[PATCH 1/2] KVM: PPC: Book3S HV: Cleanup kvmppc_load/save_fp
This cleans up kvmppc_load/save_fp. It removes unnecessary isyncs. It also removes the unnecessary resetting of the MSR bits on exit of kvmppc_save_fp. Signed-off-by: Michael Neuling mi...@neuling.org Signed-off-by: Paul Mackerras pau...@samba.org --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index f0c4db7..c4bd2d7 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2434,7 +2434,6 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 - isync addir3,r3,VCPU_FPRS bl store_fp_state #ifdef CONFIG_ALTIVEC @@ -2470,7 +2469,6 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 - isync addir3,r4,VCPU_FPRS bl load_fp_state #ifdef CONFIG_ALTIVEC -- 1.9.1 -- 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
Re: [PATCH 1/2] KVM: PPC: Book3S HV: Cleanup kvmppc_load/save_fp
On Tue, 2014-08-19 at 15:24 +1000, Paul Mackerras wrote: On Tue, Aug 19, 2014 at 02:59:29PM +1000, Michael Neuling wrote: This cleans up kvmppc_load/save_fp. It removes unnecessary isyncs. NAK - they are necessary on PPC970, which we (still) support. You could put them in a feature section if they are really annoying you. I'm not fussed, but we should at least have a comment there for why we need them. It also removes the unnecessary resetting of the MSR bits on exit of kvmppc_save_fp. ... except it doesn't. :) That got folded into e4e38121507a (KVM: PPC: Book3S HV: Add transactional memory support). Arrh, thanks. This patch was cleaning up stuff from an old local tree and couldn't see where it had been upstreamed. I missed this. Mikey -- 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
Re: [PATCH v1 2/3] powerpc/powernv: Support PCI error injection
On Mon, 2014-06-23 at 12:14 +1000, Gavin Shan wrote:
The patch implements one OPAL firmware sysfs file to support PCI error
injection: /sys/firmware/opal/errinjct, which will be used like the
way described as follows.
According to PAPR spec, there are 3 RTAS calls related to error injection:
ibm,open-errinjct: allocate token prior to doing error injection.
ibm,close-errinjct: release the token allocated from ibm,open-errinjct.
ibm,errinjct: do error injection.
Sysfs file /sys/firmware/opal/errinjct accepts strings that have fixed
format ei_token For now, we only support 32-bits and 64-bits
PCI error injection and they should have following strings written to
/sys/firmware/opal/errinjct as follows. We don't have corresponding
sysfs files for ibm,open-errinjct and ibm,close-errinjct, which
means that we rely on userland to maintain the token by itself.
This sounds cool.
Can you document the sysfs interface in Documentation/powerpc?
Mikey
32-bits PCI error: 7:addr:mask:iommu_group_id:function.
64-bits PCI error: 8:addr:mask:iommu_group_id:function.
The above 7 and 8 represent 32-bits and 64-bits PCI error seperately
and function is one of the specific PCI errors (e.g. MMIO access address
parity error), which are defined by PAPR spec.
Signed-off-by: Gavin Shan gws...@linux.vnet.ibm.com
---
arch/powerpc/include/asm/opal.h| 1 +
arch/powerpc/platforms/powernv/Makefile| 2 +-
arch/powerpc/platforms/powernv/opal-errinjct.c | 184
+
arch/powerpc/platforms/powernv/opal.c | 2 +
4 files changed, 188 insertions(+), 1 deletion(-)
create mode 100644 arch/powerpc/platforms/powernv/opal-errinjct.c
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index d982bb8..bf280d9 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -985,6 +985,7 @@ extern int opal_elog_init(void);
extern void opal_platform_dump_init(void);
extern void opal_sys_param_init(void);
extern void opal_msglog_init(void);
+extern void opal_errinjct_init(void);
extern int opal_machine_check(struct pt_regs *regs);
extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
diff --git a/arch/powerpc/platforms/powernv/Makefile
b/arch/powerpc/platforms/powernv/Makefile
index 63cebb9..4711de8 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,7 +1,7 @@
obj-y+= setup.o opal-takeover.o opal-wrappers.o
opal.o opal-async.o
obj-y+= opal-rtc.o opal-nvram.o opal-lpc.o
opal-flash.o
obj-y+= rng.o opal-elog.o opal-dump.o
opal-sysparam.o opal-sensor.o
-obj-y+= opal-msglog.o
+obj-y+= opal-msglog.o opal-errinjct.o
obj-$(CONFIG_SMP)+= smp.o
obj-$(CONFIG_PCI)+= pci.o pci-p5ioc2.o pci-ioda.o
diff --git a/arch/powerpc/platforms/powernv/opal-errinjct.c
b/arch/powerpc/platforms/powernv/opal-errinjct.c
new file mode 100644
index 000..29c9e83
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-errinjct.c
@@ -0,0 +1,184 @@
+/*
+ * The file supports error injection, which works based on OPAL API.
+ * For now, we only support PCI error injection. We need support
+ * injecting other types of errors in future.
+ *
+ * Copyright Gavin Shan, IBM Corporation 2014.
+ *
+ * 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/kernel.h
+#include linux/init.h
+#include linux/msi.h
+#include linux/pci.h
+#include linux/iommu.h
+#include linux/random.h
+#include linux/slab.h
+#include linux/sysfs.h
+#include linux/fs.h
+#include linux/fcntl.h
+#include linux/kobject.h
+
+#include asm/msi_bitmap.h
+#include asm/iommu.h
+#include asm/pci-bridge.h
+#include asm/ppc-pci.h
+#include asm/opal.h
+
+#include powernv.h
+#include pci.h
+
+static DEFINE_MUTEX(errinjct_mutex);
+
+static int errinjct_iommu_group_to_phb_and_pe(uint32_t iommu_grp_id,
+ uint64_t *phb_id,
+ uint32_t *pe_num)
+{
+#ifdef CONFIG_IOMMU_API
+ struct iommu_group *iommu_grp;
+ struct iommu_table *tbl;
+ struct pnv_ioda_pe *pe;
+
+ iommu_grp = iommu_group_get_by_id(iommu_grp_id);
+ if (!iommu_grp)
+ return -ENODEV;
+
+ tbl = iommu_group_get_iommudata(iommu_grp);
+ if (!tbl)
+ return -ENODEV;
+
+ pe = container_of(tbl, struct pnv_ioda_pe, tce32_table);
+ if (!pe-phb)
+ return -ENODEV;
+
+ *phb_id = pe-phb-opal_id;
+ *pe_num = pe-pe_number;
+
+ return 0;
+#endif
+
+
[PATCH v2 3/3] KVM: PPC: Book3S HV: Add H_SET_MODE hcall handling
This adds support for the H_SET_MODE hcall. This hcall is a
multiplexer that has several functions, some of which are called
rarely, and some which are potentially called very frequently.
Here we add support for the functions that set the debug registers
CIABR (Completed Instruction Address Breakpoint Register) and
DAWR/DAWRX (Data Address Watchpoint Register and eXtension),
since they could be updated by the guest as often as every context
switch.
This also adds a kvmppc_power8_compatible() function to test to see
if a guest is compatible with POWER8 or not. The CIABR and DAWR/X
only exist on POWER8.
Signed-off-by: Michael Neuling mi...@neuling.org
Signed-off-by: Paul Mackerras pau...@samba.org
---
v2:
add some #defines to make CIABR setting clearer. No functional change.
diff --git a/arch/powerpc/include/asm/hvcall.h
b/arch/powerpc/include/asm/hvcall.h
index 5dbbb29..85bc8c0 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -279,6 +279,12 @@
#define H_GET_24X7_DATA0xF07C
#define H_GET_PERF_COUNTER_INFO0xF080
+/* Values for 2nd argument to H_SET_MODE */
+#define H_SET_MODE_RESOURCE_SET_CIABR 1
+#define H_SET_MODE_RESOURCE_SET_DAWR 2
+#define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE3
+#define H_SET_MODE_RESOURCE_LE 4
+
#ifndef __ASSEMBLY__
/**
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e699047..e74dab2 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -557,6 +557,48 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
vcpu-arch.dtl.dirty = true;
}
+static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu)
+{
+ if (vcpu-arch.vcore-arch_compat = PVR_ARCH_207)
+ return true;
+ if ((!vcpu-arch.vcore-arch_compat)
+ cpu_has_feature(CPU_FTR_ARCH_207S))
+ return true;
+ return false;
+}
+
+static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
+unsigned long resource, unsigned long value1,
+unsigned long value2)
+{
+ switch (resource) {
+ case H_SET_MODE_RESOURCE_SET_CIABR:
+ if (!kvmppc_power8_compatible(vcpu))
+ return H_P2;
+ if (value2)
+ return H_P4;
+ if (mflags)
+ return H_UNSUPPORTED_FLAG_START;
+ /* Guests can't breakpoint the hypervisor */
+ if ((value1 CIABR_PRIV) == CIABR_PRIV_HYPER)
+ return H_P3;
+ vcpu-arch.ciabr = value1;
+ return H_SUCCESS;
+ case H_SET_MODE_RESOURCE_SET_DAWR:
+ if (!kvmppc_power8_compatible(vcpu))
+ return H_P2;
+ if (mflags)
+ return H_UNSUPPORTED_FLAG_START;
+ if (value2 DABRX_HYP)
+ return H_P4;
+ vcpu-arch.dawr = value1;
+ vcpu-arch.dawrx = value2;
+ return H_SUCCESS;
+ default:
+ return H_TOO_HARD;
+ }
+}
+
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
{
unsigned long req = kvmppc_get_gpr(vcpu, 3);
@@ -626,7 +668,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
/* Send the error out to userspace via KVM_RUN */
return rc;
-
+ case H_SET_MODE:
+ ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5),
+ kvmppc_get_gpr(vcpu, 6),
+ kvmppc_get_gpr(vcpu, 7));
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
case H_XIRR:
case H_CPPR:
case H_EOI:
@@ -652,6 +701,7 @@ static int kvmppc_hcall_impl_hv(struct kvm *kvm, unsigned
long cmd)
case H_PROD:
case H_CONFER:
case H_REGISTER_VPA:
+ case H_SET_MODE:
#ifdef CONFIG_KVM_XICS
case H_XIRR:
case H_CPPR:
--
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
powerpc/pseries: Use new defines when calling h_set_mode
+/* Values for 2nd argument to H_SET_MODE */
+#define H_SET_MODE_RESOURCE_SET_CIABR1
+#define H_SET_MODE_RESOURCE_SET_DAWR2
+#define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE3
+#define H_SET_MODE_RESOURCE_LE4
Much better, but I think you want to make use of these in non-kvm code too,
no? At least the LE one is definitely already implemented as call :)
Sure but that's a different patch below.
