* [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 13:47 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 02/10] xsm: add resource operation related xsm policy Chao Peng
` (8 subsequent siblings)
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Add a generic resource access hypercall for tool stack or other
components, e.g., accessing MSR, port I/O, etc.
The resource is abstracted as a resource address/value pair.
The resource access can be any type of XEN_RESOURCE_OP_*(current
only support MSR and it's white-listed). The resource operations
are always runs on cpu that caller specified. If caller does not
care this, it should use current cpu to eliminate the IPI overhead.
Batch resource operations in one call are also supported but the
max number currently is limited to 2. The operations in a batch are
non-preemptible and execute in their original order. If preemptible
batch is desirable, then multicall mechanism can be used.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
xen/arch/x86/platform_hypercall.c | 140 ++++++++++++++++++++++++++++++
xen/arch/x86/x86_64/platform_hypercall.c | 4 +
xen/include/public/platform.h | 28 ++++++
xen/include/xlat.lst | 1 +
4 files changed, 173 insertions(+)
diff --git a/xen/arch/x86/platform_hypercall.c b/xen/arch/x86/platform_hypercall.c
index 2162811..4b92b56 100644
--- a/xen/arch/x86/platform_hypercall.c
+++ b/xen/arch/x86/platform_hypercall.c
@@ -61,6 +61,77 @@ long cpu_down_helper(void *data);
long core_parking_helper(void *data);
uint32_t get_cur_idle_nums(void);
+struct xen_resource_access {
+ int32_t ret;
+ uint32_t nr_entries;
+ xenpf_resource_entry_t *entries;
+};
+
+static bool_t allow_access_msr(unsigned int msr)
+{
+ return 0;
+}
+
+static int check_resource_access(struct xen_resource_access *ra)
+{
+ xenpf_resource_entry_t *entry;
+ unsigned int i;
+
+ for ( i = 0; i < ra->nr_entries; i++ )
+ {
+ entry = ra->entries + i;
+
+ if ( entry->rsvd )
+ return -EINVAL;
+
+ switch ( entry->cmd )
+ {
+ case XEN_RESOURCE_OP_MSR_READ:
+ case XEN_RESOURCE_OP_MSR_WRITE:
+ if ( entry->idx >> 32 )
+ return -EINVAL;
+ else if ( !allow_access_msr(entry->idx) )
+ return -EACCES;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static void resource_access(void *info)
+{
+ struct xen_resource_access *ra = info;
+ xenpf_resource_entry_t *entry;
+ int ret = 0;
+ unsigned int i;
+
+ for ( i = 0; i < ra->nr_entries; i++ )
+ {
+ entry = ra->entries + i;
+
+ switch ( entry->cmd )
+ {
+ case XEN_RESOURCE_OP_MSR_READ:
+ case XEN_RESOURCE_OP_MSR_WRITE:
+ if ( entry->cmd == XEN_RESOURCE_OP_MSR_READ )
+ ret = rdmsr_safe(entry->idx, entry->val);
+ else
+ ret = wrmsr_safe(entry->idx, entry->val);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ if ( ret )
+ break;
+ }
+
+ ra->ret = ret;
+}
+
ret_t do_platform_op(XEN_GUEST_HANDLE_PARAM(xen_platform_op_t) u_xenpf_op)
{
ret_t ret = 0;
@@ -601,6 +672,75 @@ ret_t do_platform_op(XEN_GUEST_HANDLE_PARAM(xen_platform_op_t) u_xenpf_op)
}
break;
+ case XENPF_resource_op:
+ {
+ struct xen_resource_access ra;
+ uint32_t cpu;
+ XEN_GUEST_HANDLE(xenpf_resource_entry_t) guest_entries;
+
+#define MAX_SUPPORTED_ENTRIES 2
+
+ ra.nr_entries = op->u.resource_op.nr_entries;
+ if ( ra.nr_entries == 0 || ra.nr_entries > MAX_SUPPORTED_ENTRIES )
+ {
+ ret = -EINVAL;
+ break;
+ }
+
+ ra.entries = xmalloc_array(xenpf_resource_entry_t, ra.nr_entries);
+ if ( !ra.entries )
+ {
+ ret = -ENOMEM;
+ break;
+ }
+
+ guest_from_compat_handle(guest_entries, op->u.resource_op.entries);
+
+ if ( copy_from_guest(ra.entries, guest_entries, ra.nr_entries) )
+ {
+ xfree(ra.entries);
+ ret = -EFAULT;
+ break;
+ }
+
+ /* Do sanity check earlier to omit the potential IPI overhead. */
+ ret = check_resource_access(&ra);
+ if ( ret )
+ {
+ xfree(ra.entries);
+ break;
+ }
+
+ cpu = op->u.resource_op.cpu;
+ if ( cpu == smp_processor_id() )
+ resource_access(&ra);
+ else if ( cpu_online(cpu) )
+ on_selected_cpus(cpumask_of(cpu), resource_access, &ra, 1);
+ else
+ {
+ xfree(ra.entries);
+ ret = -ENODEV;
+ break;
+ }
+
+ if ( ra.ret )
+ {
+ xfree(ra.entries);
+ ret = ra.ret;
+ break;
+ }
+
+ if ( __copy_to_guest(guest_entries, ra.entries, ra.nr_entries) )
+ {
+ xfree(ra.entries);
+ ret = -EFAULT;
+ break;
+ }
+
+ xfree(ra.entries);
+ }
+ break;
+
default:
ret = -ENOSYS;
break;
diff --git a/xen/arch/x86/x86_64/platform_hypercall.c b/xen/arch/x86/x86_64/platform_hypercall.c
index b6f380e..ccfd30d 100644
--- a/xen/arch/x86/x86_64/platform_hypercall.c
+++ b/xen/arch/x86/x86_64/platform_hypercall.c
@@ -32,6 +32,10 @@ CHECK_pf_pcpu_version;
CHECK_pf_enter_acpi_sleep;
#undef xen_pf_enter_acpi_sleep
+#define xen_pf_resource_entry xenpf_resource_entry
+CHECK_pf_resource_entry;
+#undef xen_pf_resource_entry
+
#define COMPAT
#define _XEN_GUEST_HANDLE(t) XEN_GUEST_HANDLE(t)
#define _XEN_GUEST_HANDLE_PARAM(t) XEN_GUEST_HANDLE_PARAM(t)
diff --git a/xen/include/public/platform.h b/xen/include/public/platform.h
index 053b9fa..5951848 100644
--- a/xen/include/public/platform.h
+++ b/xen/include/public/platform.h
@@ -528,6 +528,33 @@ typedef struct xenpf_core_parking xenpf_core_parking_t;
DEFINE_XEN_GUEST_HANDLE(xenpf_core_parking_t);
/*
+ * Access generic platform resources(e.g., accessing MSR, port I/O, etc)
+ * in unified way. Batch resource operations in one call are supported and
+ * thay are always non-preemptible and execute in their original order.
