPR_TCE_SHIFT 12
#ifdef CONFIG_KVM_BOOK3S_64_HV
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER 24
-#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */
-#define HPT_NPTE (HPT_NPTEG << 3) /* 8 PTEs per PTEG */
-#define HPT_HASH_MASK (HPT_NPTEG - 1)
+#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */
+extern int kvm_hpt_order; /* order of preallocated HPTs */
#endif
#define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d848cdc..50ea12f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -237,6 +237,10 @@
unsigned long vrma_slb_v;
int rma_setup_done;
int using_mmu_notifiers;
+ u32 hpt_order;
+ atomic_t vcpus_running;
+ unsigned long hpt_npte;
+ unsigned long hpt_mask;
spinlock_t slot_phys_lock;
unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
int slot_npages[KVM_MEM_SLOTS_NUM];
@@ -414,7 +418,9 @@
ulong mcsrr1;
ulong mcsr;
u32 dec;
+#ifdef CONFIG_BOOKE
u32 decar;
+#endif
u32 tbl;
u32 tbu;
u32 tcr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f68c22f..0124937 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,7 +119,8 @@
extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
extern void kvmppc_map_magic(struct kvm_vcpu *vcpu);
-extern long kvmppc_alloc_hpt(struct kvm *kvm);
+extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp);
+extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp);
extern void kvmppc_free_hpt(struct kvm *kvm);
extern long kvmppc_prepare_vrma(struct kvm *kvm,
struct kvm_userspace_memory_region *mem);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 83afacd..bb282dd 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -128,6 +128,7 @@
obj-y += ppc_save_regs.o
endif
+obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
# Disable GCOV in odd or sensitive code
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
new file mode 100644
index 0000000..697b390
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ blr
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
new file mode 100644
index 0000000..028aeae
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -0,0 +1,52 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+
+bool epapr_paravirt_enabled;
+
+static int __init epapr_paravirt_init(void)
+{
+ struct device_node *hyper_node;
+ const u32 *insts;
+ int len, i;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return -ENODEV;
+
+ insts = of_get_property(hyper_node, "hcall-instructions", &len);
+ if (!insts)
+ return -ENODEV;
+
+ if (len % 4 || len > (4 * 4))
+ return -ENODEV;
+
+ for (i = 0; i < (len / 4); i++)
+ patch_instruction(epapr_hypercall_start + i, insts[i]);
+
+ epapr_paravirt_enabled = true;
+
+ return 0;
+}
+
+early_initcall(epapr_paravirt_init);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 02c167db..867db1d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -31,6 +31,7 @@
#include <asm/cacheflush.h>
#include <asm/disassemble.h>
#include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -726,7 +727,7 @@
unsigned long register r11 asm("r11") = nr;
unsigned long register r12 asm("r12");
- asm volatile("bl kvm_hypercall_start"
+ asm volatile("bl epapr_hypercall_start"
: "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
"=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
"=r"(r12)
@@ -747,29 +748,6 @@
}
EXPORT_SYMBOL_GPL(kvm_hypercall);
-static int kvm_para_setup(void)
-{
- extern u32 kvm_hypercall_start;
- struct device_node *hyper_node;
- u32 *insts;
- int len, i;
-
- hyper_node = of_find_node_by_path("/hypervisor");
- if (!hyper_node)
- return -1;
-
- insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
- if (len % 4)
- return -1;
- if (len > (4 * 4))
- return -1;
-
- for (i = 0; i < (len / 4); i++)
- kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
- return 0;
-}
-
static __init void kvm_free_tmp(void)
{
unsigned long start, end;
@@ -791,7 +769,7 @@
if (!kvm_para_available())
goto free_tmp;
- if (kvm_para_setup())
+ if (!epapr_paravirt_enabled)
goto free_tmp;
