* [PATCH 00/12] Remaining improvements for HV KVM
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This is the rest of my current patch queue for HV KVM on PPC. This
series is based on Alex Graf's kvm-ppc-queue branch.
The last patch in this series needs a definition of PPC_MSGCLR that is
added by the patch "powerpc/powernv: Fixes for hypervisor doorbell
handling", which has now gone upstream into Linus' tree as commit
755563bc79c7 via the linuxppc-dev mailing list. Alex, how do you want
to handle that? You could pull in the master branch of the kvm tree,
or you could cherry-pick 755563bc79c7 and let the subsequent merge fix
it up.
Paul.
arch/powerpc/include/asm/kvm_book3s_64.h | 4 +
arch/powerpc/include/asm/kvm_host.h | 44 +++-
arch/powerpc/include/asm/time.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 20 +-
arch/powerpc/kernel/time.c | 6 +
arch/powerpc/kvm/Kconfig | 14 +
arch/powerpc/kvm/book3s_64_mmu_hv.c | 136 ++++++++++
arch/powerpc/kvm/book3s_hv.c | 413 +++++++++++++++++++++--------
arch/powerpc/kvm/book3s_hv_builtin.c | 85 +++++-
arch/powerpc/kvm/book3s_hv_rm_xics.c | 12 +-
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 432 +++++++++++++++++++++----------
virt/kvm/kvm_main.c | 1 +
12 files changed, 897 insertions(+), 273 deletions(-)
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH 01/12] KVM: PPC: Book3S HV: Create debugfs file for each guest's HPT
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This creates a debugfs directory for each HV guest (assuming debugfs
is enabled in the kernel config), and within that directory, a file
by which the contents of the guest's HPT (hashed page table) can be
read. The directory is named vmnnnn, where nnnn is the PID of the
process that created the guest. The file is named "htab". This is
intended to help in debugging problems in the host's management
of guest memory.
The contents of the file consist of a series of lines like this:
3f48 4000d032bf003505 0000000bd7ff1196 00000003b5c71196
The first field is the index of the entry in the HPT, the second and
third are the HPT entry, so the third entry contains the real page
number that is mapped by the entry if the entry's valid bit is set.
The fourth field is the guest's view of the second doubleword of the
entry, so it contains the guest physical address. (The format of the
second through fourth fields are described in the Power ISA and also
in arch/powerpc/include/asm/mmu-hash64.h.)
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 2 +
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/kvm/book3s_64_mmu_hv.c | 136 +++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 12 +++
virt/kvm/kvm_main.c | 1 +
5 files changed, 153 insertions(+)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 0789a0f..869c53f 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -436,6 +436,8 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
return rcu_dereference_raw_notrace(kvm->memslots);
}
+extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 015773f..f1d0bbc 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -238,6 +238,8 @@ struct kvm_arch {
atomic_t hpte_mod_interest;
cpumask_t need_tlb_flush;
int hpt_cma_alloc;
+ struct dentry *debugfs_dir;
+ struct dentry *htab_dentry;
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
struct mutex hpt_mutex;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6c6825a..d6fe308 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -27,6 +27,7 @@
#include <linux/srcu.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -1490,6 +1491,141 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
return ret;
}
+struct debugfs_htab_state {
+ struct kvm *kvm;
+ struct mutex mutex;
+ unsigned long hpt_index;
+ int chars_left;
+ int buf_index;
+ char buf[64];
+};
+
+static int debugfs_htab_open(struct inode *inode, struct file *file)
+{
+ struct kvm *kvm = inode->i_private;
+ struct debugfs_htab_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(kvm);
+ p->kvm = kvm;
+ mutex_init(&p->mutex);
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_htab_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_htab_state *p = file->private_data;
+
+ kvm_put_kvm(p->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_htab_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_htab_state *p = file->private_data;
+ ssize_t ret, r;
+ unsigned long i, n;
+ unsigned long v, hr, gr;
+ struct kvm *kvm;
+ __be64 *hptp;
+
+ ret = mutex_lock_interruptible(&p->mutex);
+ if (ret)
+ return ret;
+
+ if (p->chars_left) {
+ n = p->chars_left;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf + p->buf_index, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index += n;
+ buf += n;
+ len -= n;
+ ret = n;
+ if (r) {
+ if (!n)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ kvm = p->kvm;
+ i = p->hpt_index;
+ hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+ for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) {
+ if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ /* lock the HPTE so it's stable and read it */
+ preempt_disable();
+ while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+ cpu_relax();
+ v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK;
+ hr = be64_to_cpu(hptp[1]);
+ gr = kvm->arch.revmap[i].guest_rpte;
+ unlock_hpte(hptp, v);
+ preempt_enable();
+
+ if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ n = scnprintf(p->buf, sizeof(p->buf),
+ "%6lx %.16lx %.16lx %.16lx\n",
+ i, v, hr, gr);
+ p->chars_left = n;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index = n;
+ buf += n;
+ len -= n;
+ ret += n;
+ if (r) {
+ if (!ret)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+ p->hpt_index = i;
+
+ out:
+ mutex_unlock(&p->mutex);
+ return ret;
+}
+
+ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_htab_fops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_htab_open,
+ .release = debugfs_htab_release,
+ .read = debugfs_htab_read,
+ .write = debugfs_htab_write,
+ .llseek = generic_file_llseek,
+};
+
+void kvmppc_mmu_debugfs_init(struct kvm *kvm)
+{
+ kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
+ kvm->arch.debugfs_dir, kvm,
+ &debugfs_htab_fops);
+}
+
void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1bb028e..cb54d90 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -32,6 +32,7 @@
#include <linux/page-flags.h>
#include <linux/srcu.h>
#include <linux/miscdevice.h>
+#include <linux/debugfs.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -2319,6 +2320,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
unsigned long lpcr, lpid;
+ char buf[32];
/* Allocate the guest's logical partition ID */
@@ -2359,6 +2361,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
*/
kvm_hv_vm_activated();
+ /*
+ * Create a debugfs directory for the VM
+ */
+ snprintf(buf, sizeof(buf), "vm%d", current->pid);
+ kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
+ if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ kvmppc_mmu_debugfs_init(kvm);
+
return 0;
}
@@ -2379,6 +2389,8 @@ static void kvmppc_free_vcores(struct kvm *kvm)
static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
+ debugfs_remove_recursive(kvm->arch.debugfs_dir);
+
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a109370..c941f67 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -89,6 +89,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
static __read_mostly struct preempt_ops kvm_preempt_ops;
struct dentry *kvm_debugfs_dir;
+EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 01/12] KVM: PPC: Book3S HV: Create debugfs file for each guest's HPT
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This creates a debugfs directory for each HV guest (assuming debugfs
is enabled in the kernel config), and within that directory, a file
by which the contents of the guest's HPT (hashed page table) can be
read. The directory is named vmnnnn, where nnnn is the PID of the
process that created the guest. The file is named "htab". This is
intended to help in debugging problems in the host's management
of guest memory.
The contents of the file consist of a series of lines like this:
3f48 4000d032bf003505 0000000bd7ff1196 00000003b5c71196
The first field is the index of the entry in the HPT, the second and
third are the HPT entry, so the third entry contains the real page
number that is mapped by the entry if the entry's valid bit is set.
The fourth field is the guest's view of the second doubleword of the
entry, so it contains the guest physical address. (The format of the
second through fourth fields are described in the Power ISA and also
in arch/powerpc/include/asm/mmu-hash64.h.)
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 2 +
arch/powerpc/include/asm/kvm_host.h | 2 +
arch/powerpc/kvm/book3s_64_mmu_hv.c | 136 +++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 12 +++
virt/kvm/kvm_main.c | 1 +
5 files changed, 153 insertions(+)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 0789a0f..869c53f 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -436,6 +436,8 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
return rcu_dereference_raw_notrace(kvm->memslots);
}
+extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 015773f..f1d0bbc 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -238,6 +238,8 @@ struct kvm_arch {
atomic_t hpte_mod_interest;
cpumask_t need_tlb_flush;
int hpt_cma_alloc;
+ struct dentry *debugfs_dir;
+ struct dentry *htab_dentry;
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
struct mutex hpt_mutex;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6c6825a..d6fe308 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -27,6 +27,7 @@
#include <linux/srcu.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -1490,6 +1491,141 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
return ret;
}
+struct debugfs_htab_state {
+ struct kvm *kvm;
+ struct mutex mutex;
+ unsigned long hpt_index;
+ int chars_left;
+ int buf_index;
+ char buf[64];
+};
+
+static int debugfs_htab_open(struct inode *inode, struct file *file)
+{
+ struct kvm *kvm = inode->i_private;
+ struct debugfs_htab_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(kvm);
+ p->kvm = kvm;
+ mutex_init(&p->mutex);
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_htab_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_htab_state *p = file->private_data;
+
+ kvm_put_kvm(p->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_htab_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_htab_state *p = file->private_data;
+ ssize_t ret, r;
+ unsigned long i, n;
+ unsigned long v, hr, gr;
+ struct kvm *kvm;
+ __be64 *hptp;
+
+ ret = mutex_lock_interruptible(&p->mutex);
+ if (ret)
+ return ret;
+
+ if (p->chars_left) {
+ n = p->chars_left;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf + p->buf_index, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index += n;
+ buf += n;
+ len -= n;
+ ret = n;
+ if (r) {
+ if (!n)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+
+ kvm = p->kvm;
+ i = p->hpt_index;
+ hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+ for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) {
+ if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ /* lock the HPTE so it's stable and read it */
+ preempt_disable();
+ while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+ cpu_relax();
+ v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK;
+ hr = be64_to_cpu(hptp[1]);
+ gr = kvm->arch.revmap[i].guest_rpte;
+ unlock_hpte(hptp, v);
+ preempt_enable();
+
+ if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ continue;
+
+ n = scnprintf(p->buf, sizeof(p->buf),
+ "%6lx %.16lx %.16lx %.16lx\n",
+ i, v, hr, gr);
+ p->chars_left = n;
+ if (n > len)
+ n = len;
+ r = copy_to_user(buf, p->buf, n);
+ n -= r;
+ p->chars_left -= n;
+ p->buf_index = n;
+ buf += n;
+ len -= n;
+ ret += n;
+ if (r) {
+ if (!ret)
+ ret = -EFAULT;
+ goto out;
+ }
+ }
+ p->hpt_index = i;
+
+ out:
+ mutex_unlock(&p->mutex);
+ return ret;
+}
+
+ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_htab_fops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_htab_open,
+ .release = debugfs_htab_release,
+ .read = debugfs_htab_read,
+ .write = debugfs_htab_write,
+ .llseek = generic_file_llseek,
+};
+
+void kvmppc_mmu_debugfs_init(struct kvm *kvm)
+{
+ kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
+ kvm->arch.debugfs_dir, kvm,
+ &debugfs_htab_fops);
+}
+
void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1bb028e..cb54d90 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -32,6 +32,7 @@
#include <linux/page-flags.h>
#include <linux/srcu.h>
#include <linux/miscdevice.h>
+#include <linux/debugfs.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -2319,6 +2320,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
unsigned long lpcr, lpid;
+ char buf[32];
/* Allocate the guest's logical partition ID */
@@ -2359,6 +2361,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
*/
kvm_hv_vm_activated();
+ /*
+ * Create a debugfs directory for the VM
+ */
+ snprintf(buf, sizeof(buf), "vm%d", current->pid);
+ kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
+ if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ kvmppc_mmu_debugfs_init(kvm);
+
return 0;
}
@@ -2379,6 +2389,8 @@ static void kvmppc_free_vcores(struct kvm *kvm)
static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
+ debugfs_remove_recursive(kvm->arch.debugfs_dir);
+
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a109370..c941f67 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -89,6 +89,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
static __read_mostly struct preempt_ops kvm_preempt_ops;
struct dentry *kvm_debugfs_dir;
+EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 29ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), or 25%, and about 43ns for
an hcall that is handled in the host kernel in virtual mode
(e.g. H_PROD), or 1.2%. Since production environments may not wish to
incur this overhead, the new code is conditional on a new config
symbol, CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 21 +++++
arch/powerpc/include/asm/time.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 13 +++
arch/powerpc/kernel/time.c | 6 ++
arch/powerpc/kvm/Kconfig | 14 +++
arch/powerpc/kvm/book3s_hv.c | 150 ++++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 129 ++++++++++++++++++++++++++-
7 files changed, 334 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f1d0bbc..d2068bb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -369,6 +369,14 @@ struct kvmppc_slb {
u8 base_page_size; /* MMU_PAGE_xxx */
};
+/* Struct used to accumulate timing information in HV real mode code */
+struct kvmhv_tb_accumulator {
+ u64 seqcount; /* used to synchronize access, also count * 2 */
+ u64 tb_total; /* total time in timebase ticks */
+ u64 tb_min; /* min time */
+ u64 tb_max; /* max time */
+};
+
# ifdef CONFIG_PPC_FSL_BOOK3E
#define KVMPPC_BOOKE_IAC_NUM 2
#define KVMPPC_BOOKE_DAC_NUM 2
@@ -657,6 +665,19 @@ struct kvm_vcpu_arch {
u32 emul_inst;
#endif
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */
+ u64 cur_tb_start; /* when it started */
+ struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
+ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
+ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */
+ struct kvmhv_tb_accumulator guest_time; /* guest execution */
+ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
+
+ struct dentry *debugfs_dir;
+ struct dentry *debugfs_timings;
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 03cbada..10fc784 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
+/* Convert timebase ticks to nanoseconds */
+unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
#endif /* __KERNEL__ */
#endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859..3fea721 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -459,6 +459,19 @@ int main(void)
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+ DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+ DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+ DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+ DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+ DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+ DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+ DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+ DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+ DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+ DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
+#endif
DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33f..56f4484 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
}
#endif
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+ return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
/*
* Scheduler clock - returns current time in nanosec units.
*
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 11850f3..2963e4d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR
processor, including emulating 32-bit processors on a 64-bit
host.
+config KVM_BOOK3S_HV_EXIT_TIMING
+ bool "Detailed timing for hypervisor real-mode code"
+ depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+ ---help---
+ Calculate time taken for each vcpu in the real-mode guest entry,
+ exit, and interrupt handling code, plus time spent in the guest
+ and in nap mode due to idle (cede) while other threads are still
+ in the guest. The total, minimum and maximum times in nanoseconds
+ together with the number of executions are reported in debugfs in
+ kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40
+ ns per exit on POWER8.
+
+ If unsure, say N.
+
config KVM_BOOKE_HV
bool
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cb54d90..c7b18ac 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1423,6 +1423,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
return vcore;
}
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+ const char *name;
+ size_t offset;
+} timings[] = {
+ {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
+ {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
+ {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
+ {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
+ {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+ struct kvm_vcpu *vcpu;
+ unsigned int buflen;
+ char buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = inode->i_private;
+ struct debugfs_timings_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(vcpu->kvm);
+ p->vcpu = vcpu;
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_timings_state *p = file->private_data;
+
+ kvm_put_kvm(p->vcpu->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_timings_state *p = file->private_data;
+ struct kvm_vcpu *vcpu = p->vcpu;
+ char *s, *buf_end;
+ struct kvmhv_tb_accumulator tb;
+ u64 count;
+ loff_t pos;
+ ssize_t n;
+ int i, loops;
+ bool ok;
+
+ if (!p->buflen) {
+ s = p->buf;
+ buf_end = s + sizeof(p->buf);
+ for (i = 0; i < N_TIMINGS; ++i) {
+ struct kvmhv_tb_accumulator *acc;
+
+ acc = (struct kvmhv_tb_accumulator *)
+ ((unsigned long)vcpu + timings[i].offset);
+ ok = false;
+ for (loops = 0; loops < 1000; ++loops) {
+ count = acc->seqcount;
+ if (!(count & 1)) {
+ smp_rmb();
+ tb = *acc;
+ smp_rmb();
+ if (count == acc->seqcount) {
+ ok = true;
+ break;
+ }
+ }
+ udelay(1);
+ }
+ if (!ok)
+ snprintf(s, buf_end - s, "%s: stuck\n",
+ timings[i].name);
+ else
+ snprintf(s, buf_end - s,
+ "%s: %llu %llu %llu %llu\n",
+ timings[i].name, count / 2,
+ tb_to_ns(tb.tb_total),
+ tb_to_ns(tb.tb_min),
+ tb_to_ns(tb.tb_max));
+ s += strlen(s);
+ }
+ p->buflen = s - p->buf;
+ }
+
+ pos = *ppos;
+ if (pos >= p->buflen)
+ return 0;
+ if (len > p->buflen - pos)
+ len = p->buflen - pos;
+ n = copy_to_user(buf, p->buf + pos, len);
+ if (n) {
+ if (n == len)
+ return -EFAULT;
+ len -= n;
+ }
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_timings_open,
+ .release = debugfs_timings_release,
+ .read = debugfs_timings_read,
+ .write = debugfs_timings_write,
+ .llseek = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+ char buf[16];
+ struct kvm *kvm = vcpu->kvm;
+
+ snprintf(buf, sizeof(buf), "vcpu%u", id);
+ if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+ if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_timings =
+ debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+ vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
@@ -1492,6 +1640,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ debugfs_vcpu_init(vcpu, id);
+
return vcpu;
free_vcpu:
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e9c3cb5..ee6ba4c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -225,7 +225,13 @@ kvm_novcpu_wakeup:
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
- bne kvmppc_got_guest
+ beq kvmppc_primary_no_guest
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+#endif
+ b kvmppc_got_guest
kvm_novcpu_exit:
b hdec_soon
@@ -376,6 +382,14 @@ kvmppc_hv_entry:
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Store initial timestamp */
+ cmpdi r4, 0
+ beq 1f
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+1:
+#endif
/* Clear out SLB */
li r6,0
slbmte r6,r6
@@ -880,6 +894,12 @@ fast_guest_return:
li r9, KVM_GUEST_MODE_GUEST_HV
stb r9, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Accumulate timing */
+ addi r3, r4, VCPU_TB_GUEST
+ bl kvmhv_accumulate_time
+#endif
+
/* Enter guest */
BEGIN_FTR_SECTION
@@ -917,6 +937,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+secondary_too_late:
+ cmpdi r4, 0
+ beq 11f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+11: b kvmhv_switch_to_host
+
+hdec_soon:
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 12f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+12: b kvmhv_do_exit
+#endif
+
/******************************************************************************
* *
* Exit code *
@@ -1002,6 +1039,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
stw r12,VCPU_TRAP(r9)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMINTR
+ mr r4, r9
+ bl kvmhv_accumulate_time
+ ld r5, VCPU_GPR(R5)(r9)
+ ld r6, VCPU_GPR(R6)(r9)
+ ld r7, VCPU_GPR(R7)(r9)
+ ld r8, VCPU_GPR(R8)(r9)
+#endif
+
/* Save HEIR (HV emulation assist reg) in emul_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
@@ -1072,6 +1119,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
beq machine_check_realmode
mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
/* Save guest CTRL register, set runlatch to 1 */
6: mfspr r6,SPRN_CTRLF
@@ -1416,7 +1468,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-hdec_soon: /* r12 = trap, r13 = paca */
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+hdec_soon:
+#endif
+kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
@@ -1475,7 +1530,10 @@ hdec_soon: /* r12 = trap, r13 = paca */
addi r6,r6,PACA_SIZE
bne 42b
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+#endif
+kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
43: ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
@@ -1561,6 +1619,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
1: addi r8,r8,16
.endr
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Finish timing, if we have a vcpu */
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ li r3, 0
+ beq 2f
+ bl kvmhv_accumulate_time
+2:
+#endif
/* Unset guest mode */
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
@@ -2068,6 +2135,12 @@ _GLOBAL(kvmppc_h_cede)
/* save FP state */
bl kvmppc_save_fp
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ addi r3, r4, VCPU_TB_CEDE
+ bl kvmhv_accumulate_time
+#endif
+
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
@@ -2108,6 +2181,11 @@ kvm_end_cede:
/* Woken by external or decrementer interrupt */
ld r1, HSTATE_HOST_R1(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMINTR
+ bl kvmhv_accumulate_time
+#endif
+
/* load up FP state */
bl kvmppc_load_fp
@@ -2428,3 +2506,50 @@ kvmppc_fix_pmao:
mtspr SPRN_PMC6, r3
isync
blr
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+/*
+ * Start timing an activity
+ * r3 = pointer to time accumulation struct, r4 = vcpu
+ */
+kvmhv_start_timing:
+ mftb r5
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ std r5, VCPU_ACTIVITY_START(r4)
+ blr
+
+/*
+ * Accumulate time to one activity and start another.