+ */
+#define XENPF_resource_op 61
+
+#define XEN_RESOURCE_OP_MSR_READ 0
+#define XEN_RESOURCE_OP_MSR_WRITE 1
+
+struct xenpf_resource_entry {
+ uint32_t cmd; /* IN: XEN_RESOURCE_OP_* */
+ uint32_t rsvd; /* IN: padding and must be zero */
+ uint64_t idx; /* IN: resource address to access */
+ uint64_t val; /* IN/OUT: resource value to set/get */
+};
+typedef struct xenpf_resource_entry xenpf_resource_entry_t;
+DEFINE_XEN_GUEST_HANDLE(xenpf_resource_entry_t);
+
+struct xenpf_resource_op {
+ uint32_t nr_entries; /* number of resource entry */
+ uint32_t cpu; /* which cpu to run */
+ XEN_GUEST_HANDLE(xenpf_resource_entry_t) entries;
+};
+typedef struct xenpf_resource_op xenpf_resource_op_t;
+DEFINE_XEN_GUEST_HANDLE(xenpf_resource_op_t);
+
+/*
* ` enum neg_errnoval
* ` HYPERVISOR_platform_op(const struct xen_platform_op*);
*/
@@ -553,6 +580,7 @@ struct xen_platform_op {
struct xenpf_cpu_hotadd cpu_add;
struct xenpf_mem_hotadd mem_add;
struct xenpf_core_parking core_parking;
+ struct xenpf_resource_op resource_op;
uint8_t pad[128];
} u;
};
diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
index 9a35dd7..234b668 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -88,6 +88,7 @@
? xenpf_enter_acpi_sleep platform.h
? xenpf_pcpuinfo platform.h
? xenpf_pcpu_version platform.h
+? xenpf_resource_entry platform.h
! sched_poll sched.h
? sched_remote_shutdown sched.h
? sched_shutdown sched.h
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall
2014-09-29 10:40 ` [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall Chao Peng
@ 2014-09-29 13:47 ` Andrew Cooper
2014-09-29 13:55 ` Jan Beulich
0 siblings, 1 reply; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 13:47 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> Add a generic resource access hypercall for tool stack or other
> components, e.g., accessing MSR, port I/O, etc.
>
> The resource is abstracted as a resource address/value pair.
> The resource access can be any type of XEN_RESOURCE_OP_*(current
> only support MSR and it's white-listed). The resource operations
> are always runs on cpu that caller specified. If caller does not
> care this, it should use current cpu to eliminate the IPI overhead.
>
> Batch resource operations in one call are also supported but the
> max number currently is limited to 2. The operations in a batch are
> non-preemptible and execute in their original order. If preemptible
> batch is desirable, then multicall mechanism can be used.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Looking much better.
However, I have noticed something which I missed in previous reviews
(appologies for not spotting it earlier), and a couple of comments.
> ---
> xen/arch/x86/platform_hypercall.c | 140 ++++++++++++++++++++++++++++++
> xen/arch/x86/x86_64/platform_hypercall.c | 4 +
> xen/include/public/platform.h | 28 ++++++
> xen/include/xlat.lst | 1 +
> 4 files changed, 173 insertions(+)
>
> diff --git a/xen/arch/x86/platform_hypercall.c b/xen/arch/x86/platform_hypercall.c
> index 2162811..4b92b56 100644
> --- a/xen/arch/x86/platform_hypercall.c
> +++ b/xen/arch/x86/platform_hypercall.c
> @@ -61,6 +61,77 @@ long cpu_down_helper(void *data);
> long core_parking_helper(void *data);
> uint32_t get_cur_idle_nums(void);
>
> +struct xen_resource_access {
> + int32_t ret;
> + uint32_t nr_entries;
This is private to Xen. It is perfectly fine to use int and unsigned
int respectively.
> + xenpf_resource_entry_t *entries;
> +};
> +
> +static bool_t allow_access_msr(unsigned int msr)
> +{
> + return 0;
> +}
> +
> +static int check_resource_access(struct xen_resource_access *ra)
> +{
> + xenpf_resource_entry_t *entry;
> + unsigned int i;
> +
> + for ( i = 0; i < ra->nr_entries; i++ )
> + {
> + entry = ra->entries + i;
> +
> + if ( entry->rsvd )
> + return -EINVAL;
> +
> + switch ( entry->cmd )
> + {
> + case XEN_RESOURCE_OP_MSR_READ:
> + case XEN_RESOURCE_OP_MSR_WRITE:
> + if ( entry->idx >> 32 )
> + return -EINVAL;
> + else if ( !allow_access_msr(entry->idx) )
> + return -EACCES;
> + default:
> + return -EINVAL;
> + }
> + }
> +
> + return 0;
> +}
> +
> +static void resource_access(void *info)
> +{
> + struct xen_resource_access *ra = info;
> + xenpf_resource_entry_t *entry;
> + int ret = 0;
> + unsigned int i;
> +
> + for ( i = 0; i < ra->nr_entries; i++ )
> + {
> + entry = ra->entries + i;
> +
> + switch ( entry->cmd )
> + {
> + case XEN_RESOURCE_OP_MSR_READ:
> + case XEN_RESOURCE_OP_MSR_WRITE:
> + if ( entry->cmd == XEN_RESOURCE_OP_MSR_READ )
> + ret = rdmsr_safe(entry->idx, entry->val);
> + else
> + ret = wrmsr_safe(entry->idx, entry->val);
> + break;
This is a little bit weird to read. Only the break statement is common
to the two case statements. It would be better just to split the two
case statements properly and do away with the if().
> + default:
> + ret = -EINVAL;
> + break;
> + }
> +
> + if ( ret )
> + break;
> + }
> +
> + ra->ret = ret;
> +}
> +
> ret_t do_platform_op(XEN_GUEST_HANDLE_PARAM(xen_platform_op_t) u_xenpf_op)
> {
> ret_t ret = 0;
> @@ -601,6 +672,75 @@ ret_t do_platform_op(XEN_GUEST_HANDLE_PARAM(xen_platform_op_t) u_xenpf_op)
> }
> break;
>
> + case XENPF_resource_op:
> + {
> + struct xen_resource_access ra;
> + uint32_t cpu;
> + XEN_GUEST_HANDLE(xenpf_resource_entry_t) guest_entries;
> +
> +#define MAX_SUPPORTED_ENTRIES 2
This name is far too generic. At the least it should be
RESOURCE_ACCESS_MAX_ENTRIES, and the definition should probably live
beside struct xen_resource_access.