Mikey
powerpc/pseries: Use new defines when calling h_set_mode
Now that we define these in the KVM code, use these defines when we call
h_set_mode. No functional change.
Signed-off-by: Michael Neuling mi...@neuling.org
--
This depends on the KVM h_set_mode patches.
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h
b/arch/powerpc/include/asm/plpar_wrappers.h
index 12c32c5..67859ed 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -273,7 +273,7 @@ static inline long plpar_set_mode(unsigned long mflags,
unsigned long resource,
static inline long enable_reloc_on_exceptions(void)
{
/* mflags = 3: Exceptions at 0xC0004000 */
- return plpar_set_mode(3, 3, 0, 0);
+ return plpar_set_mode(3, H_SET_MODE_RESOURCE_ADDR_TRANS_MODE, 0, 0);
}
/*
@@ -284,7 +284,7 @@ static inline long enable_reloc_on_exceptions(void)
* returns H_SUCCESS.
*/
static inline long disable_reloc_on_exceptions(void) {
- return plpar_set_mode(0, 3, 0, 0);
+ return plpar_set_mode(0, H_SET_MODE_RESOURCE_ADDR_TRANS_MODE, 0, 0);
}
/*
@@ -297,7 +297,7 @@ static inline long disable_reloc_on_exceptions(void) {
static inline long enable_big_endian_exceptions(void)
{
/* mflags = 0: big endian exceptions */
- return plpar_set_mode(0, 4, 0, 0);
+ return plpar_set_mode(0, H_SET_MODE_RESOURCE_LE, 0, 0);
}
/*
@@ -310,17 +310,17 @@ static inline long enable_big_endian_exceptions(void)
static inline long enable_little_endian_exceptions(void)
{
/* mflags = 1: little endian exceptions */
- return plpar_set_mode(1, 4, 0, 0);
+ return plpar_set_mode(1, H_SET_MODE_RESOURCE_LE, 0, 0);
}
static inline long plapr_set_ciabr(unsigned long ciabr)
{
- return plpar_set_mode(0, 1, ciabr, 0);
+ return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_CIABR, ciabr, 0);
}
static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long
dawrx0)
{
- return plpar_set_mode(0, 2, dawr0, dawrx0);
+ return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0);
}
#endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
--
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
Re: [PATCH 3/3] KVM: PPC: Book3S HV: Add H_SET_MODE hcall handling
Alex,
+static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
+unsigned long resource, unsigned long value1,
+unsigned long value2)
+{
+ switch (resource) {
+ case H_SET_MODE_RESOURCE_SET_CIABR:
+ if (!kvmppc_power8_compatible(vcpu))
+ return H_P2;
+ if (value2)
+ return H_P4;
+ if (mflags)
+ return H_UNSUPPORTED_FLAG_START;
+ if ((value1 0x3) == 0x3)
What is this?
It's what it says in PAPR (I wish that was public!!!). Joking aside...
If you refer to the 2.07 HW arch (not PAPR), the bottom two bits of the
CIABR tell you what mode to match in. 0x3 means match in hypervisor,
which we obviously don't want the guest to be able to do.
I'll add some #defines to make it a clearer and repost.
Mikey
--
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 v2 0/6] Implement split core for POWER8
This patch series implements split core mode on POWER8. This enables up to 4 subcores per core which can each independently run guests (per guest SPRs like SDR1, LPIDR etc are replicated per subcore). Lots more documentation on this feature in the code and commit messages. Most of this code is in the powernv platform but there's a couple of KVM specific patches too. Patch series authored by mpe and me with a few bug fixes from others. v2: There are some minor updates based on comments and I've added the Acks by Paulus and Alex for the KVM code. -- 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 v2 4/6] powerpc: Check cpu_thread_in_subcore() in __cpu_up()
From: Michael Ellerman m...@ellerman.id.au To support split core we need to change the check in __cpu_up() that determines if a cpu is allowed to come online. Currently we refuse to online cpus which are not the primary thread within their core. On POWER8 with split core support this check needs to instead refuse to online cpus which are not the primary thread within their *sub* core. On POWER7 and other systems that do not support split core, threads_per_subcore == threads_per_core and so the check is equivalent. Signed-off-by: Michael Ellerman m...@ellerman.id.au Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6edae3d..b5222c4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -489,7 +489,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Don't allow secondary threads to come online if inhibited */ if (threads_per_core 1 secondaries_inhibited() - cpu % threads_per_core != 0) + cpu_thread_in_subcore(cpu)) return -EBUSY; if (smp_ops == NULL || -- 1.9.1 -- 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 v2 2/6] powerpc/powernv: Make it possible to skip the IRQHAPPENED check in power7_nap()
From: Michael Ellerman m...@ellerman.id.au
To support split core we need to be able to force all secondaries into
nap, so the core can detect they are idle and do an unsplit.
Currently power7_nap() will return without napping if there is an irq
pending. We want to ignore the pending irq and nap anyway, we will deal
with the interrupt later.
Signed-off-by: Michael Ellerman m...@ellerman.id.au
Signed-off-by: Michael Neuling mi...@neuling.org
---
arch/powerpc/include/asm/processor.h | 2 +-
arch/powerpc/kernel/idle_power7.S| 9 +
arch/powerpc/platforms/powernv/smp.c | 2 +-
3 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h
b/arch/powerpc/include/asm/processor.h
index d660dc3..6d59072 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -449,7 +449,7 @@ extern unsigned long cpuidle_disable;
enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
-extern void power7_nap(void);
+extern void power7_nap(int check_irq);
extern void power7_sleep(void);
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
diff --git a/arch/powerpc/kernel/idle_power7.S
b/arch/powerpc/kernel/idle_power7.S
index dca6e16..2480256 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -39,6 +39,10 @@
* Pass requested state in r3:
* 0 - nap
* 1 - sleep
+ *
+ * To check IRQ_HAPPENED in r4
+ * 0 - don't check
+ * 1 - check
*/
_GLOBAL(power7_powersave_common)
/* Use r3 to pass state nap/sleep/winkle */
@@ -71,6 +75,8 @@ _GLOBAL(power7_powersave_common)
lbz r0,PACAIRQHAPPENED(r13)
cmpwi cr0,r0,0
beq 1f
+ cmpwi cr0,r4,0
+ beq 1f
addir1,r1,INT_FRAME_SIZE
ld r0,16(r1)
mtlrr0
@@ -114,15 +120,18 @@ _GLOBAL(power7_idle)
lwz r4,ADDROFF(powersave_nap)(r3)
cmpwi 0,r4,0
beqlr
+ li r3, 1
/* fall through */
_GLOBAL(power7_nap)
+ mr r4,r3
li r3,0
b power7_powersave_common
/* No return */
_GLOBAL(power7_sleep)
li r3,1
+ li r4,0
b power7_powersave_common
/* No return */
diff --git a/arch/powerpc/platforms/powernv/smp.c
b/arch/powerpc/platforms/powernv/smp.c
index 1601a1e..65faf99 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -159,7 +159,7 @@ static void pnv_smp_cpu_kill_self(void)
mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) ~(u64)LPCR_PECE1);
while (!generic_check_cpu_restart(cpu)) {
ppc64_runlatch_off();
- power7_nap();
+ power7_nap(1);
ppc64_runlatch_on();
if (!generic_check_cpu_restart(cpu)) {
DBG(CPU%d Unexpected exit while offline !\n, cpu);
--
1.9.1
--
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 v2 6/6] powerpc/powernv: Add support for POWER8 split core on powernv
From: Michael Ellerman m...@ellerman.id.au Upcoming POWER8 chips support a concept called split core. This is where the core can be split into subcores that although not full cores, are able to appear as full cores to a guest. The splitting unsplitting procedure is mildly complicated, and explained at length in the comments within the patch. One notable detail is that when splitting or unsplitting we need to pull offline cpus out of their offline state to do work as part of the procedure. The interface for changing the split mode is via a sysfs file, eg: $ echo 2 /sys/devices/system/cpu/subcores_per_core Currently supported values are '1', '2' and '4'. And indicate respectively that the core should be unsplit, split in half, and split in quarters. These modes correspond to threads_per_subcore of 8, 4 and 2. We do not allow changing the split mode while KVM VMs are active. This is to prevent the value changing while userspace is configuring the VM, and also to prevent the mode being changed in such a way that existing guests are unable to be run. CPU hotplug fixes by Srivatsa. max_cpus fixes by Mahesh. cpuset fixes by benh. Fix for irq race by paulus. The rest by mikey and mpe. Signed-off-by: Michael Ellerman m...@ellerman.id.au Signed-off-by: Michael Neuling mi...@neuling.org Signed-off-by: Srivatsa S. Bhat srivatsa.b...@linux.vnet.ibm.com Signed-off-by: Mahesh Salgaonkar mah...@linux.vnet.ibm.com Signed-off-by: Benjamin Herrenschmidt b...@kernel.crashing.org --- arch/powerpc/include/asm/reg.h | 9 + arch/powerpc/platforms/powernv/Makefile | 2 +- arch/powerpc/platforms/powernv/powernv.h | 2 + arch/powerpc/platforms/powernv/smp.c | 18 +- arch/powerpc/platforms/powernv/subcore-asm.S | 95 +++ arch/powerpc/platforms/powernv/subcore.c | 392 +++ arch/powerpc/platforms/powernv/subcore.h | 18 ++ 7 files changed, 527 insertions(+), 9 deletions(-) create mode 100644 arch/powerpc/platforms/powernv/subcore-asm.S create mode 100644 arch/powerpc/platforms/powernv/subcore.c create mode 100644 arch/powerpc/platforms/powernv/subcore.h diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 29de015..2cd799b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -225,6 +225,7 @@ #define CTRL_TE 0x00c0 /* thread enable */ #define CTRL_RUNLATCH0x1 #define SPRN_DAWR 0xB4 +#define SPRN_RPR 0xBA/* Relative Priority Register */ #define SPRN_CIABR 0xBB #define CIABR_PRIV 0x3 #define CIABR_PRIV_USER 1 @@ -273,8 +274,10 @@ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_IC0x350 /* Virtual Instruction Count */ #define SPRN_VTB 0x351 /* Virtual Time Base */ +#define SPRN_LDBAR 0x352 /* LD Base Address Register */ #define SPRN_PMICR 0x354 /* Power Management Idle Control Reg */ #define SPRN_PMSR 0x355 /* Power Management Status Reg */ +#define SPRN_PMMAR 0x356 /* Power Management Memory Activity Register */ #define SPRN_PMCR 0x374 /* Power Management Control Register */ /* HFSCR and FSCR bit numbers are the same */ @@ -434,6 +437,12 @@ #define HID0_BTCD (11) /* Branch target cache disable */ #define HID0_NOPDST(11) /* No-op dst, dstt, etc. instr. */ #define HID0_NOPTI (10) /* No-op dcbt and dcbst instr. */ +/* POWER8 HID0 bits */ +#define HID0_POWER8_4LPARMODE __MASK(61) +#define HID0_POWER8_2LPARMODE __MASK(57) +#define HID0_POWER8_1TO2LPAR __MASK(52) +#define HID0_POWER8_1TO4LPAR __MASK(51) +#define HID0_POWER8_DYNLPARDIS __MASK(48) #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ #ifdef CONFIG_6xx diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 63cebb9..4ad0d34 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,7 +1,7 @@ obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o -obj-y += opal-msglog.o +obj-y += opal-msglog.o subcore.o subcore-asm.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 0051e10..75501bf 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -25,4 +25,6 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) extern void pnv_lpc_init(void); +bool cpu_core_split_required(void); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch
Re: [PATCH v2 0/6] Implement split core for POWER8
On Fri, 2014-05-23 at 11:53 +0200, Alexander Graf wrote: On 23.05.14 10:15, Michael Neuling wrote: This patch series implements split core mode on POWER8. This enables up to 4 subcores per core which can each independently run guests (per guest SPRs like SDR1, LPIDR etc are replicated per subcore). Lots more documentation on this feature in the code and commit messages. Most of this code is in the powernv platform but there's a couple of KVM specific patches too. Patch series authored by mpe and me with a few bug fixes from others. v2: There are some minor updates based on comments and I've added the Acks by Paulus and Alex for the KVM code. I don't see changelogs inside the individual patches. Please make sure to always mention what changed from one version to the next in a particular patch, so that I have the chance to check whether that change was good :). Sure, that was a bit sloppy Only the last patch was the only one that changed. I changed the sysfs file from 600 permissions to 644 so that users can read it more easily as requested by Joel. The other change was to fix the possibility of a race when coming out of nap and checking if we need to split. This fix was form paulus' (worked offline). Also, is there any performance penalty associated with split core mode? If not, could we just always default to split-by-4 on POWER8 bare metal? Yeah, there is a performance hit . When you are split (ie subcores_per_core = 2 or 4), the core is stuck in SMT8 mode. So if you only have 1 thread active (others napped), you won't get the benefit of ST mode in the core (more register renames per HW thread, more FXUs, more FPUs etc). Mikey -- 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
Re: [PATCH 0/6] Implement split core for POWER8
This patch series implements split core mode on POWER8. This enables up to 4 subcores per core which can each independently run guests (per guest SPRs like SDR1, LPIDR etc are replicated per subcore). Lots more documentation on this feature in the code and commit messages. Most of this code is in the powernv platform but there's a couple of KVM specific patches too. Alex: If you're happy with the KVM patches, please ACK them and benh can hold this series. Alex, Any chance we can get an ACK on these two KVM patches so benh can put this series in his next branch? Mikey -- 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
Re: [PATCH 2/6] KVM: PPC: Book3S PR: Emulate TIR register
In parallel to the Processor ID Register (PIR) threaded POWER8 also adds a Thread ID Register (TID). Since PR KVM doesn't emulate more than one thread s/TID/TIR/ above per core, we can just always expose 0 here. I'm not sure if we ever do, but if we IPI ourselves using a doorbell, we'll need to emulate the doorbell as well. Mikey Signed-off-by: Alexander Graf ag...@suse.de --- arch/powerpc/kvm/book3s_emulate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 914beb2..e4e54fb 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -563,6 +563,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val case SPRN_MMCR0: case SPRN_MMCR1: case SPRN_MMCR2: + case SPRN_TIR: *spr_val = 0; break; default: -- 1.8.1.4 -- 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 -- 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 0/6] Implement split core for POWER8
This patch series implements split core mode on POWER8. This enables up to 4 subcores per core which can each independently run guests (per guest SPRs like SDR1, LPIDR etc are replicated per subcore). Lots more documentation on this feature in the code and commit messages. Most of this code is in the powernv platform but there's a couple of KVM specific patches too. Alex: If you're happy with the KVM patches, please ACK them and benh can hold this series. Patch series authored by mpe and me with a few bug fixes from others. -- 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 1/6] KVM: PPC: Book3S HV: Rework the secondary inhibit code
From: Michael Ellerman m...@ellerman.id.au
As part of the support for split core on POWER8, we want to be able to
block splitting of the core while KVM VMs are active.
The logic to do that would be exactly the same as the code we currently
have for inhibiting onlining of secondaries.
Instead of adding an identical mechanism to block split core, rework the
secondary inhibit code to be a HV KVM is active check. We can then use
that in both the cpu hotplug code and the upcoming split core code.
Signed-off-by: Michael Ellerman m...@ellerman.id.au
Signed-off-by: Michael Neuling mi...@neuling.org
---
arch/powerpc/include/asm/kvm_ppc.h | 7 +++
arch/powerpc/include/asm/smp.h | 8
arch/powerpc/kernel/smp.c| 34 +++---
arch/powerpc/kvm/book3s_hv.c | 8
arch/powerpc/kvm/book3s_hv_builtin.c | 31 +++
5 files changed, 45 insertions(+), 43 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h
b/arch/powerpc/include/asm/kvm_ppc.h
index 4096f16..2c8e399 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -337,6 +337,10 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu
*vcpu)
vcpu-kvm-arch.kvm_ops-fast_vcpu_kick(vcpu);
}
+extern void kvm_hv_vm_activated(void);
+extern void kvm_hv_vm_deactivated(void);
+extern bool kvm_hv_mode_active(void);
+
#else
static inline void __init kvm_cma_reserve(void)
{}
@@ -356,6 +360,9 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu
*vcpu)
{
kvm_vcpu_kick(vcpu);
}
+
+static inline bool kvm_hv_mode_active(void){ return false; }
+
#endif
#ifdef CONFIG_KVM_XICS
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ff51046..5a6614a 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -68,14 +68,6 @@ void generic_mach_cpu_die(void);
void generic_set_cpu_dead(unsigned int cpu);
void generic_set_cpu_up(unsigned int cpu);
int generic_check_cpu_restart(unsigned int cpu);
-
-extern void inhibit_secondary_onlining(void);
-extern void uninhibit_secondary_onlining(void);
-
-#else /* HOTPLUG_CPU */
-static inline void inhibit_secondary_onlining(void) {}
-static inline void uninhibit_secondary_onlining(void) {}
-
#endif
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e2a4232..6edae3d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -36,6 +36,7 @@
#include linux/atomic.h
#include asm/irq.h
#include asm/hw_irq.h
+#include asm/kvm_ppc.h
#include asm/page.h
#include asm/pgtable.h
#include asm/prom.h
@@ -457,38 +458,9 @@ int generic_check_cpu_restart(unsigned int cpu)
return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
}
-static atomic_t secondary_inhibit_count;
-
-/*
- * Don't allow secondary CPU threads to come online
- */
-void inhibit_secondary_onlining(void)
-{
- /*
-* This makes secondary_inhibit_count stable during cpu
-* online/offline operations.
-*/
- get_online_cpus();
-
- atomic_inc(secondary_inhibit_count);
- put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(inhibit_secondary_onlining);
-
-/*
- * Allow secondary CPU threads to come online again
- */
-void uninhibit_secondary_onlining(void)
-{
- get_online_cpus();
- atomic_dec(secondary_inhibit_count);
- put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining);
-
-static int secondaries_inhibited(void)
+static bool secondaries_inhibited(void)
{
- return atomic_read(secondary_inhibit_count);
+ return kvm_hv_mode_active();
}
#else /* HOTPLUG_CPU */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8227dba..d7b74f8 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2317,10 +2317,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
spin_lock_init(kvm-arch.slot_phys_lock);
/*
-* Don't allow secondary CPU threads to come online
-* while any KVM VMs exist.
+* Track that we now have a HV mode VM active. This blocks secondary
+* CPU threads from coming online.
*/
- inhibit_secondary_onlining();
+ kvm_hv_vm_activated();
return 0;
}
@@ -2336,7 +2336,7 @@ static void kvmppc_free_vcores(struct kvm *kvm)
static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
- uninhibit_secondary_onlining();
+ kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
if (kvm-arch.rma) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c
b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8cd0dae..7cde8a6 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -6,6 +6,7 @@
* published by the Free Software Foundation.
*/
+#include linux/cpu.h
#include linux/kvm_host.h
#include linux/preempt.h
#include linux
[PATCH 5/6] KVM: PPC: Book3S HV: Use threads_per_subcore in KVM
From: Michael Ellerman m...@ellerman.id.au
To support split core on POWER8 we need to modify various parts of the
KVM code to use threads_per_subcore instead of threads_per_core. On
systems that do not support split core threads_per_subcore ==
threads_per_core and these changes are a nop.
We use threads_per_subcore as the value reported by KVM_CAP_PPC_SMT.
This communicates to userspace that guests can only be created with
a value of threads_per_core that is less than or equal to the current
threads_per_subcore. This ensures that guests can only be created with a
thread configuration that we are able to run given the current split
core mode.
Although threads_per_subcore can change during the life of the system,
the commit that enables that will ensure that threads_per_subcore does
not change during the life of a KVM VM.