if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index e291cf3..e100ff32 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -24,16 +24,6 @@
#include <asm/page.h>
#include <asm/asm-offsets.h>
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
- li r3, -1
- nop
- nop
- nop
- blr
-
#define KVM_MAGIC_PAGE (-4096)
#ifdef CONFIG_64BIT
@@ -132,7 +122,7 @@
.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_SAFE_BITS (MSR_EE | MSR_RI)
#define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
.global kvm_emulate_mtmsr
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80a5775..d03eb6f 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,56 +37,121 @@
/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
#define MAX_LPID_970 63
-long kvmppc_alloc_hpt(struct kvm *kvm)
+/* Power architecture requires HPT is at least 256kB */
+#define PPC_MIN_HPT_ORDER 18
+
+long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
{
unsigned long hpt;
- long lpid;
struct revmap_entry *rev;
struct kvmppc_linear_info *li;
+ long order = kvm_hpt_order;
- /* Allocate guest's hashed page table */
- li = kvm_alloc_hpt();
- if (li) {
- /* using preallocated memory */
- hpt = (ulong)li->base_virt;
- kvm->arch.hpt_li = li;
- } else {
- /* using dynamic memory */
+ if (htab_orderp) {
+ order = *htab_orderp;
+ if (order < PPC_MIN_HPT_ORDER)
+ order = PPC_MIN_HPT_ORDER;
+ }
+
+ /*
+ * If the user wants a different size from default,
+ * try first to allocate it from the kernel page allocator.
+ */
+ hpt = 0;
+ if (order != kvm_hpt_order) {
hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
- __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+ __GFP_NOWARN, order - PAGE_SHIFT);
+ if (!hpt)
+ --order;
}
+ /* Next try to allocate from the preallocated pool */
if (!hpt) {
- pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
- return -ENOMEM;
+ li = kvm_alloc_hpt();
+ if (li) {
+ hpt = (ulong)li->base_virt;
+ kvm->arch.hpt_li = li;
+ order = kvm_hpt_order;
+ }
}
+
+ /* Lastly try successively smaller sizes from the page allocator */
+ while (!hpt && order > PPC_MIN_HPT_ORDER) {
+ hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+ __GFP_NOWARN, order - PAGE_SHIFT);
+ if (!hpt)
+ --order;
+ }
+
+ if (!hpt)
+ return -ENOMEM;
+
kvm->arch.hpt_virt = hpt;
+ kvm->arch.hpt_order = order;
+ /* HPTEs are 2**4 bytes long */
+ kvm->arch.hpt_npte = 1ul << (order - 4);
+ /* 128 (2**7) bytes in each HPTEG */
+ kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
/* Allocate reverse map array */
- rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+ rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
if (!rev) {
pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
goto out_freehpt;
}
kvm->arch.revmap = rev;
+ kvm->arch.sdr1 = __pa(hpt) | (order - 18);
- lpid = kvmppc_alloc_lpid();
- if (lpid < 0)
- goto out_freeboth;
+ pr_info("KVM guest htab at %lx (order %ld), LPID %x\n",
+ hpt, order, kvm->arch.lpid);
- kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
- kvm->arch.lpid = lpid;
-
- pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
+ if (htab_orderp)
+ *htab_orderp = order;
return 0;
- out_freeboth:
- vfree(rev);
out_freehpt:
- free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+ if (kvm->arch.hpt_li)
+ kvm_release_hpt(kvm->arch.hpt_li);
+ else
+ free_pages(hpt, order - PAGE_SHIFT);
return -ENOMEM;
}
+long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
+{
+ long err = -EBUSY;
+ long order;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->arch.rma_setup_done) {
+ kvm->arch.rma_setup_done = 0;
+ /* order rma_setup_done vs. vcpus_running */
+ smp_mb();
+ if (atomic_read(&kvm->arch.vcpus_running)) {
+ kvm->arch.rma_setup_done = 1;
+ goto out;
+ }
+ }
+ if (kvm->arch.hpt_virt) {
+ order = kvm->arch.hpt_order;
+ /* Set the entire HPT to 0, i.e. invalid HPTEs */
+ memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
+ /*
+ * Set the whole last_vcpu array to an invalid vcpu number.
+ * This ensures that each vcpu will flush its TLB on next entry.