> +
> + ra.nr_entries = op->u.resource_op.nr_entries;
> + if ( ra.nr_entries == 0 || ra.nr_entries > MAX_SUPPORTED_ENTRIES )
> + {
> + ret = -EINVAL;
> + break;
> + }
> +
> + ra.entries = xmalloc_array(xenpf_resource_entry_t, ra.nr_entries);
> + if ( !ra.entries )
> + {
> + ret = -ENOMEM;
> + break;
> + }
> +
> + guest_from_compat_handle(guest_entries, op->u.resource_op.entries);
> +
> + if ( copy_from_guest(ra.entries, guest_entries, ra.nr_entries) )
> + {
> + xfree(ra.entries);
> + ret = -EFAULT;
> + break;
> + }
> +
> + /* Do sanity check earlier to omit the potential IPI overhead. */
> + ret = check_resource_access(&ra);
> + if ( ret )
> + {
> + xfree(ra.entries);
> + break;
> + }
> +
> + cpu = op->u.resource_op.cpu;
> + if ( cpu == smp_processor_id() )
> + resource_access(&ra);
> + else if ( cpu_online(cpu) )
> + on_selected_cpus(cpumask_of(cpu), resource_access, &ra, 1);
> + else
> + {
> + xfree(ra.entries);
> + ret = -ENODEV;
> + break;
> + }
> +
> + if ( ra.ret )
> + {
> + xfree(ra.entries);
> + ret = ra.ret;
> + break;
> + }
> +
> + if ( __copy_to_guest(guest_entries, ra.entries, ra.nr_entries) )
> + {
> + xfree(ra.entries);
> + ret = -EFAULT;
> + break;
> + }
> +
> + xfree(ra.entries);
> + }
> + break;
> +
> default:
> ret = -ENOSYS;
> break;
> diff --git a/xen/arch/x86/x86_64/platform_hypercall.c b/xen/arch/x86/x86_64/platform_hypercall.c
> index b6f380e..ccfd30d 100644
> --- a/xen/arch/x86/x86_64/platform_hypercall.c
> +++ b/xen/arch/x86/x86_64/platform_hypercall.c
> @@ -32,6 +32,10 @@ CHECK_pf_pcpu_version;
> CHECK_pf_enter_acpi_sleep;
> #undef xen_pf_enter_acpi_sleep
>
> +#define xen_pf_resource_entry xenpf_resource_entry
> +CHECK_pf_resource_entry;
> +#undef xen_pf_resource_entry
> +
> #define COMPAT
> #define _XEN_GUEST_HANDLE(t) XEN_GUEST_HANDLE(t)
> #define _XEN_GUEST_HANDLE_PARAM(t) XEN_GUEST_HANDLE_PARAM(t)
> diff --git a/xen/include/public/platform.h b/xen/include/public/platform.h
> index 053b9fa..5951848 100644
> --- a/xen/include/public/platform.h
> +++ b/xen/include/public/platform.h
> @@ -528,6 +528,33 @@ typedef struct xenpf_core_parking xenpf_core_parking_t;
> DEFINE_XEN_GUEST_HANDLE(xenpf_core_parking_t);
>
> /*
> + * Access generic platform resources(e.g., accessing MSR, port I/O, etc)
> + * in unified way. Batch resource operations in one call are supported and
> + * thay are always non-preemptible and execute in their original order.
> + */
> +#define XENPF_resource_op 61
> +
> +#define XEN_RESOURCE_OP_MSR_READ 0
> +#define XEN_RESOURCE_OP_MSR_WRITE 1
> +
> +struct xenpf_resource_entry {
> + uint32_t cmd; /* IN: XEN_RESOURCE_OP_* */
> + uint32_t rsvd; /* IN: padding and must be zero */
This rsvd should be int32_t ret, and an out parameter.
When issuing two back to back operations, it is helpful to identify
which one failed, rather than just "something failed". Putting a
per-resource return value allows userspace to unambiguously identify
which operation failed, and why (EACCES, EFAULT etc).
In situations like this, it is also common for the main hypercall to
return -E??? for general errors, or a positive integer for the number of
successful operations.
Therefore, for complete success, the XENPF_resource_op hypercall would
return 2. If the read succeeded but the write failed, it would return
1, and if the read failed, it would return 0.
~Andrew
> + uint64_t idx; /* IN: resource address to access */
> + uint64_t val; /* IN/OUT: resource value to set/get */
> +};
> +typedef struct xenpf_resource_entry xenpf_resource_entry_t;
> +DEFINE_XEN_GUEST_HANDLE(xenpf_resource_entry_t);
> +
> +struct xenpf_resource_op {
> + uint32_t nr_entries; /* number of resource entry */
> + uint32_t cpu; /* which cpu to run */
> + XEN_GUEST_HANDLE(xenpf_resource_entry_t) entries;
> +};
> +typedef struct xenpf_resource_op xenpf_resource_op_t;
> +DEFINE_XEN_GUEST_HANDLE(xenpf_resource_op_t);
> +
> +/*
> * ` enum neg_errnoval
> * ` HYPERVISOR_platform_op(const struct xen_platform_op*);
> */
> @@ -553,6 +580,7 @@ struct xen_platform_op {
> struct xenpf_cpu_hotadd cpu_add;
> struct xenpf_mem_hotadd mem_add;
> struct xenpf_core_parking core_parking;
> + struct xenpf_resource_op resource_op;
> uint8_t pad[128];
> } u;
> };
> diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
> index 9a35dd7..234b668 100644
> --- a/xen/include/xlat.lst
> +++ b/xen/include/xlat.lst
> @@ -88,6 +88,7 @@
> ? xenpf_enter_acpi_sleep platform.h
> ? xenpf_pcpuinfo platform.h
> ? xenpf_pcpu_version platform.h
> +? xenpf_resource_entry platform.h
> ! sched_poll sched.h
> ? sched_remote_shutdown sched.h
> ? sched_shutdown sched.h
^ permalink raw reply [flat|nested] 18+ messages in thread* Re: [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall
2014-09-29 13:47 ` Andrew Cooper
@ 2014-09-29 13:55 ` Jan Beulich
0 siblings, 0 replies; 18+ messages in thread
From: Jan Beulich @ 2014-09-29 13:55 UTC (permalink / raw)
To: Andrew Cooper, Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, dgdegra
>>> On 29.09.14 at 15:47, <andrew.cooper3@citrix.com> wrote:
> On 29/09/14 11:40, Chao Peng wrote:
>> --- a/xen/include/public/platform.h
>> +++ b/xen/include/public/platform.h
>> @@ -528,6 +528,33 @@ typedef struct xenpf_core_parking xenpf_core_parking_t;
>> DEFINE_XEN_GUEST_HANDLE(xenpf_core_parking_t);
>>
>> /*
>> + * Access generic platform resources(e.g., accessing MSR, port I/O, etc)
>> + * in unified way. Batch resource operations in one call are supported and
>> + * thay are always non-preemptible and execute in their original order.
