[PATCH 03/27] KVM: PPC: Convert DSISR to shared page
The DSISR register contains information about a data page fault. It is fully
read/write from inside the guest context and we don't need to worry about
interacting based on writes of this register.
This patch converts all users of the current field to the shared page.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_book3s.h|1 -
arch/powerpc/include/asm/kvm_para.h |1 +
arch/powerpc/kvm/book3s.c| 11 ++-
arch/powerpc/kvm/book3s_emulate.c|6 +++---
arch/powerpc/kvm/book3s_paired_singles.c |2 +-
5 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h
b/arch/powerpc/include/asm/kvm_book3s.h
index 8274a2d..b5b1961 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -85,7 +85,6 @@ struct kvmppc_vcpu_book3s {
u64 hid[6];
u64 gqr[8];
int slb_nr;
- u32 dsisr;
u64 sdr1;
u64 hior;
u64 msr_mask;
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index a17dc52..9f7565b 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -24,6 +24,7 @@
struct kvm_vcpu_arch_shared {
__u64 msr;
+ __u32 dsisr;
};
#ifdef __KERNEL__
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 2efe692..eb401b6 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -595,15 +595,16 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct
kvm_vcpu *vcpu,
if (page_found == -ENOENT) {
/* Page not found in guest PTE entries */
vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
- to_book3s(vcpu)-dsisr = to_svcpu(vcpu)-fault_dsisr;
+ vcpu-arch.shared-dsisr = to_svcpu(vcpu)-fault_dsisr;
vcpu-arch.shared-msr |=
(to_svcpu(vcpu)-shadow_srr1 0xf800ULL);
kvmppc_book3s_queue_irqprio(vcpu, vec);
} else if (page_found == -EPERM) {
/* Storage protection */
vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
- to_book3s(vcpu)-dsisr = to_svcpu(vcpu)-fault_dsisr
~DSISR_NOHPTE;
- to_book3s(vcpu)-dsisr |= DSISR_PROTFAULT;
+ vcpu-arch.shared-dsisr =
+ to_svcpu(vcpu)-fault_dsisr ~DSISR_NOHPTE;
+ vcpu-arch.shared-dsisr |= DSISR_PROTFAULT;
vcpu-arch.shared-msr |=
(to_svcpu(vcpu)-shadow_srr1 0xf800ULL);
kvmppc_book3s_queue_irqprio(vcpu, vec);
@@ -867,7 +868,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu
*vcpu,
r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
} else {
vcpu-arch.dear = dar;
- to_book3s(vcpu)-dsisr = to_svcpu(vcpu)-fault_dsisr;
+ vcpu-arch.shared-dsisr = to_svcpu(vcpu)-fault_dsisr;
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
kvmppc_mmu_pte_flush(vcpu, vcpu-arch.dear, ~0xFFFUL);
r = RESUME_GUEST;
@@ -994,7 +995,7 @@ program_interrupt:
}
case BOOK3S_INTERRUPT_ALIGNMENT:
if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
- to_book3s(vcpu)-dsisr = kvmppc_alignment_dsisr(vcpu,
+ vcpu-arch.shared-dsisr = kvmppc_alignment_dsisr(vcpu,
kvmppc_get_last_inst(vcpu));
vcpu-arch.dear = kvmppc_alignment_dar(vcpu,
kvmppc_get_last_inst(vcpu));
diff --git a/arch/powerpc/kvm/book3s_emulate.c
b/arch/powerpc/kvm/book3s_emulate.c
index 35d3c16..9982ff1 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -221,7 +221,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct
kvm_vcpu *vcpu,
else if (r == -EPERM)
dsisr |= DSISR_PROTFAULT;
- to_book3s(vcpu)-dsisr = dsisr;
+ vcpu-arch.shared-dsisr = dsisr;
to_svcpu(vcpu)-fault_dsisr = dsisr;
kvmppc_book3s_queue_irqprio(vcpu,
@@ -327,7 +327,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int
sprn, int rs)
to_book3s(vcpu)-sdr1 = spr_val;
break;
case SPRN_DSISR:
- to_book3s(vcpu)-dsisr = spr_val;
+ vcpu-arch.shared-dsisr = spr_val;
break;
case SPRN_DAR:
vcpu-arch.dear = spr_val;
@@ -440,7 +440,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int
sprn, int rt)
kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)-sdr1);
[PATCH 17/27] KVM: PPC: KVM PV guest stubs
We will soon start and replace instructions from the text section with
other, paravirtualized versions. To ease the readability of those patches
I split out the generic looping and magic page mapping code out.
This patch still only contains stubs. But at least it loops through the
text section :).
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- kvm guest patch framework: introduce patch_ins
v2 - v3:
- add self-test in guest code
- remove superfluous new lines in generic guest code
---
arch/powerpc/kernel/kvm.c | 95 +
1 files changed, 95 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index a5ece71..e93366f 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,6 +33,62 @@
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
+#define KVM_MASK_RT0x03e0
+
+static bool kvm_patching_worked = true;
+
+static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
+{
+ *inst = new_inst;
+ flush_icache_range((ulong)inst, (ulong)inst + 4);
+}
+
+static void kvm_map_magic_page(void *data)
+{
+ kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
+ KVM_MAGIC_PAGE, /* Physical Address */
+ KVM_MAGIC_PAGE); /* Effective Address */
+}
+
+static void kvm_check_ins(u32 *inst)
+{
+ u32 _inst = *inst;
+ u32 inst_no_rt = _inst ~KVM_MASK_RT;
+ u32 inst_rt = _inst KVM_MASK_RT;
+
+ switch (inst_no_rt) {
+ }
+
+ switch (_inst) {
+ }
+}
+
+static void kvm_use_magic_page(void)
+{
+ u32 *p;
+ u32 *start, *end;
+ u32 tmp;
+
+ /* Tell the host to map the magic page to -4096 on all CPUs */
+ on_each_cpu(kvm_map_magic_page, NULL, 1);
+
+ /* Quick self-test to see if the mapping works */
+ if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Now loop through all code and find instructions */
+ start = (void*)_stext;
+ end = (void*)_etext;
+
+ for (p = start; p end; p++)
+ kvm_check_ins(p);
+
+ printk(KERN_INFO KVM: Live patching for a fast VM %s\n,
+kvm_patching_worked ? worked : failed);
+}
+
unsigned long kvm_hypercall(unsigned long *in,
unsigned long *out,
unsigned long nr)
@@ -69,3 +125,42 @@ unsigned long kvm_hypercall(unsigned long *in,
return r3;
}
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 int __init kvm_guest_init(void)
+{
+ if (!kvm_para_available())
+ return 0;
+
+ if (kvm_para_setup())
+ return 0;
+
+ if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
+ kvm_use_magic_page();
+
+ return 0;
+}
+
+postcore_initcall(kvm_guest_init);
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 20/27] KVM: PPC: Introduce kvm_tmp framework
We will soon require more sophisticated methods to replace single instructions
with multiple instructions. We do that by branching to a memory region where we
write replacement code for the instruction to.
This region needs to be within 32 MB of the patched instruction though, because
that's the furthest we can jump with immediate branches.
So we keep 1MB of free space around in bss. After we're done initing we can just
tell the mm system that the unused pages are free, but until then we have enough
space to fit all our code in.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/kernel/kvm.c | 42 --
1 files changed, 40 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 3258922..926f93f 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -65,6 +65,8 @@
#define KVM_INST_TLBSYNC 0x7c00046c
static bool kvm_patching_worked = true;
+static char kvm_tmp[1024 * 1024];
+static int kvm_tmp_index;
static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
{
@@ -105,6 +107,23 @@ static void kvm_patch_ins_nop(u32 *inst)
kvm_patch_ins(inst, KVM_INST_NOP);
}
+static u32 *kvm_alloc(int len)
+{
+ u32 *p;
+
+ if ((kvm_tmp_index + len) ARRAY_SIZE(kvm_tmp)) {
+ printk(KERN_ERR KVM: No more space (%d + %d)\n,
+ kvm_tmp_index, len);
+ kvm_patching_worked = false;
+ return NULL;
+ }
+
+ p = (void*)kvm_tmp[kvm_tmp_index];
+ kvm_tmp_index += len;
+
+ return p;
+}
+
static void kvm_map_magic_page(void *data)
{
kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -270,17 +289,36 @@ static int kvm_para_setup(void)
return 0;
}
+static __init void kvm_free_tmp(void)
+{
+ unsigned long start, end;
+
+ start = (ulong)kvm_tmp[kvm_tmp_index + (PAGE_SIZE - 1)] PAGE_MASK;
+ end = (ulong)kvm_tmp[ARRAY_SIZE(kvm_tmp)] PAGE_MASK;
+
+ /* Free the tmp space we don't need */
+ for (; start end; start += PAGE_SIZE) {
+ ClearPageReserved(virt_to_page(start));
+ init_page_count(virt_to_page(start));
+ free_page(start);
+ totalram_pages++;
+ }
+}
+
static int __init kvm_guest_init(void)
{
if (!kvm_para_available())
- return 0;
+ goto free_tmp;
if (kvm_para_setup())
- return 0;
+ goto free_tmp;
if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
kvm_use_magic_page();
+free_tmp:
+ kvm_free_tmp();
+
return 0;
}
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 18/27] KVM: PPC: PV instructions to loads and stores
Some instructions can simply be replaced by load and store instructions to
or from the magic page.