+ */
+ memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu));
+ *htab_orderp = order;
+ err = 0;
+ } else {
+ err = kvmppc_alloc_hpt(kvm, htab_orderp);
+ order = *htab_orderp;
+ }
+ out:
+ mutex_unlock(&kvm->lock);
+ return err;
+}
+
void kvmppc_free_hpt(struct kvm *kvm)
{
kvmppc_free_lpid(kvm->arch.lpid);
@@ -94,7 +159,8 @@
if (kvm->arch.hpt_li)
kvm_release_hpt(kvm->arch.hpt_li);
else
- free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+ free_pages(kvm->arch.hpt_virt,
+ kvm->arch.hpt_order - PAGE_SHIFT);
}
/* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
@@ -119,6 +185,7 @@
unsigned long psize;
unsigned long hp0, hp1;
long ret;
+ struct kvm *kvm = vcpu->kvm;
psize = 1ul << porder;
npages = memslot->npages >> (porder - PAGE_SHIFT);
@@ -127,8 +194,8 @@
if (npages > 1ul << (40 - porder))
npages = 1ul << (40 - porder);
/* Can't use more than 1 HPTE per HPTEG */
- if (npages > HPT_NPTEG)
- npages = HPT_NPTEG;
+ if (npages > kvm->arch.hpt_mask + 1)
+ npages = kvm->arch.hpt_mask + 1;
hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
@@ -138,7 +205,7 @@
for (i = 0; i < npages; ++i) {
addr = i << porder;
/* can't use hpt_hash since va > 64 bits */
- hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
+ hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask;
/*
* We assume that the hash table is empty and no
* vcpus are using it at this stage. Since we create
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3abe1b86..83e929e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -56,7 +56,7 @@
/* #define EXIT_DEBUG_INT */
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
@@ -1104,11 +1104,15 @@
return -EINTR;
}
- /* On the first time here, set up VRMA or RMA */
+ atomic_inc(&vcpu->kvm->arch.vcpus_running);
+ /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+ smp_mb();
+
+ /* On the first time here, set up HTAB and VRMA or RMA */
if (!vcpu->kvm->arch.rma_setup_done) {
- r = kvmppc_hv_setup_rma(vcpu);
+ r = kvmppc_hv_setup_htab_rma(vcpu);
if (r)
- return r;
+ goto out;
}
flush_fp_to_thread(current);
@@ -1126,6 +1130,9 @@
kvmppc_core_prepare_to_enter(vcpu);
}
} while (r == RESUME_GUEST);
+
+ out:
+ atomic_dec(&vcpu->kvm->arch.vcpus_running);
return r;
}
@@ -1341,7 +1348,7 @@
{
}
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
{
int err = 0;
struct kvm *kvm = vcpu->kvm;
@@ -1360,6 +1367,15 @@
if (kvm->arch.rma_setup_done)
goto out; /* another vcpu beat us to it */
+ /* Allocate hashed page table (if not done already) and reset it */
+ if (!kvm->arch.hpt_virt) {
+ err = kvmppc_alloc_hpt(kvm, NULL);
+ if (err) {
+ pr_err("KVM: Couldn't alloc HPT\n");
+ goto out;
+ }
+ }
+
/* Look up the memslot for guest physical address 0 */
memslot = gfn_to_memslot(kvm, 0);
@@ -1471,13 +1487,14 @@
int kvmppc_core_init_vm(struct kvm *kvm)
{
- long r;
- unsigned long lpcr;
+ unsigned long lpcr, lpid;
- /* Allocate hashed page table */
- r = kvmppc_alloc_hpt(kvm);
- if (r)
- return r;
+ /* Allocate the guest's logical partition ID */
+
+ lpid = kvmppc_alloc_lpid();
+ if (lpid < 0)
+ return -ENOMEM;
+ kvm->arch.lpid = lpid;
INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
@@ -1487,7 +1504,6 @@
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
/* PPC970; HID4 is effectively the LPCR */
- unsigned long lpid = kvm->arch.lpid;
kvm->arch.host_lpid = 0;
kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1b60f5..fb4eac2 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -25,6 +25,9 @@
