<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/include/kvm/arm_pmu.h, branch v4.9.52</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>arm64: KVM: fix build with CONFIG_ARM_PMU disabled</title>
<updated>2016-06-27T10:55:51+00:00</updated>
<author>
<name>Sudeep Holla</name>
<email>sudeep.holla@arm.com</email>
</author>
<published>2016-06-08T10:38:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=0efce9da1255f13d910842b62cb14371044a3c50'/>
<id>0efce9da1255f13d910842b62cb14371044a3c50</id>
<content type='text'>
When CONFIG_ARM_PMU is disabled, we get the following build error:

arch/arm64/kvm/sys_regs.c: In function 'pmu_counter_idx_valid':
arch/arm64/kvm/sys_regs.c:564:27: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
  if (idx &gt;= val &amp;&amp; idx != ARMV8_PMU_CYCLE_IDX)
                           ^
arch/arm64/kvm/sys_regs.c:564:27: note: each undeclared identifier is reported only once for each function it appears in
arch/arm64/kvm/sys_regs.c: In function 'access_pmu_evcntr':
arch/arm64/kvm/sys_regs.c:592:10: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
    idx = ARMV8_PMU_CYCLE_IDX;
          ^
arch/arm64/kvm/sys_regs.c: In function 'access_pmu_evtyper':
arch/arm64/kvm/sys_regs.c:638:14: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
   if (idx == ARMV8_PMU_CYCLE_IDX)
              ^
arch/arm64/kvm/hyp/switch.c:86:15: error: 'ARMV8_PMU_USERENR_MASK' undeclared (first use in this function)
  write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);

This patch fixes the build with CONFIG_ARM_PMU disabled.

Cc: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Cc: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Sudeep Holla &lt;sudeep.holla@arm.com&gt;
Signed-off-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When CONFIG_ARM_PMU is disabled, we get the following build error:

arch/arm64/kvm/sys_regs.c: In function 'pmu_counter_idx_valid':
arch/arm64/kvm/sys_regs.c:564:27: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
  if (idx &gt;= val &amp;&amp; idx != ARMV8_PMU_CYCLE_IDX)
                           ^
arch/arm64/kvm/sys_regs.c:564:27: note: each undeclared identifier is reported only once for each function it appears in
arch/arm64/kvm/sys_regs.c: In function 'access_pmu_evcntr':
arch/arm64/kvm/sys_regs.c:592:10: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
    idx = ARMV8_PMU_CYCLE_IDX;
          ^
arch/arm64/kvm/sys_regs.c: In function 'access_pmu_evtyper':
arch/arm64/kvm/sys_regs.c:638:14: error: 'ARMV8_PMU_CYCLE_IDX' undeclared (first use in this function)
   if (idx == ARMV8_PMU_CYCLE_IDX)
              ^
arch/arm64/kvm/hyp/switch.c:86:15: error: 'ARMV8_PMU_USERENR_MASK' undeclared (first use in this function)
  write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);

This patch fixes the build with CONFIG_ARM_PMU disabled.

Cc: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Cc: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Sudeep Holla &lt;sudeep.holla@arm.com&gt;
Signed-off-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add a new vcpu device control group for PMUv3</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2016-01-11T13:35:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=bb0c70bcca6ba3c84afc2da7426f3b923bbe6825'/>
<id>bb0c70bcca6ba3c84afc2da7426f3b923bbe6825</id>
<content type='text'>
To configure the virtual PMUv3 overflow interrupt number, we use the
vcpu kvm_device ioctl, encapsulating the KVM_ARM_VCPU_PMU_V3_IRQ
attribute within the KVM_ARM_VCPU_PMU_V3_CTRL group.

After configuring the PMUv3, call the vcpu ioctl with attribute
KVM_ARM_VCPU_PMU_V3_INIT to initialize the PMUv3.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Acked-by: Peter Maydell &lt;peter.maydell@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Reviewed-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
To configure the virtual PMUv3 overflow interrupt number, we use the
vcpu kvm_device ioctl, encapsulating the KVM_ARM_VCPU_PMU_V3_IRQ
attribute within the KVM_ARM_VCPU_PMU_V3_CTRL group.

After configuring the PMUv3, call the vcpu ioctl with attribute
KVM_ARM_VCPU_PMU_V3_INIT to initialize the PMUv3.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Acked-by: Peter Maydell &lt;peter.maydell@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Reviewed-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add a new feature bit for PMUv3</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2016-01-11T14:46:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=808e738142e7086ef793ebf9797099c392894e65'/>
<id>808e738142e7086ef793ebf9797099c392894e65</id>
<content type='text'>
To support guest PMUv3, use one bit of the VCPU INIT feature array.
Initialize the PMU when initialzing the vcpu with that bit and PMU
overflow interrupt set.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Acked-by: Peter Maydell &lt;peter.maydell@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
To support guest PMUv3, use one bit of the VCPU INIT feature array.
Initialize the PMU when initialzing the vcpu with that bit and PMU
overflow interrupt set.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Acked-by: Peter Maydell &lt;peter.maydell@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Free perf event of PMU when destroying vcpu</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-09-11T07:18:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=5f0a714a2b63c25ffba5d832773f3ca4f0d02e21'/>
<id>5f0a714a2b63c25ffba5d832773f3ca4f0d02e21</id>
<content type='text'>
When KVM frees VCPU, it needs to free the perf_event of PMU.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When KVM frees VCPU, it needs to free the perf_event of PMU.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Reset PMU state when resetting vcpu</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-09-11T03:30:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=2aa36e9840d71710f06b3c29634f044fde8bcbe5'/>
<id>2aa36e9840d71710f06b3c29634f044fde8bcbe5</id>
<content type='text'>
When resetting vcpu, it needs to reset the PMU state to initial status.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When resetting vcpu, it needs to reset the PMU state to initial status.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add PMU overflow interrupt routing</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2016-02-26T11:29:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=b02386eb7dac7555a208d81aef2a0e5c6f0f8085'/>
<id>b02386eb7dac7555a208d81aef2a0e5c6f0f8085</id>
<content type='text'>
When calling perf_event_create_kernel_counter to create perf_event,
assign a overflow handler. Then when the perf event overflows, set the
corresponding bit of guest PMOVSSET register. If this counter is enabled
and its interrupt is enabled as well, kick the vcpu to sync the
interrupt.