+ * r3 = pointer to new time accumulation struct, r4 = vcpu
+ */
+kvmhv_accumulate_time:
+ ld r5, VCPU_CUR_ACTIVITY(r4)
+ ld r6, VCPU_ACTIVITY_START(r4)
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ mftb r7
+ std r7, VCPU_ACTIVITY_START(r4)
+ cmpdi r5, 0
+ beqlr
+ subf r3, r6, r7
+ ld r8, TAS_SEQCOUNT(r5)
+ cmpdi r8, 0
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ lwsync
+ ld r7, TAS_TOTAL(r5)
+ add r7, r7, r3
+ std r7, TAS_TOTAL(r5)
+ ld r6, TAS_MIN(r5)
+ ld r7, TAS_MAX(r5)
+ beq 3f
+ cmpd r3, r6
+ bge 1f
+3: std r3, TAS_MIN(r5)
+1: cmpd r3, r7
+ ble 2f
+ std r3, TAS_MAX(r5)
+2: lwsync
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ blr
+#endif
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 29ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), or 25%, and about 43ns for
an hcall that is handled in the host kernel in virtual mode
(e.g. H_PROD), or 1.2%. Since production environments may not wish to
incur this overhead, the new code is conditional on a new config
symbol, CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 21 +++++
arch/powerpc/include/asm/time.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 13 +++
arch/powerpc/kernel/time.c | 6 ++
arch/powerpc/kvm/Kconfig | 14 +++
arch/powerpc/kvm/book3s_hv.c | 150 ++++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 129 ++++++++++++++++++++++++++-
7 files changed, 334 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f1d0bbc..d2068bb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -369,6 +369,14 @@ struct kvmppc_slb {
u8 base_page_size; /* MMU_PAGE_xxx */
};
+/* Struct used to accumulate timing information in HV real mode code */
+struct kvmhv_tb_accumulator {
+ u64 seqcount; /* used to synchronize access, also count * 2 */
+ u64 tb_total; /* total time in timebase ticks */
+ u64 tb_min; /* min time */
+ u64 tb_max; /* max time */
+};
+
# ifdef CONFIG_PPC_FSL_BOOK3E
#define KVMPPC_BOOKE_IAC_NUM 2
#define KVMPPC_BOOKE_DAC_NUM 2
@@ -657,6 +665,19 @@ struct kvm_vcpu_arch {
u32 emul_inst;
#endif
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */
+ u64 cur_tb_start; /* when it started */
+ struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
+ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
+ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */
+ struct kvmhv_tb_accumulator guest_time; /* guest execution */
+ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
+
+ struct dentry *debugfs_dir;
+ struct dentry *debugfs_timings;
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 03cbada..10fc784 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
+/* Convert timebase ticks to nanoseconds */
+unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
#endif /* __KERNEL__ */
#endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859..3fea721 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -459,6 +459,19 @@ int main(void)
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+ DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+ DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+ DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+ DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+ DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+ DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+ DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+ DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+ DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+ DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
+#endif
DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33f..56f4484 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
}
#endif
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+ return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
/*
* Scheduler clock - returns current time in nanosec units.
*
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 11850f3..2963e4d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR
processor, including emulating 32-bit processors on a 64-bit
host.
+config KVM_BOOK3S_HV_EXIT_TIMING
+ bool "Detailed timing for hypervisor real-mode code"
+ depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+ ---help---
+ Calculate time taken for each vcpu in the real-mode guest entry,
+ exit, and interrupt handling code, plus time spent in the guest
+ and in nap mode due to idle (cede) while other threads are still
+ in the guest. The total, minimum and maximum times in nanoseconds
+ together with the number of executions are reported in debugfs in
+ kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40
+ ns per exit on POWER8.
+
+ If unsure, say N.
+
config KVM_BOOKE_HV
bool
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cb54d90..c7b18ac 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1423,6 +1423,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
return vcore;
}
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+ const char *name;
+ size_t offset;
+} timings[] = {
+ {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
+ {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
+ {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
+ {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
+ {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+ struct kvm_vcpu *vcpu;
+ unsigned int buflen;
+ char buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = inode->i_private;
+ struct debugfs_timings_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(vcpu->kvm);
+ p->vcpu = vcpu;
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_timings_state *p = file->private_data;
+
+ kvm_put_kvm(p->vcpu->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_timings_state *p = file->private_data;
+ struct kvm_vcpu *vcpu = p->vcpu;
+ char *s, *buf_end;
+ struct kvmhv_tb_accumulator tb;
+ u64 count;
+ loff_t pos;
+ ssize_t n;
+ int i, loops;
+ bool ok;
+
+ if (!p->buflen) {
+ s = p->buf;
+ buf_end = s + sizeof(p->buf);
+ for (i = 0; i < N_TIMINGS; ++i) {
+ struct kvmhv_tb_accumulator *acc;
+
+ acc = (struct kvmhv_tb_accumulator *)
+ ((unsigned long)vcpu + timings[i].offset);
+ ok = false;
+ for (loops = 0; loops < 1000; ++loops) {
+ count = acc->seqcount;
+ if (!(count & 1)) {
+ smp_rmb();
+ tb = *acc;
+ smp_rmb();
+ if (count = acc->seqcount) {
+ ok = true;
+ break;
+ }
+ }
+ udelay(1);
+ }
+ if (!ok)
+ snprintf(s, buf_end - s, "%s: stuck\n",
+ timings[i].name);
+ else
+ snprintf(s, buf_end - s,
+ "%s: %llu %llu %llu %llu\n",
+ timings[i].name, count / 2,
+ tb_to_ns(tb.tb_total),
+ tb_to_ns(tb.tb_min),
+ tb_to_ns(tb.tb_max));
+ s += strlen(s);
+ }
+ p->buflen = s - p->buf;
+ }
+
+ pos = *ppos;
+ if (pos >= p->buflen)
+ return 0;
+ if (len > p->buflen - pos)
+ len = p->buflen - pos;
+ n = copy_to_user(buf, p->buf + pos, len);
+ if (n) {
+ if (n = len)
+ return -EFAULT;
+ len -= n;
+ }
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_timings_open,
+ .release = debugfs_timings_release,
+ .read = debugfs_timings_read,
+ .write = debugfs_timings_write,
+ .llseek = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+ char buf[16];
+ struct kvm *kvm = vcpu->kvm;
+
+ snprintf(buf, sizeof(buf), "vcpu%u", id);
+ if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+ if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_timings + debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+ vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
@@ -1492,6 +1640,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ debugfs_vcpu_init(vcpu, id);
+
return vcpu;
free_vcpu:
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e9c3cb5..ee6ba4c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -225,7 +225,13 @@ kvm_novcpu_wakeup:
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
- bne kvmppc_got_guest
+ beq kvmppc_primary_no_guest
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+#endif
+ b kvmppc_got_guest
kvm_novcpu_exit:
b hdec_soon
@@ -376,6 +382,14 @@ kvmppc_hv_entry:
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Store initial timestamp */
+ cmpdi r4, 0
+ beq 1f
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+1:
+#endif
/* Clear out SLB */
li r6,0
slbmte r6,r6
@@ -880,6 +894,12 @@ fast_guest_return:
li r9, KVM_GUEST_MODE_GUEST_HV
stb r9, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Accumulate timing */
+ addi r3, r4, VCPU_TB_GUEST
+ bl kvmhv_accumulate_time
+#endif
+
/* Enter guest */
BEGIN_FTR_SECTION
@@ -917,6 +937,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+secondary_too_late:
+ cmpdi r4, 0
+ beq 11f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+11: b kvmhv_switch_to_host
+
+hdec_soon:
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 12f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+12: b kvmhv_do_exit
+#endif
+
/******************************************************************************
* *
* Exit code *
@@ -1002,6 +1039,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
stw r12,VCPU_TRAP(r9)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMINTR
+ mr r4, r9
+ bl kvmhv_accumulate_time
+ ld r5, VCPU_GPR(R5)(r9)
+ ld r6, VCPU_GPR(R6)(r9)
+ ld r7, VCPU_GPR(R7)(r9)
+ ld r8, VCPU_GPR(R8)(r9)
+#endif
+
/* Save HEIR (HV emulation assist reg) in emul_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
@@ -1072,6 +1119,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
beq machine_check_realmode
mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
/* Save guest CTRL register, set runlatch to 1 */
6: mfspr r6,SPRN_CTRLF
@@ -1416,7 +1468,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-hdec_soon: /* r12 = trap, r13 = paca */
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+hdec_soon:
+#endif
+kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
@@ -1475,7 +1530,10 @@ hdec_soon: /* r12 = trap, r13 = paca */
addi r6,r6,PACA_SIZE
bne 42b
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+#endif
+kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
43: ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
@@ -1561,6 +1619,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
1: addi r8,r8,16
.endr
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Finish timing, if we have a vcpu */
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ li r3, 0
+ beq 2f
+ bl kvmhv_accumulate_time
+2:
+#endif
/* Unset guest mode */
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
@@ -2068,6 +2135,12 @@ _GLOBAL(kvmppc_h_cede)
/* save FP state */
bl kvmppc_save_fp
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ addi r3, r4, VCPU_TB_CEDE
+ bl kvmhv_accumulate_time
+#endif
+
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
@@ -2108,6 +2181,11 @@ kvm_end_cede:
/* Woken by external or decrementer interrupt */
ld r1, HSTATE_HOST_R1(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMINTR
+ bl kvmhv_accumulate_time
+#endif
+
/* load up FP state */
bl kvmppc_load_fp
@@ -2428,3 +2506,50 @@ kvmppc_fix_pmao:
mtspr SPRN_PMC6, r3
isync
blr
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+/*
+ * Start timing an activity
+ * r3 = pointer to time accumulation struct, r4 = vcpu
+ */
+kvmhv_start_timing:
+ mftb r5
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ std r5, VCPU_ACTIVITY_START(r4)
+ blr
+
+/*
+ * Accumulate time to one activity and start another.
+ * r3 = pointer to new time accumulation struct, r4 = vcpu
+ */
+kvmhv_accumulate_time:
+ ld r5, VCPU_CUR_ACTIVITY(r4)
+ ld r6, VCPU_ACTIVITY_START(r4)
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ mftb r7
+ std r7, VCPU_ACTIVITY_START(r4)
+ cmpdi r5, 0
+ beqlr
+ subf r3, r6, r7
+ ld r8, TAS_SEQCOUNT(r5)
+ cmpdi r8, 0
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ lwsync
+ ld r7, TAS_TOTAL(r5)
+ add r7, r7, r3
+ std r7, TAS_TOTAL(r5)
+ ld r6, TAS_MIN(r5)
+ ld r7, TAS_MAX(r5)
+ beq 3f
+ cmpd r3, r6
+ bge 1f
+3: std r3, TAS_MIN(r5)
+1: cmpd r3, r7
+ ble 2f
+ std r3, TAS_MAX(r5)
+2: lwsync
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ blr
+#endif
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* Re: [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 11:47 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 11:47 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
On Fri, Mar 27, 2015 at 02:29:46PM +1100, Paul Mackerras wrote:
> This reads the timebase at various points in the real-mode guest
> entry/exit code and uses that to accumulate total, minimum and
> maximum time spent in those parts of the code. Currently these
> times are accumulated per vcpu in 5 parts of the code:
I just realized that this is going to give bogus results if we have a
non-zero timebase offset, so ignore this patch for now. I'll fix it
and repost.
Paul.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
@ 2015-03-27 11:47 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 11:47 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
On Fri, Mar 27, 2015 at 02:29:46PM +1100, Paul Mackerras wrote:
> This reads the timebase at various points in the real-mode guest
> entry/exit code and uses that to accumulate total, minimum and
> maximum time spent in those parts of the code. Currently these
> times are accumulated per vcpu in 5 parts of the code:
I just realized that this is going to give bogus results if we have a
non-zero timebase offset, so ignore this patch for now. I'll fix it
and repost.
Paul.
^ permalink raw reply [flat|nested] 30+ messages in thread
* [PATCH 03/12] KVM: PPC: Book3S HV: Simplify handling of VCPUs that need a VPA update
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Previously, if kvmppc_run_core() was running a VCPU that needed a VPA
update (i.e. one of its 3 virtual processor areas needed to be pinned
in memory so the host real mode code can update it on guest entry and
exit), we would drop the vcore lock and do the update there and then.
Future changes will make it inconvenient to drop the lock, so instead
we now remove it from the list of runnable VCPUs and wake up its
VCPU task. This will have the effect that the VCPU task will exit
kvmppc_run_vcpu(), go around the do loop in kvmppc_vcpu_run_hv(), and
re-enter kvmppc_run_vcpu(), whereupon it will do the necessary call
to kvmppc_update_vpas() and then rejoin the vcore.
The one complication is that the runner VCPU (whose VCPU task is the
current task) might be one of the ones that gets removed from the
runnable list. In that case we just return from kvmppc_run_core()
and let the code in kvmppc_run_vcpu() wake up another VCPU task to be
the runner if necessary.
This all means that the VCORE_STARTING state is no longer used, so we
remove it.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 5 ++--
arch/powerpc/kvm/book3s_hv.c | 56 ++++++++++++++++++++-----------------
2 files changed, 32 insertions(+), 29 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d2068bb..2f339ff 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -306,9 +306,8 @@ struct kvmppc_vcore {
/* Values for vcore_state */
#define VCORE_INACTIVE 0
#define VCORE_SLEEPING 1
-#define VCORE_STARTING 2
-#define VCORE_RUNNING 3
-#define VCORE_EXITING 4
+#define VCORE_RUNNING 2
+#define VCORE_EXITING 3
/*
* Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c7b18ac..1a6ea6e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1863,6 +1863,25 @@ static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
}
+static void prepare_threads(struct kvmppc_vcore *vc)
+{
+ struct kvm_vcpu *vcpu, *vnext;
+
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ if (signal_pending(vcpu->arch.run_task))
+ vcpu->arch.ret = -EINTR;
+ else if (vcpu->arch.vpa.update_pending ||
+ vcpu->arch.slb_shadow.update_pending ||
+ vcpu->arch.dtl.update_pending)
+ vcpu->arch.ret = RESUME_GUEST;
+ else
+ continue;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
@@ -1872,46 +1891,31 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
struct kvm_vcpu *vcpu, *vnext;
long ret;
u64 now;
- int i, need_vpa_update;
+ int i;
int srcu_idx;
- struct kvm_vcpu *vcpus_to_update[threads_per_core];
- /* don't start if any threads have a signal pending */
- need_vpa_update = 0;
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- if (signal_pending(vcpu->arch.run_task))
- return;
- if (vcpu->arch.vpa.update_pending ||
- vcpu->arch.slb_shadow.update_pending ||
- vcpu->arch.dtl.update_pending)
- vcpus_to_update[need_vpa_update++] = vcpu;
- }
+ /*
+ * Remove from the list any threads that have a signal pending
+ * or need a VPA update done
+ */
+ prepare_threads(vc);
+
+ /* if the runner is no longer runnable, let the caller pick a new one */
+ if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
+ return;
/*
- * Initialize *vc, in particular vc->vcore_state, so we can
- * drop the vcore lock if necessary.
+ * Initialize *vc.
*/
vc->n_woken = 0;
vc->nap_count = 0;
vc->entry_exit_count = 0;
vc->preempt_tb = TB_NIL;
- vc->vcore_state = VCORE_STARTING;
vc->in_guest = 0;
vc->napping_threads = 0;
vc->conferring_threads = 0;
/*
- * Updating any of the vpas requires calling kvmppc_pin_guest_page,
- * which can't be called with any spinlocks held.
- */
- if (need_vpa_update) {
- spin_unlock(&vc->lock);
- for (i = 0; i < need_vpa_update; ++i)
- kvmppc_update_vpas(vcpus_to_update[i]);
- spin_lock(&vc->lock);
- }
-
- /*
* 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.
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 03/12] KVM: PPC: Book3S HV: Simplify handling of VCPUs that need a VPA update
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Previously, if kvmppc_run_core() was running a VCPU that needed a VPA
update (i.e. one of its 3 virtual processor areas needed to be pinned
in memory so the host real mode code can update it on guest entry and
exit), we would drop the vcore lock and do the update there and then.
Future changes will make it inconvenient to drop the lock, so instead
we now remove it from the list of runnable VCPUs and wake up its
VCPU task. This will have the effect that the VCPU task will exit
kvmppc_run_vcpu(), go around the do loop in kvmppc_vcpu_run_hv(), and
re-enter kvmppc_run_vcpu(), whereupon it will do the necessary call
to kvmppc_update_vpas() and then rejoin the vcore.
The one complication is that the runner VCPU (whose VCPU task is the
current task) might be one of the ones that gets removed from the
runnable list. In that case we just return from kvmppc_run_core()
and let the code in kvmppc_run_vcpu() wake up another VCPU task to be
the runner if necessary.
This all means that the VCORE_STARTING state is no longer used, so we
remove it.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 5 ++--
arch/powerpc/kvm/book3s_hv.c | 56 ++++++++++++++++++++-----------------
2 files changed, 32 insertions(+), 29 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d2068bb..2f339ff 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -306,9 +306,8 @@ struct kvmppc_vcore {
/* Values for vcore_state */
#define VCORE_INACTIVE 0
#define VCORE_SLEEPING 1
-#define VCORE_STARTING 2
-#define VCORE_RUNNING 3
-#define VCORE_EXITING 4
+#define VCORE_RUNNING 2
+#define VCORE_EXITING 3
/*
* Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c7b18ac..1a6ea6e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1863,6 +1863,25 @@ static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
}
+static void prepare_threads(struct kvmppc_vcore *vc)
+{
+ struct kvm_vcpu *vcpu, *vnext;
+
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ if (signal_pending(vcpu->arch.run_task))
+ vcpu->arch.ret = -EINTR;
+ else if (vcpu->arch.vpa.update_pending ||
+ vcpu->arch.slb_shadow.update_pending ||
+ vcpu->arch.dtl.update_pending)
+ vcpu->arch.ret = RESUME_GUEST;
+ else
+ continue;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
@@ -1872,46 +1891,31 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
struct kvm_vcpu *vcpu, *vnext;
long ret;
u64 now;
- int i, need_vpa_update;
+ int i;
int srcu_idx;
- struct kvm_vcpu *vcpus_to_update[threads_per_core];
- /* don't start if any threads have a signal pending */
- need_vpa_update = 0;
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- if (signal_pending(vcpu->arch.run_task))
- return;
- if (vcpu->arch.vpa.update_pending ||
- vcpu->arch.slb_shadow.update_pending ||
- vcpu->arch.dtl.update_pending)
- vcpus_to_update[need_vpa_update++] = vcpu;
- }
+ /*
+ * Remove from the list any threads that have a signal pending
+ * or need a VPA update done
+ */
+ prepare_threads(vc);
+
+ /* if the runner is no longer runnable, let the caller pick a new one */
+ if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
+ return;
/*
- * Initialize *vc, in particular vc->vcore_state, so we can
- * drop the vcore lock if necessary.
+ * Initialize *vc.
*/
vc->n_woken = 0;
vc->nap_count = 0;
vc->entry_exit_count = 0;
vc->preempt_tb = TB_NIL;
- vc->vcore_state = VCORE_STARTING;
vc->in_guest = 0;
vc->napping_threads = 0;
vc->conferring_threads = 0;
/*
- * Updating any of the vpas requires calling kvmppc_pin_guest_page,
- * which can't be called with any spinlocks held.
- */
- if (need_vpa_update) {
- spin_unlock(&vc->lock);
- for (i = 0; i < need_vpa_update; ++i)
- kvmppc_update_vpas(vcpus_to_update[i]);
- spin_lock(&vc->lock);
- }
-
- /*
* 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.
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 04/12] KVM: PPC: Book3S HV: Minor cleanups
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
* Remove unused kvmppc_vcore::n_busy field.