This patch replaces often called instructions that fall into the above category.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- use kvm_patch_ins
---
arch/powerpc/kernel/kvm.c | 109 +
1 files changed, 109 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index e93366f..9ec572c 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,7 +33,34 @@
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
+#define KVM_INST_LWZ 0x8000
+#define KVM_INST_STW 0x9000
+#define KVM_INST_LD0xe800
+#define KVM_INST_STD 0xf800
+#define KVM_INST_NOP 0x6000
+#define KVM_INST_B 0x4800
+#define KVM_INST_B_MASK0x03ff
+#define KVM_INST_B_MAX 0x01ff
+
#define KVM_MASK_RT0x03e0
+#define KVM_INST_MFMSR 0x7ca6
+#define KVM_INST_MFSPR_SPRG0 0x7c1042a6
+#define KVM_INST_MFSPR_SPRG1 0x7c1142a6
+#define KVM_INST_MFSPR_SPRG2 0x7c1242a6
+#define KVM_INST_MFSPR_SPRG3 0x7c1342a6
+#define KVM_INST_MFSPR_SRR00x7c1a02a6
+#define KVM_INST_MFSPR_SRR10x7c1b02a6
+#define KVM_INST_MFSPR_DAR 0x7c1302a6
+#define KVM_INST_MFSPR_DSISR 0x7c1202a6
+
+#define KVM_INST_MTSPR_SPRG0 0x7c1043a6
+#define KVM_INST_MTSPR_SPRG1 0x7c1143a6
+#define KVM_INST_MTSPR_SPRG2 0x7c1243a6
+#define KVM_INST_MTSPR_SPRG3 0x7c1343a6
+#define KVM_INST_MTSPR_SRR00x7c1a03a6
+#define KVM_INST_MTSPR_SRR10x7c1b03a6
+#define KVM_INST_MTSPR_DAR 0x7c1303a6
+#define KVM_INST_MTSPR_DSISR 0x7c1203a6
static bool kvm_patching_worked = true;
@@ -43,6 +70,34 @@ static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
flush_icache_range((ulong)inst, (ulong)inst + 4);
}
+static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+ kvm_patch_ins(inst, KVM_INST_LD | rt | (addr 0xfffc));
+#else
+ kvm_patch_ins(inst, KVM_INST_LWZ | rt | ((addr + 4) 0xfffc));
+#endif
+}
+
+static void kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
+{
+ kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr 0x));
+}
+
+static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+ kvm_patch_ins(inst, KVM_INST_STD | rt | (addr 0xfffc));
+#else
+ kvm_patch_ins(inst, KVM_INST_STW | rt | ((addr + 4) 0xfffc));
+#endif
+}
+
+static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
+{
+ kvm_patch_ins(inst, KVM_INST_STW | rt | (addr 0xfffc));
+}
+
static void kvm_map_magic_page(void *data)
{
kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -57,6 +112,60 @@ static void kvm_check_ins(u32 *inst)
u32 inst_rt = _inst KVM_MASK_RT;
switch (inst_no_rt) {
+ /* Loads */
+ case KVM_INST_MFMSR:
+ kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SPRG0:
+ kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SPRG1:
+ kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SPRG2:
+ kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SPRG3:
+ kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SRR0:
+ kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
+ break;
+ case KVM_INST_MFSPR_SRR1:
+ kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
+ break;
+ case KVM_INST_MFSPR_DAR:
+ kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
+ break;
+ case KVM_INST_MFSPR_DSISR:
+ kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
+ break;
+
+ /* Stores */
+ case KVM_INST_MTSPR_SPRG0:
+ kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
+ break;
+ case KVM_INST_MTSPR_SPRG1:
+ kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
+ break;
+ case KVM_INST_MTSPR_SPRG2:
+ kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
+ break;
+ case KVM_INST_MTSPR_SPRG3:
+ kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
+ break;
+ case KVM_INST_MTSPR_SRR0:
+ kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
+ break;
+ case KVM_INST_MTSPR_SRR1:
+ kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
+ break;
+ case KVM_INST_MTSPR_DAR:
+ kvm_patch_ins_std(inst,
[PATCH 26/27] KVM: PPC: Add Documentation about PV interface
We just introduced a new PV interface that screams for documentation. So here
it is - a shiny new and awesome text file describing the internal works of
the PPC KVM paravirtual interface.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- clarify guest implementation
- clarify that privileged instructions still work
- explain safe MSR bits
- Fix dsisr patch description
- change hypervisor calls to use new register values
v2 - v3:
- update documentation to new hypercall interface
- change detection to be device tree based
---
Documentation/kvm/ppc-pv.txt | 180 ++
1 files changed, 180 insertions(+), 0 deletions(-)
create mode 100644 Documentation/kvm/ppc-pv.txt
diff --git a/Documentation/kvm/ppc-pv.txt b/Documentation/kvm/ppc-pv.txt
new file mode 100644
index 000..960cd51
--- /dev/null
+++ b/Documentation/kvm/ppc-pv.txt
@@ -0,0 +1,180 @@
+The PPC KVM paravirtual interface
+=
+
+The basic execution principle by which KVM on PowerPC works is to run all
kernel
+space code in PR=1 which is user space. This way we trap all privileged
+instructions and can emulate them accordingly.
+
+Unfortunately that is also the downfall. There are quite some privileged
+instructions that needlessly return us to the hypervisor even though they
+could be handled differently.
+
+This is what the PPC PV interface helps with. It takes privileged instructions
+and transforms them into unprivileged ones with some help from the hypervisor.
+This cuts down virtualization costs by about 50% on some of my benchmarks.
+
+The code for that interface can be found in arch/powerpc/kernel/kvm*
+
+Querying for existence
+==
+
+To find out if we're running on KVM or not, we leverage the device tree. When
+Linux is running on KVM, a node /hypervisor exists. That node contains a
+compatible property with the value linux,kvm.
+
+Once you determined you're running under a PV capable KVM, you can now use
+hypercalls as described below.
+
+KVM hypercalls
+==
+
+Inside the device tree's /hypervisor node there's a property called
+'hypercall-instructions'. This property contains at most 4 opcodes that make
+up the hypercall. To call a hypercall, just call these instructions.
+
+The parameters are as follows:
+
+ RegisterIN OUT
+
+ r0 - volatile
+ r3 1st parameter Return code
+ r4 2nd parameter 1st output value
+ r5 3rd parameter 2nd output value
+ r6 4th parameter 3rd output value
+ r7 5th parameter 4th output value
+ r8 6th parameter 5th output value
+ r9 7th parameter 6th output value
+ r10 8th parameter 7th output value
+ r11 hypercall number8th output value
+ r12 - volatile
+
+Hypercall definitions are shared in generic code, so the same hypercall numbers
+apply for x86 and powerpc alike with the exception that each KVM hypercall
+also needs to be ORed with the KVM vendor code which is (42 16).
+
+Return codes can be as follows:
+
+ CodeMeaning
+
+ 0 Success
+ 12 Hypercall not implemented
+ 0 Error
+
+The magic page
+==
+
+To enable communication between the hypervisor and guest there is a new shared
+page that contains parts of supervisor visible register state. The guest can
+map this shared page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE.
+
+With this hypercall issued the guest always gets the magic page mapped at the
+desired location in effective and physical address space. For now, we always
+map the page to -4096. This way we can access it using absolute load and store
+functions. The following instruction reads the first field of the magic page:
+
+ ld rX, -4096(0)
+
+The interface is designed to be extensible should there be need later to add
+additional registers to the magic page. If you add fields to the magic page,
+also define a new hypercall feature to indicate that the host can give you more
+registers. Only if the host supports the additional features, make use of them.
+
+The magic page has the following layout as described in
+arch/powerpc/include/asm/kvm_para.h:
+
+struct kvm_vcpu_arch_shared {
+ __u64 scratch1;
+ __u64 scratch2;
+ __u64 scratch3;
+ __u64 critical; /* Guest may not get interrupts if == r1 */
+ __u64 sprg0;
+ __u64 sprg1;
+ __u64 sprg2;
+ __u64 sprg3;
+ __u64 srr0;
+ __u64 srr1;
+ __u64 dar;
+ __u64 msr;
+ __u32 dsisr;
+ __u32 int_pending; /* Tells the guest if we have an interrupt */
+};
+
+Additions to the
[PATCH 27/27] KVM: PPC: Add get_pvinfo interface to query hypercall instructions
We need to tell the guest the opcodes that make up a hypercall through
interfaces that are controlled by userspace. So we need to add a call
for userspace to allow it to query those opcodes so it can pass them
on.
This is required because the hypercall opcodes can change based on
the hypervisor conditions. If we're running in hardware accelerated
hypervisor mode, a hypercall looks different from when we're running
without hardware acceleration.
Signed-off-by: Alexander Graf ag...@suse.de
---
Documentation/kvm/api.txt | 23 +++
arch/powerpc/kvm/powerpc.c | 38 ++
include/linux/kvm.h| 11 +++
3 files changed, 72 insertions(+), 0 deletions(-)
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 5f5b649..44d9893 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -1032,6 +1032,29 @@ are defined as follows:
eax, ebx, ecx, edx: the values returned by the cpuid instruction for
this function/index combination
+4.46 KVM_PPC_GET_PVINFO
+
+Capability: KVM_CAP_PPC_GET_PVINFO
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_pvinfo (out)
+Returns: 0 on success, !0 on error
+
+struct kvm_ppc_pvinfo {
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+This ioctl fetches PV specific information that need to be passed to the guest
+using the device tree or other means from vm context.
+
+For now the only implemented piece of information distributed here is an array
+of 4 instructions that make up a hypercall.
+
+If any additional field gets added to this structure later on, a bit for that
+additional piece of information will be set in the flags bitmap.