Signed-off-by: Michael Ellerman m...@ellerman.id.au
Signed-off-by: Michael Neuling mi...@neuling.org
---
arch/powerpc/kvm/book3s_hv.c | 26 --
arch/powerpc/kvm/powerpc.c | 2 +-
2 files changed, 17 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d7b74f8..5e86f28 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1266,7 +1266,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct
kvm *kvm,
int core;
struct kvmppc_vcore *vcore;
- core = id / threads_per_core;
+ core = id / threads_per_subcore;
if (core = KVM_MAX_VCORES)
goto out;
@@ -1305,7 +1305,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct
kvm *kvm,
init_waitqueue_head(vcore-wq);
vcore-preempt_tb = TB_NIL;
vcore-lpcr = kvm-arch.lpcr;
- vcore-first_vcpuid = core * threads_per_core;
+ vcore-first_vcpuid = core * threads_per_subcore;
vcore-kvm = kvm;
}
kvm-arch.vcores[core] = vcore;
@@ -1495,16 +1495,19 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
static int on_primary_thread(void)
{
int cpu = smp_processor_id();
- int thr = cpu_thread_in_core(cpu);
+ int thr;
- if (thr)
+ /* Are we on a primary subcore? */
+ if (cpu_thread_in_subcore(cpu))
return 0;
- while (++thr threads_per_core)
+
+ thr = 0;
+ while (++thr threads_per_subcore)
if (cpu_online(cpu + thr))
return 0;
/* Grab all hw threads so they can't go into the kernel */
- for (thr = 1; thr threads_per_core; ++thr) {
+ for (thr = 1; thr threads_per_subcore; ++thr) {
if (kvmppc_grab_hwthread(cpu + thr)) {
/* Couldn't grab one; let the others go */
do {
@@ -1563,15 +1566,18 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
}
/*
-* Make sure we are running on thread 0, and that
-* secondary threads are offline.
+* Make sure we are running on primary threads, and that secondary
+* threads are offline. Also check if the number of threads in this
+* guest are greater than the current system threads per guest.
*/
- if (threads_per_core 1 !on_primary_thread()) {
+ if ((threads_per_core 1)
+ ((vc-num_threads threads_per_subcore) || !on_primary_thread())) {
list_for_each_entry(vcpu, vc-runnable_threads, arch.run_list)
vcpu-arch.ret = -EBUSY;
goto out;
}
+
vc-pcpu = smp_processor_id();
list_for_each_entry(vcpu, vc-runnable_threads, arch.run_list) {
kvmppc_start_thread(vcpu);
@@ -1599,7 +1605,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
/* wait for secondary threads to finish writing their state to memory */
if (vc-nap_count vc-n_woken)
kvmppc_wait_for_nap(vc);
- for (i = 0; i threads_per_core; ++i)
+ for (i = 0; i threads_per_subcore; ++i)
kvmppc_release_hwthread(vc-pcpu + i);
/* prevent other vcpu threads from doing kvmppc_start_thread() now */
vc-vcore_state = VCORE_EXITING;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3cf541a..27919a8 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -384,7 +384,7 @@ int kvm_dev_ioctl_check_extension(long ext)
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_SMT:
if (hv_enabled)
- r = threads_per_core;
+ r = threads_per_subcore;
else
r = 0;
break;
--
1.8.3.2
--
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
[PATCH 3/6] powerpc: Add threads_per_subcore
From: Michael Ellerman m...@ellerman.id.au
On POWER8 we have a new concept of a subcore. This is what happens when
you take a regular core and split it. A subcore is a grouping of two or
four SMT threads, as well as a handfull of SPRs which allows the subcore
to appear as if it were a core from the point of view of a guest.
Unlike threads_per_core which is fixed at boot, threads_per_subcore can
change while the system is running. Most code will not want to use
threads_per_subcore.
Signed-off-by: Michael Ellerman m...@ellerman.id.au
Signed-off-by: Michael Neuling mi...@neuling.org
---
arch/powerpc/include/asm/cputhreads.h | 7 +++
arch/powerpc/kernel/setup-common.c| 4 +++-
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/cputhreads.h
b/arch/powerpc/include/asm/cputhreads.h
index ac3eedb..2bf8e93 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -18,10 +18,12 @@
#ifdef CONFIG_SMP
extern int threads_per_core;
+extern int threads_per_subcore;
extern int threads_shift;
extern cpumask_t threads_core_mask;
#else
#define threads_per_core 1
+#define threads_per_subcore1
#define threads_shift 0
#define threads_core_mask (CPU_MASK_CPU0)
#endif
@@ -74,6 +76,11 @@ static inline int cpu_thread_in_core(int cpu)
return cpu (threads_per_core - 1);
}
+static inline int cpu_thread_in_subcore(int cpu)
+{
+ return cpu (threads_per_subcore - 1);
+}
+
static inline int cpu_first_thread_sibling(int cpu)
{
return cpu ~(threads_per_core - 1);
diff --git a/arch/powerpc/kernel/setup-common.c
b/arch/powerpc/kernel/setup-common.c
index 79b7612..f9faf1e 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -382,9 +382,10 @@ void __init check_for_initrd(void)
#ifdef CONFIG_SMP
-int threads_per_core, threads_shift;
+int threads_per_core, threads_per_subcore, threads_shift;
cpumask_t threads_core_mask;
EXPORT_SYMBOL_GPL(threads_per_core);
+EXPORT_SYMBOL_GPL(threads_per_subcore);
EXPORT_SYMBOL_GPL(threads_shift);
EXPORT_SYMBOL_GPL(threads_core_mask);
@@ -393,6 +394,7 @@ static void __init cpu_init_thread_core_maps(int tpc)
int i;
threads_per_core = tpc;
+ threads_per_subcore = tpc;
cpumask_clear(threads_core_mask);
/* This implementation only supports power of 2 number of threads
--
1.8.3.2
--
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 4/6] powerpc: Check cpu_thread_in_subcore() in __cpu_up()
From: Michael Ellerman m...@ellerman.id.au To support split core we need to change the check in __cpu_up() that determines if a cpu is allowed to come online. Currently we refuse to online cpus which are not the primary thread within their core. On POWER8 with split core support this check needs to instead refuse to online cpus which are not the primary thread within their *sub* core. On POWER7 and other systems that do not support split core, threads_per_subcore == threads_per_core and so the check is equivalent. Signed-off-by: Michael Ellerman m...@ellerman.id.au Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6edae3d..b5222c4 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -489,7 +489,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Don't allow secondary threads to come online if inhibited */ if (threads_per_core 1 secondaries_inhibited() - cpu % threads_per_core != 0) + cpu_thread_in_subcore(cpu)) return -EBUSY; if (smp_ops == NULL || -- 1.8.3.2 -- 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 6/6] powerpc/powernv: Add support for POWER8 split core on powernv
From: Michael Ellerman m...@ellerman.id.au Upcoming POWER8 chips support a concept called split core. This is where the core can be split into subcores that although not full cores, are able to appear as full cores to a guest. The splitting unsplitting procedure is mildly complicated, and explained at length in the comments within the patch. One notable detail is that when splitting or unsplitting we need to pull offline cpus out of their offline state to do work as part of the procedure. The interface for changing the split mode is via a sysfs file, eg: $ echo 2 /sys/devices/system/cpu/subcores_per_core Currently supported values are '1', '2' and '4'. And indicate respectively that the core should be unsplit, split in half, and split in quarters. These modes correspond to threads_per_subcore of 8, 4 and 2. We do not allow changing the split mode while KVM VMs are active. This is to prevent the value changing while userspace is configuring the VM, and also to prevent the mode being changed in such a way that existing guests are unable to be run. CPU hotplug fixes by Srivatsa. max_cpus fixes by Mahesh. cpuset fixes by benh. The rest by mikey and mpe. Signed-off-by: Michael Ellerman m...@ellerman.id.au Signed-off-by: Michael Neuling mi...@neuling.org Signed-off-by: Srivatsa S. Bhat srivatsa.b...@linux.vnet.ibm.com Signed-off-by: Mahesh Salgaonkar mah...@linux.vnet.ibm.com Signed-off-by: Benjamin Herrenschmidt b...@kernel.crashing.org --- arch/powerpc/include/asm/reg.h | 9 + arch/powerpc/platforms/powernv/Makefile | 2 +- arch/powerpc/platforms/powernv/powernv.h | 2 + arch/powerpc/platforms/powernv/smp.c | 8 + arch/powerpc/platforms/powernv/subcore-asm.S | 95 +++ arch/powerpc/platforms/powernv/subcore.c | 392 +++ arch/powerpc/platforms/powernv/subcore.h | 18 ++ 7 files changed, 525 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/platforms/powernv/subcore-asm.S create mode 100644 arch/powerpc/platforms/powernv/subcore.c create mode 100644 arch/powerpc/platforms/powernv/subcore.h diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e5d2e0b..154c419 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -224,6 +224,7 @@ #define CTRL_TE 0x00c0 /* thread enable */ #define CTRL_RUNLATCH0x1 #define SPRN_DAWR 0xB4 +#define SPRN_RPR 0xBA/* Relative Priority Register */ #define SPRN_CIABR 0xBB #define CIABR_PRIV 0x3 #define CIABR_PRIV_USER 1 @@ -272,8 +273,10 @@ #define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_IC0x350 /* Virtual Instruction Count */ #define SPRN_VTB 0x351 /* Virtual Time Base */ +#define SPRN_LDBAR 0x352 /* LD Base Address Register */ #define SPRN_PMICR 0x354 /* Power Management Idle Control Reg */ #define SPRN_PMSR 0x355 /* Power Management Status Reg */ +#define SPRN_PMMAR 0x356 /* Power Management Memory Activity Register */ #define SPRN_PMCR 0x374 /* Power Management Control Register */ /* HFSCR and FSCR bit numbers are the same */ @@ -433,6 +436,12 @@ #define HID0_BTCD (11) /* Branch target cache disable */ #define HID0_NOPDST(11) /* No-op dst, dstt, etc. instr. */ #define HID0_NOPTI (10) /* No-op dcbt and dcbst instr. */ +/* POWER8 HID0 bits */ +#define HID0_POWER8_4LPARMODE __MASK(61) +#define HID0_POWER8_2LPARMODE __MASK(57) +#define HID0_POWER8_1TO2LPAR __MASK(52) +#define HID0_POWER8_1TO4LPAR __MASK(51) +#define HID0_POWER8_DYNLPARDIS __MASK(48) #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ #ifdef CONFIG_6xx diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 63cebb9..4ad0d34 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,7 +1,7 @@ obj-y += setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o -obj-y += opal-msglog.o +obj-y += opal-msglog.o subcore.o subcore-asm.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 0051e10..75501bf 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -25,4 +25,6 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) extern void pnv_lpc_init(void); +bool cpu_core_split_required(void); + #endif /* _POWERNV_H */ diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv
[PATCH 2/6] powerpc/powernv: Make it possible to skip the IRQHAPPENED check in power7_nap()
From: Michael Ellerman m...@ellerman.id.au
To support split core we need to be able to force all secondaries into
nap, so the core can detect they are idle and do an unsplit.