>> + */
>> +#define XENPF_resource_op 61
>> +
>> +#define XEN_RESOURCE_OP_MSR_READ 0
>> +#define XEN_RESOURCE_OP_MSR_WRITE 1
>> +
>> +struct xenpf_resource_entry {
>> + uint32_t cmd; /* IN: XEN_RESOURCE_OP_* */
>> + uint32_t rsvd; /* IN: padding and must be zero */
>
> This rsvd should be int32_t ret, and an out parameter.
I guess I'd prefer keeping the reserved field as is and
overloading the cmd field (i.e. making it a union). That way
we retain extensibility for something future use of which is
really rather vague at this point.
Jan
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 02/10] xsm: add resource operation related xsm policy
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
2014-09-29 10:40 ` [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 10:40 ` [PATCH v17 03/10] tools: provide interface for generic resource access Chao Peng
` (7 subsequent siblings)
9 siblings, 0 replies; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Add xsm policies for resource access related hypercall, such as MSR
access, port I/O read/write, and other related resource operations.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Daniel De Graaf <dgdegra@tycho.nsa.gov>
---
tools/flask/policy/policy/modules/xen/xen.te | 3 +++
xen/xsm/flask/hooks.c | 4 ++++
xen/xsm/flask/policy/access_vectors | 14 +++++++++++---
xen/xsm/flask/policy/security_classes | 1 +
4 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/tools/flask/policy/policy/modules/xen/xen.te b/tools/flask/policy/policy/modules/xen/xen.te
index 1937883..6cecf97 100644
--- a/tools/flask/policy/policy/modules/xen/xen.te
+++ b/tools/flask/policy/policy/modules/xen/xen.te
@@ -64,6 +64,9 @@ allow dom0_t xen_t:xen {
getidle debug getcpuinfo heap pm_op mca_op lockprof cpupool_op tmem_op
tmem_control getscheduler setscheduler
};
+allow dom0_t xen_t:xen2 {
+ resource_op
+};
allow dom0_t xen_t:mmu memorymap;
# Allow dom0 to use these domctls on itself. For domctls acting on other
diff --git a/xen/xsm/flask/hooks.c b/xen/xsm/flask/hooks.c
index df05566..9f36503 100644
--- a/xen/xsm/flask/hooks.c
+++ b/xen/xsm/flask/hooks.c
@@ -1391,6 +1391,10 @@ static int flask_platform_op(uint32_t op)
case XENPF_get_cpuinfo:
return domain_has_xen(current->domain, XEN__GETCPUINFO);
+ case XENPF_resource_op:
+ return avc_current_has_perm(SECINITSID_XEN, SECCLASS_XEN2,
+ XEN2__RESOURCE_OP, NULL);
+
default:
printk("flask_platform_op: Unknown op %d\n", op);
return -EPERM;
diff --git a/xen/xsm/flask/policy/access_vectors b/xen/xsm/flask/policy/access_vectors
index d279841..daf0de5 100644
--- a/xen/xsm/flask/policy/access_vectors
+++ b/xen/xsm/flask/policy/access_vectors
@@ -3,9 +3,9 @@
#
# class class_name { permission_name ... }
-# Class xen consists of dom0-only operations dealing with the hypervisor itself.
-# Unless otherwise specified, the source is the domain executing the hypercall,
-# and the target is the xen initial sid (type xen_t).
+# Class xen and xen2 consists of dom0-only operations dealing with the
+# hypervisor itself. Unless otherwise specified, the source is the domain
+# executing the hypercall, and the target is the xen initial sid (type xen_t).
class xen
{
# XENPF_settime
@@ -75,6 +75,14 @@ class xen
setscheduler
}
+# This is a continuation of class xen, since only 32 permissions can be
+# defined per class
+class xen2
+{
+# XENPF_resource_op
+ resource_op
+}
+
# Classes domain and domain2 consist of operations that a domain performs on
# another domain or on itself. Unless otherwise specified, the source is the
# domain executing the hypercall, and the target is the domain being operated on
diff --git a/xen/xsm/flask/policy/security_classes b/xen/xsm/flask/policy/security_classes
index ef134a7..ca191db 100644
--- a/xen/xsm/flask/policy/security_classes
+++ b/xen/xsm/flask/policy/security_classes
@@ -8,6 +8,7 @@
# for userspace object managers
class xen
+class xen2
class domain
class domain2
class hvm
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* [PATCH v17 03/10] tools: provide interface for generic resource access
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
2014-09-29 10:40 ` [PATCH v17 01/10] x86: add generic resource (e.g. MSR) access hypercall Chao Peng
2014-09-29 10:40 ` [PATCH v17 02/10] xsm: add resource operation related xsm policy Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 10:40 ` [PATCH v17 04/10] x86: detect and initialize Cache Monitoring Technology feature Chao Peng
` (6 subsequent siblings)
9 siblings, 0 replies; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Xen added a new platform_op hypercall for generic MSR access, and this
is the the tool side change to wrapper the hypercall into xc APIs.