+
5. The kvm_run structure
Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index fecfe04..6a53a3f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -191,6 +191,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_PPC_UNSET_IRQ:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_PPC_OSI:
+ case KVM_CAP_PPC_GET_PVINFO:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -578,16 +579,53 @@ out:
return r;
}
+static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
+{
+ u32 inst_lis = 0x3c00;
+ u32 inst_ori = 0x6000;
+ u32 inst_nop = 0x6000;
+ u32 inst_sc = 0x4402;
+ u32 inst_imm_mask = 0x;
+
+ /*
+* The hypercall to get into KVM from within guest context is as
+* follows:
+*
+*lis r0, r0, kvm_sc_magic...@h
+*ori r0, kvm_sc_magic...@l
+*sc
+*nop
+*/
+ pvinfo-hcall[0] = inst_lis | ((KVM_SC_MAGIC_R0 16) inst_imm_mask);
+ pvinfo-hcall[1] = inst_ori | (KVM_SC_MAGIC_R0 inst_imm_mask);
+ pvinfo-hcall[2] = inst_sc;
+ pvinfo-hcall[3] = inst_nop;
+
+ return 0;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
+ void __user *argp = (void __user *)arg;
long r;
switch (ioctl) {
+ case KVM_PPC_GET_PVINFO: {
+ struct kvm_ppc_pvinfo pvinfo;
+ r = kvm_vm_ioctl_get_pvinfo(pvinfo);
+ if (copy_to_user(argp, pvinfo, sizeof(pvinfo))) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ break;
+ }
default:
r = -ENOTTY;
}
+out:
return r;
}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 636fc38..3707704 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -414,6 +414,14 @@ struct kvm_enable_cap {
__u8 pad[64];
};
+/* for KVM_PPC_GET_PVINFO */
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
#define KVMIO 0xAE
/*
@@ -530,6 +538,7 @@ struct kvm_enable_cap {
#ifdef __KVM_HAVE_XCRS
#define KVM_CAP_XCRS 56
#endif
+#define KVM_CAP_PPC_GET_PVINFO 57
#ifdef KVM_CAP_IRQ_ROUTING
@@ -664,6 +673,8 @@ struct kvm_clock_data {
/* Available with KVM_CAP_PIT_STATE2 */
#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2)
#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2)
+/* Available with KVM_CAP_PPC_GET_PVINFO */
+#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo)
/*
* ioctls for vcpu fds
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 10/27] KVM: PPC: Tell guest about pending interrupts
When the guest turns on interrupts again, it needs to know if we have an
interrupt pending for it. Because if so, it should rather get out of guest
context and get the interrupt.
So we introduce a new field in the shared page that we use to tell the guest
that there's a pending interrupt lying around.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_para.h |1 +
arch/powerpc/kvm/book3s.c |7 +++
arch/powerpc/kvm/booke.c|7 +++
3 files changed, 15 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index 5be00c9..0653b0d 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -37,6 +37,7 @@ struct kvm_vcpu_arch_shared {
__u64 dar;
__u64 msr;
__u32 dsisr;
+ __u32 int_pending; /* Tells the guest if we have an interrupt */
};
#define KVM_SC_MAGIC_R00x4b564d21 /* KVM! */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d6227ff..06229fe 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -337,6 +337,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
unsigned int priority)
void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
unsigned long *pending = vcpu-arch.pending_exceptions;
+ unsigned long old_pending = vcpu-arch.pending_exceptions;
unsigned int priority;
#ifdef EXIT_DEBUG
@@ -356,6 +357,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
BITS_PER_BYTE * sizeof(*pending),
priority + 1);
}
+
+ /* Tell the guest about our interrupt status */
+ if (*pending)
+ vcpu-arch.shared-int_pending = 1;
+ else if (old_pending)
+ vcpu-arch.shared-int_pending = 0;
}
void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 104d0ee..c604277 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -224,6 +224,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu
*vcpu,
void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
{
unsigned long *pending = vcpu-arch.pending_exceptions;
+ unsigned long old_pending = vcpu-arch.pending_exceptions;
unsigned int priority;
priority = __ffs(*pending);
@@ -235,6 +236,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
BITS_PER_BYTE * sizeof(*pending),
priority + 1);
}
+
+ /* Tell the guest about our interrupt status */
+ if (*pending)
+ vcpu-arch.shared-int_pending = 1;
+ else if (old_pending)
+ vcpu-arch.shared-int_pending = 0;
}
/**
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 23/27] KVM: PPC: PV mtmsrd L=1
The PowerPC ISA has a special instruction for mtmsr that only changes the EE
and RI bits, namely the L=1 form.
Since that one is reasonably often occuring and simple to implement, let's
go with this first. Writing EE=0 is always just a store. Doing EE=1 also
requires us to check for pending interrupts and if necessary exit back to the
hypervisor.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- use kvm_patch_ins_b
---
arch/powerpc/kernel/kvm.c | 45
arch/powerpc/kernel/kvm_emul.S | 56
2 files changed, 101 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 239a70d..717ab0d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -63,6 +63,7 @@
#define KVM_INST_MTSPR_DSISR 0x7c1203a6
#define KVM_INST_TLBSYNC 0x7c00046c
+#define KVM_INST_MTMSRD_L1 0x7c010164
static bool kvm_patching_worked = true;
static char kvm_tmp[1024 * 1024];
@@ -138,6 +139,43 @@ static u32 *kvm_alloc(int len)
return p;
}
+extern u32 kvm_emulate_mtmsrd_branch_offs;
+extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_len;
+extern u32 kvm_emulate_mtmsrd[];
+
+static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_mtmsrd_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)p[kvm_emulate_mtmsrd_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
+ p[kvm_emulate_mtmsrd_branch_offs] |= distance_end KVM_INST_B_MASK;
+ p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
static void kvm_map_magic_page(void *data)
{
kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -211,6 +249,13 @@ static void kvm_check_ins(u32 *inst)
case KVM_INST_TLBSYNC:
kvm_patch_ins_nop(inst);
break;
+
+ /* Rewrites */
+ case KVM_INST_MTMSRD_L1:
+ /* We use r30 and r31 during the hook */
+ if (get_rt(inst_rt) 30)
+ kvm_patch_ins_mtmsrd(inst, inst_rt);
+ break;
}
switch (_inst) {
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 1dac72d..10dc4a6 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -64,3 +64,59 @@ kvm_hypercall_start:
/* Disable critical section. We are critical if \
shared-critical == r1 and r2 is always != r1 */ \
STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
+
+.global kvm_emulate_mtmsrd
+kvm_emulate_mtmsrd:
+
+ SCRATCH_SAVE
+
+ /* Put MSR ~(MSR_EE|MSR_RI) in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+ lis r30, (~(MSR_EE | MSR_RI))@h
+ ori r30, r30, (~(MSR_EE | MSR_RI))@l
+ and r31, r31, r30
+
+ /* OR the register's (MSR_EE|MSR_RI) on MSR */
+kvm_emulate_mtmsrd_reg:
+ andi. r30, r0, (MSR_EE|MSR_RI)
+ or r31, r31, r30
+
+ /* Put MSR back into magic page */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Check if we have to fetch an interrupt */
+ lwz r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+ cmpwi r31, 0
+ beq+no_check
+
+ /* Check if we may trigger an interrupt */
+ andi. r30, r30, MSR_EE
+ beq no_check
+
+ SCRATCH_RESTORE
+
+ /* Nag hypervisor */
+ tlbsync
+
+ b kvm_emulate_mtmsrd_branch
+
+no_check:
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_mtmsrd_branch:
+ b .
+kvm_emulate_mtmsrd_end:
+
+.global kvm_emulate_mtmsrd_branch_offs
+kvm_emulate_mtmsrd_branch_offs:
+ .long (kvm_emulate_mtmsrd_branch - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_reg_offs
+kvm_emulate_mtmsrd_reg_offs:
+ .long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_len
+kvm_emulate_mtmsrd_len:
+ .long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 12/27] KVM: PPC: First magic page steps
We will be introducing a method to project the shared page in guest context.
As soon as we're talking about this coupling, the shared page is colled magic
page.
This patch introduces simple defines, so the follow-up patches are easier to
read.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_host.h |2 ++
include/linux/kvm_para.h|1 +
2 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
index 1674da8..e1da775 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -287,6 +287,8 @@ struct kvm_vcpu_arch {
u64 dec_jiffies;
unsigned long pending_exceptions;
struct kvm_vcpu_arch_shared *shared;
+ unsigned long magic_page_pa; /* phys addr to map the magic page to */
+ unsigned long magic_page_ea; /* effect. addr to map the magic page to */
#ifdef CONFIG_PPC_BOOK3S
struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 3b8080e..ac2015a 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -18,6 +18,7 @@
#define KVM_HC_VAPIC_POLL_IRQ 1
#define KVM_HC_MMU_OP 2
#define KVM_HC_FEATURES3
+#define KVM_HC_PPC_MAP_MAGIC_PAGE 4
/*
* hypercalls use architecture specific
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 04/27] KVM: PPC: Convert DAR to shared page.
The DAR register contains the address a data page fault occured at. This
register behaves pretty much like a simple data storage register that gets
written to on data faults. There is no hypervisor interaction required on
read or write.