static struct kvmppc_linear_info *kvm_alloc_linear(int type);
static void kvm_release_linear(struct kvmppc_linear_info *ri);
+int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
+EXPORT_SYMBOL_GPL(kvm_hpt_order);
+
/*************** RMA *************/
/*
@@ -209,7 +212,7 @@
void __init kvm_linear_init(void)
{
/* HPT */
- kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+ kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
/* RMA */
/* Only do this on PPC970 in HV mode */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index cec4dad..5c70d19 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -237,7 +237,7 @@
/* Find and lock the HPTEG slot to use */
do_insert:
- if (pte_index >= HPT_NPTE)
+ if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
if (likely((flags & H_EXACT) == 0)) {
pte_index &= ~7UL;
@@ -352,7 +352,7 @@
unsigned long v, r, rb;
struct revmap_entry *rev;
- if (pte_index >= HPT_NPTE)
+ if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
@@ -419,7 +419,8 @@
i = 4;
break;
}
- if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+ if (req != 1 || flags == 3 ||
+ pte_index >= kvm->arch.hpt_npte) {
/* parameter error */
args[j] = ((0xa0 | flags) << 56) + pte_index;
ret = H_PARAMETER;
@@ -521,7 +522,7 @@
struct revmap_entry *rev;
unsigned long v, r, rb, mask, bits;
- if (pte_index >= HPT_NPTE)
+ if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
@@ -583,7 +584,7 @@
int i, n = 1;
struct revmap_entry *rev = NULL;
- if (pte_index >= HPT_NPTE)
+ if (pte_index >= kvm->arch.hpt_npte)
return H_PARAMETER;
if (flags & H_READ_4) {
pte_index &= ~3;
@@ -678,7 +679,7 @@
somask = (1UL << 28) - 1;
vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
}
- hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+ hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask;
avpn = slb_v & ~(somask >> 16); /* also includes B */
avpn |= (eaddr & somask) >> 16;
@@ -723,7 +724,7 @@
if (val & HPTE_V_SECONDARY)
break;
val |= HPTE_V_SECONDARY;
- hash = hash ^ HPT_HASH_MASK;
+ hash = hash ^ kvm->arch.hpt_mask;
}
return -1;
}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 72f13f4..d25a097 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -612,6 +612,12 @@
regs->link = lr;
}
+/*
+ * For interrupts needed to be handled by host interrupt handlers,
+ * corresponding host handler are called from here in similar way
+ * (but not exact) as they are called from low level handler
+ * (such as from arch/powerpc/kernel/head_fsl_booke.S).
+ */
static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
unsigned int exit_nr)
{
@@ -639,6 +645,17 @@
kvmppc_fill_pt_regs(®s);
performance_monitor_exception(®s);
break;
+ case BOOKE_INTERRUPT_WATCHDOG:
+ kvmppc_fill_pt_regs(®s);
+#ifdef CONFIG_BOOKE_WDT
+ WatchdogException(®s);
+#else
+ unknown_exception(®s);
+#endif
+ break;
+ case BOOKE_INTERRUPT_CRITICAL:
+ unknown_exception(®s);
+ break;
}
}
@@ -683,6 +700,10 @@
r = RESUME_GUEST;
break;
+ case BOOKE_INTERRUPT_WATCHDOG:
+ r = RESUME_GUEST;
+ break;
+
case BOOKE_INTERRUPT_DOORBELL:
kvmppc_account_exit(vcpu, DBELL_EXITS);
r = RESUME_GUEST;
@@ -1267,6 +1288,11 @@
{
struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+ if (vcpu->arch.tcr & TCR_ARE) {
+ vcpu->arch.dec = vcpu->arch.decar;
+ kvmppc_emulate_dec(vcpu);
+ }
+
kvmppc_set_tsr_bits(vcpu, TSR_DIS);
}
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 6c76397..12834bb 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -24,6 +24,7 @@