* Remove setting of RMOR, since it was only used on PPC970 and the
PPC970 KVM support has been removed.
* Don't use r1 or r2 in setting the runlatch since they are
conventionally reserved for other things; use r0 instead.
* Streamline the code a little and remove the ext_interrupt_to_host
label.
* Add some comments about register usage.
* hcall_try_real_mode doesn't need to be global, and can't be
called from C code anyway.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 44 ++++++++++++++-------------------
3 files changed, 19 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2f339ff..3eecd88 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -227,7 +227,6 @@ struct kvm_arch {
unsigned long host_sdr1;
int tlbie_lock;
unsigned long lpcr;
- unsigned long rmor;
unsigned long vrma_slb_v;
int hpte_setup_done;
u32 hpt_order;
@@ -271,7 +270,6 @@ struct kvm_arch {
*/
struct kvmppc_vcore {
int n_runnable;
- int n_busy;
int num_threads;
int entry_exit_count;
int n_woken;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3fea721..92ec3fc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -505,7 +505,6 @@ int main(void)
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
- DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ee6ba4c..a69e09e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -245,9 +245,9 @@ kvm_novcpu_exit:
kvm_start_guest:
/* Set runlatch bit the minute you wake up from nap */
- mfspr r1, SPRN_CTRLF
- ori r1, r1, 1
- mtspr SPRN_CTRLT, r1
+ mfspr r0, SPRN_CTRLF
+ ori r0, r0, 1
+ mtspr SPRN_CTRLT, r0
ld r2,PACATOC(r13)
@@ -493,11 +493,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi r0,0
beq 20b
- /* Set LPCR and RMOR. */
+ /* Set LPCR. */
10: ld r8,VCORE_LPCR(r5)
mtspr SPRN_LPCR,r8
- ld r8,KVM_RMOR(r9)
- mtspr SPRN_RMOR,r8
isync
/* Check if HDEC expires soon */
@@ -1074,7 +1072,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
bne 2f
mfspr r3,SPRN_HDEC
cmpwi r3,0
- bge ignore_hdec
+ mr r4,r9
+ bge fast_guest_return
2:
/* See if this is an hcall we can handle in real mode */
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
@@ -1082,26 +1081,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
- bne+ ext_interrupt_to_host
+ bne+ guest_exit_cont
/* External interrupt, first check for host_ipi. If this is
* set, we know the host wants us out so let's do it now
*/
bl kvmppc_read_intr
cmpdi r3, 0
- bgt ext_interrupt_to_host
+ bgt guest_exit_cont
/* Check if any CPU is heading out to the host, if so head out too */
ld r5, HSTATE_KVM_VCORE(r13)
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
- bge ext_interrupt_to_host
-
- /* Return to guest after delivering any pending interrupt */
mr r4, r9
- b deliver_guest_interrupt
-
-ext_interrupt_to_host:
+ blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
/* Save more register state */
@@ -1762,8 +1756,10 @@ kvmppc_hisi:
* Returns to the guest if we handle it, or continues on up to
* the kernel if we can't (i.e. if we don't have a handler for
* it, or if the handler returns H_TOO_HARD).
+ *
+ * r5 - r8 contain hcall args,
+ * r9 = vcpu, r10 = pc, r11 = msr, r12 = trap, r13 = paca
*/
- .globl hcall_try_real_mode
hcall_try_real_mode:
ld r3,VCPU_GPR(R3)(r9)
andi. r0,r11,MSR_PR
@@ -2023,10 +2019,6 @@ hcall_real_table:
.globl hcall_real_table_end
hcall_real_table_end:
-ignore_hdec:
- mr r4,r9
- b fast_guest_return
-
_GLOBAL(kvmppc_h_set_xdabr)
andi. r0, r5, DABRX_USER | DABRX_KERNEL
beq 6f
@@ -2065,7 +2057,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r3, 0
blr
-_GLOBAL(kvmppc_h_cede)
+_GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
ori r11,r11,MSR_EE
std r11,VCPU_MSR(r3)
li r0,1
@@ -2147,9 +2139,9 @@ _GLOBAL(kvmppc_h_cede)
* runlatch bit before napping.
*/
kvm_do_nap:
- mfspr r2, SPRN_CTRLF
- clrrdi r2, r2, 1
- mtspr SPRN_CTRLT, r2
+ mfspr r0, SPRN_CTRLF
+ clrrdi r0, r0, 1
+ mtspr SPRN_CTRLT, r0
li r0,1
stb r0,HSTATE_HWTHREAD_REQ(r13)
@@ -2281,13 +2273,14 @@ machine_check_realmode:
/*
* Check the reason we woke from nap, and take appropriate action.
- * Returns:
+ * Returns (in r3):
* 0 if nothing needs to be done
* 1 if something happened that needs to be handled by the host
* -1 if there was a guest wakeup (IPI)
*
* Also sets r12 to the interrupt vector for any interrupt that needs
* to be handled now by the host (0x500 for external interrupt), or zero.
+ * Modifies r0, r6, r7, r8.
*/
kvmppc_check_wake_reason:
mfspr r6, SPRN_SRR1
@@ -2323,6 +2316,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* 0 if no interrupt is pending
* 1 if an interrupt is pending that needs to be handled by the host
* -1 if there was a guest wakeup IPI (which has now been cleared)
+ * Modifies r0, r6, r7, r8, returns value in r3.
*/
kvmppc_read_intr:
/* see if a host IPI is pending */
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 04/12] KVM: PPC: Book3S HV: Minor cleanups
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
* Remove unused kvmppc_vcore::n_busy field.
* Remove setting of RMOR, since it was only used on PPC970 and the
PPC970 KVM support has been removed.
* Don't use r1 or r2 in setting the runlatch since they are
conventionally reserved for other things; use r0 instead.
* Streamline the code a little and remove the ext_interrupt_to_host
label.
* Add some comments about register usage.
* hcall_try_real_mode doesn't need to be global, and can't be
called from C code anyway.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 44 ++++++++++++++-------------------
3 files changed, 19 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2f339ff..3eecd88 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -227,7 +227,6 @@ struct kvm_arch {
unsigned long host_sdr1;
int tlbie_lock;
unsigned long lpcr;
- unsigned long rmor;
unsigned long vrma_slb_v;
int hpte_setup_done;
u32 hpt_order;
@@ -271,7 +270,6 @@ struct kvm_arch {
*/
struct kvmppc_vcore {
int n_runnable;
- int n_busy;
int num_threads;
int entry_exit_count;
int n_woken;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3fea721..92ec3fc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -505,7 +505,6 @@ int main(void)
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
- DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ee6ba4c..a69e09e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -245,9 +245,9 @@ kvm_novcpu_exit:
kvm_start_guest:
/* Set runlatch bit the minute you wake up from nap */
- mfspr r1, SPRN_CTRLF
- ori r1, r1, 1
- mtspr SPRN_CTRLT, r1
+ mfspr r0, SPRN_CTRLF
+ ori r0, r0, 1
+ mtspr SPRN_CTRLT, r0
ld r2,PACATOC(r13)
@@ -493,11 +493,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
cmpwi r0,0
beq 20b
- /* Set LPCR and RMOR. */
+ /* Set LPCR. */
10: ld r8,VCORE_LPCR(r5)
mtspr SPRN_LPCR,r8
- ld r8,KVM_RMOR(r9)
- mtspr SPRN_RMOR,r8
isync
/* Check if HDEC expires soon */
@@ -1074,7 +1072,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
bne 2f
mfspr r3,SPRN_HDEC
cmpwi r3,0
- bge ignore_hdec
+ mr r4,r9
+ bge fast_guest_return
2:
/* See if this is an hcall we can handle in real mode */
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
@@ -1082,26 +1081,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
- bne+ ext_interrupt_to_host
+ bne+ guest_exit_cont
/* External interrupt, first check for host_ipi. If this is
* set, we know the host wants us out so let's do it now
*/
bl kvmppc_read_intr
cmpdi r3, 0
- bgt ext_interrupt_to_host
+ bgt guest_exit_cont
/* Check if any CPU is heading out to the host, if so head out too */
ld r5, HSTATE_KVM_VCORE(r13)
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
- bge ext_interrupt_to_host
-
- /* Return to guest after delivering any pending interrupt */
mr r4, r9
- b deliver_guest_interrupt
-
-ext_interrupt_to_host:
+ blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
/* Save more register state */
@@ -1762,8 +1756,10 @@ kvmppc_hisi:
* Returns to the guest if we handle it, or continues on up to
* the kernel if we can't (i.e. if we don't have a handler for
* it, or if the handler returns H_TOO_HARD).
+ *
+ * r5 - r8 contain hcall args,
+ * r9 = vcpu, r10 = pc, r11 = msr, r12 = trap, r13 = paca
*/
- .globl hcall_try_real_mode
hcall_try_real_mode:
ld r3,VCPU_GPR(R3)(r9)
andi. r0,r11,MSR_PR
@@ -2023,10 +2019,6 @@ hcall_real_table:
.globl hcall_real_table_end
hcall_real_table_end:
-ignore_hdec:
- mr r4,r9
- b fast_guest_return
-
_GLOBAL(kvmppc_h_set_xdabr)
andi. r0, r5, DABRX_USER | DABRX_KERNEL
beq 6f
@@ -2065,7 +2057,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r3, 0
blr
-_GLOBAL(kvmppc_h_cede)
+_GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
ori r11,r11,MSR_EE
std r11,VCPU_MSR(r3)
li r0,1
@@ -2147,9 +2139,9 @@ _GLOBAL(kvmppc_h_cede)
* runlatch bit before napping.
*/
kvm_do_nap:
- mfspr r2, SPRN_CTRLF
- clrrdi r2, r2, 1
- mtspr SPRN_CTRLT, r2
+ mfspr r0, SPRN_CTRLF
+ clrrdi r0, r0, 1
+ mtspr SPRN_CTRLT, r0
li r0,1
stb r0,HSTATE_HWTHREAD_REQ(r13)
@@ -2281,13 +2273,14 @@ machine_check_realmode:
/*
* Check the reason we woke from nap, and take appropriate action.
- * Returns:
+ * Returns (in r3):
* 0 if nothing needs to be done
* 1 if something happened that needs to be handled by the host
* -1 if there was a guest wakeup (IPI)
*
* Also sets r12 to the interrupt vector for any interrupt that needs
* to be handled now by the host (0x500 for external interrupt), or zero.
+ * Modifies r0, r6, r7, r8.
*/
kvmppc_check_wake_reason:
mfspr r6, SPRN_SRR1
@@ -2323,6 +2316,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* 0 if no interrupt is pending
* 1 if an interrupt is pending that needs to be handled by the host
* -1 if there was a guest wakeup IPI (which has now been cleared)
+ * Modifies r0, r6, r7, r8, returns value in r3.
*/
kvmppc_read_intr:
/* see if a host IPI is pending */
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 05/12] KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 5 +-
arch/powerpc/kvm/book3s_hv.c | 92 +++++++++++++++++++++----------------
2 files changed, 55 insertions(+), 42 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3eecd88..83c4425 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,8 +304,9 @@ struct kvmppc_vcore {
/* Values for vcore_state */
#define VCORE_INACTIVE 0
#define VCORE_SLEEPING 1
-#define VCORE_RUNNING 2
-#define VCORE_EXITING 3
+#define VCORE_PREEMPT 2
+#define VCORE_RUNNING 3
+#define VCORE_EXITING 4
/*
* Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1a6ea6e..5a1abf6 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1882,15 +1882,50 @@ static void prepare_threads(struct kvmppc_vcore *vc)
}
}
+static void post_guest_process(struct kvmppc_vcore *vc)
+{
+ u64 now;
+ long ret;
+ struct kvm_vcpu *vcpu, *vnext;
+
+ now = get_tb();
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ /* cancel pending dec exception if dec is positive */
+ if (now < vcpu->arch.dec_expires &&
+ kvmppc_core_pending_dec(vcpu))
+ kvmppc_core_dequeue_dec(vcpu);
+
+ trace_kvm_guest_exit(vcpu);
+
+ ret = RESUME_GUEST;
+ if (vcpu->arch.trap)
+ ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+ vcpu->arch.run_task);
+
+ vcpu->arch.ret = ret;
+ vcpu->arch.trap = 0;
+
+ if (vcpu->arch.ceded) {
+ if (!is_kvmppc_resume_guest(ret))
+ kvmppc_end_cede(vcpu);
+ else
+ kvmppc_set_timer(vcpu);
+ }
+ if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
static void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu, *vnext;
- long ret;
- u64 now;
+ struct kvm_vcpu *vcpu;
int i;
int srcu_idx;
@@ -1922,8 +1957,11 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
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)
+ list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
vcpu->arch.ret = -EBUSY;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
goto out;
}
@@ -1979,44 +2017,12 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
kvm_guest_exit();
preempt_enable();
- cond_resched();
spin_lock(&vc->lock);
- now = get_tb();
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- /* cancel pending dec exception if dec is positive */
- if (now < vcpu->arch.dec_expires &&
- kvmppc_core_pending_dec(vcpu))
- kvmppc_core_dequeue_dec(vcpu);
-
- trace_kvm_guest_exit(vcpu);
-
- ret = RESUME_GUEST;
- if (vcpu->arch.trap)
- ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
- vcpu->arch.run_task);
-
- vcpu->arch.ret = ret;
- vcpu->arch.trap = 0;
-
- if (vcpu->arch.ceded) {
- if (!is_kvmppc_resume_guest(ret))
- kvmppc_end_cede(vcpu);
- else
- kvmppc_set_timer(vcpu);
- }
- }
+ post_guest_process(vc);
out:
vc->vcore_state = VCORE_INACTIVE;
- list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
- arch.run_list) {
- if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
- kvmppc_remove_runnable(vc, vcpu);
- wake_up(&vcpu->arch.cpu_run);
- }
- }
-
trace_kvmppc_run_core(vc, 1);
}
@@ -2138,7 +2144,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
}
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
break;
- vc->runner = vcpu;
n_ceded = 0;
list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
if (!v->arch.pending_exceptions)
@@ -2146,10 +2151,17 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
else
v->arch.ceded = 0;
}
- if (n_ceded == vc->n_runnable)
+ vc->runner = vcpu;
+ if (n_ceded == vc->n_runnable) {
kvmppc_vcore_blocked(vc);
- else
+ } else if (should_resched()) {
+ vc->vcore_state = VCORE_PREEMPT;
+ /* Let something else run */
+ cond_resched_lock(&vc->lock);
+ vc->vcore_state = VCORE_INACTIVE;
+ } else {
kvmppc_run_core(vc);
+ }
vc->runner = NULL;
}
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 05/12] KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 5 +-
arch/powerpc/kvm/book3s_hv.c | 92 +++++++++++++++++++++----------------
2 files changed, 55 insertions(+), 42 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 3eecd88..83c4425 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,8 +304,9 @@ struct kvmppc_vcore {
/* Values for vcore_state */
#define VCORE_INACTIVE 0
#define VCORE_SLEEPING 1
-#define VCORE_RUNNING 2
-#define VCORE_EXITING 3
+#define VCORE_PREEMPT 2
+#define VCORE_RUNNING 3
+#define VCORE_EXITING 4
/*
* Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1a6ea6e..5a1abf6 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1882,15 +1882,50 @@ static void prepare_threads(struct kvmppc_vcore *vc)
}
}
+static void post_guest_process(struct kvmppc_vcore *vc)
+{
+ u64 now;
+ long ret;
+ struct kvm_vcpu *vcpu, *vnext;
+
+ now = get_tb();
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ /* cancel pending dec exception if dec is positive */
+ if (now < vcpu->arch.dec_expires &&
+ kvmppc_core_pending_dec(vcpu))
+ kvmppc_core_dequeue_dec(vcpu);
+
+ trace_kvm_guest_exit(vcpu);
+
+ ret = RESUME_GUEST;
+ if (vcpu->arch.trap)
+ ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+ vcpu->arch.run_task);
+
+ vcpu->arch.ret = ret;
+ vcpu->arch.trap = 0;
+
+ if (vcpu->arch.ceded) {
+ if (!is_kvmppc_resume_guest(ret))
+ kvmppc_end_cede(vcpu);
+ else
+ kvmppc_set_timer(vcpu);
+ }
+ if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
static void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu, *vnext;
- long ret;
- u64 now;
+ struct kvm_vcpu *vcpu;
int i;
int srcu_idx;
@@ -1922,8 +1957,11 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
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)
+ list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
vcpu->arch.ret = -EBUSY;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
goto out;
}
@@ -1979,44 +2017,12 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
kvm_guest_exit();
preempt_enable();
- cond_resched();
spin_lock(&vc->lock);
- now = get_tb();
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- /* cancel pending dec exception if dec is positive */
- if (now < vcpu->arch.dec_expires &&
- kvmppc_core_pending_dec(vcpu))
- kvmppc_core_dequeue_dec(vcpu);
-
- trace_kvm_guest_exit(vcpu);
-
- ret = RESUME_GUEST;
- if (vcpu->arch.trap)
- ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
- vcpu->arch.run_task);
-
- vcpu->arch.ret = ret;
- vcpu->arch.trap = 0;
-
- if (vcpu->arch.ceded) {
- if (!is_kvmppc_resume_guest(ret))
- kvmppc_end_cede(vcpu);
- else
- kvmppc_set_timer(vcpu);
- }
- }
+ post_guest_process(vc);
out:
vc->vcore_state = VCORE_INACTIVE;
- list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
- arch.run_list) {
- if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
- kvmppc_remove_runnable(vc, vcpu);
- wake_up(&vcpu->arch.cpu_run);
- }
- }
-
trace_kvmppc_run_core(vc, 1);
}
@@ -2138,7 +2144,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
}
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
break;
- vc->runner = vcpu;
n_ceded = 0;
list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
if (!v->arch.pending_exceptions)
@@ -2146,10 +2151,17 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
else
v->arch.ceded = 0;
}
- if (n_ceded = vc->n_runnable)
+ vc->runner = vcpu;
+ if (n_ceded = vc->n_runnable) {
kvmppc_vcore_blocked(vc);
- else
+ } else if (should_resched()) {
+ vc->vcore_state = VCORE_PREEMPT;
+ /* Let something else run */
+ cond_resched_lock(&vc->lock);
+ vc->vcore_state = VCORE_INACTIVE;
+ } else {
kvmppc_run_core(vc);
+ }
vc->runner = NULL;
}
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 06/12] KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
We can tell when a secondary thread has finished running a guest by
the fact that it clears its kvm_hstate.kvm_vcpu pointer, so there
is no real need for the nap_count field in the kvmppc_vcore struct.
This changes kvmppc_wait_for_nap to poll the kvm_hstate.kvm_vcpu
pointers of the secondary threads rather than polling vc->nap_count.
Besides reducing the size of the kvmppc_vcore struct by 8 bytes,
this also means that we can tell which secondary threads have got
stuck and thus print a more informative error message.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kvm/book3s_hv.c | 47 +++++++++++++++++++--------------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 19 +++++--------
4 files changed, 34 insertions(+), 35 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 83c4425..1517faa 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -272,8 +272,6 @@ struct kvmppc_vcore {
int n_runnable;
int num_threads;
int entry_exit_count;
- int n_woken;
- int nap_count;
int napping_threads;
int first_vcpuid;
u16 pcpu;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 92ec3fc..8aa8246 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -563,7 +563,6 @@ int main(void)
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
- DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5a1abf6..6741505 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1729,8 +1729,10 @@ static int kvmppc_grab_hwthread(int cpu)
tpaca = &paca[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
- tpaca->kvm_hstate.hwthread_req = 1;
tpaca->kvm_hstate.kvm_vcpu = NULL;
+ tpaca->kvm_hstate.napping = 0;
+ smp_wmb();
+ tpaca->kvm_hstate.hwthread_req = 1;
/*
* If the thread is already executing in the kernel (e.g. handling
@@ -1773,35 +1775,43 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
}
cpu = vc->pcpu + vcpu->arch.ptid;
tpaca = &paca[cpu];
- tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.kvm_vcore = vc;
tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
vcpu->cpu = vc->pcpu;
+ /* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
smp_wmb();
+ tpaca->kvm_hstate.kvm_vcpu = vcpu;
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (cpu != smp_processor_id()) {
+ if (cpu != smp_processor_id())
xics_wake_cpu(cpu);
- if (vcpu->arch.ptid)
- ++vc->n_woken;
- }
#endif
}
-static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+static void kvmppc_wait_for_nap(void)
{
- int i;
+ int cpu = smp_processor_id();
+ int i, loops;
- HMT_low();
- i = 0;
- while (vc->nap_count < vc->n_woken) {
- if (++i >= 1000000) {
- pr_err("kvmppc_wait_for_nap timeout %d %d\n",
- vc->nap_count, vc->n_woken);
- break;
+ for (loops = 0; loops < 1000000; ++loops) {
+ /*
+ * Check if all threads are finished.