Currently power7_nap() will return without napping if there is an irq
pending. We want to ignore the pending irq and nap anyway, we will deal
with the interrupt later.
Signed-off-by: Michael Ellerman m...@ellerman.id.au
Signed-off-by: Michael Neuling mi...@neuling.org
---
arch/powerpc/include/asm/processor.h | 2 +-
arch/powerpc/kernel/idle_power7.S| 9 +
arch/powerpc/platforms/powernv/smp.c | 2 +-
3 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/processor.h
b/arch/powerpc/include/asm/processor.h
index d660dc3..6d59072 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -449,7 +449,7 @@ extern unsigned long cpuidle_disable;
enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
extern int powersave_nap; /* set if nap mode can be used in idle loop */
-extern void power7_nap(void);
+extern void power7_nap(int check_irq);
extern void power7_sleep(void);
extern void flush_instruction_cache(void);
extern void hard_reset_now(void);
diff --git a/arch/powerpc/kernel/idle_power7.S
b/arch/powerpc/kernel/idle_power7.S
index c3ab869..063c7cb 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -39,6 +39,10 @@
* Pass requested state in r3:
* 0 - nap
* 1 - sleep
+ *
+ * To check IRQ_HAPPENED in r4
+ * 0 - don't check
+ * 1 - check
*/
_GLOBAL(power7_powersave_common)
/* Use r3 to pass state nap/sleep/winkle */
@@ -71,6 +75,8 @@ _GLOBAL(power7_powersave_common)
lbz r0,PACAIRQHAPPENED(r13)
cmpwi cr0,r0,0
beq 1f
+ cmpwi cr0,r4,0
+ beq 1f
addir1,r1,INT_FRAME_SIZE
ld r0,16(r1)
mtlrr0
@@ -115,14 +121,17 @@ _GLOBAL(power7_idle)
cmpwi 0,r4,0
beqlr
/* fall through */
+ li r3, 1
_GLOBAL(power7_nap)
+ mr r4,r3
li r3,0
b power7_powersave_common
/* No return */
_GLOBAL(power7_sleep)
li r3,1
+ li r4,0
b power7_powersave_common
/* No return */
diff --git a/arch/powerpc/platforms/powernv/smp.c
b/arch/powerpc/platforms/powernv/smp.c
index 908672b..ab8b4ad 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -156,7 +156,7 @@ static void pnv_smp_cpu_kill_self(void)
*/
mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) ~(u64)LPCR_PECE1);
while (!generic_check_cpu_restart(cpu)) {
- power7_nap();
+ power7_nap(1);
if (!generic_check_cpu_restart(cpu)) {
DBG(CPU%d Unexpected exit while offline !\n, cpu);
/* We may be getting an IPI, so we re-enable
--
1.8.3.2
--
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
Re: [PATCH 6/6] powerpc/powernv: Add support for POWER8 split core on powernv
Joel Stanley j...@jms.id.au wrote: Hi Mikey, On Thu, Apr 24, 2014 at 11:02 AM, Michael Neuling mi...@neuling.org wrote: +static DEVICE_ATTR(subcores_per_core, 0600, + show_subcores_per_core, store_subcores_per_core); Can we make this 644, so users can query the state of the system without being root? This is useful for tools like ppc64_cpu --info. Good point... I'll update. Thanks, Mikey -- 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 1/2] KVM: PPC: Book3S HV: Make TM avoid program check
Currently using kvmppc_set_one_reg() a transaction could be setup without TEXASR Failure Summary (FS) not set. When this is switched back in by the host, this will result in a TM Bad Thing (ie 0x700 program check) when the trechkpt is run. This avoids this by always setting the TEXASR FS when there is an active transaction being started. This patch is on top of Paulus' recent KVM TM patch set. Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 217a22e..01d5701 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -639,6 +639,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 beq 1f /* TM not active in guest */ + /* Make sure the failure summary is set, otherwise we'll program check +* when we trechkpt. It's possible that this might have been not set +* on a kvmppc_set_one_reg() call but we shouldn't let this crash the +* host. +*/ + orisr7, r7, (TEXASR_FS)@h + mtspr SPRN_TEXASR, r7 + /* * We need to load up the checkpointed state for the guest. * We need to do this early as it will blow away any GPRs, VSRs and -- 1.8.3.2 -- 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 2/2] KVM: PPC: Book3S HV: Add branch label
This branch label is over a large section so let's give it a real name. Signed-off-by: Michael Neuling mi...@neuling.org --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 01d5701..832750d 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -612,7 +612,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION - b 1f + b skip_tm END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Turn on TM/FP/VSX/VMX so we can restore them. */ @@ -637,7 +637,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) ld r5, VCPU_MSR(r4) rldicl. r5, r5, 64 - MSR_TS_S_LG, 62 - beq 1f /* TM not active in guest */ + beq skip_tm /* TM not active in guest */ /* Make sure the failure summary is set, otherwise we'll program check * when we trechkpt. It's possible that this might have been not set @@ -717,7 +717,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) /* Set the MSR RI since we have our registers back. */ li r5, MSR_RI mtmsrd r5, 1 -1: +skip_tm: #endif /* Load guest PMU registers */ -- 1.8.3.2 -- 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
Re: [PATCH RFC 0/5] Eliminate double-copying of FP/VMX/VSX state
At present, PR KVM and BookE KVM does multiple copies of FP and related state because of the way that they use the arrays in the thread_struct as an intermediate staging post for the state. They do this so that they can use the existing system functions for loading and saving state, and so that they can keep guest state in the CPU registers while executing general kernel code. This patch series reorganizes things so that KVM and the main kernel use the same representation for FP/VMX/VSX state, and so that guest state can be loaded/save directly from/to the vcpu struct instead of having to go via the thread_struct. This simplifies things and should be a little faster. This series is against Alex Graf's kvm-ppc-queue branch plus my recent series of 23 patches to make PR and HV KVM coexist. This is great! Alex, can you pull this into your tree? It's going to be very useful for POWER8 transactional memory as we have to save another set of VSX state. The changes in 4/5 are going to make coding this up a lot cleaner There are a lot of generic powerpc changes in here also. Perhaps, if Alex is fine with these, he can ACK them and benh can pull this in? Mikey Paul. -- 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 -- 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
Re: [PATCH RFC 0/5] Eliminate double-copying of FP/VMX/VSX state
Alexander Graf ag...@suse.de wrote: On 09.09.2013, at 09:28, Michael Neuling wrote: At present, PR KVM and BookE KVM does multiple copies of FP and related state because of the way that they use the arrays in the thread_struct as an intermediate staging post for the state. They do this so that they can use the existing system functions for loading and saving state, and so that they can keep guest state in the CPU registers while executing general kernel code. This patch series reorganizes things so that KVM and the main kernel use the same representation for FP/VMX/VSX state, and so that guest state can be loaded/save directly from/to the vcpu struct instead of having to go via the thread_struct. This simplifies things and should be a little faster. This series is against Alex Graf's kvm-ppc-queue branch plus my recent series of 23 patches to make PR and HV KVM coexist. This is great! Alex, can you pull this into your tree? I never apply RFC patches if I can avoid it. Paul, if you think they're ready for inclusion, please repost them as actual patches. Arrh, good point. I'll talk to paulus about reposting them. Your kvm-ppc-queue branch on github seems to be based on 3.11-rc1. Is that the tree we should be aiming for currently? Mikey -- 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 v2] KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg
This reserves space in get/set_one_reg ioctl for the extra guest state
needed for POWER8. It doesn't implement these at all, it just reserves
them so that the ABI is defined now.
A few things to note here:
- This add *a lot* state for transactional memory. TM suspend mode,
this is unavoidable, you can't simply roll back all transactions and
store only the checkpointed state. I've added this all to
get/set_one_reg (including GPRs) rather than creating a new ioctl
which returns a struct kvm_regs like KVM_GET_REGS does. This means we
if we need to extract the TM state, we are going to need a bucket load
of IOCTLs. Hopefully most of the time this will not be needed as we
can look at the MSR to see if TM is active and only grab them when
needed. If this becomes a bottle neck in future we can add another
ioctl to grab all this state in one go.
- The TM state is offset by 0x8000.
- For TM, I've done away with VMX and FP and created a single 64x128 bit
VSX register space.
- I've left a space of 1 (at 0x9c) since Paulus needs to add a value
which applies to POWER7 as well.
Signed-off-by: Michael Neuling mi...@neuling.org
diff --git a/Documentation/virtual/kvm/api.txt
b/Documentation/virtual/kvm/api.txt
index ef925ea..341058c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1810,6 +1810,45 @@ registers, find a list below:
PPC | KVM_REG_PPC_TLB3PS | 32
PPC | KVM_REG_PPC_EPTCFG | 32
PPC | KVM_REG_PPC_ICP_STATE | 64
+ PPC | KVM_REG_PPC_SPMC1| 32
+ PPC | KVM_REG_PPC_SPMC2| 32
+ PPC | KVM_REG_PPC_IAMR | 64
+ PPC | KVM_REG_PPC_TFHAR| 64
+ PPC | KVM_REG_PPC_TFIAR| 64
+ PPC | KVM_REG_PPC_TEXASR | 64
+ PPC | KVM_REG_PPC_FSCR | 64
+ PPC | KVM_REG_PPC_PSPB | 32
+ PPC | KVM_REG_PPC_EBBHR| 64
+ PPC | KVM_REG_PPC_EBBRR| 64
+ PPC | KVM_REG_PPC_BESCR| 64
+ PPC | KVM_REG_PPC_TAR | 64
+ PPC | KVM_REG_PPC_DPDES| 64
+ PPC | KVM_REG_PPC_DAWR | 64
+ PPC | KVM_REG_PPC_DAWRX| 64
+ PPC | KVM_REG_PPC_CIABR| 64
+ PPC | KVM_REG_PPC_IC | 64
+ PPC | KVM_REG_PPC_VTB | 64
+ PPC | KVM_REG_PPC_CSIGR| 64
+ PPC | KVM_REG_PPC_TACR | 64
+ PPC | KVM_REG_PPC_TCSCR| 64
+ PPC | KVM_REG_PPC_PID | 64
+ PPC | KVM_REG_PPC_ACOP | 64
+ PPC | KVM_REG_PPC_TM_GPR0 | 64
+ ...