This patch converts all users of the current field to the shared page.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_host.h |1 -
arch/powerpc/include/asm/kvm_para.h |1 +
arch/powerpc/kvm/book3s.c| 14 +++---
arch/powerpc/kvm/book3s_emulate.c|6 +++---
arch/powerpc/kvm/book3s_paired_singles.c |2 +-
arch/powerpc/kvm/booke.c |2 +-
arch/powerpc/kvm/booke_emulate.c |4 ++--
7 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
index ba20f90..c852408 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -231,7 +231,6 @@ struct kvm_vcpu_arch {
ulong csrr1;
ulong dsrr0;
ulong dsrr1;
- ulong dear;
ulong esr;
u32 dec;
u32 decar;
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index 9f7565b..ec72a1c 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,7 @@
#include linux/types.h
struct kvm_vcpu_arch_shared {
+ __u64 dar;
__u64 msr;
__u32 dsisr;
};
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index eb401b6..4d46f8b 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -594,14 +594,14 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct
kvm_vcpu *vcpu,
if (page_found == -ENOENT) {
/* Page not found in guest PTE entries */
- vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu-arch.shared-dar = kvmppc_get_fault_dar(vcpu);
vcpu-arch.shared-dsisr = to_svcpu(vcpu)-fault_dsisr;
vcpu-arch.shared-msr |=
(to_svcpu(vcpu)-shadow_srr1 0xf800ULL);
kvmppc_book3s_queue_irqprio(vcpu, vec);
} else if (page_found == -EPERM) {
/* Storage protection */
- vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu-arch.shared-dar = kvmppc_get_fault_dar(vcpu);
vcpu-arch.shared-dsisr =
to_svcpu(vcpu)-fault_dsisr ~DSISR_NOHPTE;
vcpu-arch.shared-dsisr |= DSISR_PROTFAULT;
@@ -610,7 +610,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct
kvm_vcpu *vcpu,
kvmppc_book3s_queue_irqprio(vcpu, vec);
} else if (page_found == -EINVAL) {
/* Page not found in guest SLB */
- vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu-arch.shared-dar = kvmppc_get_fault_dar(vcpu);
kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
} else if (!is_mmio
kvmppc_visible_gfn(vcpu, pte.raddr PAGE_SHIFT)) {
@@ -867,17 +867,17 @@ int kvmppc_handle_exit(struct kvm_run *run, struct
kvm_vcpu *vcpu,
if (to_svcpu(vcpu)-fault_dsisr DSISR_NOHPTE) {
r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
} else {
- vcpu-arch.dear = dar;
+ vcpu-arch.shared-dar = dar;
vcpu-arch.shared-dsisr = to_svcpu(vcpu)-fault_dsisr;
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
- kvmppc_mmu_pte_flush(vcpu, vcpu-arch.dear, ~0xFFFUL);
+ kvmppc_mmu_pte_flush(vcpu, dar, ~0xFFFUL);
r = RESUME_GUEST;
}
break;
}
case BOOK3S_INTERRUPT_DATA_SEGMENT:
if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu))
0) {
- vcpu-arch.dear = kvmppc_get_fault_dar(vcpu);
+ vcpu-arch.shared-dar = kvmppc_get_fault_dar(vcpu);
kvmppc_book3s_queue_irqprio(vcpu,
BOOK3S_INTERRUPT_DATA_SEGMENT);
}
@@ -997,7 +997,7 @@ program_interrupt:
if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
vcpu-arch.shared-dsisr = kvmppc_alignment_dsisr(vcpu,
kvmppc_get_last_inst(vcpu));
- vcpu-arch.dear = kvmppc_alignment_dar(vcpu,
+ vcpu-arch.shared-dar = kvmppc_alignment_dar(vcpu,
kvmppc_get_last_inst(vcpu));
kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
}
diff --git a/arch/powerpc/kvm/book3s_emulate.c
b/arch/powerpc/kvm/book3s_emulate.c
index 9982ff1..c147864 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++
[PATCH 07/27] KVM: PPC: Implement hypervisor interface
To communicate with KVM directly we need to plumb some sort of interface
between the guest and KVM. Usually those interfaces use hypercalls.
This hypercall implementation is described in the last patch of the series
in a special documentation file. Please read that for further information.
This patch implements stubs to handle KVM PPC hypercalls on the host and
guest side alike.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- change hypervisor calls to use new register values
v2 - v3:
- move PV interface to ePAPR
- only check R0 on hypercall
- remove PVR hack
- align hypercalls to in/out of ePAPR
- add kvm.c with hypercall function
---
arch/powerpc/include/asm/kvm_para.h | 114 ++-
arch/powerpc/include/asm/kvm_ppc.h |1 +
arch/powerpc/kernel/Makefile|2 +
arch/powerpc/kernel/kvm.c | 68 +
arch/powerpc/kvm/book3s.c |9 ++-
arch/powerpc/kvm/booke.c| 10 +++-
arch/powerpc/kvm/powerpc.c | 32 ++
include/linux/kvm_para.h|1 +
8 files changed, 233 insertions(+), 4 deletions(-)
create mode 100644 arch/powerpc/kernel/kvm.c
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index e402999..556fd59 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -21,6 +21,7 @@
#define __POWERPC_KVM_PARA_H__
#include linux/types.h
+#include linux/of.h
struct kvm_vcpu_arch_shared {
__u64 sprg0;
@@ -34,16 +35,127 @@ struct kvm_vcpu_arch_shared {
__u32 dsisr;
};
+#define KVM_SC_MAGIC_R00x4b564d21 /* KVM! */
+#define HC_VENDOR_KVM (42 16)
+#define HC_EV_SUCCESS 0
+#define HC_EV_UNIMPLEMENTED12
+
#ifdef __KERNEL__
+#ifdef CONFIG_KVM_GUEST
+
+static inline int kvm_para_available(void)
+{
+ struct device_node *hyper_node;
+
+ hyper_node = of_find_node_by_path(/hypervisor);
+ if (!hyper_node)
+ return 0;
+
+ if (!of_device_is_compatible(hyper_node, linux,kvm))
+ return 0;
+
+ return 1;
+}
+
+extern unsigned long kvm_hypercall(unsigned long *in,
+ unsigned long *out,
+ unsigned long nr);
+
+#else
+
static inline int kvm_para_available(void)
{
return 0;
}
+static unsigned long kvm_hypercall(unsigned long *in,
+ unsigned long *out,
+ unsigned long nr)
+{
+ return HC_EV_UNIMPLEMENTED;
+}
+
+#endif
+
+static inline long kvm_hypercall0_1(unsigned int nr, unsigned long *r2)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+ unsigned long r;
+
+ r = kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+ *r2 = out[0];
+
+ return r;
+}
+
+static inline long kvm_hypercall0(unsigned int nr)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+
+ return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+
+ in[0] = p1;
+ return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
+ unsigned long p2)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+
+ in[0] = p1;
+ in[1] = p2;
+ return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
+ unsigned long p2, unsigned long p3)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+
+ in[0] = p1;
+ in[1] = p2;
+ in[2] = p3;
+ return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
+ unsigned long p2, unsigned long p3,
+ unsigned long p4)
+{
+ unsigned long in[8];
+ unsigned long out[8];
+
+ in[0] = p1;
+ in[1] = p2;
+ in[2] = p3;
+ in[3] = p4;
+ return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+
static inline unsigned int kvm_arch_para_features(void)
{
- return 0;
+ unsigned long r;
+
+ if (!kvm_para_available())
+ return 0;
+
+ if(kvm_hypercall0_1(KVM_HC_FEATURES, r))
+ return 0;
+
+ return r;
}
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h
b/arch/powerpc/include/asm/kvm_ppc.h
index 18d139e..ecb3bc7 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -107,6 +107,7 @@ extern int kvmppc_booke_init(void);
extern void kvmppc_booke_exit(void);
extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
+extern int kvmppc_kvm_pv(struct
[PATCH 25/27] KVM: PPC: PV wrteei
On BookE the preferred way to write the EE bit is the wrteei instruction. It
already encodes the EE bit in the instruction.
So in order to get BookE some speedups as well, let's also PV'nize thati
instruction.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- use kvm_patch_ins_b
---
arch/powerpc/kernel/kvm.c | 50
arch/powerpc/kernel/kvm_emul.S | 41
2 files changed, 91 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 8ac57e2..e936817 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -67,6 +67,9 @@
#define KVM_INST_MTMSRD_L1 0x7c010164
#define KVM_INST_MTMSR 0x7c000124
+#define KVM_INST_WRTEEI_0 0x7c000146
+#define KVM_INST_WRTEEI_1 0x7c008146
+
static bool kvm_patching_worked = true;
static char kvm_tmp[1024 * 1024];
static int kvm_tmp_index;
@@ -221,6 +224,47 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
kvm_patch_ins_b(inst, distance_start);
}
+#ifdef CONFIG_BOOKE
+
+extern u32 kvm_emulate_wrteei_branch_offs;
+extern u32 kvm_emulate_wrteei_ee_offs;
+extern u32 kvm_emulate_wrteei_len;
+extern u32 kvm_emulate_wrteei[];
+
+static void kvm_patch_ins_wrteei(u32 *inst)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)p[kvm_emulate_wrteei_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
+ p[kvm_emulate_wrteei_branch_offs] |= distance_end KVM_INST_B_MASK;
+ p[kvm_emulate_wrteei_ee_offs] |= (*inst MSR_EE);
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
static void kvm_map_magic_page(void *data)
{
kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -310,6 +354,12 @@ static void kvm_check_ins(u32 *inst)
}
switch (_inst) {
+#ifdef CONFIG_BOOKE
+ case KVM_INST_WRTEEI_0:
+ case KVM_INST_WRTEEI_1:
+ kvm_patch_ins_wrteei(inst);
+ break;
+#endif
}
}
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 8cd22f4..3199f65 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -204,3 +204,44 @@ kvm_emulate_mtmsr_orig_ins_offs:
.global kvm_emulate_mtmsr_len
kvm_emulate_mtmsr_len:
.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
+
+
+
+.global kvm_emulate_wrteei
+kvm_emulate_wrteei:
+
+ SCRATCH_SAVE
+
+ /* Fetch old MSR in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Remove MSR_EE from old MSR */
+ li r30, 0
+ ori r30, r30, MSR_EE
+ andcr31, r31, r30
+
+ /* OR new MSR_EE onto the old MSR */
+kvm_emulate_wrteei_ee:
+ ori r31, r31, 0
+
+ /* Write new MSR value back */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_wrteei_branch:
+ b .