For non-preemptible batch resource operations, group them in entries of
xc_resource_op structure. For preemptible ones, use multiple
xc_resource_op structure instead.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
---
tools/libxc/Makefile | 1 +
tools/libxc/xc_private.h | 51 +++++++++++++++
tools/libxc/xc_resource.c | 150 +++++++++++++++++++++++++++++++++++++++++++++
tools/libxc/xenctrl.h | 17 +++++
4 files changed, 219 insertions(+)
create mode 100644 tools/libxc/xc_resource.c
diff --git a/tools/libxc/Makefile b/tools/libxc/Makefile
index 3b04027..dde6109 100644
--- a/tools/libxc/Makefile
+++ b/tools/libxc/Makefile
@@ -34,6 +34,7 @@ CTRL_SRCS-y += xc_foreign_memory.c
CTRL_SRCS-y += xc_kexec.c
CTRL_SRCS-y += xtl_core.c
CTRL_SRCS-y += xtl_logger_stdio.c
+CTRL_SRCS-y += xc_resource.c
CTRL_SRCS-$(CONFIG_X86) += xc_pagetab.c
CTRL_SRCS-$(CONFIG_Linux) += xc_linux.c xc_linux_osdep.c
CTRL_SRCS-$(CONFIG_FreeBSD) += xc_freebsd.c xc_freebsd_osdep.c
diff --git a/tools/libxc/xc_private.h b/tools/libxc/xc_private.h
index 94df688..3fd5324 100644
--- a/tools/libxc/xc_private.h
+++ b/tools/libxc/xc_private.h
@@ -46,6 +46,7 @@
#define DECLARE_SYSCTL struct xen_sysctl sysctl
#define DECLARE_PHYSDEV_OP struct physdev_op physdev_op
#define DECLARE_FLASK_OP struct xen_flask_op op
+#define DECLARE_PLATFORM_OP struct xen_platform_op platform_op
#undef PAGE_SHIFT
#undef PAGE_SIZE
@@ -310,6 +311,56 @@ static inline int do_sysctl(xc_interface *xch, struct xen_sysctl *sysctl)
return ret;
}
+static inline int do_platform_op(xc_interface *xch,
+ struct xen_platform_op *platform_op)
+{
+ int ret = -1;
+ DECLARE_HYPERCALL;
+ DECLARE_HYPERCALL_BOUNCE(platform_op, sizeof(*platform_op),
+ XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
+
+ platform_op->interface_version = XENPF_INTERFACE_VERSION;
+
+ if ( xc_hypercall_bounce_pre(xch, platform_op) )
+ {
+ PERROR("Could not bounce buffer for platform_op hypercall");
+ return -1;
+ }
+
+ hypercall.op = __HYPERVISOR_platform_op;
+ hypercall.arg[0] = HYPERCALL_BUFFER_AS_ARG(platform_op);
+ if ( (ret = do_xen_hypercall(xch, &hypercall)) < 0 )
+ {
+ if ( errno == EACCES )
+ DPRINTF("platform operation failed -- need to"
+ " rebuild the user-space tool set?\n");
+ }
+
+ xc_hypercall_bounce_post(xch, platform_op);
+ return ret;
+}
+
+static inline int do_multicall_op(xc_interface *xch,
+ xc_hypercall_buffer_t *call_list,
+ uint32_t nr_calls)
+{
+ int ret = -1;
+ DECLARE_HYPERCALL;
+ DECLARE_HYPERCALL_BUFFER_ARGUMENT(call_list);
+
+ hypercall.op = __HYPERVISOR_multicall;
+ hypercall.arg[0] = HYPERCALL_BUFFER_AS_ARG(call_list);
+ hypercall.arg[1] = nr_calls;
+ if ( (ret = do_xen_hypercall(xch, &hypercall)) < 0 )
+ {
+ if ( errno == EACCES )
+ DPRINTF("multicall operation failed -- need to"
+ " rebuild the user-space tool set?\n");
+ }
+
+ return ret;
+}
+
int do_memory_op(xc_interface *xch, int cmd, void *arg, size_t len);
void *xc_map_foreign_ranges(xc_interface *xch, uint32_t dom,
diff --git a/tools/libxc/xc_resource.c b/tools/libxc/xc_resource.c
new file mode 100644
index 0000000..3abadbd
--- /dev/null
+++ b/tools/libxc/xc_resource.c
@@ -0,0 +1,150 @@
+/*
+ * xc_resource.c
+ *
+ * Generic resource access API
+ *
+ * Copyright (C) 2014 Intel Corporation
+ * Author Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#include "xc_private.h"
+
+static int xc_resource_op_one(xc_interface *xch, xc_resource_op_t *op)
+{
+ int rc;
+ DECLARE_PLATFORM_OP;
+ DECLARE_NAMED_HYPERCALL_BOUNCE(entries, op->entries,
+ op->nr_entries * sizeof(*op->entries),
+ XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
+
+ if ( xc_hypercall_bounce_pre(xch, entries) )
+ return -1;
+
+ platform_op.cmd = XENPF_resource_op;
+ platform_op.u.resource_op.nr_entries = op->nr_entries;
+ platform_op.u.resource_op.cpu = op->cpu;
+ set_xen_guest_handle(platform_op.u.resource_op.entries, entries);
+
+ rc = do_platform_op(xch, &platform_op);
+ op->result = rc;
+
+ xc_hypercall_bounce_post(xch, entries);
+
+ return rc;
+}
+
+static int xc_resource_op_multi(xc_interface *xch, uint32_t nr_ops, xc_resource_op_t *ops)
+{
+ int rc, i, entries_size;
+ xc_resource_op_t *op;
+ multicall_entry_t *call;
+ DECLARE_HYPERCALL_BUFFER(multicall_entry_t, call_list);
+ xc_hypercall_buffer_array_t *platform_ops, *entries_list = NULL;
+
+ call_list = xc_hypercall_buffer_alloc(xch, call_list,
+ sizeof(*call_list) * nr_ops);
+ if ( !call_list )
+ return -1;
+
+ platform_ops = xc_hypercall_buffer_array_create(xch, nr_ops);
+ if ( !platform_ops )
+ {
+ rc = -1;
+ goto out;
+ }
+
+ entries_list = xc_hypercall_buffer_array_create(xch, nr_ops);
+ if ( !entries_list )
+ {
+ rc = -1;
+ goto out;
+ }
+
+ for ( i = 0; i < nr_ops; i++ )
+ {
+ DECLARE_HYPERCALL_BUFFER(xen_platform_op_t, platform_op);
+ DECLARE_HYPERCALL_BUFFER(xc_resource_entry_t, entries);
+
+ op = ops + i;
+
+ platform_op = xc_hypercall_buffer_array_alloc(xch, platform_ops, i,
+ platform_op, sizeof(xen_platform_op_t));
+ if ( !platform_op )
+ {
+ rc = -1;
+ goto out;
+ }
+
+ entries_size = sizeof(xc_resource_entry_t) * op->nr_entries;
+ entries = xc_hypercall_buffer_array_alloc(xch, entries_list, i,
+ entries, entries_size);
+ if ( !entries)