+ PPC | KVM_REG_PPC_TM_GPR31 | 64
+ PPC | KVM_REG_PPC_TM_VSR0 | 128
+ ...
+ PPC | KVM_REG_PPC_TM_VSR63 | 128
+ PPC | KVM_REG_PPC_TM_CR| 64
+ PPC | KVM_REG_PPC_TM_LR| 64
+ PPC | KVM_REG_PPC_TM_CTR | 64
+ PPC | KVM_REG_PPC_TM_FPSCR | 64
+ PPC | KVM_REG_PPC_TM_AMR | 64
+ PPC | KVM_REG_PPC_TM_PPR | 64
+ PPC | KVM_REG_PPC_TM_VRSAVE| 64
+ PPC | KVM_REG_PPC_TM_VSCR | 32
+ PPC | KVM_REG_PPC_TM_DSCR | 64
+ PPC | KVM_REG_PPC_TM_TAR | 64
ARM registers are mapped using the lower 32 bits. The upper 16 of that
is the register group type, or coprocessor number:
diff --git a/arch/powerpc/include/uapi/asm/kvm.h
b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1a6e..8e687a1 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -429,6 +429,11 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
#define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
#define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
#define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
#define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
@@ -499,6 +504,55 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
#define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_EBBRR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define
[PATCH v3] KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg
This reserves space in get/set_one_reg ioctl for the extra guest state
needed for POWER8. It doesn't implement these at all, it just reserves
them so that the ABI is defined now.
A few things to note here:
- This add *a lot* state for transactional memory. TM suspend mode,
this is unavoidable, you can't simply roll back all transactions and
store only the checkpointed state. I've added this all to
get/set_one_reg (including GPRs) rather than creating a new ioctl
which returns a struct kvm_regs like KVM_GET_REGS does. This means we
if we need to extract the TM state, we are going to need a bucket load
of IOCTLs. Hopefully most of the time this will not be needed as we
can look at the MSR to see if TM is active and only grab them when
needed. If this becomes a bottle neck in future we can add another
ioctl to grab all this state in one go.
- The TM state is offset by 0x8000.
- For TM, I've done away with VMX and FP and created a single 64x128 bit
VSX register space.
- I've left a space of 1 (at 0x9c) since Paulus needs to add a value
which applies to POWER7 as well.
Signed-off-by: Michael Neuling mi...@neuling.org
---
The last one was screwed up... sorry..
v3:
fix naming mistake and whitespace screwage.
v2:
integrate feedback
diff --git a/Documentation/virtual/kvm/api.txt
b/Documentation/virtual/kvm/api.txt
index ef925ea..341058c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1810,6 +1810,45 @@ registers, find a list below:
PPC | KVM_REG_PPC_TLB3PS | 32
PPC | KVM_REG_PPC_EPTCFG | 32
PPC | KVM_REG_PPC_ICP_STATE | 64
+ PPC | KVM_REG_PPC_SPMC1| 32
+ PPC | KVM_REG_PPC_SPMC2| 32
+ PPC | KVM_REG_PPC_IAMR | 64
+ PPC | KVM_REG_PPC_TFHAR| 64
+ PPC | KVM_REG_PPC_TFIAR| 64
+ PPC | KVM_REG_PPC_TEXASR | 64
+ PPC | KVM_REG_PPC_FSCR | 64
+ PPC | KVM_REG_PPC_PSPB | 32
+ PPC | KVM_REG_PPC_EBBHR| 64
+ PPC | KVM_REG_PPC_EBBRR| 64
+ PPC | KVM_REG_PPC_BESCR| 64
+ PPC | KVM_REG_PPC_TAR | 64
+ PPC | KVM_REG_PPC_DPDES| 64
+ PPC | KVM_REG_PPC_DAWR | 64
+ PPC | KVM_REG_PPC_DAWRX| 64
+ PPC | KVM_REG_PPC_CIABR| 64
+ PPC | KVM_REG_PPC_IC | 64
+ PPC | KVM_REG_PPC_VTB | 64
+ PPC | KVM_REG_PPC_CSIGR| 64
+ PPC | KVM_REG_PPC_TACR | 64
+ PPC | KVM_REG_PPC_TCSCR| 64
+ PPC | KVM_REG_PPC_PID | 64
+ PPC | KVM_REG_PPC_ACOP | 64
+ PPC | KVM_REG_PPC_TM_GPR0 | 64
+ ...
+ PPC | KVM_REG_PPC_TM_GPR31 | 64
+ PPC | KVM_REG_PPC_TM_VSR0 | 128
+ ...
+ PPC | KVM_REG_PPC_TM_VSR63 | 128
+ PPC | KVM_REG_PPC_TM_CR| 64
+ PPC | KVM_REG_PPC_TM_LR| 64
+ PPC | KVM_REG_PPC_TM_CTR | 64
+ PPC | KVM_REG_PPC_TM_FPSCR | 64
+ PPC | KVM_REG_PPC_TM_AMR | 64
+ PPC | KVM_REG_PPC_TM_PPR | 64
+ PPC | KVM_REG_PPC_TM_VRSAVE| 64
+ PPC | KVM_REG_PPC_TM_VSCR | 32
+ PPC | KVM_REG_PPC_TM_DSCR | 64
+ PPC | KVM_REG_PPC_TM_TAR | 64
ARM registers are mapped using the lower 32 bits. The upper 16 of that
is the register group type, or coprocessor number:
diff --git a/arch/powerpc/include/uapi/asm/kvm.h
b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1a6e..7ed41c0 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -429,6 +429,11 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
#define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
#define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
#define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
#define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
@@ -499,6 +504,55 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
#define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR
[PATCH RFC] KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg
Alex,
This reserves space in get/set_one_reg ioctl for the extra guest state
needed for POWER8. It doesn't implement these at all, it just reserves
them so that the ABI is defined now.
A few things to note here:
- POWER8 has 6 PMCs and an additional 2 SPMCs for the supervisor. Here
I'm storing these 2 SPMCs in PMC7/8.
- This add *a lot* state for transactional memory. TM suspend mode,
this is unavoidable, you can't simply roll back all transactions and
store only the checkpointed state. I've added this all to
get/set_one_reg (including GPRs) rather than creating a new ioctl
which returns a struct kvm_regs like KVM_GET_REGS does. This means we
if we need to extract the TM state, we are going to need a bucket load
of IOCTLs. Hopefully most of the time this will not be needed as we
can look at the MSR to see if TM is active and only grab them when
needed.
- The TM state is offset bu 0x1000. Other than being bigger than the
SPR space, it's fairly arbitrarily chose.
- For TM, I've done away with VMX and FP and created a single 64x128 bit
VSX register space.
Alex: I'll add the documentation Documentation/virtual/kvm/api.txt if
you're happy with all this.
Signed-off-by: Michael Neuling mi...@neuling.org
diff --git a/arch/powerpc/include/uapi/asm/kvm.h
b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1a6e..33b8007 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -429,6 +429,11 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
#define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
#define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
#define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
#define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
@@ -499,6 +504,53 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
#define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+/* POWER8 new SPRs */
+#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9d)
+#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9e)
+#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa1)
+#define KVM_REG_PPC_EBBHR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_EBBRR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_BESCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa4)
+#define KVM_REG_PPC_TAR(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_DPDES (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define KVM_REG_PPC_DAWR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7)
+#define KVM_REG_PPC_DAWRX (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8)
+#define KVM_REG_PPC_CIABR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9)
+#define KVM_REG_PPC_IC (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa)
+#define KVM_REG_PPC_VTB(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab)
+#define KVM_REG_PPC_CSIGR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac)
+#define KVM_REG_PPC_TACR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad)
+#define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae)
+#define KVM_REG_PPC_PID(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf)
+#define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0)
+
+/* Transactional Memory checkpointed state:
+ * This is all GPRs, all VSX regs and a subset of SPRs
+ */
+#define KVM_REG_PPC_TM (KVM_REG_PPC | 0x1000)
+/* TM GPRs */
+#define KVM_REG_PPC_TM_GPR0(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_PPC_TM_GPR(n) (KVM_REG_PPC_TM_GPR0 + (n))
+#define KVM_REG_PPC_TM_GPR31 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f)
+/* TM VSX */
+#define KVM_REG_PPC_TM_VSR0(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x20)
+#define KVM_REG_PPC_TM_VSR(n) (KVM_REG_PPC_VSR0 + (n))
+#define KVM_REG_PPC_VSR63 (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x5f)
+/* TM SPRS */
+#define KVM_REG_PPC_TM_CR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60)
+#define KVM_REG_PPC_TM_LR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61)
+#define KVM_REG_PPC_TM_CTR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62)
+#define KVM_REG_PPC_TM_FPSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63)
+#define KVM_REG_PPC_TM_AMR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64)
+#define
Re: [PATCH RFC] KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg
On Sat, Aug 31, 2013 at 8:17 AM, Benjamin Herrenschmidt b...@kernel.crashing.org wrote: On Fri, 2013-08-30 at 16:01 +0200, Alexander Graf wrote: - The TM state is offset bu 0x1000. Other than being bigger than the SPR space, it's fairly arbitrarily chose. Make it higher, just in case Ok but how high? KVM_REG_SiZE is set by generic code and it's way up at 0x0030ULL Mikey -- 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
Re: [PATCH RFC] KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg
On Sat, Aug 31, 2013 at 12:01 AM, Alexander Graf ag...@suse.de wrote: On 30.08.2013, at 08:09, Michael Neuling wrote: Alex, This reserves space in get/set_one_reg ioctl for the extra guest state needed for POWER8. It doesn't implement these at all, it just reserves them so that the ABI is defined now. A few things to note here: - POWER8 has 6 PMCs and an additional 2 SPMCs for the supervisor. Here I'm storing these 2 SPMCs in PMC7/8. Is this safe to do? Are we guaranteed that POWER9 or POWER10 doesn't introduce a real PMC7? Good point. I'll change it. - This add *a lot* state for transactional memory. TM suspend mode, this is unavoidable, you can't simply roll back all transactions and store only the checkpointed state. I've added this all to get/set_one_reg (including GPRs) rather than creating a new ioctl which returns a struct kvm_regs like KVM_GET_REGS does. This means we if we need to extract the TM state, we are going to need a bucket load of IOCTLs. Hopefully most of the time this will not be needed as we can look at the MSR to see if TM is active and only grab them when needed. If we find this to be a performance issue, we can always add a new ioctl that allows multiple ONE_REG accesses at a time. The only reason we don't have that yet is that bulk one_reg access hasn't happened in any performance critical path so far. Ok. - The TM state is offset bu 0x1000. Other than being bigger than the SPR space, it's fairly arbitrarily chose. - For TM, I've done away with VMX and FP and created a single 64x128 bit VSX register space. Alex: I'll add the documentation Documentation/virtual/kvm/api.txt if you're happy with all this. Looks perfectly reasonable to me :). Thanks. I'll repost. Mikey -- 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
Re: [PATCH] KVM: PPC: BookE: HV: Fix compile
Alexander Graf ag...@suse.de wrote: After merging the register type check patches from Ben's tree, the hv enabled booke implementation ceased to compile. This patch fixes things up so everyone's happy again. Is there a defconfig which catches this? Mikey Signed-off-by: Alexander Graf ag...@suse.de --- arch/powerpc/kvm/bookehv_interrupts.S | 77 + 1 files changed, 39 insertions(+), 38 deletions(-) diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index d28c2d4..099fe82 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -50,8 +50,9 @@ #define HOST_R2 (3 * LONGBYTES) #define HOST_CR (4 * LONGBYTES) #define HOST_NV_GPRS(5 * LONGBYTES) -#define HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * LONGBYTES)) -#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + LONGBYTES) +#define __HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * LONGBYTES)) +#define HOST_NV_GPR(n) __HOST_NV_GPR(__REG_##n) +#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + LONGBYTES) #define HOST_STACK_SIZE ((HOST_MIN_STACK_SIZE + 15) ~15) /* Align. */ #define HOST_STACK_LR (HOST_STACK_SIZE + LONGBYTES) /* In caller stack frame. */ @@ -410,24 +411,24 @@ heavyweight_exit: PPC_STL r31, VCPU_GPR(R31)(r4) /* Load host non-volatile register state from host stack. */ - PPC_LL r14, HOST_NV_GPR(r14)(r1) - PPC_LL r15, HOST_NV_GPR(r15)(r1) - PPC_LL r16, HOST_NV_GPR(r16)(r1) - PPC_LL r17, HOST_NV_GPR(r17)(r1) - PPC_LL r18, HOST_NV_GPR(r18)(r1) - PPC_LL r19, HOST_NV_GPR(r19)(r1) - PPC_LL r20, HOST_NV_GPR(r20)(r1) - PPC_LL r21, HOST_NV_GPR(r21)(r1) - PPC_LL r22, HOST_NV_GPR(r22)(r1) - PPC_LL r23, HOST_NV_GPR(r23)(r1) - PPC_LL r24, HOST_NV_GPR(r24)(r1) - PPC_LL r25, HOST_NV_GPR(r25)(r1) - PPC_LL r26, HOST_NV_GPR(r26)(r1) - PPC_LL r27, HOST_NV_GPR(r27)(r1) - PPC_LL r28, HOST_NV_GPR(r28)(r1) - PPC_LL r29, HOST_NV_GPR(r29)(r1) - PPC_LL r30, HOST_NV_GPR(r30)(r1) - PPC_LL r31, HOST_NV_GPR(r31)(r1) + PPC_LL r14, HOST_NV_GPR(R14)(r1) + PPC_LL r15, HOST_NV_GPR(R15)(r1) + PPC_LL r16, HOST_NV_GPR(R16)(r1) + PPC_LL r17, HOST_NV_GPR(R17)(r1) + PPC_LL r18, HOST_NV_GPR(R18)(r1) + PPC_LL r19, HOST_NV_GPR(R19)(r1) + PPC_LL r20, HOST_NV_GPR(R20)(r1) + PPC_LL r21, HOST_NV_GPR(R21)(r1) + PPC_LL r22, HOST_NV_GPR(R22)(r1) + PPC_LL r23, HOST_NV_GPR(R23)(r1) + PPC_LL r24, HOST_NV_GPR(R24)(r1) + PPC_LL r25, HOST_NV_GPR(R25)(r1) + PPC_LL r26, HOST_NV_GPR(R26)(r1) + PPC_LL r27, HOST_NV_GPR(R27)(r1) + PPC_LL r28, HOST_NV_GPR(R28)(r1) + PPC_LL r29, HOST_NV_GPR(R29)(r1) + PPC_LL r30, HOST_NV_GPR(R30)(r1) + PPC_LL r31, HOST_NV_GPR(R31)(r1) /* Return to kvm_vcpu_run(). */ mtlrr5 @@ -453,24 +454,24 @@ _GLOBAL(__kvmppc_vcpu_run) stw r5, HOST_CR(r1) /* Save host non-volatile register state to stack. */ - PPC_STL r14, HOST_NV_GPR(r14)(r1) - PPC_STL r15, HOST_NV_GPR(r15)(r1) - PPC_STL r16, HOST_NV_GPR(r16)(r1) - PPC_STL r17, HOST_NV_GPR(r17)(r1) - PPC_STL r18, HOST_NV_GPR(r18)(r1) - PPC_STL r19, HOST_NV_GPR(r19)(r1) - PPC_STL r20, HOST_NV_GPR(r20)(r1) - PPC_STL r21, HOST_NV_GPR(r21)(r1) - PPC_STL r22, HOST_NV_GPR(r22)(r1) - PPC_STL r23, HOST_NV_GPR(r23)(r1) - PPC_STL r24, HOST_NV_GPR(r24)(r1) - PPC_STL r25, HOST_NV_GPR(r25)(r1) - PPC_STL r26, HOST_NV_GPR(r26)(r1) - PPC_STL r27, HOST_NV_GPR(r27)(r1) - PPC_STL r28, HOST_NV_GPR(r28)(r1) - PPC_STL r29, HOST_NV_GPR(r29)(r1) - PPC_STL r30, HOST_NV_GPR(r30)(r1) - PPC_STL r31, HOST_NV_GPR(r31)(r1) + PPC_STL r14, HOST_NV_GPR(R14)(r1) + PPC_STL r15, HOST_NV_GPR(R15)(r1) + PPC_STL r16, HOST_NV_GPR(R16)(r1) + PPC_STL r17, HOST_NV_GPR(R17)(r1) + PPC_STL r18, HOST_NV_GPR(R18)(r1) + PPC_STL r19, HOST_NV_GPR(R19)(r1) + PPC_STL r20, HOST_NV_GPR(R20)(r1) + PPC_STL r21, HOST_NV_GPR(R21)(r1) + PPC_STL r22, HOST_NV_GPR(R22)(r1) + PPC_STL r23, HOST_NV_GPR(R23)(r1) + PPC_STL r24, HOST_NV_GPR(R24)(r1) + PPC_STL r25, HOST_NV_GPR(R25)(r1) + PPC_STL r26, HOST_NV_GPR(R26)(r1) + PPC_STL r27, HOST_NV_GPR(R27)(r1) + PPC_STL r28, HOST_NV_GPR(R28)(r1) + PPC_STL r29, HOST_NV_GPR(R29)(r1) + PPC_STL r30, HOST_NV_GPR(R30)(r1) + PPC_STL r31, HOST_NV_GPR(R31)(r1) /* Load guest non-volatiles. */ PPC_LL r14, VCPU_GPR(R14)(r4) -- 1.6.0.2 ___ Linuxppc-dev mailing list linuxppc-...@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev -- 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
Re: [PATCH] powerpc kvm: fix kvmppc_start_thread() for CONFIG_SMP=N
In message 4ebd46f4.5040...@suse.de you wrote: On 11/11/2011 03:03 AM, Michael Neuling wrote: Currently kvmppc_start_thread() tries to wake other SMT threads via xics_wake_cpu(). Unfortunately xics_wake_cpu only exists when CONFIG_SMP=Y so when compiling with CONFIG_SMP=N we get: arch/powerpc/kvm/built-in.o: In function `.kvmppc_start_thread': book3s_hv.c:(.text+0xa1e0): undefined reference to `.xics_wake_cpu' The following should be fine since kvmppc_start_thread() shouldn't called to start non-zero threads when SMP=N since threads_per_core=1. Signed-off-by: Michael Neulingmi...@neuling.org Thanks, applied to kvm-ppc-next. Please CC kvm-ppc@vger next time :). Thanks will do. Mikey -- 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
Re: [PATCH] powerpc: remove fpscr use from [kvm_]cvt_{fd,df}
In message 1282699836.22370.566.ca...@pasglop you wrote: On Tue, 2010-08-24 at 15:15 +1000, Michael Neuling wrote: Do some 32 bit processors need this? In 32 bit before the merge, we use to have code that did: #if defined(CONFIG_4xx) || defined(CONFIG_E500) #define cvt_fd without save/restore fpscr #else #define cvt_fd with save/restore fpscr #end if Kumar; does this ring any bells? I don't see anything in the various 440 docs I have at hand that would hint at lfd/stfs adffecting FPSCR. The way the ifdefs are, it's the other way around. 4xx procs don't need to save/restore fpscr and others do. Right, my bad. In any case, Paulus reckons it's all his mistake and we really never need to save/restore fpscr. ACK :-P Mikey -- 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
Re: [PATCH] powerpc: remove fpscr use from [kvm_]cvt_{fd,df}
Neither lfs nor stfs touch the fpscr, so remove the restore/save of = it around them. =20 Do some 32 bit processors need this?=20 =20 In 32 bit before the merge, we use to have code that did: =20 #if defined(CONFIG_4xx) || defined(CONFIG_E500) #define cvt_fd without save/restore fpscr #else #define cvt_fd with save/restore fpscr #end if =20 Kumar; does this ring any bells? =20 (The addition of this predates even bitkeeper) =20 Mikey Not really. However if the ifdef is as you say that seems wrong to me. We should be using CONFIG_PPC_FPU or !CONFIG_PPC_FPU. As both 4xx and E500 have variants w/FPUs. It actually got changed to CONFIG_PPC_FPU, then dwg merged it with some other versions that were around. Mikey -- 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
Re: [PATCH] powerpc: remove fpscr use from [kvm_]cvt_{fd,df}
Neither lfs nor stfs touch the fpscr, so remove the restore/save of it
around them.