+kvm_emulate_wrteei_end:
+
+.global kvm_emulate_wrteei_branch_offs
+kvm_emulate_wrteei_branch_offs:
+ .long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_ee_offs
+kvm_emulate_wrteei_ee_offs:
+ .long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_len
+kvm_emulate_wrteei_len:
+ .long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 19/27] KVM: PPC: PV tlbsync to nop
With our current MMU scheme we don't need to know about the tlbsync instruction.
So we can just nop it out.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- use kvm_patch_ins
---
arch/powerpc/kernel/kvm.c | 12
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 9ec572c..3258922 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -62,6 +62,8 @@
#define KVM_INST_MTSPR_DAR 0x7c1303a6
#define KVM_INST_MTSPR_DSISR 0x7c1203a6
+#define KVM_INST_TLBSYNC 0x7c00046c
+
static bool kvm_patching_worked = true;
static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
@@ -98,6 +100,11 @@ static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
kvm_patch_ins(inst, KVM_INST_STW | rt | (addr 0xfffc));
}
+static void kvm_patch_ins_nop(u32 *inst)
+{
+ kvm_patch_ins(inst, KVM_INST_NOP);
+}
+
static void kvm_map_magic_page(void *data)
{
kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -166,6 +173,11 @@ static void kvm_check_ins(u32 *inst)
case KVM_INST_MTSPR_DSISR:
kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
break;
+
+ /* Nops */
+ case KVM_INST_TLBSYNC:
+ kvm_patch_ins_nop(inst);
+ break;
}
switch (_inst) {
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 16/27] KVM: PPC: Generic KVM PV guest support
We have all the hypervisor pieces in place now, but the guest parts are still missing. This patch implements basic awareness of KVM when running Linux as guest. It doesn't do anything with it yet though. Signed-off-by: Alexander Graf ag...@suse.de --- v2 - v3: - Add hypercall stub --- arch/powerpc/kernel/Makefile |2 +- arch/powerpc/kernel/asm-offsets.c | 15 +++ arch/powerpc/kernel/kvm.c |3 +++ arch/powerpc/kernel/kvm_emul.S| 37 + arch/powerpc/platforms/Kconfig| 10 ++ 5 files changed, 66 insertions(+), 1 deletions(-) create mode 100644 arch/powerpc/kernel/kvm_emul.S diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 5ea853d..d8e29b4 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -125,7 +125,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) obj-y += ppc_save_regs.o endif -obj-$(CONFIG_KVM_GUEST)+= kvm.o +obj-$(CONFIG_KVM_GUEST)+= kvm.o kvm_emul.o # Disable GCOV in odd or sensitive code GCOV_PROFILE_prom_init.o := n diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a55d47e..e3e740b 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -465,6 +465,21 @@ int main(void) DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr)); #endif /* CONFIG_PPC_BOOK3S */ #endif + +#ifdef CONFIG_KVM_GUEST + DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared, + scratch1)); + DEFINE(KVM_MAGIC_SCRATCH2, offsetof(struct kvm_vcpu_arch_shared, + scratch2)); + DEFINE(KVM_MAGIC_SCRATCH3, offsetof(struct kvm_vcpu_arch_shared, + scratch3)); + DEFINE(KVM_MAGIC_INT, offsetof(struct kvm_vcpu_arch_shared, + int_pending)); + DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr)); + DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared, + critical)); +#endif + #ifdef CONFIG_44x DEFINE(PGD_T_LOG2, PGD_T_LOG2); DEFINE(PTE_T_LOG2, PTE_T_LOG2); diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 4f85505..a5ece71 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -30,6 +30,9 @@ #include asm/cacheflush.h #include asm/disassemble.h +#define KVM_MAGIC_PAGE (-4096L) +#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x) + unsigned long kvm_hypercall(unsigned long *in, unsigned long *out, unsigned long nr) diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S new file mode 100644 index 000..e0d4183 --- /dev/null +++ b/arch/powerpc/kernel/kvm_emul.S @@ -0,0 +1,37 @@ +/* + * 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 SUSE Linux Products GmbH 2010 + * + * Authors: Alexander Graf ag...@suse.de + */ + +#include asm/ppc_asm.h +#include asm/kvm_asm.h +#include asm/reg.h +#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) + diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d1663db..1744349 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -21,6 +21,16 @@ source arch/powerpc/platforms/44x/Kconfig source arch/powerpc/platforms/40x/Kconfig source arch/powerpc/platforms/amigaone/Kconfig +config KVM_GUEST + bool KVM Guest support + default y + ---help--- + This option enables various optimizations for running under the KVM + hypervisor. Overhead for the kernel when not running inside KVM should + be minimal. + + In case of doubt, say Y + config PPC_NATIVE bool depends on 6xx || PPC64 -- 1.6.0.2 -- To unsubscribe from this list: send the line unsubscribe kvm-ppc in the body of a message to
[PATCH 13/27] KVM: PPC: Magic Page Book3s support
We need to override EA as well as PA lookups for the magic page. When the guest
tells us to project it, the magic page overrides any guest mappings.
In order to reflect that, we need to hook into all the MMU layers of KVM to
force map the magic page if necessary.
Signed-off-by: Alexander Graf ag...@suse.de
---
v2 - v3:
- RMO - PAM
- combine 32 and 64 real page magic override
- remove leftover goto point
- align hypercalls to in/out of ePAPR
---
arch/powerpc/include/asm/kvm_book3s.h |1 +
arch/powerpc/kvm/book3s.c | 35 ++--
arch/powerpc/kvm/book3s_32_mmu.c | 16 +++
arch/powerpc/kvm/book3s_32_mmu_host.c |2 +-
arch/powerpc/kvm/book3s_64_mmu.c | 30 +++-
arch/powerpc/kvm/book3s_64_mmu_host.c |9 +--
6 files changed, 81 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h
b/arch/powerpc/include/asm/kvm_book3s.h
index b5b1961..00cf8b0 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -130,6 +130,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct
kvmppc_bat *bat,
bool upper, u32 val);
extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu
*vcpu);
+extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
extern u32 kvmppc_trampoline_lowmem;
extern u32 kvmppc_trampoline_enter;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 0ed5376..eee97b5 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -419,6 +419,25 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
}
}
+pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ ulong mp_pa = vcpu-arch.magic_page_pa;
+
+ /* Magic page override */
+ if (unlikely(mp_pa)
+ unlikely(((gfn PAGE_SHIFT) KVM_PAM) ==
+((mp_pa PAGE_MASK) KVM_PAM))) {
+ ulong shared_page = ((ulong)vcpu-arch.shared) PAGE_MASK;
+ pfn_t pfn;
+
+ pfn = (pfn_t)virt_to_phys((void*)shared_page) PAGE_SHIFT;
+ get_page(pfn_to_page(pfn));
+ return pfn;
+ }
+
+ return gfn_to_pfn(vcpu-kvm, gfn);
+}
+
/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
* make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
* emulate 32 bytes dcbz length.
@@ -554,6 +573,13 @@ mmio:
static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
+ ulong mp_pa = vcpu-arch.magic_page_pa;
+
+ if (unlikely(mp_pa)
+ unlikely((mp_pa KVM_PAM) PAGE_SHIFT == gfn)) {
+ return 1;
+ }
+
return kvm_is_visible_gfn(vcpu-kvm, gfn);
}
@@ -1257,6 +1283,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
unsigned int id)
struct kvmppc_vcpu_book3s *vcpu_book3s;
struct kvm_vcpu *vcpu;
int err = -ENOMEM;
+ unsigned long p;
vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
if (!vcpu_book3s)
@@ -1274,8 +1301,10 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm
*kvm, unsigned int id)
if (err)
goto free_shadow_vcpu;
- vcpu-arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
- if (!vcpu-arch.shared)
+ p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
+ /* the real shared page fills the last 4k of our page */
+ vcpu-arch.shared = (void*)(p + PAGE_SIZE - 4096);
+ if (!p)
goto uninit_vcpu;
vcpu-arch.host_retip = kvm_return_point;
@@ -1322,7 +1351,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
- free_page((unsigned long)vcpu-arch.shared);
+ free_page((unsigned long)vcpu-arch.shared PAGE_MASK);
kvm_vcpu_uninit(vcpu);
kfree(vcpu_book3s-shadow_vcpu);
vfree(vcpu_book3s);
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 449bce5..a7d121a 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -281,8 +281,24 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu
*vcpu, gva_t eaddr,
struct kvmppc_pte *pte, bool data)
{
int r;
+ ulong mp_ea = vcpu-arch.magic_page_ea;
pte-eaddr = eaddr;
+
+ /* Magic page override */
+ if (unlikely(mp_ea)
+ unlikely((eaddr ~0xfffULL) == (mp_ea ~0xfffULL))
+ !(vcpu-arch.shared-msr MSR_PR)) {
+ pte-vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
+ pte-raddr = vcpu-arch.magic_page_pa | (pte-raddr 0xfff);
+ pte-raddr = KVM_PAM;
+ pte-may_execute = true;
+
[PATCH 08/27] KVM: PPC: Add PV guest critical sections
When running in hooked code we need a way to disable interrupts without
clobbering any interrupts or exiting out to the hypervisor.