On VM entry, if there is counter overflowed and interrupt level is
changed, inject the interrupt with corresponding level. On VM exit, sync
the interrupt level as well if it has been changed.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Reviewed-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When calling perf_event_create_kernel_counter to create perf_event,
assign a overflow handler. Then when the perf event overflows, set the
corresponding bit of guest PMOVSSET register. If this counter is enabled
and its interrupt is enabled as well, kick the vcpu to sync the
interrupt.

On VM entry, if there is counter overflowed and interrupt level is
changed, inject the interrupt with corresponding level. On VM exit, sync
the interrupt level as well if it has been changed.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Reviewed-by: Christoffer Dall &lt;christoffer.dall@linaro.org&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add helper to handle PMCR register bits</title>
<updated>2016-02-29T18:34:21+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-10-28T04:10:30+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=76993739cd6f5b42e881fe3332b9f8eb98cd6907'/>
<id>76993739cd6f5b42e881fe3332b9f8eb98cd6907</id>
<content type='text'>
According to ARMv8 spec, when writing 1 to PMCR.E, all counters are
enabled by PMCNTENSET, while writing 0 to PMCR.E, all counters are
disabled. When writing 1 to PMCR.P, reset all event counters, not
including PMCCNTR, to zero. When writing 1 to PMCR.C, reset PMCCNTR to
zero.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
According to ARMv8 spec, when writing 1 to PMCR.E, all counters are
enabled by PMCNTENSET, while writing 0 to PMCR.E, all counters are
disabled. When writing 1 to PMCR.P, reset all event counters, not
including PMCCNTR, to zero. When writing 1 to PMCR.C, reset PMCCNTR to
zero.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add access handler for PMSWINC register</title>
<updated>2016-02-29T18:34:20+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-09-08T07:49:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=7a0adc7064b88609e2917446af8789fac1d4fdd1'/>
<id>7a0adc7064b88609e2917446af8789fac1d4fdd1</id>
<content type='text'>
Add access handler which emulates writing and reading PMSWINC
register and add support for creating software increment event.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add access handler which emulates writing and reading PMSWINC
register and add support for creating software increment event.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: Add access handler for PMOVSSET and PMOVSCLR register</title>
<updated>2016-02-29T18:34:20+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-09-08T07:03:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=76d883c4e6401b98ea26d40c437ff62719a517ad'/>
<id>76d883c4e6401b98ea26d40c437ff62719a517ad</id>
<content type='text'>
Since the reset value of PMOVSSET and PMOVSCLR is UNKNOWN, use
reset_unknown for its reset handler. Add a handler to emulate writing
PMOVSSET or PMOVSCLR register.

When writing non-zero value to PMOVSSET, the counter and its interrupt
is enabled, kick this vcpu to sync PMU interrupt.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Since the reset value of PMOVSSET and PMOVSCLR is UNKNOWN, use
reset_unknown for its reset handler. Add a handler to emulate writing
PMOVSSET or PMOVSCLR register.

When writing non-zero value to PMOVSSET, the counter and its interrupt
is enabled, kick this vcpu to sync PMU interrupt.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Andrew Jones &lt;drjones@redhat.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>arm64: KVM: PMU: Add perf event map and introduce perf event creating function</title>
<updated>2016-02-29T18:34:20+00:00</updated>
<author>
<name>Shannon Zhao</name>
<email>shannon.zhao@linaro.org</email>
</author>
<published>2015-07-03T06:27:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=7f7663587165fe1a81c3390358cb70eb7234706f'/>
<id>7f7663587165fe1a81c3390358cb70eb7234706f</id>
<content type='text'>
When we use tools like perf on host, perf passes the event type and the
id of this event type category to kernel, then kernel will map them to
hardware event number and write this number to PMU PMEVTYPER&lt;n&gt;_EL0
register. When getting the event number in KVM, directly use raw event
type to create a perf_event for it.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When we use tools like perf on host, perf passes the event type and the
id of this event type category to kernel, then kernel will map them to
hardware event number and write this number to PMU PMEVTYPER&lt;n&gt;_EL0
register. When getting the event number in KVM, directly use raw event
type to create a perf_event for it.

Signed-off-by: Shannon Zhao &lt;shannon.zhao@linaro.org&gt;
Reviewed-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
Signed-off-by: Marc Zyngier &lt;marc.zyngier@arm.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