#include "booke.h"
#define OP_19_XOP_RFI 50
+#define OP_19_XOP_RFCI 51
#define OP_31_XOP_MFMSR 83
#define OP_31_XOP_WRTEE 131
@@ -36,6 +37,12 @@
kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
}
+static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pc = vcpu->arch.csrr0;
+ kvmppc_set_msr(vcpu, vcpu->arch.csrr1);
+}
+
int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int inst, int *advance)
{
@@ -52,6 +59,12 @@
*advance = 0;
break;
+ case OP_19_XOP_RFCI:
+ kvmppc_emul_rfci(vcpu);
+ kvmppc_set_exit_type(vcpu, EMULATED_RFCI_EXITS);
+ *advance = 0;
+ break;
+
default:
emulated = EMULATE_FAIL;
break;
@@ -113,6 +126,12 @@
case SPRN_ESR:
vcpu->arch.shared->esr = spr_val;
break;
+ case SPRN_CSRR0:
+ vcpu->arch.csrr0 = spr_val;
+ break;
+ case SPRN_CSRR1:
+ vcpu->arch.csrr1 = spr_val;
+ break;
case SPRN_DBCR0:
vcpu->arch.dbcr0 = spr_val;
break;
@@ -129,6 +148,9 @@
kvmppc_set_tcr(vcpu, spr_val);
break;
+ case SPRN_DECAR:
+ vcpu->arch.decar = spr_val;
+ break;
/*
* Note: SPRG4-7 are user-readable.
* These values are loaded into the real SPRGs when resuming the
@@ -229,6 +251,12 @@
case SPRN_ESR:
*spr_val = vcpu->arch.shared->esr;
break;
+ case SPRN_CSRR0:
+ *spr_val = vcpu->arch.csrr0;
+ break;
+ case SPRN_CSRR1:
+ *spr_val = vcpu->arch.csrr1;
+ break;
case SPRN_DBCR0:
*spr_val = vcpu->arch.dbcr0;
break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 8fd4b2a..bb46b32 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -52,16 +52,21 @@
(1<<BOOKE_INTERRUPT_PROGRAM) | \
(1<<BOOKE_INTERRUPT_DTLB_MISS))
-.macro KVM_HANDLER ivor_nr
+.macro KVM_HANDLER ivor_nr scratch srr0
_GLOBAL(kvmppc_handler_\ivor_nr)
/* Get pointer to vcpu and record exit number. */
- mtspr SPRN_SPRG_WSCRATCH0, r4
+ mtspr \scratch , r4
mfspr r4, SPRN_SPRG_RVCPU
+ stw r3, VCPU_GPR(R3)(r4)
stw r5, VCPU_GPR(R5)(r4)
stw r6, VCPU_GPR(R6)(r4)
+ mfspr r3, \scratch
mfctr r5
- lis r6, kvmppc_resume_host@h
+ stw r3, VCPU_GPR(R4)(r4)
stw r5, VCPU_CTR(r4)
+ mfspr r3, \srr0
+ lis r6, kvmppc_resume_host@h
+ stw r3, VCPU_PC(r4)
li r5, \ivor_nr
ori r6, r6, kvmppc_resume_host@l
mtctr r6
@@ -69,37 +74,35 @@
.endm
_GLOBAL(kvmppc_handlers_start)
-KVM_HANDLER BOOKE_INTERRUPT_CRITICAL
-KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK
-KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL
-KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT
-KVM_HANDLER BOOKE_INTERRUPT_PROGRAM
-KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SYSCALL
-KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER
-KVM_HANDLER BOOKE_INTERRUPT_FIT
-KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
-KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_DEBUG
-KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
_GLOBAL(kvmppc_handler_len)
.long kvmppc_handler_1 - kvmppc_handler_0
-
/* Registers:
* SPRG_SCRATCH0: guest r4
* r4: vcpu pointer
* r5: KVM exit number
*/
_GLOBAL(kvmppc_resume_host)
- stw r3, VCPU_GPR(R3)(r4)
mfcr r3
stw r3, VCPU_CR(r4)
stw r7, VCPU_GPR(R7)(r4)
@@ -180,10 +183,6 @@
stw r3, VCPU_LR(r4)
mfxer r3
stw r3, VCPU_XER(r4)
- mfspr r3, SPRN_SPRG_RSCRATCH0
- stw r3, VCPU_GPR(R4)(r4)
- mfspr r3, SPRN_SRR0
- stw r3, VCPU_PC(r4)
/* Restore host stack pointer and PID before IVPR, since the host
* exception handlers use them. */
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 1685dc4..d28c2d4 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -262,7 +262,7 @@
kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \
SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0
kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \
- SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR)
+ SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 8b99e07..e04b0ef 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -269,6 +269,9 @@
*spr_val = vcpu->arch.shared->mas7_3 >> 32;
break;
#endif
+ case SPRN_DECAR:
+ *spr_val = vcpu->arch.decar;
+ break;
case SPRN_TLB0CFG:
*spr_val = vcpu->arch.tlbcfg[0];
break;
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index fe6c1de..1f89d26 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Varun Sethi, <varun.sethi@freescale.com>
*
@@ -57,7 +57,8 @@
struct kvm_book3e_206_tlb_entry *gtlbe)
{
unsigned int tid, ts;
- u32 val, eaddr, lpid;
+ gva_t eaddr;
+ u32 val, lpid;
unsigned long flags;
ts = get_tlb_ts(gtlbe);
@@ -183,6 +184,9 @@
vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \
SPRN_EPCR_DUVD;
+#ifdef CONFIG_64BIT
+ vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM;
+#endif
vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
vcpu->arch.epsc = vcpu->arch.eplc;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index f90e86d..ee04aba 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -59,11 +59,13 @@
#define OP_31_XOP_STHBRX 918
#define OP_LWZ 32
+#define OP_LD 58
#define OP_LWZU 33
#define OP_LBZ 34
#define OP_LBZU 35
#define OP_STW 36
#define OP_STWU 37
+#define OP_STD 62
#define OP_STB 38
#define OP_STBU 39
#define OP_LHZ 40
@@ -392,6 +394,12 @@
emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
break;
+ /* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */
+ case OP_LD:
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+ break;
+
case OP_LWZU:
emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
@@ -412,6 +420,14 @@
4, 1);
break;
+ /* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */
+ case OP_STD:
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu,
+ kvmppc_get_gpr(vcpu, rs),
+ 8, 1);
+ break;
+
case OP_STWU:
emulated = kvmppc_handle_store(run, vcpu,
kvmppc_get_gpr(vcpu, rs),
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1493c8d..87f4dc8 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -246,6 +246,7 @@
#endif
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
+ case KVM_CAP_PPC_ALLOC_HTAB:
r = 1;
break;
#endif /* CONFIG_PPC_BOOK3S_64 */
@@ -802,6 +803,23 @@
r = -EFAULT;
break;
}
+
+ case KVM_PPC_ALLOCATE_HTAB: {
+ struct kvm *kvm = filp->private_data;
+ u32 htab_order;
+
+ r = -EFAULT;
+ if (get_user(htab_order, (u32 __user *)argp))
+ break;
+ r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+ if (r)
+ break;
+ r = -EFAULT;
+ if (put_user(htab_order, (u32 __user *)argp))
+ break;
+ r = 0;
+ break;
+ }
#endif /* CONFIG_KVM_BOOK3S_64_HV */
#ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a35ca44..e7a896a 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -25,6 +25,7 @@
config KVM_GUEST
bool "KVM Guest support"
default n
+ select EPAPR_PARAVIRT
---help---
This option enables various optimizations for running under the KVM
hypervisor. Overhead for the kernel when not running inside KVM should
@@ -32,6 +33,14 @@
In case of doubt, say Y
+config EPAPR_PARAVIRT
+ bool "ePAPR para-virtualization support"
+ default n
+ help
+ Enables ePAPR para-virtualization support for guests.
+
+ In case of doubt, say Y
+
config PPC_NATIVE
bool
depends on 6xx || PPC64