+ * We set the vcpu pointer when starting a thread
+ * and the thread clears it when finished, so we look
+ * for any threads that still have a non-NULL vcpu ptr.
+ */
+ for (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ break;
+ if (i == threads_per_subcore) {
+ HMT_medium();
+ return;
}
- cpu_relax();
+ HMT_low();
}
HMT_medium();
+ for (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
/*
@@ -1942,8 +1952,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
/*
* Initialize *vc.
*/
- vc->n_woken = 0;
- vc->nap_count = 0;
vc->entry_exit_count = 0;
vc->preempt_tb = TB_NIL;
vc->in_guest = 0;
@@ -2002,8 +2010,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
vcpu->cpu = -1;
/* wait for secondary threads to finish writing their state to memory */
- if (vc->nap_count < vc->n_woken)
- kvmppc_wait_for_nap(vc);
+ kvmppc_wait_for_nap();
for (i = 0; i < threads_per_subcore; ++i)
kvmppc_release_hwthread(vc->pcpu + i);
/* prevent other vcpu threads from doing kvmppc_start_thread() now */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index a69e09e..0a35b8d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -292,26 +292,21 @@ kvm_secondary_got_guest:
ld r6, PACA_DSCR(r13)
std r6, HSTATE_DSCR(r13)
+ /* Order load of vcore, ptid etc. after load of vcpu */
+ lwsync
bl kvmppc_hv_entry
/* Back from the guest, go back to nap */
/* Clear our vcpu pointer so we don't come back in early */
li r0, 0
- std r0, HSTATE_KVM_VCPU(r13)
/*
- * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
- * the nap_count, because once the increment to nap_count is
- * visible we could be given another vcpu.
+ * Once we clear HSTATE_KVM_VCPU(r13), the code in
+ * kvmppc_run_core() is going to assume that all our vcpu
+ * state is visible in memory. This lwsync makes sure
+ * that that is true.
*/
lwsync
-
- /* increment the nap count and then go to nap mode */
- ld r4, HSTATE_KVM_VCORE(r13)
- addi r4, r4, VCORE_NAP_COUNT
-51: lwarx r3, 0, r4
- addi r3, r3, 1
- stwcx. r3, 0, r4
- bne 51b
+ std r0, HSTATE_KVM_VCPU(r13)
/*
* At this point we have finished executing in the guest.
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 06/12] KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
We can tell when a secondary thread has finished running a guest by
the fact that it clears its kvm_hstate.kvm_vcpu pointer, so there
is no real need for the nap_count field in the kvmppc_vcore struct.
This changes kvmppc_wait_for_nap to poll the kvm_hstate.kvm_vcpu
pointers of the secondary threads rather than polling vc->nap_count.
Besides reducing the size of the kvmppc_vcore struct by 8 bytes,
this also means that we can tell which secondary threads have got
stuck and thus print a more informative error message.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 2 --
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kvm/book3s_hv.c | 47 +++++++++++++++++++--------------
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 19 +++++--------
4 files changed, 34 insertions(+), 35 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 83c4425..1517faa 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -272,8 +272,6 @@ struct kvmppc_vcore {
int n_runnable;
int num_threads;
int entry_exit_count;
- int n_woken;
- int nap_count;
int napping_threads;
int first_vcpuid;
u16 pcpu;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 92ec3fc..8aa8246 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -563,7 +563,6 @@ int main(void)
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
- DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5a1abf6..6741505 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1729,8 +1729,10 @@ static int kvmppc_grab_hwthread(int cpu)
tpaca = &paca[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
- tpaca->kvm_hstate.hwthread_req = 1;
tpaca->kvm_hstate.kvm_vcpu = NULL;
+ tpaca->kvm_hstate.napping = 0;
+ smp_wmb();
+ tpaca->kvm_hstate.hwthread_req = 1;
/*
* If the thread is already executing in the kernel (e.g. handling
@@ -1773,35 +1775,43 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
}
cpu = vc->pcpu + vcpu->arch.ptid;
tpaca = &paca[cpu];
- tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.kvm_vcore = vc;
tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
vcpu->cpu = vc->pcpu;
+ /* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
smp_wmb();
+ tpaca->kvm_hstate.kvm_vcpu = vcpu;
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (cpu != smp_processor_id()) {
+ if (cpu != smp_processor_id())
xics_wake_cpu(cpu);
- if (vcpu->arch.ptid)
- ++vc->n_woken;
- }
#endif
}
-static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+static void kvmppc_wait_for_nap(void)
{
- int i;
+ int cpu = smp_processor_id();
+ int i, loops;
- HMT_low();
- i = 0;
- while (vc->nap_count < vc->n_woken) {
- if (++i >= 1000000) {
- pr_err("kvmppc_wait_for_nap timeout %d %d\n",
- vc->nap_count, vc->n_woken);
- break;
+ for (loops = 0; loops < 1000000; ++loops) {
+ /*
+ * Check if all threads are finished.
+ * We set the vcpu pointer when starting a thread
+ * and the thread clears it when finished, so we look
+ * for any threads that still have a non-NULL vcpu ptr.
+ */
+ for (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ break;
+ if (i = threads_per_subcore) {
+ HMT_medium();
+ return;
}
- cpu_relax();
+ HMT_low();
}
HMT_medium();
+ for (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
/*
@@ -1942,8 +1952,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
/*
* Initialize *vc.
*/
- vc->n_woken = 0;
- vc->nap_count = 0;
vc->entry_exit_count = 0;
vc->preempt_tb = TB_NIL;
vc->in_guest = 0;
@@ -2002,8 +2010,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
vcpu->cpu = -1;
/* wait for secondary threads to finish writing their state to memory */
- if (vc->nap_count < vc->n_woken)
- kvmppc_wait_for_nap(vc);
+ kvmppc_wait_for_nap();
for (i = 0; i < threads_per_subcore; ++i)
kvmppc_release_hwthread(vc->pcpu + i);
/* prevent other vcpu threads from doing kvmppc_start_thread() now */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index a69e09e..0a35b8d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -292,26 +292,21 @@ kvm_secondary_got_guest:
ld r6, PACA_DSCR(r13)
std r6, HSTATE_DSCR(r13)
+ /* Order load of vcore, ptid etc. after load of vcpu */
+ lwsync
bl kvmppc_hv_entry
/* Back from the guest, go back to nap */
/* Clear our vcpu pointer so we don't come back in early */
li r0, 0
- std r0, HSTATE_KVM_VCPU(r13)
/*
- * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
- * the nap_count, because once the increment to nap_count is
- * visible we could be given another vcpu.
+ * Once we clear HSTATE_KVM_VCPU(r13), the code in
+ * kvmppc_run_core() is going to assume that all our vcpu
+ * state is visible in memory. This lwsync makes sure
+ * that that is true.
*/
lwsync
-
- /* increment the nap count and then go to nap mode */
- ld r4, HSTATE_KVM_VCORE(r13)
- addi r4, r4, VCORE_NAP_COUNT
-51: lwarx r3, 0, r4
- addi r3, r3, 1
- stwcx. r3, 0, r4
- bne 51b
+ std r0, HSTATE_KVM_VCPU(r13)
/*
* At this point we have finished executing in the guest.
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 07/12] KVM: PPC: Book3S HV: Don't wake thread with no vcpu on guest IPI
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
When running a multi-threaded guest and vcpu 0 in a virtual core
is not running in the guest (i.e. it is busy elsewhere in the host),
thread 0 of the physical core will switch the MMU to the guest and
then go to nap mode in the code at kvm_do_nap. If the guest sends
an IPI to thread 0 using the msgsndp instruction, that will wake
up thread 0 and cause all the threads in the guest to exit to the
host unnecessarily. To avoid the unnecessary exit, this arranges
for the PECEDP bit to be cleared in this situation. When napping
due to a H_CEDE from the guest, we still set PECEDP so that the
thread will wake up on an IPI sent using msgsndp.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 0a35b8d..35b1847 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -191,6 +191,7 @@ kvmppc_primary_no_guest:
li r3, NAPPING_NOVCPU
stb r3, HSTATE_NAPPING(r13)
+ li r3, 0 /* Don't wake on privileged (OS) doorbell */
b kvm_do_nap
kvm_novcpu_wakeup:
@@ -2128,10 +2129,13 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
bl kvmhv_accumulate_time
#endif
+ lis r3, LPCR_PECEDP@h /* Do wake on privileged doorbell */
+
/*
* Take a nap until a decrementer or external or doobell interrupt
- * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
- * runlatch bit before napping.
+ * occurs, with PECE1 and PECE0 set in LPCR.
+ * On POWER8, if we are ceding, also set PECEDP.
+ * Also clear the runlatch bit before napping.
*/
kvm_do_nap:
mfspr r0, SPRN_CTRLF
@@ -2143,7 +2147,7 @@ kvm_do_nap:
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
- oris r5,r5,LPCR_PECEDP@h
+ rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r5
isync
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 07/12] KVM: PPC: Book3S HV: Don't wake thread with no vcpu on guest IPI
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
When running a multi-threaded guest and vcpu 0 in a virtual core
is not running in the guest (i.e. it is busy elsewhere in the host),
thread 0 of the physical core will switch the MMU to the guest and
then go to nap mode in the code at kvm_do_nap. If the guest sends
an IPI to thread 0 using the msgsndp instruction, that will wake
up thread 0 and cause all the threads in the guest to exit to the
host unnecessarily. To avoid the unnecessary exit, this arranges
for the PECEDP bit to be cleared in this situation. When napping
due to a H_CEDE from the guest, we still set PECEDP so that the
thread will wake up on an IPI sent using msgsndp.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 0a35b8d..35b1847 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -191,6 +191,7 @@ kvmppc_primary_no_guest:
li r3, NAPPING_NOVCPU
stb r3, HSTATE_NAPPING(r13)
+ li r3, 0 /* Don't wake on privileged (OS) doorbell */
b kvm_do_nap
kvm_novcpu_wakeup:
@@ -2128,10 +2129,13 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
bl kvmhv_accumulate_time
#endif
+ lis r3, LPCR_PECEDP@h /* Do wake on privileged doorbell */
+
/*
* Take a nap until a decrementer or external or doobell interrupt
- * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
- * runlatch bit before napping.
+ * occurs, with PECE1 and PECE0 set in LPCR.
+ * On POWER8, if we are ceding, also set PECEDP.
+ * Also clear the runlatch bit before napping.
*/
kvm_do_nap:
mfspr r0, SPRN_CTRLF
@@ -2143,7 +2147,7 @@ kvm_do_nap:
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
- oris r5,r5,LPCR_PECEDP@h
+ rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r5
isync
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 08/12] KVM: PPC: Book3S HV: Use decrementer to wake napping threads
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This arranges for threads that are napping due to their vcpu having
ceded or due to not having a vcpu to wake up at the end of the guest's
timeslice without having to be poked with an IPI. We do that by
arranging for the decrementer to contain a value no greater than the
number of timebase ticks remaining until the end of the timeslice.
In the case of a thread with no vcpu, this number is in the hypervisor
decrementer already. In the case of a ceded vcpu, we use the smaller
of the HDEC value and the DEC value.
Using the DEC like this when ceded means we need to save and restore
the guest decrementer value around the nap.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 43 +++++++++++++++++++++++++++++++--
1 file changed, 41 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 35b1847..bc2ab3d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -172,6 +172,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
+ /* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+ mfspr r3, SPRN_HDEC
+ mtspr SPRN_DEC, r3
/* set our bit in napping_threads */
ld r5, HSTATE_KVM_VCORE(r13)
lbz r7, HSTATE_PTID(r13)
@@ -223,6 +226,12 @@ kvm_novcpu_wakeup:
cmpdi r3, 0
bge kvm_novcpu_exit
+ /* See if our timeslice has expired (HDEC is negative) */
+ mfspr r0, SPRN_HDEC
+ li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+ cmpwi r0, 0
+ blt kvm_novcpu_exit
+
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
@@ -1492,10 +1501,10 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
cmpwi r3,0x100 /* Are we the first here? */
bge 43f
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 40f
+ beq 43f
li r0,0
mtspr SPRN_HDEC,r0
-40:
+
/*
* Send an IPI to any napping threads, since an HDEC interrupt
* doesn't wake CPUs up from nap.
@@ -2123,6 +2132,27 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
/* save FP state */
bl kvmppc_save_fp
+ /*
+ * Set DEC to the smaller of DEC and HDEC, so that we wake
+ * no later than the end of our timeslice (HDEC interrupts
+ * don't wake us from nap).
+ */
+ mfspr r3, SPRN_DEC
+ mfspr r4, SPRN_HDEC
+ mftb r5
+ cmpw r3, r4
+ ble 67f
+ mtspr SPRN_DEC, r4
+67:
+ /* save expiry time of guest decrementer */
+ extsw r3, r3
+ add r3, r3, r5
+ ld r4, HSTATE_KVM_VCPU(r13)
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r6, VCORE_TB_OFFSET(r5)
+ subf r3, r6, r3 /* convert to host TB value */
+ std r3, VCPU_DEC_EXPIRES(r4)
+
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
ld r4, HSTATE_KVM_VCPU(r13)
addi r3, r4, VCPU_TB_CEDE
@@ -2180,6 +2210,15 @@ kvm_end_cede:
/* load up FP state */
bl kvmppc_load_fp
+ /* Restore guest decrementer */
+ ld r3, VCPU_DEC_EXPIRES(r4)
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r6, VCORE_TB_OFFSET(r5)
+ add r3, r3, r6 /* convert host TB to guest TB value */
+ mftb r7
+ subf r3, r7, r3
+ mtspr SPRN_DEC, r3
+
/* Load NV GPRS */
ld r14, VCPU_GPR(R14)(r4)
ld r15, VCPU_GPR(R15)(r4)
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 08/12] KVM: PPC: Book3S HV: Use decrementer to wake napping threads
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This arranges for threads that are napping due to their vcpu having
ceded or due to not having a vcpu to wake up at the end of the guest's
timeslice without having to be poked with an IPI. We do that by
arranging for the decrementer to contain a value no greater than the
number of timebase ticks remaining until the end of the timeslice.
In the case of a thread with no vcpu, this number is in the hypervisor
decrementer already. In the case of a ceded vcpu, we use the smaller
of the HDEC value and the DEC value.
Using the DEC like this when ceded means we need to save and restore
the guest decrementer value around the nap.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 43 +++++++++++++++++++++++++++++++--
1 file changed, 41 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 35b1847..bc2ab3d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -172,6 +172,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
+ /* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+ mfspr r3, SPRN_HDEC
+ mtspr SPRN_DEC, r3
/* set our bit in napping_threads */
ld r5, HSTATE_KVM_VCORE(r13)
lbz r7, HSTATE_PTID(r13)
@@ -223,6 +226,12 @@ kvm_novcpu_wakeup:
cmpdi r3, 0
bge kvm_novcpu_exit
+ /* See if our timeslice has expired (HDEC is negative) */
+ mfspr r0, SPRN_HDEC
+ li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+ cmpwi r0, 0
+ blt kvm_novcpu_exit
+
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
@@ -1492,10 +1501,10 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
cmpwi r3,0x100 /* Are we the first here? */
bge 43f
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 40f
+ beq 43f
li r0,0
mtspr SPRN_HDEC,r0
-40:
+
/*
* Send an IPI to any napping threads, since an HDEC interrupt
* doesn't wake CPUs up from nap.
@@ -2123,6 +2132,27 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
/* save FP state */
bl kvmppc_save_fp
+ /*
+ * Set DEC to the smaller of DEC and HDEC, so that we wake
+ * no later than the end of our timeslice (HDEC interrupts
+ * don't wake us from nap).
+ */
+ mfspr r3, SPRN_DEC
+ mfspr r4, SPRN_HDEC
+ mftb r5
+ cmpw r3, r4
+ ble 67f
+ mtspr SPRN_DEC, r4
+67:
+ /* save expiry time of guest decrementer */
+ extsw r3, r3
+ add r3, r3, r5
+ ld r4, HSTATE_KVM_VCPU(r13)
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r6, VCORE_TB_OFFSET(r5)
+ subf r3, r6, r3 /* convert to host TB value */
+ std r3, VCPU_DEC_EXPIRES(r4)
+
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
ld r4, HSTATE_KVM_VCPU(r13)
addi r3, r4, VCPU_TB_CEDE
@@ -2180,6 +2210,15 @@ kvm_end_cede:
/* load up FP state */
bl kvmppc_load_fp
+ /* Restore guest decrementer */
+ ld r3, VCPU_DEC_EXPIRES(r4)
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r6, VCORE_TB_OFFSET(r5)
+ add r3, r3, r6 /* convert host TB to guest TB value */
+ mftb r7
+ subf r3, r7, r3
+ mtspr SPRN_DEC, r3
+
/* Load NV GPRS */
ld r14, VCPU_GPR(R14)(r4)
ld r15, VCPU_GPR(R15)(r4)
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 09/12] KVM: PPC: Book3S HV: Use bitmap of active threads rather than count
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Currently, the entry_exit_count field in the kvmppc_vcore struct
contains two 8-bit counts, one of the threads that have started entering
the guest, and one of the threads that have started exiting the guest.
This changes it to an entry_exit_map field which contains two bitmaps
of 8 bits each. The advantage of doing this is that it gives us a
bitmap of which threads need to be signalled when exiting the guest.
That means that we no longer need to use the trick of setting the
HDEC to 0 to pull the other threads out of the guest, which led in
some cases to a spurious HDEC interrupt on the next guest entry.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 15 ++++----
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kvm/book3s_hv.c | 5 ++-
arch/powerpc/kvm/book3s_hv_builtin.c | 10 +++---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 61 +++++++++++++++------------------
5 files changed, 44 insertions(+), 49 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1517faa..d67a838 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -263,15 +263,15 @@ struct kvm_arch {
/*
* Struct for a virtual core.
- * Note: entry_exit_count combines an entry count in the bottom 8 bits
- * and an exit count in the next 8 bits. This is so that we can
- * atomically increment the entry count iff the exit count is 0
- * without taking the lock.
+ * Note: entry_exit_map combines a bitmap of threads that have entered
+ * in the bottom 8 bits and a bitmap of threads that have exited in the
+ * next 8 bits. This is so that we can atomically set the entry bit
+ * iff the exit map is 0 without taking a lock.
*/
struct kvmppc_vcore {
int n_runnable;
int num_threads;
- int entry_exit_count;
+ int entry_exit_map;
int napping_threads;
int first_vcpuid;
u16 pcpu;
@@ -296,8 +296,9 @@ struct kvmppc_vcore {
ulong conferring_threads;
};
-#define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff)
-#define VCORE_EXIT_COUNT(vc) ((vc)->entry_exit_count >> 8)
+#define VCORE_ENTRY_MAP(vc) ((vc)->entry_exit_map & 0xff)
+#define VCORE_EXIT_MAP(vc) ((vc)->entry_exit_map >> 8)
+#define VCORE_IS_EXITING(vc) (VCORE_EXIT_MAP(vc) != 0)
/* Values for vcore_state */
#define VCORE_INACTIVE 0
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8aa8246..0d07efb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -562,7 +562,7 @@ int main(void)
DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
- DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
+ DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6741505..1426459 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
/*
* Initialize *vc.
*/
- vc->entry_exit_count = 0;
+ vc->entry_exit_map = 0;
vc->preempt_tb = TB_NIL;
vc->in_guest = 0;
vc->napping_threads = 0;
@@ -2119,8 +2119,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
* this thread straight away and have it join in.