To achieve this, we have an additional critical field in the shared page. If
that field is equal to the r1 register of the guest, it tells the hypervisor
that we're in such a critical section and thus may not receive any interrupts.
Signed-off-by: Alexander Graf ag...@suse.de
---
v1 - v2:
- make crit detection only trigger in supervisor mode
---
arch/powerpc/include/asm/kvm_para.h |1 +
arch/powerpc/kvm/book3s.c | 18 --
arch/powerpc/kvm/booke.c| 15 +++
3 files changed, 32 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index 556fd59..4577e7b 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -24,6 +24,7 @@
#include linux/of.h
struct kvm_vcpu_arch_shared {
+ __u64 critical; /* Guest may not get interrupts if == r1 */
__u64 sprg0;
__u64 sprg1;
__u64 sprg2;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 5cb5f0d..d6227ff 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -251,14 +251,28 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
unsigned int priority)
int deliver = 1;
int vec = 0;
ulong flags = 0ULL;
+ ulong crit_raw = vcpu-arch.shared-critical;
+ ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+ bool crit;
+
+ /* Truncate crit indicators in 32 bit mode */
+ if (!(vcpu-arch.shared-msr MSR_SF)) {
+ crit_raw = 0x;
+ crit_r1 = 0x;
+ }
+
+ /* Critical section when crit == r1 */
+ crit = (crit_raw == crit_r1);
+ /* ... and we're in supervisor mode */
+ crit = crit !(vcpu-arch.shared-msr MSR_PR);
switch (priority) {
case BOOK3S_IRQPRIO_DECREMENTER:
- deliver = vcpu-arch.shared-msr MSR_EE;
+ deliver = (vcpu-arch.shared-msr MSR_EE) !crit;
vec = BOOK3S_INTERRUPT_DECREMENTER;
break;
case BOOK3S_IRQPRIO_EXTERNAL:
- deliver = vcpu-arch.shared-msr MSR_EE;
+ deliver = (vcpu-arch.shared-msr MSR_EE) !crit;
vec = BOOK3S_INTERRUPT_EXTERNAL;
break;
case BOOK3S_IRQPRIO_SYSTEM_RESET:
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 13e0747..104d0ee 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -147,6 +147,20 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu
*vcpu,
int allowed = 0;
ulong uninitialized_var(msr_mask);
bool update_esr = false, update_dear = false;
+ ulong crit_raw = vcpu-arch.shared-critical;
+ ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+ bool crit;
+
+ /* Truncate crit indicators in 32 bit mode */
+ if (!(vcpu-arch.shared-msr MSR_SF)) {
+ crit_raw = 0x;
+ crit_r1 = 0x;
+ }
+
+ /* Critical section when crit == r1 */
+ crit = (crit_raw == crit_r1);
+ /* ... and we're in supervisor mode */
+ crit = crit !(vcpu-arch.shared-msr MSR_PR);
switch (priority) {
case BOOKE_IRQPRIO_DTLB_MISS:
@@ -181,6 +195,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu
*vcpu,
case BOOKE_IRQPRIO_DECREMENTER:
case BOOKE_IRQPRIO_FIT:
allowed = vcpu-arch.shared-msr MSR_EE;
+ allowed = allowed !crit;
msr_mask = MSR_CE|MSR_ME|MSR_DE;
break;
case BOOKE_IRQPRIO_DEBUG:
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 11/27] KVM: PPC: Make PAM a define
On PowerPC it's very normal to not support all of the physical RAM in real mode.
To check if we're matching on the shared page or not, we need to know the limits
so we can restrain ourselves to that range.
So let's make it a define instead of open-coding it. And while at it, let's also
increase it.
Signed-off-by: Alexander Graf ag...@suse.de
v2 - v3:
- RMO - PAM (non-magic page)
---
arch/powerpc/include/asm/kvm_host.h |3 +++
arch/powerpc/kvm/book3s.c |4 ++--
2 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
index 221cf85..1674da8 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -48,6 +48,9 @@
#define HPTEG_HASH_NUM_VPTE(1 HPTEG_HASH_BITS_VPTE)
#define HPTEG_HASH_NUM_VPTE_LONG (1 HPTEG_HASH_BITS_VPTE_LONG)
+/* Physical Address Mask - allowed range of real mode RAM access */
+#define KVM_PAM0x0fffULL
+
struct kvm;
struct kvm_run;
struct kvm_vcpu;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 06229fe..0ed5376 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -465,7 +465,7 @@ static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr,
bool data,
r = vcpu-arch.mmu.xlate(vcpu, eaddr, pte, data);
} else {
pte-eaddr = eaddr;
- pte-raddr = eaddr 0x;
+ pte-raddr = eaddr KVM_PAM;
pte-vpage = VSID_REAL | eaddr 12;
pte-may_read = true;
pte-may_write = true;
@@ -579,7 +579,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct
kvm_vcpu *vcpu,
pte.may_execute = true;
pte.may_read = true;
pte.may_write = true;
- pte.raddr = eaddr 0x;
+ pte.raddr = eaddr KVM_PAM;
pte.eaddr = eaddr;
pte.vpage = eaddr 12;
}
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 05/27] KVM: PPC: Convert SRR0 and SRR1 to shared page
The SRR0 and SRR1 registers contain cached values of the PC and MSR
respectively. They get written to by the hypervisor when an interrupt
occurs or directly by the kernel. They are also used to tell the rfi(d)
instruction where to jump to.
Because it only gets touched on defined events that, it's very simple to
share with the guest. Hypervisor and guest both have full r/w access.
This patch converts all users of the current field to the shared page.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_host.h |2 --
arch/powerpc/include/asm/kvm_para.h |2 ++
arch/powerpc/kvm/book3s.c | 12 ++--
arch/powerpc/kvm/book3s_emulate.c |4 ++--
arch/powerpc/kvm/booke.c| 15 ---
arch/powerpc/kvm/booke_emulate.c|4 ++--
arch/powerpc/kvm/emulate.c | 12
7 files changed, 28 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
index c852408..5255d75 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -225,8 +225,6 @@ struct kvm_vcpu_arch {
ulong sprg5;
ulong sprg6;
ulong sprg7;
- ulong srr0;
- ulong srr1;
ulong csrr0;
ulong csrr1;
ulong dsrr0;
diff --git a/arch/powerpc/include/asm/kvm_para.h
b/arch/powerpc/include/asm/kvm_para.h
index ec72a1c..d7fc6c2 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,8 @@
#include linux/types.h
struct kvm_vcpu_arch_shared {
+ __u64 srr0;
+ __u64 srr1;
__u64 dar;
__u64 msr;
__u32 dsisr;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 4d46f8b..afa0dd4 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -162,8 +162,8 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
{
- vcpu-arch.srr0 = kvmppc_get_pc(vcpu);
- vcpu-arch.srr1 = vcpu-arch.shared-msr | flags;
+ vcpu-arch.shared-srr0 = kvmppc_get_pc(vcpu);
+ vcpu-arch.shared-srr1 = vcpu-arch.shared-msr | flags;
kvmppc_set_pc(vcpu, to_book3s(vcpu)-hior + vec);
vcpu-arch.mmu.reset_msr(vcpu);
}
@@ -1059,8 +1059,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu,
struct kvm_regs *regs)
regs-lr = kvmppc_get_lr(vcpu);
regs-xer = kvmppc_get_xer(vcpu);
regs-msr = vcpu-arch.shared-msr;
- regs-srr0 = vcpu-arch.srr0;
- regs-srr1 = vcpu-arch.srr1;
+ regs-srr0 = vcpu-arch.shared-srr0;
+ regs-srr1 = vcpu-arch.shared-srr1;
regs-pid = vcpu-arch.pid;
regs-sprg0 = vcpu-arch.sprg0;
regs-sprg1 = vcpu-arch.sprg1;
@@ -1086,8 +1086,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu,
struct kvm_regs *regs)
kvmppc_set_lr(vcpu, regs-lr);
kvmppc_set_xer(vcpu, regs-xer);
kvmppc_set_msr(vcpu, regs-msr);
- vcpu-arch.srr0 = regs-srr0;
- vcpu-arch.srr1 = regs-srr1;
+ vcpu-arch.shared-srr0 = regs-srr0;
+ vcpu-arch.shared-srr1 = regs-srr1;
vcpu-arch.sprg0 = regs-sprg0;
vcpu-arch.sprg1 = regs-sprg1;
vcpu-arch.sprg2 = regs-sprg2;
diff --git a/arch/powerpc/kvm/book3s_emulate.c
b/arch/powerpc/kvm/book3s_emulate.c
index c147864..f333cb4 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -73,8 +73,8 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct
kvm_vcpu *vcpu,
switch (get_xop(inst)) {
case OP_19_XOP_RFID:
case OP_19_XOP_RFI:
- kvmppc_set_pc(vcpu, vcpu-arch.srr0);
- kvmppc_set_msr(vcpu, vcpu-arch.srr1);
+ kvmppc_set_pc(vcpu, vcpu-arch.shared-srr0);
+ kvmppc_set_msr(vcpu, vcpu-arch.shared-srr1);
*advance = 0;
break;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 4aab6d2..793df28 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -64,7 +64,8 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
printk(pc: %08lx msr: %08llx\n, vcpu-arch.pc,
vcpu-arch.shared-msr);
printk(lr: %08lx ctr: %08lx\n, vcpu-arch.lr, vcpu-arch.ctr);
- printk(srr0: %08lx srr1: %08lx\n, vcpu-arch.srr0, vcpu-arch.srr1);
+ printk(srr0: %08llx srr1: %08llx\n, vcpu-arch.shared-srr0,
+ vcpu-arch.shared-srr1);
printk(exceptions: %08lx\n, vcpu-arch.pending_exceptions);
@@ -189,8 +190,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu
*vcpu,
}
if (allowed) {
- vcpu-arch.srr0 = vcpu-arch.pc;
- vcpu-arch.srr1 = vcpu-arch.shared-msr;
+ vcpu-arch.shared-srr0 = vcpu-arch.pc;
+
[PATCH 00/27] KVM PPC PV framework v3
On PPC we run PR=0 (kernel mode) code in PR=1 (user mode) and don't use the
hypervisor extensions.