Do some 32 bit processors need this?
In 32 bit before the merge, we use to have code that did:
#if defined(CONFIG_4xx) || defined(CONFIG_E500)
#define cvt_fd without save/restore fpscr
#else
#define cvt_fd with save/restore fpscr
#end if
Kumar; does this ring any bells?
(The addition of this predates even bitkeeper)
Mikey
Signed-off-by: Andreas Schwab sch...@linux-m68k.org
---
arch/powerpc/include/asm/kvm_fpu.h |4 +-
arch/powerpc/include/asm/system.h|4 +-
arch/powerpc/kernel/align.c |4 +-
arch/powerpc/kernel/fpu.S| 10 ---
arch/powerpc/kvm/book3s_paired_singles.c | 44 +---
-
arch/powerpc/kvm/fpu.S |8 -
6 files changed, 26 insertions(+), 48 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kv
m_fpu.h
index c3d4f05..92daae1 100644
--- a/arch/powerpc/include/asm/kvm_fpu.h
+++ b/arch/powerpc/include/asm/kvm_fpu.h
@@ -82,7 +82,7 @@ FPD_THREE_IN(fmadd)
FPD_THREE_IN(fnmsub)
FPD_THREE_IN(fnmadd)
-extern void kvm_cvt_fd(u32 *from, u64 *to, u64 *fpscr);
-extern void kvm_cvt_df(u64 *from, u32 *to, u64 *fpscr);
+extern void kvm_cvt_fd(u32 *from, u64 *to);
+extern void kvm_cvt_df(u64 *from, u32 *to);
#endif
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/sys
tem.h
index 6c294ac..0b3fe78 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -154,8 +154,8 @@ extern void enable_kernel_spe(void);
extern void giveup_spe(struct task_struct *);
extern void load_up_spe(struct task_struct *);
extern int fix_alignment(struct pt_regs *);
-extern void cvt_fd(float *from, double *to, struct thread_struct *thread);
-extern void cvt_df(double *from, float *to, struct thread_struct *thread);
+extern void cvt_fd(float *from, double *to);
+extern void cvt_df(double *from, float *to);
#ifndef CONFIG_SMP
extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index b876e98..8184ee9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -889,7 +889,7 @@ int fix_alignment(struct pt_regs *regs)
#ifdef CONFIG_PPC_FPU
preempt_disable();
enable_kernel_fp();
- cvt_df(data.dd, (float *)data.v[4], current-thread)
;
+ cvt_df(data.dd, (float *)data.v[4]);
preempt_enable();
#else
return 0;
@@ -933,7 +933,7 @@ int fix_alignment(struct pt_regs *regs)
#ifdef CONFIG_PPC_FPU
preempt_disable();
enable_kernel_fp();
- cvt_fd((float *)data.v[4], data.dd, current-thread);
+ cvt_fd((float *)data.v[4], data.dd);
preempt_enable();
#else
return 0;
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index fc8f5b1..e86c040 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -163,24 +163,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
/*
* These are used in the alignment trap handler when emulating
* single-precision loads and stores.
- * We restore and save the fpscr so the task gets the same result
- * and exceptions as if the cpu had performed the load or store.
*/
_GLOBAL(cvt_fd)
- lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */
- MTFSF_L(0)
lfs 0,0(r3)
stfd0,0(r4)
- mffs0
- stfd0,THREAD_FPSCR(r5) /* save new fpscr value */
blr
_GLOBAL(cvt_df)
- lfd 0,THREAD_FPSCR(r5) /* load up fpscr value */
- MTFSF_L(0)
lfd 0,0(r3)
stfs0,0(r4)
- mffs0
- stfd0,THREAD_FPSCR(r5) /* save new fpscr value */
blr
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book
3s_paired_singles.c
index 474f2e2..35a701f 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -159,7 +159,7 @@
static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
{
- kvm_cvt_df(vcpu-arch.fpr[rt], vcpu-arch.qpr[rt], vcpu-arch.fpscr)
;
+ kvm_cvt_df(vcpu-arch.fpr[rt], vcpu-arch.qpr[rt]);
}
static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_sto
re)
@@ -204,7 +204,7 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, s
truct kvm_vcpu *vcpu,
/* put in registers */
switch (ls_type) {
case FPU_LS_SINGLE:
- kvm_cvt_fd((u32*)tmp, vcpu-arch.fpr[rs], vcpu-arch.fpscr);
+ kvm_cvt_fd((u32*)tmp, vcpu-arch.fpr[rs]);
vcpu-arch.qpr[rs] = *((u32*)tmp);
break;
case FPU_LS_DOUBLE:
@@ -230,7 +230,7 @@ static int
Re: [PATCH 08/27] Add SLB switching code for entry/exit
This is the really low level of guest entry/exit code. Book3s_64 has an SLB, which stores all ESID - VSID mappings we're currently aware of. The segments in the guest differ from the ones on the host, so we need to switch the SLB to tell the MMU that we're in a new context. So we store a shadow of the guest's SLB in the PACA, switch to that on entry and only restore bolted entries on exit, leaving the rest to the Linux SLB fault handler. That way we get a really clean way of switching the SLB. Signed-off-by: Alexander Graf ag...@suse.de --- arch/powerpc/kvm/book3s_64_slb.S | 277 ++ 1 files changed, 277 insertions(+), 0 deletions(-) create mode 100644 arch/powerpc/kvm/book3s_64_slb.S diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/ book3s_64_sl b.S new file mode 100644 index 000..00a8367 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -0,0 +1,277 @@ +/* + * 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 2009 + * + * Authors: Alexander Graf ag...@suse.de + */ + +/ *** *** * *** + * * + * Entry code * + * * + *** *** * **/ + +.global kvmppc_handler_trampoline_enter +kvmppc_handler_trampoline_enter: + +/* Required state: + * + * MSR = ~IR|DR + * R13 = PACA + * R9 = guest IP + * R10 = guest MSR + * R11 = free + * R12 = free + * PACA[PACA_EXMC + EX_R9] = guest R9 + * PACA[PACA_EXMC + EX_R10] = guest R10 + * PACA[PACA_EXMC + EX_R11] = guest R11 + * PACA[PACA_EXMC + EX_R12] = guest R12 + * PACA[PACA_EXMC + EX_R13] = guest R13 + * PACA[PACA_EXMC + EX_CCR] = guest CR + * PACA[PACA_EXMC + EX_R3] = guest XER + */ + +mtsrr0r9 +mtsrr1r10 + +mtsprSPRN_SPRG_SCRATCH0, r0 + +/* Remove LPAR shadow entries */ + +#if SLB_NUM_BOLTED == 3 You could alternatively check the persistent entry in the slb_shawdow buffer. This would give you a run time check. Not sure what's best though. Well we're in the hot path here, so anything using as few registers as possible and being simple is the best :-). I'd guess the more we are clever at compile time the better. Yeah, I tend to agree. + +ldr12, PACA_SLBSHADOWPTR(r13) +ldr10, 0x10(r12) +ldr11, 0x18(r12) Can you define something in asm-offsets.c for these magic constants 0x10 and 0x18. Similarly below. +/* Invalid? Skip. */ +rldicl. r0, r10, 37, 63 +beqslb_entry_skip_1 +xorisr9, r10, slb_esi...@h +stdr9, 0x10(r12) +slb_entry_skip_1: +ldr9, 0x20(r12) +/* Invalid? Skip. */ +rldicl. r0, r9, 37, 63 +beqslb_entry_skip_2 +xorisr9, r9, slb_esi...@h +stdr9, 0x20(r12) +slb_entry_skip_2: +ldr9, 0x30(r12) +/* Invalid? Skip. */ +rldicl. r0, r9, 37, 63 +beqslb_entry_skip_3 +xorisr9, r9, slb_esi...@h +stdr9, 0x30(r12) Can these 3 be made into a macro? Phew - dynamically generating jump points sounds rather hard. I can give it a try... +slb_entry_skip_3: + +#else +#error unknown number of bolted entries +#endif + +/* Flush SLB */ + +slbia + +/* r0 = esid ESID_MASK */ +rldicr r10, r10, 0, 35 +/* r0 |= CLASS_BIT(VSID) */ +rldic r12, r11, 56 - 36, 36 +or r10, r10, r12 +slbier10 + +isync + +/* Fill SLB with our shadow */ + +lbzr12, PACA_KVM_SLB_MAX(r13) +mullir12, r12, 16 +addir12, r12, PACA_KVM_SLB +addr12, r12, r13 + +/* for (r11 = kvm_slb; r11 kvm_slb + kvm_slb_size; r11+=slb_entry) */ +lir11, PACA_KVM_SLB +addr11, r11, r13 + +slb_loop_enter: + +ldr10, 0(r11) + +rldicl. r0, r10, 37, 63 +beqslb_loop_enter_skip + +ldr9, 8(r11) +slbmter9, r10 If you're updating the first 3
Re: [PATCH 11/27] Add book3s_64 Host MMU handling
snip
+static void invalidate_pte(struct hpte_cache *pte)
+{
+ dprintk_mmu(KVM: Flushing SPT %d: 0x%llx (0x%llx) - 0x%llx\n,
+ i, pte-pte.eaddr, pte-pte.vpage, pte-host_va);
+
+ ppc_md.hpte_invalidate(pte-slot, pte-host_va,
+MMU_PAGE_4K, MMU_SEGSIZE_256M,
+false);
Are we assuming 256M segments here (and elsewhere)?
snip
+static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
+{
+ int i;
+ int max_slb_size = 64;
+ int found_inval = -1;
+ int r;
+
+ if (!get_paca()-kvm_slb_max)
+ get_paca()-kvm_slb_max = 1;
+
+ /* Are we overwriting? */
+ for (i = 1; i get_paca()-kvm_slb_max; i++) {
+ if (!(get_paca()-kvm_slb[i].esid SLB_ESID_V))
+ found_inval = i;
+ else if ((get_paca()-kvm_slb[i].esid ESID_MASK) == esid)
+ return i;
+ }
+
+ /* Found a spare entry that was invalidated before */
+ if (found_inval 0)
+ return found_inval;
+
+ /* No spare invalid entry, so create one */
+
+ if (mmu_slb_size 64)
+ max_slb_size = mmu_slb_size;
Can we just use the global mmu_slb_size eliminate max_slb_size?
snip
Mikey
--
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