*/
if (!signal_pending(current)) {
- if (vc->vcore_state == VCORE_RUNNING &&
- VCORE_EXIT_COUNT(vc) == 0) {
+ if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) {
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
trace_kvm_guest_enter(vcpu);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 1954a1c..2754251 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -115,11 +115,11 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
int rv = H_SUCCESS; /* => don't yield */
set_bit(vcpu->arch.ptid, &vc->conferring_threads);
- while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) {
- threads_running = VCORE_ENTRY_COUNT(vc);
- threads_ceded = hweight32(vc->napping_threads);
- threads_conferring = hweight32(vc->conferring_threads);
- if (threads_ceded + threads_conferring >= threads_running) {
+ while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
+ threads_running = VCORE_ENTRY_MAP(vc);
+ threads_ceded = vc->napping_threads;
+ threads_conferring = vc->conferring_threads;
+ if ((threads_ceded | threads_conferring) == threads_running) {
rv = H_TOO_HARD; /* => do yield */
break;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc2ab3d..2edbf66 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -185,7 +185,7 @@ kvmppc_primary_no_guest:
or r3, r3, r0
stwcx. r3, 0, r6
bne 1b
- /* order napping_threads update vs testing entry_exit_count */
+ /* order napping_threads update vs testing entry_exit_map */
isync
li r12, 0
lwz r7, VCORE_ENTRY_EXIT(r5)
@@ -406,19 +406,21 @@ kvmppc_hv_entry:
* We don't have to lock against concurrent tlbies,
* but we do have to coordinate across hardware threads.
*/
- /* Increment entry count iff exit count is zero. */
- ld r5,HSTATE_KVM_VCORE(r13)
- addi r9,r5,VCORE_ENTRY_EXIT
-21: lwarx r3,0,r9
- cmpwi r3,0x100 /* any threads starting to exit? */
+ /* Set bit in entry map iff exit map is zero. */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ li r7, 1
+ lbz r6, HSTATE_PTID(r13)
+ sld r7, r7, r6
+ addi r9, r5, VCORE_ENTRY_EXIT
+21: lwarx r3, 0, r9
+ cmpwi r3, 0x100 /* any threads starting to exit? */
bge secondary_too_late /* if so we're too late to the party */
- addi r3,r3,1
- stwcx. r3,0,r9
+ or r3, r3, r7
+ stwcx. r3, 0, r9
bne 21b
/* Primary thread switches to guest partition. */
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
- lbz r6,HSTATE_PTID(r13)
cmpwi r6,0
bne 20f
ld r6,KVM_SDR1(r9)
@@ -1476,13 +1478,16 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
- /* Increment the threads-exiting-guest count in the 0xff00
- bits of vcore->entry_exit_count */
- ld r5,HSTATE_KVM_VCORE(r13)
- addi r6,r5,VCORE_ENTRY_EXIT
-41: lwarx r3,0,r6
- addi r0,r3,0x100
- stwcx. r0,0,r6
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r4, HSTATE_PTID(r13)
+ li r7, 0x100
+ sld r7, r7, r4
+ addi r6, r5, VCORE_ENTRY_EXIT
+41: lwarx r3, 0, r6
+ or r0, r3, r7
+ stwcx. r0, 0, r6
bne 41b
isync /* order stwcx. vs. reading napping_threads */
@@ -1491,9 +1496,9 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
* up to the kernel or qemu; we can't handle it in real mode.
* Thus we have to do a partition switch, so we have to
* collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we set the HDEC to 0,
- * which causes an HDEC interrupt in all threads within 2ns
- * because the HDEC register is shared between all 4 threads.
+ * to take an interrupt. To do this, we send a message or
+ * IPI to all the threads that have their bit set in the entry
+ * map in vcore->entry_exit_map (other than ourselves).
* However, we don't need to bother if this is an HDEC
* interrupt, since the other threads will already be on their
* way here in that case.
@@ -1502,17 +1507,8 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
bge 43f
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
beq 43f
- li r0,0
- mtspr SPRN_HDEC,r0
- /*
- * Send an IPI to any napping threads, since an HDEC interrupt
- * doesn't wake CPUs up from nap.
- */
- lwz r3,VCORE_NAPPING_THREADS(r5)
- lbz r4,HSTATE_PTID(r13)
- li r0,1
- sld r0,r0,r4
+ srwi r0,r7,8
andc. r3,r3,r0 /* no sense IPI'ing ourselves */
beq 43f
/* Order entry/exit update vs. IPIs */
@@ -2090,12 +2086,11 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
addi r6,r5,VCORE_NAPPING_THREADS
31: lwarx r4,0,r6
or r4,r4,r0
- PPC_POPCNTW(R7,R4)
- cmpw r7,r8
- bge kvm_cede_exit
+ cmpw r4,r8
+ beq kvm_cede_exit
stwcx. r4,0,r6
bne 31b
- /* order napping_threads update vs testing entry_exit_count */
+ /* order napping_threads update vs testing entry_exit_map */
isync
li r0,NAPPING_CEDE
stb r0,HSTATE_NAPPING(r13)
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 09/12] KVM: PPC: Book3S HV: Use bitmap of active threads rather than count
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
Currently, the entry_exit_count field in the kvmppc_vcore struct
contains two 8-bit counts, one of the threads that have started entering
the guest, and one of the threads that have started exiting the guest.
This changes it to an entry_exit_map field which contains two bitmaps
of 8 bits each. The advantage of doing this is that it gives us a
bitmap of which threads need to be signalled when exiting the guest.
That means that we no longer need to use the trick of setting the
HDEC to 0 to pull the other threads out of the guest, which led in
some cases to a spurious HDEC interrupt on the next guest entry.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 15 ++++----
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kvm/book3s_hv.c | 5 ++-
arch/powerpc/kvm/book3s_hv_builtin.c | 10 +++---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 61 +++++++++++++++------------------
5 files changed, 44 insertions(+), 49 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1517faa..d67a838 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -263,15 +263,15 @@ struct kvm_arch {
/*
* Struct for a virtual core.
- * Note: entry_exit_count combines an entry count in the bottom 8 bits
- * and an exit count in the next 8 bits. This is so that we can
- * atomically increment the entry count iff the exit count is 0
- * without taking the lock.
+ * Note: entry_exit_map combines a bitmap of threads that have entered
+ * in the bottom 8 bits and a bitmap of threads that have exited in the
+ * next 8 bits. This is so that we can atomically set the entry bit
+ * iff the exit map is 0 without taking a lock.
*/
struct kvmppc_vcore {
int n_runnable;
int num_threads;
- int entry_exit_count;
+ int entry_exit_map;
int napping_threads;
int first_vcpuid;
u16 pcpu;
@@ -296,8 +296,9 @@ struct kvmppc_vcore {
ulong conferring_threads;
};
-#define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff)
-#define VCORE_EXIT_COUNT(vc) ((vc)->entry_exit_count >> 8)
+#define VCORE_ENTRY_MAP(vc) ((vc)->entry_exit_map & 0xff)
+#define VCORE_EXIT_MAP(vc) ((vc)->entry_exit_map >> 8)
+#define VCORE_IS_EXITING(vc) (VCORE_EXIT_MAP(vc) != 0)
/* Values for vcore_state */
#define VCORE_INACTIVE 0
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8aa8246..0d07efb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -562,7 +562,7 @@ int main(void)
DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
- DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
+ DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6741505..1426459 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
/*
* Initialize *vc.
*/
- vc->entry_exit_count = 0;
+ vc->entry_exit_map = 0;
vc->preempt_tb = TB_NIL;
vc->in_guest = 0;
vc->napping_threads = 0;
@@ -2119,8 +2119,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
* this thread straight away and have it join in.
*/
if (!signal_pending(current)) {
- if (vc->vcore_state = VCORE_RUNNING &&
- VCORE_EXIT_COUNT(vc) = 0) {
+ if (vc->vcore_state = VCORE_RUNNING && !VCORE_IS_EXITING(vc)) {
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
trace_kvm_guest_enter(vcpu);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 1954a1c..2754251 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -115,11 +115,11 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
int rv = H_SUCCESS; /* => don't yield */
set_bit(vcpu->arch.ptid, &vc->conferring_threads);
- while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) = 0)) {
- threads_running = VCORE_ENTRY_COUNT(vc);
- threads_ceded = hweight32(vc->napping_threads);
- threads_conferring = hweight32(vc->conferring_threads);
- if (threads_ceded + threads_conferring >= threads_running) {
+ while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
+ threads_running = VCORE_ENTRY_MAP(vc);
+ threads_ceded = vc->napping_threads;
+ threads_conferring = vc->conferring_threads;
+ if ((threads_ceded | threads_conferring) = threads_running) {
rv = H_TOO_HARD; /* => do yield */
break;
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc2ab3d..2edbf66 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -185,7 +185,7 @@ kvmppc_primary_no_guest:
or r3, r3, r0
stwcx. r3, 0, r6
bne 1b
- /* order napping_threads update vs testing entry_exit_count */
+ /* order napping_threads update vs testing entry_exit_map */
isync
li r12, 0
lwz r7, VCORE_ENTRY_EXIT(r5)
@@ -406,19 +406,21 @@ kvmppc_hv_entry:
* We don't have to lock against concurrent tlbies,
* but we do have to coordinate across hardware threads.
*/
- /* Increment entry count iff exit count is zero. */
- ld r5,HSTATE_KVM_VCORE(r13)
- addi r9,r5,VCORE_ENTRY_EXIT
-21: lwarx r3,0,r9
- cmpwi r3,0x100 /* any threads starting to exit? */
+ /* Set bit in entry map iff exit map is zero. */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ li r7, 1
+ lbz r6, HSTATE_PTID(r13)
+ sld r7, r7, r6
+ addi r9, r5, VCORE_ENTRY_EXIT
+21: lwarx r3, 0, r9
+ cmpwi r3, 0x100 /* any threads starting to exit? */
bge secondary_too_late /* if so we're too late to the party */
- addi r3,r3,1
- stwcx. r3,0,r9
+ or r3, r3, r7
+ stwcx. r3, 0, r9
bne 21b
/* Primary thread switches to guest partition. */
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
- lbz r6,HSTATE_PTID(r13)
cmpwi r6,0
bne 20f
ld r6,KVM_SDR1(r9)
@@ -1476,13 +1478,16 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
- /* Increment the threads-exiting-guest count in the 0xff00
- bits of vcore->entry_exit_count */
- ld r5,HSTATE_KVM_VCORE(r13)
- addi r6,r5,VCORE_ENTRY_EXIT
-41: lwarx r3,0,r6
- addi r0,r3,0x100
- stwcx. r0,0,r6
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r4, HSTATE_PTID(r13)
+ li r7, 0x100
+ sld r7, r7, r4
+ addi r6, r5, VCORE_ENTRY_EXIT
+41: lwarx r3, 0, r6
+ or r0, r3, r7
+ stwcx. r0, 0, r6
bne 41b
isync /* order stwcx. vs. reading napping_threads */
@@ -1491,9 +1496,9 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
* up to the kernel or qemu; we can't handle it in real mode.
* Thus we have to do a partition switch, so we have to
* collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we set the HDEC to 0,
- * which causes an HDEC interrupt in all threads within 2ns
- * because the HDEC register is shared between all 4 threads.
+ * to take an interrupt. To do this, we send a message or
+ * IPI to all the threads that have their bit set in the entry
+ * map in vcore->entry_exit_map (other than ourselves).
* However, we don't need to bother if this is an HDEC
* interrupt, since the other threads will already be on their
* way here in that case.
@@ -1502,17 +1507,8 @@ kvmhv_do_exit: /* r12 = trap, r13 = paca */
bge 43f
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
beq 43f
- li r0,0
- mtspr SPRN_HDEC,r0
- /*
- * Send an IPI to any napping threads, since an HDEC interrupt
- * doesn't wake CPUs up from nap.
- */
- lwz r3,VCORE_NAPPING_THREADS(r5)
- lbz r4,HSTATE_PTID(r13)
- li r0,1
- sld r0,r0,r4
+ srwi r0,r7,8
andc. r3,r3,r0 /* no sense IPI'ing ourselves */
beq 43f
/* Order entry/exit update vs. IPIs */
@@ -2090,12 +2086,11 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
addi r6,r5,VCORE_NAPPING_THREADS
31: lwarx r4,0,r6
or r4,r4,r0
- PPC_POPCNTW(R7,R4)
- cmpw r7,r8
- bge kvm_cede_exit
+ cmpw r4,r8
+ beq kvm_cede_exit
stwcx. r4,0,r6
bne 31b
- /* order napping_threads update vs testing entry_exit_count */
+ /* order napping_threads update vs testing entry_exit_map */
isync
li r0,NAPPING_CEDE
stb r0,HSTATE_NAPPING(r13)
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 10/12] KVM: PPC: Book3S HV: Streamline guest entry and exit
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
On entry to the guest, secondary threads now wait for the primary to
switch the MMU after loading up most of their state, rather than before.
This means that the secondary threads get into the guest sooner, in the
common case where the secondary threads get to kvmppc_hv_entry before
the primary thread.
On exit, the first thread out increments the exit count and interrupts
the other threads (to get them out of the guest) before saving most
of its state, rather than after. That means that the other threads
exit sooner and means that the first thread doesn't spend so much
time waiting for the other threads at the point where the MMU gets
switched back to the host.
This pulls out the code that increments the exit count and interrupts
other threads into a separate function, kvmhv_commence_exit().
This also makes sure that r12 and vcpu->arch.trap are set correctly
in some corner cases.
Statistics from /sys/kernel/debug/kvm/vm*/vcpu*/timings show the
improvement. Aggregating across vcpus for a guest with 32 vcpus,
8 threads/vcore, running on a POWER8, gives this before the change:
rm_entry: avg 4537.3ns (222 - 48444, 1068878 samples)
rm_exit: avg 4787.6ns (152 - 165490, 1010717 samples)
rm_intr: avg 1673.6ns (12 - 341304, 3818691 samples)
and this after the change:
rm_entry: avg 3427.7ns (232 - 68150, 1118921 samples)
rm_exit: avg 4716.0ns (12 - 150720, 1119477 samples)
rm_intr: avg 1614.8ns (12 - 522436, 3850432 samples)
showing a substantial reduction in the time spent per guest entry in
the real-mode guest entry code, and smaller reductions in the real
mode guest exit and interrupt handling times. (The test was to start
the guest and boot Fedora 20 big-endian to the login prompt.)
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 212 +++++++++++++++++++-------------
1 file changed, 126 insertions(+), 86 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2edbf66..7074783 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -175,6 +175,19 @@ kvmppc_primary_no_guest:
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
mfspr r3, SPRN_HDEC
mtspr SPRN_DEC, r3
+ /*
+ * Make sure the primary has finished the MMU switch.
+ * We should never get here on a secondary thread, but
+ * check it for robustness' sake.
+ */
+ ld r5, HSTATE_KVM_VCORE(r13)
+65: lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ beq 65b
+ /* Set LPCR. */
+ ld r8,VCORE_LPCR(r5)
+ mtspr SPRN_LPCR,r8
+ isync
/* set our bit in napping_threads */
ld r5, HSTATE_KVM_VCORE(r13)
lbz r7, HSTATE_PTID(r13)
@@ -206,7 +219,7 @@ kvm_novcpu_wakeup:
/* check the wake reason */
bl kvmppc_check_wake_reason
-
+
/* see if any other thread is already exiting */
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
@@ -244,7 +257,15 @@ kvm_novcpu_wakeup:
b kvmppc_got_guest
kvm_novcpu_exit:
- b hdec_soon
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 13f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+#endif
+13: bl kvmhv_commence_exit
+ b kvmhv_switch_to_host
/*
* We come in here when wakened from nap mode.
@@ -422,7 +443,7 @@ kvmppc_hv_entry:
/* Primary thread switches to guest partition. */
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
cmpwi r6,0
- bne 20f
+ bne 10f
ld r6,KVM_SDR1(r9)
lwz r7,KVM_LPID(r9)
li r0,LPID_RSVD /* switch to reserved LPID */
@@ -493,26 +514,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r0,1
stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */
- b 10f
-
- /* Secondary threads wait for primary to have done partition switch */
-20: lbz r0,VCORE_IN_GUEST(r5)
- cmpwi r0,0
- beq 20b
-
- /* Set LPCR. */
-10: ld r8,VCORE_LPCR(r5)
- mtspr SPRN_LPCR,r8
- isync
-
- /* Check if HDEC expires soon */
- mfspr r3,SPRN_HDEC
- cmpwi r3,512 /* 1 microsecond */
- li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- blt hdec_soon
/* Do we have a guest vcpu to run? */
- cmpdi r4, 0
+10: cmpdi r4, 0
beq kvmppc_primary_no_guest
kvmppc_got_guest:
@@ -837,6 +841,30 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
clrrdi r6,r6,1
mtspr SPRN_CTRLT,r6
4:
+ /* Secondary threads wait for primary to have done partition switch */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r6, HSTATE_PTID(r13)
+ cmpwi r6, 0
+ beq 21f
+ lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ bne 21f
+ HMT_LOW
+20: lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ beq 20b
+ HMT_MEDIUM
+21:
+ /* Set LPCR. */
+ ld r8,VCORE_LPCR(r5)
+ mtspr SPRN_LPCR,r8
+ isync
+
+ /* Check if HDEC expires soon */
+ mfspr r3, SPRN_HDEC
+ cmpwi r3, 512 /* 1 microsecond */
+ blt hdec_soon
+
ld r6, VCPU_CTR(r4)
lwz r7, VCPU_XER(r4)
@@ -942,22 +970,26 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+ li r12, 0
cmpdi r4, 0
beq 11f
+ stw r12, VCPU_TRAP(r4)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
+#endif
11: b kvmhv_switch_to_host
hdec_soon:
- ld r4, HSTATE_KVM_VCPU(r13)
- cmpdi r4, 0
- beq 12f
+ li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+ stw r12, VCPU_TRAP(r4)
+ mr r9, r4
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
-12: b kvmhv_do_exit
#endif
+ b guest_exit_cont
/******************************************************************************
* *
@@ -1112,7 +1144,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
stw r7, VCPU_DSISR(r9)
/* don't overwrite fault_dar/fault_dsisr if HDSI */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
- beq 6f
+ beq mc_cont
std r6, VCPU_FAULT_DAR(r9)
stw r7, VCPU_FAULT_DSISR(r9)
@@ -1126,8 +1158,11 @@ mc_cont:
bl kvmhv_accumulate_time
#endif
+ /* Increment exit count, poke other threads to exit */
+ bl kvmhv_commence_exit
+
/* Save guest CTRL register, set runlatch to 1 */
-6: mfspr r6,SPRN_CTRLF
+ mfspr r6,SPRN_CTRLF
stw r6,VCPU_CTRL(r9)
andi. r0,r6,1
bne 4f
@@ -1469,68 +1504,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-hdec_soon:
-#endif
-kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
- /* Set our bit in the threads-exiting-guest map in the 0xff00
- bits of vcore->entry_exit_map */
- ld r5, HSTATE_KVM_VCORE(r13)
- lbz r4, HSTATE_PTID(r13)
- li r7, 0x100
- sld r7, r7, r4
- addi r6, r5, VCORE_ENTRY_EXIT
-41: lwarx r3, 0, r6
- or r0, r3, r7
- stwcx. r0, 0, r6
- bne 41b
- isync /* order stwcx. vs. reading napping_threads */
-
- /*
- * At this point we have an interrupt that we have to pass
- * up to the kernel or qemu; we can't handle it in real mode.
- * Thus we have to do a partition switch, so we have to
- * collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we send a message or
- * IPI to all the threads that have their bit set in the entry
- * map in vcore->entry_exit_map (other than ourselves).
- * However, we don't need to bother if this is an HDEC
- * interrupt, since the other threads will already be on their
- * way here in that case.