While that is all great to show that virtualization is possible, there are
quite some cases where the emulation overhead of privileged instructions is
killing performance.
This patchset tackles exactly that issue. It introduces a paravirtual framework
using which KVM and Linux share a page to exchange register state with. That
way we don't have to switch to the hypervisor just to change a value of a
privileged register.
To prove my point, I ran the same test I did for the MMU optimizations against
the PV framework. Here are the results:
[without]
debian-powerpc:~# time for i in {1..1000}; do /bin/echo hello /dev/null; done
real0m14.659s
user0m8.967s
sys 0m5.688s
[with]
debian-powerpc:~# time for i in {1..1000}; do /bin/echo hello /dev/null; done
real0m7.557s
user0m4.121s
sys 0m3.426s
So this is a significant performance improvement! I'm quite happy how fast this
whole thing becomes :)
I tried to take all comments I've heard from people so far about such a PV
framework into account. In case you told me something before that is a no-go
and I still did it, please just tell me again.
To make use of this whole thing you also need patches to qemu and openbios. I
have them in my queue, but want to see this set upstream first before I start
sending patches to the other projects.
Now go and have fun with fast VMs on PPC! Get yourself a G5 on ebay and start
experiencing the power yourself. - heh
v1 - v2:
- change hypervisor calls to use r0 and r3
- make crit detection only trigger in supervisor mode
- RMO - PAM
- introduce kvm_patch_ins
- only flush icache when patching
- introduce kvm_patch_ins_b
- update documentation
v2 - v3:
- use pPAPR conventions for hypercall interface
- only use r0 as magic sc number
- remove PVR detection
- remove BookE shared page mapping support
- combine book3s-64 and -32 magic page ra override
- add self-test check if the mapping works to guest code
- add safety check for relocatable kernels
Alexander Graf (27):
KVM: PPC: Introduce shared page
KVM: PPC: Convert MSR to shared page
KVM: PPC: Convert DSISR to shared page
KVM: PPC: Convert DAR to shared page.
KVM: PPC: Convert SRR0 and SRR1 to shared page
KVM: PPC: Convert SPRG[0-4] to shared page
KVM: PPC: Implement hypervisor interface
KVM: PPC: Add PV guest critical sections
KVM: PPC: Add PV guest scratch registers
KVM: PPC: Tell guest about pending interrupts
KVM: PPC: Make PAM a define
KVM: PPC: First magic page steps
KVM: PPC: Magic Page Book3s support
KVM: PPC: Expose magic page support to guest
KVM: Move kvm_guest_init out of generic code
KVM: PPC: Generic KVM PV guest support
KVM: PPC: KVM PV guest stubs
KVM: PPC: PV instructions to loads and stores
KVM: PPC: PV tlbsync to nop
KVM: PPC: Introduce kvm_tmp framework
KVM: PPC: Introduce branch patching helper
KVM: PPC: PV assembler helpers
KVM: PPC: PV mtmsrd L=1
KVM: PPC: PV mtmsrd L=0 and mtmsr
KVM: PPC: PV wrteei
KVM: PPC: Add Documentation about PV interface
KVM: PPC: Add get_pvinfo interface to query hypercall instructions
Documentation/kvm/api.txt| 23 ++
Documentation/kvm/ppc-pv.txt | 180 +++
arch/powerpc/include/asm/kvm_book3s.h|2 +-
arch/powerpc/include/asm/kvm_host.h | 15 +-
arch/powerpc/include/asm/kvm_para.h | 135 -
arch/powerpc/include/asm/kvm_ppc.h |1 +
arch/powerpc/kernel/Makefile |2 +
arch/powerpc/kernel/asm-offsets.c| 18 +-
arch/powerpc/kernel/kvm.c| 485 ++
arch/powerpc/kernel/kvm_emul.S | 247 +++
arch/powerpc/kvm/44x.c |7 +
arch/powerpc/kvm/44x_tlb.c |8 +-
arch/powerpc/kvm/book3s.c| 188
arch/powerpc/kvm/book3s_32_mmu.c | 28 ++-
arch/powerpc/kvm/book3s_32_mmu_host.c|6 +-
arch/powerpc/kvm/book3s_64_mmu.c | 42 +++-
arch/powerpc/kvm/book3s_64_mmu_host.c| 13 +-
arch/powerpc/kvm/book3s_emulate.c| 25 +-
arch/powerpc/kvm/book3s_paired_singles.c | 11 +-
arch/powerpc/kvm/booke.c | 83 --
arch/powerpc/kvm/booke.h |6 +-
arch/powerpc/kvm/booke_emulate.c | 14 +-
arch/powerpc/kvm/booke_interrupts.S |3 +-
arch/powerpc/kvm/e500.c |7 +
arch/powerpc/kvm/e500_tlb.c | 12 +-
arch/powerpc/kvm/e500_tlb.h |2 +-
arch/powerpc/kvm/emulate.c | 36 ++-
arch/powerpc/kvm/powerpc.c | 84 +-
arch/powerpc/platforms/Kconfig | 10 +
arch/x86/include/asm/kvm_para.h |6 +
include/linux/kvm.h | 11 +
include/linux/kvm_para.h |7 +-
32 files changed, 1538
[PATCH 7/7] KVM: PPC: Move KVM trampolines before __end_interrupts
When using a relocatable kernel we need to make sure that the trampline code and the interrupt handlers are both copied to low memory. The only way to do this reliably is to put them in the copied section. This patch should make relocated kernels work with KVM. KVM-Stable-Tag Signed-off-by: Alexander Graf ag...@suse.de --- arch/powerpc/kernel/exceptions-64s.S |6 ++ arch/powerpc/kernel/head_64.S|6 -- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3e423fb..a0f25fb 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -299,6 +299,12 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ +/* KVM's trampoline code needs to be close to the interrupt handlers */ + +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER +#include ../kvm/book3s_rmhandlers.S +#endif + .align 7 .globl __end_interrupts __end_interrupts: diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 844a44b..d3010a3 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -166,12 +166,6 @@ exception_marker: #include exceptions-64s.S #endif -/* KVM trampoline code needs to be close to the interrupt handlers */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#include ../kvm/book3s_rmhandlers.S -#endif - _GLOBAL(generic_secondary_thread_init) mr r24,r3 -- 1.6.0.2 -- To unsubscribe from this list: send the line unsubscribe kvm-ppc in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 5/7] KVM: PPC: Use MSR_DR for external load_up
Book3S_32 requires MSR_DR to be disabled during load_up_xxx while on Book3S_64 it's supposed to be enabled. I misread the code and disabled it in both cases, potentially breaking the PS3 which has a really small RMA. This patch makes KVM work on the PS3 again. Signed-off-by: Alexander Graf ag...@suse.de --- arch/powerpc/kvm/book3s_rmhandlers.S | 28 +++- 1 files changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 506d5c3..229d3d6 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -202,8 +202,25 @@ _GLOBAL(kvmppc_rmcall) #if defined(CONFIG_PPC_BOOK3S_32) #define STACK_LR INT_FRAME_SIZE+4 + +/* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */ +#define MSR_EXT_START \ + PPC_STL r20, _NIP(r1); \ + mfmsr r20;\ + LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \ + andcr3,r20,r3; /* Disable DR,EE */ \ + mtmsr r3; \ + sync + +#define MSR_EXT_END\ + mtmsr r20;/* Enable DR,EE */ \ + sync; \ + PPC_LL r20, _NIP(r1) + #elif defined(CONFIG_PPC_BOOK3S_64) #define STACK_LR _LINK +#define MSR_EXT_START +#define MSR_EXT_END #endif /* @@ -215,19 +232,12 @@ _GLOBAL(kvmppc_load_up_ ## what); \ PPC_STLU r1, -INT_FRAME_SIZE(r1); \ mflrr3; \ PPC_STL r3, STACK_LR(r1); \ - PPC_STL r20, _NIP(r1); \ - mfmsr r20;\ - LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \ - andcr3,r20,r3; /* Disable DR,EE */ \ - mtmsr r3; \ - sync; \ + MSR_EXT_START; \ \ bl FUNC(load_up_ ## what); \ \ - mtmsr r20;/* Enable DR,EE */ \ - sync; \ + MSR_EXT_END;\ PPC_LL r3, STACK_LR(r1); \ - PPC_LL r20, _NIP(r1); \ mtlrr3; \ addir1, r1, INT_FRAME_SIZE; \ blr -- 1.6.0.2 -- To unsubscribe from this list: send the line unsubscribe kvm-ppc in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 3/7] KVM: PPC: correctly check gfn_to_pfn() return value
From: Gleb Natapov g...@redhat.com
On failure gfn_to_pfn returns bad_page so use correct function to check
for that.