+ {
+ rc = -1;
+ goto out;
+ }
+ memcpy(entries, op->entries, entries_size);
+
+ call = call_list + i;
+ call->op = __HYPERVISOR_platform_op;
+ call->args[0] = HYPERCALL_BUFFER_AS_ARG(platform_op);
+
+ platform_op->interface_version = XENPF_INTERFACE_VERSION;
+ platform_op->cmd = XENPF_resource_op;
+ platform_op->u.resource_op.cpu = op->cpu;
+ platform_op->u.resource_op.nr_entries = op->nr_entries;
+ set_xen_guest_handle(platform_op->u.resource_op.entries, entries);
+ }
+
+ rc = do_multicall_op(xch, HYPERCALL_BUFFER(call_list), nr_ops);
+
+ for ( i = 0; i < nr_ops; i++ )
+ {
+ DECLARE_HYPERCALL_BUFFER(xc_resource_entry_t, entries);
+ op = ops + i;
+
+ call = call_list + i;
+ op->result = call->result;
+
+ entries_size = sizeof(xc_resource_entry_t) * op->nr_entries;
+ entries = xc_hypercall_buffer_array_get(xch, entries_list, i,
+ entries, entries_size);
+ memcpy(op->entries, entries, entries_size);
+ }
+
+out:
+ xc_hypercall_buffer_array_destroy(xch, entries_list);
+ xc_hypercall_buffer_array_destroy(xch, platform_ops);
+ xc_hypercall_buffer_free(xch, call_list);
+ return rc;
+}
+
+int xc_resource_op(xc_interface *xch, uint32_t nr_ops, xc_resource_op_t *ops)
+{
+ if ( nr_ops == 1 )
+ return xc_resource_op_one(xch, ops);
+ else if ( nr_ops > 1 )
+ return xc_resource_op_multi(xch, nr_ops, ops);
+ else
+ return -1;
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h
index 514b241..6edb738 100644
--- a/tools/libxc/xenctrl.h
+++ b/tools/libxc/xenctrl.h
@@ -47,6 +47,7 @@
#include <xen/xsm/flask_op.h>
#include <xen/tmem.h>
#include <xen/kexec.h>
+#include <xen/platform.h>
#include "xentoollog.h"
@@ -2655,6 +2656,22 @@ int xc_kexec_load(xc_interface *xch, uint8_t type, uint16_t arch,
*/
int xc_kexec_unload(xc_interface *xch, int type);
+typedef xenpf_resource_entry_t xc_resource_entry_t;
+
+/*
+ * Generic resource operation which contains multiple non-preemptible
+ * resource access entries that passed to xc_resource_op().
+ */
+struct xc_resource_op {
+ uint64_t result; /* on return, check this field first */
+ uint32_t cpu; /* which cpu to run */
+ uint32_t nr_entries; /* number of resource entries */
+ xc_resource_entry_t *entries;
+};
+
+typedef struct xc_resource_op xc_resource_op_t;
+int xc_resource_op(xc_interface *xch, uint32_t nr_ops, xc_resource_op_t *ops);
+
#endif /* XENCTRL_H */
/*
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* [PATCH v17 04/10] x86: detect and initialize Cache Monitoring Technology feature
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (2 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 03/10] tools: provide interface for generic resource access Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 14:03 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 05/10] x86: dynamically attach/detach CMT service for a guest Chao Peng
` (5 subsequent siblings)
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Detect Cache Monitoring Technology(CMT) feature and enumerate the
resource types, one of which is to monitor the L3 cache occupancy.
Also introduce a Xen command line parameter to control the Platform
Shared Resource such as CMT.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
docs/misc/xen-command-line.markdown | 21 +++++++
xen/arch/x86/Makefile | 1 +
xen/arch/x86/psr.c | 114 +++++++++++++++++++++++++++++++++++
xen/arch/x86/setup.c | 1 +
xen/include/asm-x86/cpufeature.h | 1 +
xen/include/asm-x86/psr.h | 51 ++++++++++++++++
6 files changed, 189 insertions(+)
create mode 100644 xen/arch/x86/psr.c
create mode 100644 xen/include/asm-x86/psr.h
diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index af93e17..5514431 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1005,6 +1005,27 @@ This option can be specified more than once (up to 8 times at present).
### ple\_window
> `= <integer>`
+### psr (Intel)
+> `= List of ( cmt:<boolean> | rmid_max:<integer> )`
+
+> Default: `psr=cmt:0,rmid_max:255`
+
+Platform Shared Resource(PSR) Services. Intel Haswell and later server
+platforms offer information about the sharing of resources.
+
+To use the PSR monitoring service for a certain domain, a Resource
+Monitoring ID(RMID) is used to bind the domain to corresponding shared
+resource. RMID is a hardware-provided layer of abstraction between software
+and logical processors.
+
+The following resources are available:
+* Cache Monitoring Technology (Haswell and later). Information
+regarding the L3 cache occupancy.
+
+`cmt` instructs Xen to enable/disable Cache Monitoring Technology.
+
+`rmid_max` indicates the max value for rmid.
+
### reboot
> `= t[riple] | k[bd] | a[cpi] | p[ci] | n[o] [, [w]arm | [c]old]`
diff --git a/xen/arch/x86/Makefile b/xen/arch/x86/Makefile
index c1e244d..86ca5f8 100644
--- a/xen/arch/x86/Makefile
+++ b/xen/arch/x86/Makefile
@@ -42,6 +42,7 @@ obj-y += numa.o
obj-y += pci.o
obj-y += percpu.o
obj-y += physdev.o
+obj-y += psr.o
obj-y += setup.o
obj-y += shutdown.o
obj-y += smp.o
diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
new file mode 100644
index 0000000..a4cbc0a
--- /dev/null
+++ b/xen/arch/x86/psr.c
@@ -0,0 +1,114 @@
+/*
+ * pqos.c: Platform Shared Resource related service for guest.