- */
- cmpwi r3,0x100 /* Are we the first here? */
- bge 43f
- cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 43f
-
- srwi r0,r7,8
- andc. r3,r3,r0 /* no sense IPI'ing ourselves */
- beq 43f
- /* Order entry/exit update vs. IPIs */
- sync
- mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
- subf r6,r4,r13
-42: andi. r0,r3,1
- beq 44f
- ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
- li r0,IPI_PRIORITY
- li r7,XICS_MFRR
- stbcix r0,r7,r8 /* trigger the IPI */
-44: srdi. r3,r3,1
- addi r6,r6,PACA_SIZE
- bne 42b
-
-#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-secondary_too_late:
-#endif
kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
-43: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
lbz r3,HSTATE_PTID(r13)
cmpwi r3,0
@@ -1632,6 +1613,63 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtlr r0
blr
+kvmhv_commence_exit: /* r12 = trap, r13 = paca, doesn't trash r9 */
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+ stdu r1, -PPC_MIN_STKFRM(r1)
+
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r4, HSTATE_PTID(r13)
+ li r7, 0x100
+ sld r7, r7, r4
+ addi r6, r5, VCORE_ENTRY_EXIT
+41: lwarx r3, 0, r6
+ or r0, r3, r7
+ stwcx. r0, 0, r6
+ bne 41b
+ isync /* order stwcx. vs. reading napping_threads */
+
+ /*
+ * At this point we have an interrupt that we have to pass
+ * up to the kernel or qemu; we can't handle it in real mode.
+ * Thus we have to do a partition switch, so we have to
+ * collect the other threads, if we are the first thread
+ * to take an interrupt. To do this, we send a message or
+ * IPI to all the threads that have their bit set in the entry
+ * map in vcore->entry_exit_map (other than ourselves).
+ * However, we don't need to bother if this is an HDEC
+ * interrupt, since the other threads will already be on their
+ * way here in that case.
+ */
+ cmpwi r3,0x100 /* Are we the first here? */
+ bge 43f
+ cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+ beq 43f
+
+ srwi r0,r7,8
+ andc. r3,r3,r0 /* no sense IPI'ing ourselves */
+ beq 43f
+ /* Order entry/exit update vs. IPIs */
+ sync
+ mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
+ subf r6,r4,r13
+42: andi. r0,r3,1
+ beq 44f
+ ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
+ li r0,IPI_PRIORITY
+ li r7,XICS_MFRR
+ stbcix r0,r7,r8 /* trigger the IPI */
+44: srdi. r3,r3,1
+ addi r6,r6,PACA_SIZE
+ bne 42b
+
+43: ld r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
+ addi r1, r1, PPC_MIN_STKFRM
+ mtlr r0
+ blr
+
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
@@ -2067,8 +2105,8 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
lbz r5,VCPU_PRODDED(r3)
cmpwi r5,0
bne kvm_cede_prodded
- li r0,0 /* set trap to 0 to say hcall is handled */
- stw r0,VCPU_TRAP(r3)
+ li r12,0 /* set trap to 0 to say hcall is handled */
+ stw r12,VCPU_TRAP(r3)
li r0,H_SUCCESS
std r0,VCPU_GPR(R3)(r3)
@@ -2274,7 +2312,8 @@ kvm_cede_prodded:
/* we've ceded but we want to give control to the host */
kvm_cede_exit:
- b hcall_real_fallback
+ ld r9, HSTATE_KVM_VCPU(r13)
+ b guest_exit_cont
/* Try to handle a machine check in real mode */
machine_check_realmode:
@@ -2404,6 +2443,7 @@ kvmppc_read_intr:
bne- 43f
/* OK, it's an IPI for us */
+ li r12, 0
li r3, -1
1: blr
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 10/12] KVM: PPC: Book3S HV: Streamline guest entry and exit
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
On entry to the guest, secondary threads now wait for the primary to
switch the MMU after loading up most of their state, rather than before.
This means that the secondary threads get into the guest sooner, in the
common case where the secondary threads get to kvmppc_hv_entry before
the primary thread.
On exit, the first thread out increments the exit count and interrupts
the other threads (to get them out of the guest) before saving most
of its state, rather than after. That means that the other threads
exit sooner and means that the first thread doesn't spend so much
time waiting for the other threads at the point where the MMU gets
switched back to the host.
This pulls out the code that increments the exit count and interrupts
other threads into a separate function, kvmhv_commence_exit().
This also makes sure that r12 and vcpu->arch.trap are set correctly
in some corner cases.
Statistics from /sys/kernel/debug/kvm/vm*/vcpu*/timings show the
improvement. Aggregating across vcpus for a guest with 32 vcpus,
8 threads/vcore, running on a POWER8, gives this before the change:
rm_entry: avg 4537.3ns (222 - 48444, 1068878 samples)
rm_exit: avg 4787.6ns (152 - 165490, 1010717 samples)
rm_intr: avg 1673.6ns (12 - 341304, 3818691 samples)
and this after the change:
rm_entry: avg 3427.7ns (232 - 68150, 1118921 samples)
rm_exit: avg 4716.0ns (12 - 150720, 1119477 samples)
rm_intr: avg 1614.8ns (12 - 522436, 3850432 samples)
showing a substantial reduction in the time spent per guest entry in
the real-mode guest entry code, and smaller reductions in the real
mode guest exit and interrupt handling times. (The test was to start
the guest and boot Fedora 20 big-endian to the login prompt.)
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 212 +++++++++++++++++++-------------
1 file changed, 126 insertions(+), 86 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2edbf66..7074783 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -175,6 +175,19 @@ kvmppc_primary_no_guest:
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
mfspr r3, SPRN_HDEC
mtspr SPRN_DEC, r3
+ /*
+ * Make sure the primary has finished the MMU switch.
+ * We should never get here on a secondary thread, but
+ * check it for robustness' sake.
+ */
+ ld r5, HSTATE_KVM_VCORE(r13)
+65: lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ beq 65b
+ /* Set LPCR. */
+ ld r8,VCORE_LPCR(r5)
+ mtspr SPRN_LPCR,r8
+ isync
/* set our bit in napping_threads */
ld r5, HSTATE_KVM_VCORE(r13)
lbz r7, HSTATE_PTID(r13)
@@ -206,7 +219,7 @@ kvm_novcpu_wakeup:
/* check the wake reason */
bl kvmppc_check_wake_reason
-
+
/* see if any other thread is already exiting */
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
@@ -244,7 +257,15 @@ kvm_novcpu_wakeup:
b kvmppc_got_guest
kvm_novcpu_exit:
- b hdec_soon
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 13f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+#endif
+13: bl kvmhv_commence_exit
+ b kvmhv_switch_to_host
/*
* We come in here when wakened from nap mode.
@@ -422,7 +443,7 @@ kvmppc_hv_entry:
/* Primary thread switches to guest partition. */
ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
cmpwi r6,0
- bne 20f
+ bne 10f
ld r6,KVM_SDR1(r9)
lwz r7,KVM_LPID(r9)
li r0,LPID_RSVD /* switch to reserved LPID */
@@ -493,26 +514,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
li r0,1
stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */
- b 10f
-
- /* Secondary threads wait for primary to have done partition switch */
-20: lbz r0,VCORE_IN_GUEST(r5)
- cmpwi r0,0
- beq 20b
-
- /* Set LPCR. */
-10: ld r8,VCORE_LPCR(r5)
- mtspr SPRN_LPCR,r8
- isync
-
- /* Check if HDEC expires soon */
- mfspr r3,SPRN_HDEC
- cmpwi r3,512 /* 1 microsecond */
- li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- blt hdec_soon
/* Do we have a guest vcpu to run? */
- cmpdi r4, 0
+10: cmpdi r4, 0
beq kvmppc_primary_no_guest
kvmppc_got_guest:
@@ -837,6 +841,30 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
clrrdi r6,r6,1
mtspr SPRN_CTRLT,r6
4:
+ /* Secondary threads wait for primary to have done partition switch */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r6, HSTATE_PTID(r13)
+ cmpwi r6, 0
+ beq 21f
+ lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ bne 21f
+ HMT_LOW
+20: lbz r0, VCORE_IN_GUEST(r5)
+ cmpwi r0, 0
+ beq 20b
+ HMT_MEDIUM
+21:
+ /* Set LPCR. */
+ ld r8,VCORE_LPCR(r5)
+ mtspr SPRN_LPCR,r8
+ isync
+
+ /* Check if HDEC expires soon */
+ mfspr r3, SPRN_HDEC
+ cmpwi r3, 512 /* 1 microsecond */
+ blt hdec_soon
+
ld r6, VCPU_CTR(r4)
lwz r7, VCPU_XER(r4)
@@ -942,22 +970,26 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+ li r12, 0
cmpdi r4, 0
beq 11f
+ stw r12, VCPU_TRAP(r4)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
+#endif
11: b kvmhv_switch_to_host
hdec_soon:
- ld r4, HSTATE_KVM_VCPU(r13)
- cmpdi r4, 0
- beq 12f
+ li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+ stw r12, VCPU_TRAP(r4)
+ mr r9, r4
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
-12: b kvmhv_do_exit
#endif
+ b guest_exit_cont
/******************************************************************************
* *
@@ -1112,7 +1144,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
stw r7, VCPU_DSISR(r9)
/* don't overwrite fault_dar/fault_dsisr if HDSI */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
- beq 6f
+ beq mc_cont
std r6, VCPU_FAULT_DAR(r9)
stw r7, VCPU_FAULT_DSISR(r9)
@@ -1126,8 +1158,11 @@ mc_cont:
bl kvmhv_accumulate_time
#endif
+ /* Increment exit count, poke other threads to exit */
+ bl kvmhv_commence_exit
+
/* Save guest CTRL register, set runlatch to 1 */
-6: mfspr r6,SPRN_CTRLF
+ mfspr r6,SPRN_CTRLF
stw r6,VCPU_CTRL(r9)
andi. r0,r6,1
bne 4f
@@ -1469,68 +1504,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-hdec_soon:
-#endif
-kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
- /* Set our bit in the threads-exiting-guest map in the 0xff00
- bits of vcore->entry_exit_map */
- ld r5, HSTATE_KVM_VCORE(r13)
- lbz r4, HSTATE_PTID(r13)
- li r7, 0x100
- sld r7, r7, r4
- addi r6, r5, VCORE_ENTRY_EXIT
-41: lwarx r3, 0, r6
- or r0, r3, r7
- stwcx. r0, 0, r6
- bne 41b
- isync /* order stwcx. vs. reading napping_threads */
-
- /*
- * At this point we have an interrupt that we have to pass
- * up to the kernel or qemu; we can't handle it in real mode.
- * Thus we have to do a partition switch, so we have to
- * collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we send a message or
- * IPI to all the threads that have their bit set in the entry
- * map in vcore->entry_exit_map (other than ourselves).
- * However, we don't need to bother if this is an HDEC
- * interrupt, since the other threads will already be on their
- * way here in that case.
- */
- cmpwi r3,0x100 /* Are we the first here? */
- bge 43f
- cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 43f
-
- srwi r0,r7,8
- andc. r3,r3,r0 /* no sense IPI'ing ourselves */
- beq 43f
- /* Order entry/exit update vs. IPIs */
- sync
- mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
- subf r6,r4,r13
-42: andi. r0,r3,1
- beq 44f
- ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
- li r0,IPI_PRIORITY
- li r7,XICS_MFRR
- stbcix r0,r7,r8 /* trigger the IPI */
-44: srdi. r3,r3,1
- addi r6,r6,PACA_SIZE
- bne 42b
-
-#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
-secondary_too_late:
-#endif
kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
-43: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
lbz r3,HSTATE_PTID(r13)
cmpwi r3,0
@@ -1632,6 +1613,63 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtlr r0
blr
+kvmhv_commence_exit: /* r12 = trap, r13 = paca, doesn't trash r9 */
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+ stdu r1, -PPC_MIN_STKFRM(r1)
+
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r4, HSTATE_PTID(r13)
+ li r7, 0x100
+ sld r7, r7, r4
+ addi r6, r5, VCORE_ENTRY_EXIT
+41: lwarx r3, 0, r6
+ or r0, r3, r7
+ stwcx. r0, 0, r6
+ bne 41b
+ isync /* order stwcx. vs. reading napping_threads */
+
+ /*
+ * At this point we have an interrupt that we have to pass
+ * up to the kernel or qemu; we can't handle it in real mode.
+ * Thus we have to do a partition switch, so we have to
+ * collect the other threads, if we are the first thread
+ * to take an interrupt. To do this, we send a message or
+ * IPI to all the threads that have their bit set in the entry
+ * map in vcore->entry_exit_map (other than ourselves).
+ * However, we don't need to bother if this is an HDEC
+ * interrupt, since the other threads will already be on their
+ * way here in that case.
+ */
+ cmpwi r3,0x100 /* Are we the first here? */
+ bge 43f
+ cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+ beq 43f
+
+ srwi r0,r7,8
+ andc. r3,r3,r0 /* no sense IPI'ing ourselves */
+ beq 43f
+ /* Order entry/exit update vs. IPIs */
+ sync
+ mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
+ subf r6,r4,r13
+42: andi. r0,r3,1
+ beq 44f
+ ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
+ li r0,IPI_PRIORITY
+ li r7,XICS_MFRR
+ stbcix r0,r7,r8 /* trigger the IPI */
+44: srdi. r3,r3,1
+ addi r6,r6,PACA_SIZE
+ bne 42b
+
+43: ld r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
+ addi r1, r1, PPC_MIN_STKFRM
+ mtlr r0
+ blr
+
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
@@ -2067,8 +2105,8 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
lbz r5,VCPU_PRODDED(r3)
cmpwi r5,0
bne kvm_cede_prodded
- li r0,0 /* set trap to 0 to say hcall is handled */
- stw r0,VCPU_TRAP(r3)
+ li r12,0 /* set trap to 0 to say hcall is handled */
+ stw r12,VCPU_TRAP(r3)
li r0,H_SUCCESS
std r0,VCPU_GPR(R3)(r3)
@@ -2274,7 +2312,8 @@ kvm_cede_prodded:
/* we've ceded but we want to give control to the host */
kvm_cede_exit:
- b hcall_real_fallback
+ ld r9, HSTATE_KVM_VCPU(r13)
+ b guest_exit_cont
/* Try to handle a machine check in real mode */
machine_check_realmode:
@@ -2404,6 +2443,7 @@ kvmppc_read_intr:
bne- 43f
/* OK, it's an IPI for us */
+ li r12, 0
li r3, -1
1: blr
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 11/12] KVM: PPC: Book3S HV: Translate kvmhv_commence_exit to C
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This replaces the assembler code for kvmhv_commence_exit() with C code
in book3s_hv_builtin.c. It also moves the IPI sending code that was
in book3s_hv_rm_xics.c into a new kvmhv_rm_send_ipi() function so it
can be used by kvmhv_commence_exit() as well as icp_rm_set_vcpu_irq().
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 2 +
arch/powerpc/kvm/book3s_hv_builtin.c | 63 ++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rm_xics.c | 12 +-----
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 66 ++++----------------------------
4 files changed, 75 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 869c53f..2b84e48 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -438,6 +438,8 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+extern void kvmhv_rm_send_ipi(int cpu);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 2754251..c42aa55 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -22,6 +22,7 @@
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
+#include <asm/xics.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -184,3 +185,65 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
return H_HARDWARE;
}
+
+static inline void rm_writeb(unsigned long paddr, u8 val)
+{
+ __asm__ __volatile__("stbcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
+/*
+ * Send an interrupt to another CPU.
+ * This can only be called in real mode.
+ * The caller needs to include any barrier needed to order writes
+ * to memory vs. the IPI/message.
+ */
+void kvmhv_rm_send_ipi(int cpu)
+{
+ unsigned long xics_phys;
+
+ /* Poke the target */
+ xics_phys = paca[cpu].kvm_hstate.xics_phys;
+ rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+}
+
+/*
+ * The following functions are called from the assembly code
+ * in book3s_hv_rmhandlers.S.
+ */
+static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
+{
+ int cpu = vc->pcpu;
+
+ /* Order setting of exit map vs. msgsnd/IPI */
+ smp_mb();
+ for (; active; active >>= 1, ++cpu)
+ if (active & 1)
+ kvmhv_rm_send_ipi(cpu);
+}
+
+void kvmhv_commence_exit(int trap)
+{
+ struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
+ int ptid = local_paca->kvm_hstate.ptid;
+ int me, ee;
+
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ me = 0x100 << ptid;
+ do {
+ ee = vc->entry_exit_map;
+ } while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
+
+ /* Are we the first here? */
+ if ((ee >> 8) != 0)
+ return;
+
+ /*
+ * Trigger the other threads in this vcore to exit the guest.
+ * If this is a hypervisor decrementer interrupt then they
+ * will be already on their way out of the guest.
+ */
+ if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
+ kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 6dded8c..00e45b6 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -26,12 +26,6 @@
static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
u32 new_irq);
-static inline void rm_writeb(unsigned long paddr, u8 val)
-{
- __asm__ __volatile__("sync; stbcix %0,0,%1"
- : : "r" (val), "r" (paddr) : "memory");
-}
-
/* -- ICS routines -- */
static void ics_rm_check_resend(struct kvmppc_xics *xics,
struct kvmppc_ics *ics, struct kvmppc_icp *icp)
@@ -60,7 +54,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
struct kvm_vcpu *this_vcpu)
{
struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
- unsigned long xics_phys;
int cpu;
/* Mark the target VCPU as having an interrupt pending */
@@ -83,9 +76,8 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
/* In SMT cpu will always point to thread 0, we adjust it */
cpu += vcpu->arch.ptid;
- /* Not too hard, then poke the target */
- xics_phys = paca[cpu].kvm_hstate.xics_phys;
- rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ smp_mb();
+ kvmhv_rm_send_ipi(cpu);
}
static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7074783..13e7523 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -264,7 +264,11 @@ kvm_novcpu_exit:
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
-13: bl kvmhv_commence_exit
+13: mr r3, r12
+ stw r12, 112-4(r1)
+ bl kvmhv_commence_exit
+ nop
+ lwz r12, 112-4(r1)
b kvmhv_switch_to_host
/*
@@ -1160,6 +1164,9 @@ mc_cont:
/* Increment exit count, poke other threads to exit */
bl kvmhv_commence_exit
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+ lwz r12, VCPU_TRAP(r9)
/* Save guest CTRL register, set runlatch to 1 */
mfspr r6,SPRN_CTRLF
@@ -1613,63 +1620,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtlr r0
blr
-kvmhv_commence_exit: /* r12 = trap, r13 = paca, doesn't trash r9 */
- mflr r0
- std r0, PPC_LR_STKOFF(r1)
- stdu r1, -PPC_MIN_STKFRM(r1)
-
- /* Set our bit in the threads-exiting-guest map in the 0xff00
- bits of vcore->entry_exit_map */
- ld r5, HSTATE_KVM_VCORE(r13)
- lbz r4, HSTATE_PTID(r13)
- li r7, 0x100
- sld r7, r7, r4
- addi r6, r5, VCORE_ENTRY_EXIT
-41: lwarx r3, 0, r6
- or r0, r3, r7
- stwcx. r0, 0, r6
- bne 41b
- isync /* order stwcx. vs. reading napping_threads */
-
- /*
- * At this point we have an interrupt that we have to pass
- * up to the kernel or qemu; we can't handle it in real mode.
- * Thus we have to do a partition switch, so we have to
- * collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we send a message or
- * IPI to all the threads that have their bit set in the entry
- * map in vcore->entry_exit_map (other than ourselves).
- * However, we don't need to bother if this is an HDEC
- * interrupt, since the other threads will already be on their
- * way here in that case.
- */
- cmpwi r3,0x100 /* Are we the first here? */
- bge 43f
- cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 43f
-
- srwi r0,r7,8
- andc. r3,r3,r0 /* no sense IPI'ing ourselves */
- beq 43f
- /* Order entry/exit update vs. IPIs */
- sync
- mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
- subf r6,r4,r13
-42: andi. r0,r3,1
- beq 44f
- ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
- li r0,IPI_PRIORITY
- li r7,XICS_MFRR
- stbcix r0,r7,r8 /* trigger the IPI */
-44: srdi. r3,r3,1
- addi r6,r6,PACA_SIZE
- bne 42b
-
-43: ld r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
- addi r1, r1, PPC_MIN_STKFRM
- mtlr r0
- blr
-
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 11/12] KVM: PPC: Book3S HV: Translate kvmhv_commence_exit to C
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This replaces the assembler code for kvmhv_commence_exit() with C code
in book3s_hv_builtin.c. It also moves the IPI sending code that was
in book3s_hv_rm_xics.c into a new kvmhv_rm_send_ipi() function so it
can be used by kvmhv_commence_exit() as well as icp_rm_set_vcpu_irq().