Signed-off-by: Gleb Natapov g...@redhat.com
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/kvm/book3s_32_mmu_host.c |2 +-
arch/powerpc/kvm/book3s_64_mmu_host.c |2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c
b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 05e8c9e..343452c 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -148,7 +148,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct
kvmppc_pte *orig_pte)
/* Get host physical address for gpa */
hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte-raddr PAGE_SHIFT);
- if (kvm_is_error_hva(hpaddr)) {
+ if (is_error_pfn(hpaddr)) {
printk(KERN_INFO Couldn't get guest page for gfn %lx!\n,
orig_pte-eaddr);
return -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c
b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 6cdd19a..672b149 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -102,7 +102,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct
kvmppc_pte *orig_pte)
/* Get host physical address for gpa */
hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte-raddr PAGE_SHIFT);
- if (kvm_is_error_hva(hpaddr)) {
+ if (is_error_pfn(hpaddr)) {
printk(KERN_INFO Couldn't get guest page for gfn %lx!\n,
orig_pte-eaddr);
return -EINVAL;
}
--
1.6.0.2
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH 4/7] KVM: PPC: Add book3s_32 tlbie flush acceleration
On Book3s_32 the tlbie instruction flushed effective addresses by the mask
0x0000. This is pretty hard to reflect with a hash that hashes ~0xfff, so
to speed up that target we should also keep a special hash around for it.
Signed-off-by: Alexander Graf ag...@suse.de
---
arch/powerpc/include/asm/kvm_host.h |4 +++
arch/powerpc/kvm/book3s_mmu_hpte.c | 40 ++
2 files changed, 39 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h
b/arch/powerpc/include/asm/kvm_host.h
index fafc71a..bba3b9b 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -42,9 +42,11 @@
#define HPTEG_CACHE_NUM(1 15)
#define HPTEG_HASH_BITS_PTE13
+#define HPTEG_HASH_BITS_PTE_LONG 12
#define HPTEG_HASH_BITS_VPTE 13
#define HPTEG_HASH_BITS_VPTE_LONG 5
#define HPTEG_HASH_NUM_PTE (1 HPTEG_HASH_BITS_PTE)
+#define HPTEG_HASH_NUM_PTE_LONG(1 HPTEG_HASH_BITS_PTE_LONG)
#define HPTEG_HASH_NUM_VPTE(1 HPTEG_HASH_BITS_VPTE)
#define HPTEG_HASH_NUM_VPTE_LONG (1 HPTEG_HASH_BITS_VPTE_LONG)
@@ -163,6 +165,7 @@ struct kvmppc_mmu {
struct hpte_cache {
struct hlist_node list_pte;
+ struct hlist_node list_pte_long;
struct hlist_node list_vpte;
struct hlist_node list_vpte_long;
struct rcu_head rcu_head;
@@ -293,6 +296,7 @@ struct kvm_vcpu_arch {
#ifdef CONFIG_PPC_BOOK3S
struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
+ struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
int hpte_cache_count;
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c
b/arch/powerpc/kvm/book3s_mmu_hpte.c
index b643893..02c64ab 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -45,6 +45,12 @@ static inline u64 kvmppc_mmu_hash_pte(u64 eaddr)
return hash_64(eaddr PTE_SIZE, HPTEG_HASH_BITS_PTE);
}
+static inline u64 kvmppc_mmu_hash_pte_long(u64 eaddr)
+{
+ return hash_64((eaddr 0x0000) PTE_SIZE,
+ HPTEG_HASH_BITS_PTE_LONG);
+}
+
static inline u64 kvmppc_mmu_hash_vpte(u64 vpage)
{
return hash_64(vpage 0xfULL, HPTEG_HASH_BITS_VPTE);
@@ -66,6 +72,11 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct
hpte_cache *pte)
index = kvmppc_mmu_hash_pte(pte-pte.eaddr);
hlist_add_head_rcu(pte-list_pte, vcpu-arch.hpte_hash_pte[index]);
+ /* Add to ePTE_long list */
+ index = kvmppc_mmu_hash_pte_long(pte-pte.eaddr);
+ hlist_add_head_rcu(pte-list_pte_long,
+ vcpu-arch.hpte_hash_pte_long[index]);
+
/* Add to vPTE list */
index = kvmppc_mmu_hash_vpte(pte-pte.vpage);
hlist_add_head_rcu(pte-list_vpte, vcpu-arch.hpte_hash_vpte[index]);
@@ -99,6 +110,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct
hpte_cache *pte)
spin_lock(vcpu-arch.mmu_lock);
hlist_del_init_rcu(pte-list_pte);
+ hlist_del_init_rcu(pte-list_pte_long);
hlist_del_init_rcu(pte-list_vpte);
hlist_del_init_rcu(pte-list_vpte_long);
@@ -150,10 +162,28 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu
*vcpu, ulong guest_ea)
rcu_read_unlock();
}
-void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea)
{
- u64 i;
+ struct hlist_head *list;
+ struct hlist_node *node;
+ struct hpte_cache *pte;
+
+ /* Find the list of entries in the map */
+ list = vcpu-arch.hpte_hash_pte_long[
+ kvmppc_mmu_hash_pte_long(guest_ea)];
+ rcu_read_lock();
+
+ /* Check the list for matching entries and invalidate */
+ hlist_for_each_entry_rcu(pte, node, list, list_pte_long)
+ if ((pte-pte.eaddr 0x0000UL) == guest_ea)
+ invalidate_pte(vcpu, pte);
+
+ rcu_read_unlock();
+}
+
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+{
dprintk_mmu(KVM: Flushing %d Shadow PTEs: 0x%lx 0x%lx\n,
vcpu-arch.hpte_cache_count, guest_ea, ea_mask);
@@ -164,9 +194,7 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong
guest_ea, ulong ea_mask)
kvmppc_mmu_pte_flush_page(vcpu, guest_ea);
break;
case 0x0000:
- /* 32-bit flush w/o segment, go through all possible segments */
- for (i = 0; i 0x1ULL; i += 0x1000ULL)
- kvmppc_mmu_pte_flush(vcpu, guest_ea | i, ~0xfffUL);
+ kvmppc_mmu_pte_flush_long(vcpu, guest_ea);
break;
case 0:
/* Doing a complete
[PATCH] KVM: PPC: initialize IVORs in addition to IVPR
Developers can now tell at a glace the exact type of the premature interrupt,
instead of just knowing that there was some interrupt.
Signed-off-by: Hollis Blanchard hol...@penguinppc.org
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -466,15 +466,19 @@ int kvmppc_handle_exit(struct kvm_run *r
/* Initial guest state: 16MB mapping 0 - 0, PC = 0, MSR = 0, R1 = 16MB */
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
+ int i;
+
vcpu-arch.pc = 0;
vcpu-arch.msr = 0;
kvmppc_set_gpr(vcpu, 1, (1620) - 8); /* -8 for the callee-save LR
slot */
vcpu-arch.shadow_pid = 1;
- /* Eye-catching number so we know if the guest takes an interrupt
-* before it's programmed its own IVPR. */
+ /* Eye-catching numbers so we know if the guest takes an interrupt
+* before it's programmed its own IVPR/IVORs. */
vcpu-arch.ivpr = 0x;
+ for (i = 0; i BOOKE_IRQPRIO_MAX; i++)
+ vcpu-arch.ivor[i] = 0x7700 | i * 4;
kvmppc_init_timing_stats(vcpu);
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH] KVM: PPC: fix compilation of dump tlbs debug function
Signed-off-by: Hollis Blanchard hol...@penguinppc.org
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -47,6 +47,7 @@
#ifdef DEBUG
void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
{
+ struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
struct kvmppc_44x_tlbe *tlbe;
int i;
--
To unsubscribe from this list: send the line unsubscribe kvm-ppc in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH] PPC4xx: don't unregister RAM at reset
The PowerPC 4xx SDRAM controller emulation unregisters RAM in its reset callback. However, qemu_system_reset() is now called at initialization time, so RAM is unregistered before starting the guest. Signed-off-by: Hollis Blanchard hol...@penguinppc.org --- hw/ppc4xx_devs.c |1 - 1 files changed, 0 insertions(+), 1 deletions(-) diff --git a/hw/ppc4xx_devs.c b/hw/ppc4xx_devs.c index be130c4..7f698b8 100644 --- a/hw/ppc4xx_devs.c +++ b/hw/ppc4xx_devs.c @@ -619,7 +619,6 @@ static void sdram_reset (void *opaque) /* We pre-initialize RAM banks */ sdram-status = 0x; sdram-cfg = 0x0080; -sdram_unmap_bcr(sdram); } void ppc4xx_sdram_init (CPUState *env, qemu_irq irq, int nbanks, -- 1.7.1.1 -- To unsubscribe from this list: send the line unsubscribe kvm-ppc in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
[PATCH] loader: pad kernel size when loaded from a uImage
The kernel's BSS size is lost by mkimage, which only considers file size. As a result, loading other blobs (e.g. device tree, initrd) immediately after the kernel location can result in them being zeroed by the kernel's BSS initialization code. Signed-off-by: Hollis Blanchard hol...@penguinppc.org --- hw/loader.c |7 +++ 1 files changed, 7 insertions(+), 0 deletions(-) diff --git a/hw/loader.c b/hw/loader.c index 79a6f95..35bc25a 100644 --- a/hw/loader.c +++ b/hw/loader.c @@ -507,6 +507,13 @@ int load_uimage(const char *filename, target_phys_addr_t *ep, ret = hdr-ih_size; + /* The kernel's BSS size is lost by mkimage, which only considers file +* size. We don't know how big it is, but we do know we can't place +* anything immediately after the kernel. The padding seems like it should +* be proportional to overall file size, but we also make sure it's at +* least 4-byte aligned. */ + ret += (hdr-ih_size / 16) ~0x3; + out: if (data) qemu_free(data); -- 1.7.1.1 -- To unsubscribe from this list: send the line unsubscribe kvm-ppc in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