+ *
+ * Copyright (c) 2014, Intel Corporation
+ * Author: Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <xen/init.h>
+#include <xen/cpu.h>
+#include <asm/psr.h>
+
+#define PSR_CMT (1<<0)
+
+struct psr_cmt *__read_mostly psr_cmt;
+static bool_t __initdata opt_psr;
+static unsigned int __initdata opt_rmid_max = 255;
+
+static void __init parse_psr_param(char *s)
+{
+ char *ss, *val_str;
+
+ do {
+ ss = strchr(s, ',');
+ if ( ss )
+ *ss = '\0';
+
+ val_str = strchr(s, ':');
+ if ( val_str )
+ *val_str++ = '\0';
+
+ if ( !strcmp(s, "cmt") && ( !val_str || parse_bool(val_str) == 1 ) )
+ opt_psr |= PSR_CMT;
+ else if ( val_str && !strcmp(s, "rmid_max") )
+ opt_rmid_max = simple_strtoul(val_str, NULL, 0);
+
+ s = ss + 1;
+ } while ( ss );
+}
+custom_param("psr", parse_psr_param);
+
+static void __init init_psr_cmt(unsigned int rmid_max)
+{
+ unsigned int eax, ebx, ecx, edx;
+ unsigned int rmid;
+
+ if ( !boot_cpu_has(X86_FEATURE_CMT) )
+ return;
+
+ cpuid_count(0xf, 0, &eax, &ebx, &ecx, &edx);
+ if ( !edx )
+ return;
+
+ psr_cmt = xzalloc(struct psr_cmt);
+ if ( !psr_cmt )
+ return;
+
+ psr_cmt->features = edx;
+ psr_cmt->rmid_mask = ~(~0ull << get_count_order(ebx));
+ psr_cmt->rmid_max = min(rmid_max, ebx);
+
+ if ( psr_cmt->features & PSR_RESOURCE_TYPE_L3 )
+ {
+ cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+ psr_cmt->l3.upscaling_factor = ebx;
+ psr_cmt->l3.rmid_max = ecx;
+ psr_cmt->l3.features = edx;
+ }
+
+ psr_cmt->rmid_max = min(rmid_max, psr_cmt->l3.rmid_max);
+ psr_cmt->rmid_to_dom = xmalloc_array(domid_t, psr_cmt->rmid_max + 1);
+ if ( !psr_cmt->rmid_to_dom )
+ {
+ xfree(psr_cmt);
+ psr_cmt = NULL;
+ return;
+ }
+
+ /*
+ * Once CMT is enabled each CPU will always require a RMID to associate
+ * with it. To reduce the waste of RMID, reserve RMID 0 for all CPUs that
+ * have no domain being monitored.
+ */
+ psr_cmt->rmid_to_dom[0] = DOMID_XEN;
+ for ( rmid = 1; rmid <= psr_cmt->rmid_max; rmid++ )
+ psr_cmt->rmid_to_dom[rmid] = DOMID_INVALID;
+
+ printk(XENLOG_INFO "Cache Monitoring Technology enabled\n");
+}
+
+static int __init init_psr(void)
+{
+ if ( opt_psr & PSR_CMT && opt_rmid_max )
+ init_psr_cmt(opt_rmid_max);
+ return 0;
+}
+__initcall(init_psr);
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index 8c8b91f..3856fcc 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -49,6 +49,7 @@
#include <xen/cpu.h>
#include <asm/nmi.h>
#include <asm/alternative.h>
+#include <asm/psr.h>
/* opt_nosmp: If true, secondary processors are ignored. */
static bool_t __initdata opt_nosmp;
diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
index 8014241..137d75c 100644
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -148,6 +148,7 @@
#define X86_FEATURE_ERMS (7*32+ 9) /* Enhanced REP MOVSB/STOSB */
#define X86_FEATURE_INVPCID (7*32+10) /* Invalidate Process Context ID */
#define X86_FEATURE_RTM (7*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CMT (7*32+12) /* Cache Monitoring Technology */
#define X86_FEATURE_NO_FPU_SEL (7*32+13) /* FPU CS/DS stored as zero */
#define X86_FEATURE_MPX (7*32+14) /* Memory Protection Extensions */
#define X86_FEATURE_RDSEED (7*32+18) /* RDSEED instruction */
diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
new file mode 100644
index 0000000..8a3803c
--- /dev/null
+++ b/xen/include/asm-x86/psr.h
@@ -0,0 +1,51 @@
+/*
+ * psr.h: Platform Shared Resource related service for guest.
+ *
+ * Copyright (c) 2014, Intel Corporation
+ * Author: Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#ifndef __ASM_PSR_H__
+#define __ASM_PSR_H__
+
+/* Resource Type Enumeration */
+#define PSR_RESOURCE_TYPE_L3 0x2
+
+/* L3 Monitoring Features */
+#define PSR_CMT_L3_OCCUPANCY 0x1
+
+struct psr_cmt_l3 {
+ unsigned int features;
+ unsigned int upscaling_factor;
+ unsigned int rmid_max;
+};
+
+struct psr_cmt {
+ unsigned long rmid_mask;
+ unsigned int rmid_max;
+ unsigned int features;
+ domid_t *rmid_to_dom;
+ struct psr_cmt_l3 l3;
+};
+
+extern struct psr_cmt *psr_cmt;
+
+#endif /* __ASM_PSR_H__ */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 04/10] x86: detect and initialize Cache Monitoring Technology feature
2014-09-29 10:40 ` [PATCH v17 04/10] x86: detect and initialize Cache Monitoring Technology feature Chao Peng
@ 2014-09-29 14:03 ` Andrew Cooper
0 siblings, 0 replies; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 14:03 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> Detect Cache Monitoring Technology(CMT) feature and enumerate the
> resource types, one of which is to monitor the L3 cache occupancy.
>
> Also introduce a Xen command line parameter to control the Platform
> Shared Resource such as CMT.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> docs/misc/xen-command-line.markdown | 21 +++++++
> xen/arch/x86/Makefile | 1 +
> xen/arch/x86/psr.c | 114 +++++++++++++++++++++++++++++++++++
> xen/arch/x86/setup.c | 1 +
> xen/include/asm-x86/cpufeature.h | 1 +
> xen/include/asm-x86/psr.h | 51 ++++++++++++++++
> 6 files changed, 189 insertions(+)
> create mode 100644 xen/arch/x86/psr.c
> create mode 100644 xen/include/asm-x86/psr.h
>
> diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
> index af93e17..5514431 100644
> --- a/docs/misc/xen-command-line.markdown
> +++ b/docs/misc/xen-command-line.markdown
> @@ -1005,6 +1005,27 @@ This option can be specified more than once (up to 8 times at present).
> ### ple\_window
> > `= <integer>`
>
> +### psr (Intel)
> +> `= List of ( cmt:<boolean> | rmid_max:<integer> )`
> +
> +> Default: `psr=cmt:0,rmid_max:255`
> +
> +Platform Shared Resource(PSR) Services. Intel Haswell and later server
> +platforms offer information about the sharing of resources.
> +
> +To use the PSR monitoring service for a certain domain, a Resource
> +Monitoring ID(RMID) is used to bind the domain to corresponding shared
> +resource. RMID is a hardware-provided layer of abstraction between software
> +and logical processors.