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 2 +
arch/powerpc/kvm/book3s_hv_builtin.c | 63 ++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rm_xics.c | 12 +-----
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 66 ++++----------------------------
4 files changed, 75 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 869c53f..2b84e48 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -438,6 +438,8 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+extern void kvmhv_rm_send_ipi(int cpu);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 2754251..c42aa55 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -22,6 +22,7 @@
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
+#include <asm/xics.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -184,3 +185,65 @@ long kvmppc_h_random(struct kvm_vcpu *vcpu)
return H_HARDWARE;
}
+
+static inline void rm_writeb(unsigned long paddr, u8 val)
+{
+ __asm__ __volatile__("stbcix %0,0,%1"
+ : : "r" (val), "r" (paddr) : "memory");
+}
+
+/*
+ * Send an interrupt to another CPU.
+ * This can only be called in real mode.
+ * The caller needs to include any barrier needed to order writes
+ * to memory vs. the IPI/message.
+ */
+void kvmhv_rm_send_ipi(int cpu)
+{
+ unsigned long xics_phys;
+
+ /* Poke the target */
+ xics_phys = paca[cpu].kvm_hstate.xics_phys;
+ rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+}
+
+/*
+ * The following functions are called from the assembly code
+ * in book3s_hv_rmhandlers.S.
+ */
+static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
+{
+ int cpu = vc->pcpu;
+
+ /* Order setting of exit map vs. msgsnd/IPI */
+ smp_mb();
+ for (; active; active >>= 1, ++cpu)
+ if (active & 1)
+ kvmhv_rm_send_ipi(cpu);
+}
+
+void kvmhv_commence_exit(int trap)
+{
+ struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
+ int ptid = local_paca->kvm_hstate.ptid;
+ int me, ee;
+
+ /* Set our bit in the threads-exiting-guest map in the 0xff00
+ bits of vcore->entry_exit_map */
+ me = 0x100 << ptid;
+ do {
+ ee = vc->entry_exit_map;
+ } while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
+
+ /* Are we the first here? */
+ if ((ee >> 8) != 0)
+ return;
+
+ /*
+ * Trigger the other threads in this vcore to exit the guest.
+ * If this is a hypervisor decrementer interrupt then they
+ * will be already on their way out of the guest.
+ */
+ if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
+ kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 6dded8c..00e45b6 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -26,12 +26,6 @@
static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
u32 new_irq);
-static inline void rm_writeb(unsigned long paddr, u8 val)
-{
- __asm__ __volatile__("sync; stbcix %0,0,%1"
- : : "r" (val), "r" (paddr) : "memory");
-}
-
/* -- ICS routines -- */
static void ics_rm_check_resend(struct kvmppc_xics *xics,
struct kvmppc_ics *ics, struct kvmppc_icp *icp)
@@ -60,7 +54,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
struct kvm_vcpu *this_vcpu)
{
struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
- unsigned long xics_phys;
int cpu;
/* Mark the target VCPU as having an interrupt pending */
@@ -83,9 +76,8 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
/* In SMT cpu will always point to thread 0, we adjust it */
cpu += vcpu->arch.ptid;
- /* Not too hard, then poke the target */
- xics_phys = paca[cpu].kvm_hstate.xics_phys;
- rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+ smp_mb();
+ kvmhv_rm_send_ipi(cpu);
}
static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7074783..13e7523 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -264,7 +264,11 @@ kvm_novcpu_exit:
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
-13: bl kvmhv_commence_exit
+13: mr r3, r12
+ stw r12, 112-4(r1)
+ bl kvmhv_commence_exit
+ nop
+ lwz r12, 112-4(r1)
b kvmhv_switch_to_host
/*
@@ -1160,6 +1164,9 @@ mc_cont:
/* Increment exit count, poke other threads to exit */
bl kvmhv_commence_exit
+ nop
+ ld r9, HSTATE_KVM_VCPU(r13)
+ lwz r12, VCPU_TRAP(r9)
/* Save guest CTRL register, set runlatch to 1 */
mfspr r6,SPRN_CTRLF
@@ -1613,63 +1620,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtlr r0
blr
-kvmhv_commence_exit: /* r12 = trap, r13 = paca, doesn't trash r9 */
- mflr r0
- std r0, PPC_LR_STKOFF(r1)
- stdu r1, -PPC_MIN_STKFRM(r1)
-
- /* Set our bit in the threads-exiting-guest map in the 0xff00
- bits of vcore->entry_exit_map */
- ld r5, HSTATE_KVM_VCORE(r13)
- lbz r4, HSTATE_PTID(r13)
- li r7, 0x100
- sld r7, r7, r4
- addi r6, r5, VCORE_ENTRY_EXIT
-41: lwarx r3, 0, r6
- or r0, r3, r7
- stwcx. r0, 0, r6
- bne 41b
- isync /* order stwcx. vs. reading napping_threads */
-
- /*
- * At this point we have an interrupt that we have to pass
- * up to the kernel or qemu; we can't handle it in real mode.
- * Thus we have to do a partition switch, so we have to
- * collect the other threads, if we are the first thread
- * to take an interrupt. To do this, we send a message or
- * IPI to all the threads that have their bit set in the entry
- * map in vcore->entry_exit_map (other than ourselves).
- * However, we don't need to bother if this is an HDEC
- * interrupt, since the other threads will already be on their
- * way here in that case.
- */
- cmpwi r3,0x100 /* Are we the first here? */
- bge 43f
- cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- beq 43f
-
- srwi r0,r7,8
- andc. r3,r3,r0 /* no sense IPI'ing ourselves */
- beq 43f
- /* Order entry/exit update vs. IPIs */
- sync
- mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
- subf r6,r4,r13
-42: andi. r0,r3,1
- beq 44f
- ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
- li r0,IPI_PRIORITY
- li r7,XICS_MFRR
- stbcix r0,r7,r8 /* trigger the IPI */
-44: srdi. r3,r3,1
- addi r6,r6,PACA_SIZE
- bne 42b
-
-43: ld r0, PPC_MIN_STKFRM+PPC_LR_STKOFF(r1)
- addi r1, r1, PPC_MIN_STKFRM
- mtlr r0
- blr
-
/*
* Check whether an HDSI is an HPTE not found fault or something else.
* If it is an HPTE not found fault that is due to the guest accessing
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 12/12] KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
2015-03-27 3:29 ` Paul Mackerras
@ 2015-03-27 3:29 ` Paul Mackerras
-1 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Note that this patch depends on the patch "powerpc/powernv: Fixes for
hypervisor doorbell handling", which is now upstream in Linus' tree as
commit 755563bc79c7, for the definition of PPC_MSGCLR().
arch/powerpc/kernel/asm-offsets.c | 3 ++
arch/powerpc/kvm/book3s_hv.c | 51 ++++++++++++++++++++++-----------
arch/powerpc/kvm/book3s_hv_builtin.c | 16 +++++++++--
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 22 ++++++++++++--
4 files changed, 70 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0d07efb..0034b6b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -37,6 +37,7 @@
#include <asm/thread_info.h>
#include <asm/rtas.h>
#include <asm/vdso_datapage.h>
+#include <asm/dbell.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/lppaca.h>
@@ -759,5 +760,7 @@ int main(void)
offsetof(struct paca_struct, subcore_sibling_mask));
#endif
+ DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
+
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1426459..bb29e75 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -51,6 +51,7 @@
#include <asm/hvcall.h>
#include <asm/switch_to.h>
#include <asm/smp.h>
+#include <asm/dbell.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -84,9 +85,35 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
+static bool kvmppc_ipi_thread(int cpu)
+{
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ preempt_disable();
+ if (cpu_first_thread_sibling(cpu) ==
+ cpu_first_thread_sibling(smp_processor_id())) {
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ msg |= cpu_thread_in_core(cpu);
+ smp_mb();
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ preempt_enable();
+ return true;
+ }
+ preempt_enable();
+ }
+
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
+ if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
+ xics_wake_cpu(cpu);
+ return true;
+ }
+#endif
+
+ return false;
+}
+
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
- int me;
int cpu = vcpu->cpu;
wait_queue_head_t *wqp;
@@ -96,20 +123,12 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
++vcpu->stat.halt_wakeup;
}
- me = get_cpu();
+ if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
+ return;
/* CPU points to the first thread of the core */
- if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_PPC_ICP_NATIVE
- int real_cpu = cpu + vcpu->arch.ptid;
- if (paca[real_cpu].kvm_hstate.xics_phys)
- xics_wake_cpu(real_cpu);
- else
-#endif
- if (cpu_online(cpu))
- smp_send_reschedule(cpu);
- }
- put_cpu();
+ if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
+ smp_send_reschedule(cpu);
}
/*
@@ -1781,10 +1800,8 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
/* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
smp_wmb();
tpaca->kvm_hstate.kvm_vcpu = vcpu;
-#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
if (cpu != smp_processor_id())
- xics_wake_cpu(cpu);
-#endif
+ kvmppc_ipi_thread(cpu);
}
static void kvmppc_wait_for_nap(void)
@@ -1933,7 +1950,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
-static void kvmppc_run_core(struct kvmppc_vcore *vc)
+static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
struct kvm_vcpu *vcpu;
int i;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index c42aa55..ed2589d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -23,6 +23,8 @@
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
#include <asm/xics.h>
+#include <asm/dbell.h>
+#include <asm/cputhreads.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -193,7 +195,7 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
}
/*
- * Send an interrupt to another CPU.
+ * Send an interrupt or message to another CPU.
* This can only be called in real mode.
* The caller needs to include any barrier needed to order writes
* to memory vs. the IPI/message.
@@ -202,7 +204,17 @@ void kvmhv_rm_send_ipi(int cpu)
{
unsigned long xics_phys;
- /* Poke the target */
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ cpu_first_thread_sibling(cpu) ==
+ cpu_first_thread_sibling(raw_smp_processor_id())) {
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ msg |= cpu_thread_in_core(cpu);
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return;
+ }
+
+ /* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 13e7523..fb5b19c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1122,6 +1122,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
+ /* Hypervisor doorbell - exit only if host IPI flag set */
+ cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
+ bne 3f
+ lbz r0, HSTATE_HOST_IPI(r13)
+ beq 4f
+ b guest_exit_cont
+3:
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
bne+ guest_exit_cont
@@ -1134,7 +1141,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
bgt guest_exit_cont
/* Check if any CPU is heading out to the host, if so head out too */
- ld r5, HSTATE_KVM_VCORE(r13)
+4: ld r5, HSTATE_KVM_VCORE(r13)
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
mr r4, r9
@@ -2147,7 +2154,7 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1 and PECE0 set in LPCR.
- * On POWER8, if we are ceding, also set PECEDP.
+ * On POWER8, set PECEDH, and if we are ceding, also set PECEDP.
* Also clear the runlatch bit before napping.
*/
kvm_do_nap:
@@ -2160,6 +2167,7 @@ kvm_do_nap:
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
+ ori r5, r5, LPCR_PECEDH
rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r5
@@ -2298,7 +2306,7 @@ machine_check_realmode:
* Returns (in r3):
* 0 if nothing needs to be done
* 1 if something happened that needs to be handled by the host
- * -1 if there was a guest wakeup (IPI)
+ * -1 if there was a guest wakeup (IPI or msgsnd)
*
* Also sets r12 to the interrupt vector for any interrupt that needs
* to be handled now by the host (0x500 for external interrupt), or zero.
@@ -2329,7 +2337,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
/* hypervisor doorbell */
3: li r12, BOOK3S_INTERRUPT_H_DOORBELL
+ /* see if it's a host IPI */
li r3, 1
+ lbz r0, HSTATE_HOST_IPI(r13)
+ cmpwi r0, 0
+ bnelr
+ /* if not, clear it and return -1 */
+ lis r6, (PPC_DBELL_SERVER << (63-36))@h
+ PPC_MSGCLR(6)
+ li r3, -1
blr
/*
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 12/12] KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8
@ 2015-03-27 3:29 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-27 3:29 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller. This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.
Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:
rm_entry: 3387.6ns (228 - 86600, 1008969 samples)
rm_exit: 4561.5ns (12 - 3477452, 1009402 samples)
rm_intr: 1660.0ns (12 - 553050, 3600051 samples)
and this after the change:
rm_entry: 3060.1ns (212 - 65138, 953873 samples)
rm_exit: 4244.1ns (12 - 9693408, 954331 samples)
rm_intr: 1342.3ns (12 - 1104718, 3405326 samples)
for a test of booting Fedora 20 big-endian to the login prompt.
The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.
The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
Note that this patch depends on the patch "powerpc/powernv: Fixes for
hypervisor doorbell handling", which is now upstream in Linus' tree as
commit 755563bc79c7, for the definition of PPC_MSGCLR().
arch/powerpc/kernel/asm-offsets.c | 3 ++
arch/powerpc/kvm/book3s_hv.c | 51 ++++++++++++++++++++++-----------
arch/powerpc/kvm/book3s_hv_builtin.c | 16 +++++++++--
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 22 ++++++++++++--
4 files changed, 70 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0d07efb..0034b6b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -37,6 +37,7 @@
#include <asm/thread_info.h>
#include <asm/rtas.h>
#include <asm/vdso_datapage.h>
+#include <asm/dbell.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/lppaca.h>
@@ -759,5 +760,7 @@ int main(void)
offsetof(struct paca_struct, subcore_sibling_mask));
#endif
+ DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
+
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1426459..bb29e75 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -51,6 +51,7 @@
#include <asm/hvcall.h>
#include <asm/switch_to.h>
#include <asm/smp.h>
+#include <asm/dbell.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -84,9 +85,35 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
+static bool kvmppc_ipi_thread(int cpu)
+{
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ preempt_disable();
+ if (cpu_first_thread_sibling(cpu) =
+ cpu_first_thread_sibling(smp_processor_id())) {
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ msg |= cpu_thread_in_core(cpu);
+ smp_mb();
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ preempt_enable();
+ return true;
+ }
+ preempt_enable();
+ }
+
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
+ if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
+ xics_wake_cpu(cpu);
+ return true;
+ }
+#endif
+
+ return false;
+}
+
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
- int me;
int cpu = vcpu->cpu;
wait_queue_head_t *wqp;
@@ -96,20 +123,12 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
++vcpu->stat.halt_wakeup;
}
- me = get_cpu();
+ if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
+ return;
/* CPU points to the first thread of the core */
- if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_PPC_ICP_NATIVE
- int real_cpu = cpu + vcpu->arch.ptid;
- if (paca[real_cpu].kvm_hstate.xics_phys)
- xics_wake_cpu(real_cpu);
- else
-#endif
- if (cpu_online(cpu))
- smp_send_reschedule(cpu);
- }
- put_cpu();
+ if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
+ smp_send_reschedule(cpu);
}
/*
@@ -1781,10 +1800,8 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
/* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
smp_wmb();
tpaca->kvm_hstate.kvm_vcpu = vcpu;
-#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
if (cpu != smp_processor_id())
- xics_wake_cpu(cpu);
-#endif
+ kvmppc_ipi_thread(cpu);
}
static void kvmppc_wait_for_nap(void)
@@ -1933,7 +1950,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
-static void kvmppc_run_core(struct kvmppc_vcore *vc)
+static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
struct kvm_vcpu *vcpu;
int i;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index c42aa55..ed2589d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -23,6 +23,8 @@
#include <asm/kvm_book3s.h>
#include <asm/archrandom.h>
#include <asm/xics.h>
+#include <asm/dbell.h>
+#include <asm/cputhreads.h>
#define KVM_CMA_CHUNK_ORDER 18
@@ -193,7 +195,7 @@ static inline void rm_writeb(unsigned long paddr, u8 val)
}
/*
- * Send an interrupt to another CPU.
+ * Send an interrupt or message to another CPU.
* This can only be called in real mode.
* The caller needs to include any barrier needed to order writes
* to memory vs. the IPI/message.
@@ -202,7 +204,17 @@ void kvmhv_rm_send_ipi(int cpu)
{
unsigned long xics_phys;
- /* Poke the target */
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+ cpu_first_thread_sibling(cpu) =
+ cpu_first_thread_sibling(raw_smp_processor_id())) {
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ msg |= cpu_thread_in_core(cpu);
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ return;
+ }
+
+ /* Else poke the target with an IPI */
xics_phys = paca[cpu].kvm_hstate.xics_phys;
rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 13e7523..fb5b19c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1122,6 +1122,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
+ /* Hypervisor doorbell - exit only if host IPI flag set */
+ cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
+ bne 3f
+ lbz r0, HSTATE_HOST_IPI(r13)
+ beq 4f
+ b guest_exit_cont
+3:
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
bne+ guest_exit_cont
@@ -1134,7 +1141,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
bgt guest_exit_cont
/* Check if any CPU is heading out to the host, if so head out too */
- ld r5, HSTATE_KVM_VCORE(r13)
+4: ld r5, HSTATE_KVM_VCORE(r13)
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
mr r4, r9
@@ -2147,7 +2154,7 @@ _GLOBAL(kvmppc_h_cede) /* r3 = vcpu pointer, r11 = msr, r13 = paca */
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1 and PECE0 set in LPCR.
- * On POWER8, if we are ceding, also set PECEDP.
+ * On POWER8, set PECEDH, and if we are ceding, also set PECEDP.
* Also clear the runlatch bit before napping.
*/
kvm_do_nap:
@@ -2160,6 +2167,7 @@ kvm_do_nap:
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
BEGIN_FTR_SECTION
+ ori r5, r5, LPCR_PECEDH
rlwimi r5, r3, 0, LPCR_PECEDP
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r5
@@ -2298,7 +2306,7 @@ machine_check_realmode:
* Returns (in r3):
* 0 if nothing needs to be done
* 1 if something happened that needs to be handled by the host
- * -1 if there was a guest wakeup (IPI)
+ * -1 if there was a guest wakeup (IPI or msgsnd)
*
* Also sets r12 to the interrupt vector for any interrupt that needs
* to be handled now by the host (0x500 for external interrupt), or zero.
@@ -2329,7 +2337,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
/* hypervisor doorbell */
3: li r12, BOOK3S_INTERRUPT_H_DOORBELL
+ /* see if it's a host IPI */
li r3, 1
+ lbz r0, HSTATE_HOST_IPI(r13)
+ cmpwi r0, 0
+ bnelr
+ /* if not, clear it and return -1 */
+ lis r6, (PPC_DBELL_SERVER << (63-36))@h
+ PPC_MSGCLR(6)
+ li r3, -1
blr
/*
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
2015-03-28 3:21 [PATCH v2 00/12] Remaining improvements for HV KVM Paul Mackerras
@ 2015-03-28 3:21 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-28 3:21 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 21 +++++
arch/powerpc/include/asm/time.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 13 +++
arch/powerpc/kernel/time.c | 6 ++
arch/powerpc/kvm/Kconfig | 14 +++
arch/powerpc/kvm/book3s_hv.c | 150 ++++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 141 +++++++++++++++++++++++++++++-
7 files changed, 346 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f1d0bbc..d2068bb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -369,6 +369,14 @@ struct kvmppc_slb {
u8 base_page_size; /* MMU_PAGE_xxx */
};
+/* Struct used to accumulate timing information in HV real mode code */
+struct kvmhv_tb_accumulator {
+ u64 seqcount; /* used to synchronize access, also count * 2 */
+ u64 tb_total; /* total time in timebase ticks */
+ u64 tb_min; /* min time */
+ u64 tb_max; /* max time */
+};
+
# ifdef CONFIG_PPC_FSL_BOOK3E
#define KVMPPC_BOOKE_IAC_NUM 2
#define KVMPPC_BOOKE_DAC_NUM 2
@@ -657,6 +665,19 @@ struct kvm_vcpu_arch {
u32 emul_inst;
#endif
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */
+ u64 cur_tb_start; /* when it started */
+ struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
+ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
+ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */
+ struct kvmhv_tb_accumulator guest_time; /* guest execution */
+ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
+
+ struct dentry *debugfs_dir;
+ struct dentry *debugfs_timings;
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 03cbada..10fc784 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
+/* Convert timebase ticks to nanoseconds */
+unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
#endif /* __KERNEL__ */
#endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859..3fea721 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -459,6 +459,19 @@ int main(void)
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+ DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+ DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+ DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+ DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+ DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+ DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+ DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+ DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+ DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+ DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
+#endif
DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33f..56f4484 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
}
#endif
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+ return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
/*
* Scheduler clock - returns current time in nanosec units.
*
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 11850f3..2963e4d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR
processor, including emulating 32-bit processors on a 64-bit
host.
+config KVM_BOOK3S_HV_EXIT_TIMING
+ bool "Detailed timing for hypervisor real-mode code"
+ depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+ ---help---
+ Calculate time taken for each vcpu in the real-mode guest entry,
+ exit, and interrupt handling code, plus time spent in the guest
+ and in nap mode due to idle (cede) while other threads are still
+ in the guest. The total, minimum and maximum times in nanoseconds
+ together with the number of executions are reported in debugfs in
+ kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40
+ ns per exit on POWER8.
+
+ If unsure, say N.
+
config KVM_BOOKE_HV
bool
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cb54d90..c7b18ac 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1423,6 +1423,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
return vcore;
}
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+ const char *name;
+ size_t offset;
+} timings[] = {
+ {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
+ {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
+ {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
+ {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
+ {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+ struct kvm_vcpu *vcpu;
+ unsigned int buflen;
+ char buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = inode->i_private;
+ struct debugfs_timings_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(vcpu->kvm);
+ p->vcpu = vcpu;
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_timings_state *p = file->private_data;
+
+ kvm_put_kvm(p->vcpu->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_timings_state *p = file->private_data;
+ struct kvm_vcpu *vcpu = p->vcpu;
+ char *s, *buf_end;
+ struct kvmhv_tb_accumulator tb;
+ u64 count;
+ loff_t pos;
+ ssize_t n;
+ int i, loops;
+ bool ok;
+
+ if (!p->buflen) {
+ s = p->buf;
+ buf_end = s + sizeof(p->buf);
+ for (i = 0; i < N_TIMINGS; ++i) {
+ struct kvmhv_tb_accumulator *acc;
+
+ acc = (struct kvmhv_tb_accumulator *)
+ ((unsigned long)vcpu + timings[i].offset);
+ ok = false;
+ for (loops = 0; loops < 1000; ++loops) {
+ count = acc->seqcount;
+ if (!(count & 1)) {
+ smp_rmb();
+ tb = *acc;
+ smp_rmb();
+ if (count == acc->seqcount) {
+ ok = true;
+ break;
+ }
+ }
+ udelay(1);
+ }
+ if (!ok)
+ snprintf(s, buf_end - s, "%s: stuck\n",
+ timings[i].name);
+ else
+ snprintf(s, buf_end - s,
+ "%s: %llu %llu %llu %llu\n",
+ timings[i].name, count / 2,
+ tb_to_ns(tb.tb_total),
+ tb_to_ns(tb.tb_min),
+ tb_to_ns(tb.tb_max));
+ s += strlen(s);
+ }
+ p->buflen = s - p->buf;
+ }
+
+ pos = *ppos;
+ if (pos >= p->buflen)
+ return 0;
+ if (len > p->buflen - pos)
+ len = p->buflen - pos;
+ n = copy_to_user(buf, p->buf + pos, len);
+ if (n) {
+ if (n == len)
+ return -EFAULT;
+ len -= n;
+ }
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_timings_open,
+ .release = debugfs_timings_release,
+ .read = debugfs_timings_read,
+ .write = debugfs_timings_write,
+ .llseek = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+ char buf[16];
+ struct kvm *kvm = vcpu->kvm;
+
+ snprintf(buf, sizeof(buf), "vcpu%u", id);
+ if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+ if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_timings =
+ debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+ vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
@@ -1492,6 +1640,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ debugfs_vcpu_init(vcpu, id);
+
return vcpu;
free_vcpu:
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e9c3cb5..f05ae0c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -225,7 +225,13 @@ kvm_novcpu_wakeup:
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
- bne kvmppc_got_guest
+ beq kvmppc_primary_no_guest
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+#endif
+ b kvmppc_got_guest
kvm_novcpu_exit:
b hdec_soon
@@ -376,6 +382,14 @@ kvmppc_hv_entry:
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Store initial timestamp */
+ cmpdi r4, 0
+ beq 1f
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+1:
+#endif
/* Clear out SLB */
li r6,0
slbmte r6,r6
@@ -880,6 +894,12 @@ fast_guest_return:
li r9, KVM_GUEST_MODE_GUEST_HV
stb r9, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Accumulate timing */
+ addi r3, r4, VCPU_TB_GUEST
+ bl kvmhv_accumulate_time
+#endif
+
/* Enter guest */
BEGIN_FTR_SECTION
@@ -917,6 +937,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+secondary_too_late:
+ cmpdi r4, 0
+ beq 11f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+11: b kvmhv_switch_to_host
+
+hdec_soon:
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 12f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+12: b kvmhv_do_exit
+#endif
+
/******************************************************************************
* *
* Exit code *
@@ -1002,6 +1039,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
stw r12,VCPU_TRAP(r9)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMINTR
+ mr r4, r9
+ bl kvmhv_accumulate_time
+ ld r5, VCPU_GPR(R5)(r9)
+ ld r6, VCPU_GPR(R6)(r9)
+ ld r7, VCPU_GPR(R7)(r9)
+ ld r8, VCPU_GPR(R8)(r9)
+#endif
+
/* Save HEIR (HV emulation assist reg) in emul_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
@@ -1072,6 +1119,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
beq machine_check_realmode
mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
/* Save guest CTRL register, set runlatch to 1 */
6: mfspr r6,SPRN_CTRLF
@@ -1416,7 +1468,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-hdec_soon: /* r12 = trap, r13 = paca */
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+hdec_soon:
+#endif
+kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
@@ -1475,7 +1530,10 @@ hdec_soon: /* r12 = trap, r13 = paca */
addi r6,r6,PACA_SIZE
bne 42b
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+#endif
+kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
43: ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
@@ -1561,6 +1619,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
1: addi r8,r8,16
.endr
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Finish timing, if we have a vcpu */
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ li r3, 0
+ beq 2f
+ bl kvmhv_accumulate_time
+2:
+#endif
/* Unset guest mode */
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
@@ -2068,6 +2135,12 @@ _GLOBAL(kvmppc_h_cede)
/* save FP state */
bl kvmppc_save_fp
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ addi r3, r4, VCPU_TB_CEDE
+ bl kvmhv_accumulate_time
+#endif
+
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
@@ -2108,6 +2181,11 @@ kvm_end_cede:
/* Woken by external or decrementer interrupt */
ld r1, HSTATE_HOST_R1(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMINTR
+ bl kvmhv_accumulate_time
+#endif
+
/* load up FP state */
bl kvmppc_load_fp
@@ -2428,3 +2506,62 @@ kvmppc_fix_pmao:
mtspr SPRN_PMC6, r3
isync
blr
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+/*
+ * Start timing an activity
+ * r3 = pointer to time accumulation struct, r4 = vcpu
+ */
+kvmhv_start_timing:
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r6, VCORE_IN_GUEST(r5)
+ cmpwi r6, 0
+ beq 5f /* if in guest, need to */
+ ld r6, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
+5: mftb r5
+ subf r5, r6, r5
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ std r5, VCPU_ACTIVITY_START(r4)
+ blr
+
+/*
+ * Accumulate time to one activity and start another.
+ * r3 = pointer to new time accumulation struct, r4 = vcpu
+ */
+kvmhv_accumulate_time:
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r8, VCORE_IN_GUEST(r5)
+ cmpwi r8, 0
+ beq 4f /* if in guest, need to */
+ ld r8, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
+4: ld r5, VCPU_CUR_ACTIVITY(r4)
+ ld r6, VCPU_ACTIVITY_START(r4)
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ mftb r7
+ subf r7, r8, r7
+ std r7, VCPU_ACTIVITY_START(r4)
+ cmpdi r5, 0
+ beqlr
+ subf r3, r6, r7
+ ld r8, TAS_SEQCOUNT(r5)
+ cmpdi r8, 0
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ lwsync
+ ld r7, TAS_TOTAL(r5)
+ add r7, r7, r3
+ std r7, TAS_TOTAL(r5)
+ ld r6, TAS_MIN(r5)
+ ld r7, TAS_MAX(r5)
+ beq 3f
+ cmpd r3, r6
+ bge 1f
+3: std r3, TAS_MIN(r5)
+1: cmpd r3, r7
+ ble 2f
+ std r3, TAS_MAX(r5)
+2: lwsync
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ blr
+#endif
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread
* [PATCH 02/12] KVM: PPC: Book3S HV: Accumulate timing information for real-mode code
@ 2015-03-28 3:21 ` Paul Mackerras
0 siblings, 0 replies; 30+ messages in thread
From: Paul Mackerras @ 2015-03-28 3:21 UTC (permalink / raw)
To: kvm-ppc, kvm; +Cc: Alexander Graf
This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code. Currently these
times are accumulated per vcpu in 5 parts of the code:
* rm_entry - time taken from the start of kvmppc_hv_entry() until
just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
guest until we either re-enter the guest or decide to exit to the
host. This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
while other threads in the same vcore are active.
These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings". This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.
The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 21 +++++
arch/powerpc/include/asm/time.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 13 +++
arch/powerpc/kernel/time.c | 6 ++
arch/powerpc/kvm/Kconfig | 14 +++
arch/powerpc/kvm/book3s_hv.c | 150 ++++++++++++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 141 +++++++++++++++++++++++++++++-
7 files changed, 346 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f1d0bbc..d2068bb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -369,6 +369,14 @@ struct kvmppc_slb {
u8 base_page_size; /* MMU_PAGE_xxx */
};
+/* Struct used to accumulate timing information in HV real mode code */
+struct kvmhv_tb_accumulator {
+ u64 seqcount; /* used to synchronize access, also count * 2 */
+ u64 tb_total; /* total time in timebase ticks */
+ u64 tb_min; /* min time */
+ u64 tb_max; /* max time */
+};
+
# ifdef CONFIG_PPC_FSL_BOOK3E
#define KVMPPC_BOOKE_IAC_NUM 2
#define KVMPPC_BOOKE_DAC_NUM 2
@@ -657,6 +665,19 @@ struct kvm_vcpu_arch {
u32 emul_inst;
#endif
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */
+ u64 cur_tb_start; /* when it started */
+ struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
+ struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
+ struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */
+ struct kvmhv_tb_accumulator guest_time; /* guest execution */
+ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
+
+ struct dentry *debugfs_dir;
+ struct dentry *debugfs_timings;
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
};
#define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 03cbada..10fc784 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
+/* Convert timebase ticks to nanoseconds */
+unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
#endif /* __KERNEL__ */
#endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859..3fea721 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -459,6 +459,19 @@ int main(void)
DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+ DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+ DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+ DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+ DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+ DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+ DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+ DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+ DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+ DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+ DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
+#endif
DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33f..56f4484 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
}
#endif
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+ return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
/*
* Scheduler clock - returns current time in nanosec units.
*
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 11850f3..2963e4d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR
processor, including emulating 32-bit processors on a 64-bit
host.
+config KVM_BOOK3S_HV_EXIT_TIMING
+ bool "Detailed timing for hypervisor real-mode code"
+ depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+ ---help---
+ Calculate time taken for each vcpu in the real-mode guest entry,
+ exit, and interrupt handling code, plus time spent in the guest
+ and in nap mode due to idle (cede) while other threads are still
+ in the guest. The total, minimum and maximum times in nanoseconds
+ together with the number of executions are reported in debugfs in
+ kvm/vm#/vcpu#/timings. The overhead is of the order of 30 - 40
+ ns per exit on POWER8.
+
+ If unsure, say N.
+
config KVM_BOOKE_HV
bool
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cb54d90..c7b18ac 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1423,6 +1423,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
return vcore;
}
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+ const char *name;
+ size_t offset;
+} timings[] = {
+ {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
+ {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
+ {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
+ {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
+ {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+ struct kvm_vcpu *vcpu;
+ unsigned int buflen;
+ char buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = inode->i_private;
+ struct debugfs_timings_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(vcpu->kvm);
+ p->vcpu = vcpu;
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_timings_state *p = file->private_data;
+
+ kvm_put_kvm(p->vcpu->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_timings_state *p = file->private_data;
+ struct kvm_vcpu *vcpu = p->vcpu;
+ char *s, *buf_end;
+ struct kvmhv_tb_accumulator tb;
+ u64 count;
+ loff_t pos;
+ ssize_t n;
+ int i, loops;
+ bool ok;
+
+ if (!p->buflen) {
+ s = p->buf;
+ buf_end = s + sizeof(p->buf);
+ for (i = 0; i < N_TIMINGS; ++i) {
+ struct kvmhv_tb_accumulator *acc;
+
+ acc = (struct kvmhv_tb_accumulator *)
+ ((unsigned long)vcpu + timings[i].offset);
+ ok = false;
+ for (loops = 0; loops < 1000; ++loops) {
+ count = acc->seqcount;
+ if (!(count & 1)) {
+ smp_rmb();
+ tb = *acc;
+ smp_rmb();
+ if (count = acc->seqcount) {
+ ok = true;
+ break;
+ }
+ }
+ udelay(1);
+ }
+ if (!ok)
+ snprintf(s, buf_end - s, "%s: stuck\n",
+ timings[i].name);
+ else
+ snprintf(s, buf_end - s,
+ "%s: %llu %llu %llu %llu\n",
+ timings[i].name, count / 2,
+ tb_to_ns(tb.tb_total),
+ tb_to_ns(tb.tb_min),
+ tb_to_ns(tb.tb_max));
+ s += strlen(s);
+ }
+ p->buflen = s - p->buf;
+ }
+
+ pos = *ppos;
+ if (pos >= p->buflen)
+ return 0;
+ if (len > p->buflen - pos)
+ len = p->buflen - pos;
+ n = copy_to_user(buf, p->buf + pos, len);
+ if (n) {
+ if (n = len)
+ return -EFAULT;
+ len -= n;
+ }
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_timings_open,
+ .release = debugfs_timings_release,
+ .read = debugfs_timings_read,
+ .write = debugfs_timings_write,
+ .llseek = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+ char buf[16];
+ struct kvm *kvm = vcpu->kvm;
+
+ snprintf(buf, sizeof(buf), "vcpu%u", id);
+ if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+ if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_timings + debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+ vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
@@ -1492,6 +1640,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ debugfs_vcpu_init(vcpu, id);
+
return vcpu;
free_vcpu:
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e9c3cb5..f05ae0c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -225,7 +225,13 @@ kvm_novcpu_wakeup:
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
- bne kvmppc_got_guest
+ beq kvmppc_primary_no_guest
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+#endif
+ b kvmppc_got_guest
kvm_novcpu_exit:
b hdec_soon
@@ -376,6 +382,14 @@ kvmppc_hv_entry:
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Store initial timestamp */
+ cmpdi r4, 0
+ beq 1f
+ addi r3, r4, VCPU_TB_RMENTRY
+ bl kvmhv_start_timing
+1:
+#endif
/* Clear out SLB */
li r6,0
slbmte r6,r6
@@ -880,6 +894,12 @@ fast_guest_return:
li r9, KVM_GUEST_MODE_GUEST_HV
stb r9, HSTATE_IN_GUEST(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Accumulate timing */
+ addi r3, r4, VCPU_TB_GUEST
+ bl kvmhv_accumulate_time
+#endif
+
/* Enter guest */
BEGIN_FTR_SECTION
@@ -917,6 +937,23 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
hrfid
b .
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+secondary_too_late:
+ cmpdi r4, 0
+ beq 11f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+11: b kvmhv_switch_to_host
+
+hdec_soon:
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq 12f
+ addi r3, r4, VCPU_TB_RMEXIT
+ bl kvmhv_accumulate_time
+12: b kvmhv_do_exit
+#endif
+
/******************************************************************************
* *
* Exit code *
@@ -1002,6 +1039,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
stw r12,VCPU_TRAP(r9)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMINTR
+ mr r4, r9
+ bl kvmhv_accumulate_time
+ ld r5, VCPU_GPR(R5)(r9)
+ ld r6, VCPU_GPR(R6)(r9)
+ ld r7, VCPU_GPR(R7)(r9)
+ ld r8, VCPU_GPR(R8)(r9)
+#endif
+
/* Save HEIR (HV emulation assist reg) in emul_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
@@ -1072,6 +1119,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
beq machine_check_realmode
mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
/* Save guest CTRL register, set runlatch to 1 */
6: mfspr r6,SPRN_CTRLF
@@ -1416,7 +1468,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
slbia
ptesync
-hdec_soon: /* r12 = trap, r13 = paca */
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+hdec_soon:
+#endif
+kvmhv_do_exit: /* r12 = trap, r13 = paca */
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
@@ -1475,7 +1530,10 @@ hdec_soon: /* r12 = trap, r13 = paca */
addi r6,r6,PACA_SIZE
bne 42b
+#ifndef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
secondary_too_late:
+#endif
+kvmhv_switch_to_host:
/* Secondary threads wait for primary to do partition switch */
43: ld r5,HSTATE_KVM_VCORE(r13)
ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
@@ -1561,6 +1619,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
1: addi r8,r8,16
.endr
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ /* Finish timing, if we have a vcpu */
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ li r3, 0
+ beq 2f
+ bl kvmhv_accumulate_time
+2:
+#endif
/* Unset guest mode */
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
@@ -2068,6 +2135,12 @@ _GLOBAL(kvmppc_h_cede)
/* save FP state */
bl kvmppc_save_fp
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ ld r4, HSTATE_KVM_VCPU(r13)
+ addi r3, r4, VCPU_TB_CEDE
+ bl kvmhv_accumulate_time
+#endif
+
/*
* Take a nap until a decrementer or external or doobell interrupt
* occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
@@ -2108,6 +2181,11 @@ kvm_end_cede:
/* Woken by external or decrementer interrupt */
ld r1, HSTATE_HOST_R1(r13)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r4, VCPU_TB_RMINTR
+ bl kvmhv_accumulate_time
+#endif
+
/* load up FP state */
bl kvmppc_load_fp
@@ -2428,3 +2506,62 @@ kvmppc_fix_pmao:
mtspr SPRN_PMC6, r3
isync
blr
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+/*
+ * Start timing an activity
+ * r3 = pointer to time accumulation struct, r4 = vcpu
+ */
+kvmhv_start_timing:
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r6, VCORE_IN_GUEST(r5)
+ cmpwi r6, 0
+ beq 5f /* if in guest, need to */
+ ld r6, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
+5: mftb r5
+ subf r5, r6, r5
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ std r5, VCPU_ACTIVITY_START(r4)
+ blr
+
+/*
+ * Accumulate time to one activity and start another.
+ * r3 = pointer to new time accumulation struct, r4 = vcpu
+ */
+kvmhv_accumulate_time:
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r8, VCORE_IN_GUEST(r5)
+ cmpwi r8, 0
+ beq 4f /* if in guest, need to */
+ ld r8, VCORE_TB_OFFSET(r5) /* subtract timebase offset */
+4: ld r5, VCPU_CUR_ACTIVITY(r4)
+ ld r6, VCPU_ACTIVITY_START(r4)
+ std r3, VCPU_CUR_ACTIVITY(r4)
+ mftb r7
+ subf r7, r8, r7
+ std r7, VCPU_ACTIVITY_START(r4)
+ cmpdi r5, 0
+ beqlr
+ subf r3, r6, r7
+ ld r8, TAS_SEQCOUNT(r5)
+ cmpdi r8, 0
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ lwsync
+ ld r7, TAS_TOTAL(r5)
+ add r7, r7, r3
+ std r7, TAS_TOTAL(r5)
+ ld r6, TAS_MIN(r5)
+ ld r7, TAS_MAX(r5)
+ beq 3f
+ cmpd r3, r6
+ bge 1f
+3: std r3, TAS_MIN(r5)
+1: cmpd r3, r7
+ ble 2f
+ std r3, TAS_MAX(r5)
+2: lwsync
+ addi r8, r8, 1
+ std r8, TAS_SEQCOUNT(r5)
+ blr
+#endif
--
2.1.4
^ permalink raw reply related [flat|nested] 30+ messages in thread