> +
> +The following resources are available:
> +* Cache Monitoring Technology (Haswell and later). Information
> +regarding the L3 cache occupancy.
> +
> +`cmt` instructs Xen to enable/disable Cache Monitoring Technology.
> +
> +`rmid_max` indicates the max value for rmid.
> +
> ### reboot
> > `= t[riple] | k[bd] | a[cpi] | p[ci] | n[o] [, [w]arm | [c]old]`
>
> diff --git a/xen/arch/x86/Makefile b/xen/arch/x86/Makefile
> index c1e244d..86ca5f8 100644
> --- a/xen/arch/x86/Makefile
> +++ b/xen/arch/x86/Makefile
> @@ -42,6 +42,7 @@ obj-y += numa.o
> obj-y += pci.o
> obj-y += percpu.o
> obj-y += physdev.o
> +obj-y += psr.o
> obj-y += setup.o
> obj-y += shutdown.o
> obj-y += smp.o
> diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
> new file mode 100644
> index 0000000..a4cbc0a
> --- /dev/null
> +++ b/xen/arch/x86/psr.c
> @@ -0,0 +1,114 @@
> +/*
> + * pqos.c: Platform Shared Resource related service for guest.
> + *
> + * Copyright (c) 2014, Intel Corporation
> + * Author: Dongxiao Xu <dongxiao.xu@intel.com>
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
> + * more details.
> + */
> +#include <xen/init.h>
> +#include <xen/cpu.h>
> +#include <asm/psr.h>
> +
> +#define PSR_CMT (1<<0)
> +
> +struct psr_cmt *__read_mostly psr_cmt;
> +static bool_t __initdata opt_psr;
> +static unsigned int __initdata opt_rmid_max = 255;
> +
> +static void __init parse_psr_param(char *s)
> +{
> + char *ss, *val_str;
> +
> + do {
> + ss = strchr(s, ',');
> + if ( ss )
> + *ss = '\0';
> +
> + val_str = strchr(s, ':');
> + if ( val_str )
> + *val_str++ = '\0';
> +
> + if ( !strcmp(s, "cmt") && ( !val_str || parse_bool(val_str) == 1 ) )
> + opt_psr |= PSR_CMT;
> + else if ( val_str && !strcmp(s, "rmid_max") )
> + opt_rmid_max = simple_strtoul(val_str, NULL, 0);
> +
> + s = ss + 1;
> + } while ( ss );
> +}
> +custom_param("psr", parse_psr_param);
> +
> +static void __init init_psr_cmt(unsigned int rmid_max)
> +{
> + unsigned int eax, ebx, ecx, edx;
> + unsigned int rmid;
> +
> + if ( !boot_cpu_has(X86_FEATURE_CMT) )
> + return;
> +
> + cpuid_count(0xf, 0, &eax, &ebx, &ecx, &edx);
> + if ( !edx )
> + return;
> +
> + psr_cmt = xzalloc(struct psr_cmt);
> + if ( !psr_cmt )
> + return;
> +
> + psr_cmt->features = edx;
> + psr_cmt->rmid_mask = ~(~0ull << get_count_order(ebx));
> + psr_cmt->rmid_max = min(rmid_max, ebx);
> +
> + if ( psr_cmt->features & PSR_RESOURCE_TYPE_L3 )
> + {
> + cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
> + psr_cmt->l3.upscaling_factor = ebx;
> + psr_cmt->l3.rmid_max = ecx;
> + psr_cmt->l3.features = edx;
> + }
> +
> + psr_cmt->rmid_max = min(rmid_max, psr_cmt->l3.rmid_max);
> + psr_cmt->rmid_to_dom = xmalloc_array(domid_t, psr_cmt->rmid_max + 1);
> + if ( !psr_cmt->rmid_to_dom )
> + {
> + xfree(psr_cmt);
> + psr_cmt = NULL;
> + return;
> + }
> +
> + /*
> + * Once CMT is enabled each CPU will always require a RMID to associate
> + * with it. To reduce the waste of RMID, reserve RMID 0 for all CPUs that
> + * have no domain being monitored.
> + */
> + psr_cmt->rmid_to_dom[0] = DOMID_XEN;
> + for ( rmid = 1; rmid <= psr_cmt->rmid_max; rmid++ )
> + psr_cmt->rmid_to_dom[rmid] = DOMID_INVALID;
> +
> + printk(XENLOG_INFO "Cache Monitoring Technology enabled\n");
> +}
> +
> +static int __init init_psr(void)
> +{
> + if ( opt_psr & PSR_CMT && opt_rmid_max )
> + init_psr_cmt(opt_rmid_max);
> + return 0;
> +}
> +__initcall(init_psr);
> +
> +/*
> + * Local variables:
> + * mode: C
> + * c-file-style: "BSD"
> + * c-basic-offset: 4
> + * tab-width: 4
> + * indent-tabs-mode: nil
> + * End:
> + */
> diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
> index 8c8b91f..3856fcc 100644
> --- a/xen/arch/x86/setup.c
> +++ b/xen/arch/x86/setup.c
> @@ -49,6 +49,7 @@
> #include <xen/cpu.h>
> #include <asm/nmi.h>
> #include <asm/alternative.h>
> +#include <asm/psr.h>
>
> /* opt_nosmp: If true, secondary processors are ignored. */
> static bool_t __initdata opt_nosmp;
> diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
> index 8014241..137d75c 100644
> --- a/xen/include/asm-x86/cpufeature.h
> +++ b/xen/include/asm-x86/cpufeature.h
> @@ -148,6 +148,7 @@
> #define X86_FEATURE_ERMS (7*32+ 9) /* Enhanced REP MOVSB/STOSB */
> #define X86_FEATURE_INVPCID (7*32+10) /* Invalidate Process Context ID */
> #define X86_FEATURE_RTM (7*32+11) /* Restricted Transactional Memory */
> +#define X86_FEATURE_CMT (7*32+12) /* Cache Monitoring Technology */
> #define X86_FEATURE_NO_FPU_SEL (7*32+13) /* FPU CS/DS stored as zero */
> #define X86_FEATURE_MPX (7*32+14) /* Memory Protection Extensions */
> #define X86_FEATURE_RDSEED (7*32+18) /* RDSEED instruction */
> diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
> new file mode 100644
> index 0000000..8a3803c
> --- /dev/null
> +++ b/xen/include/asm-x86/psr.h
> @@ -0,0 +1,51 @@
> +/*
> + * psr.h: Platform Shared Resource related service for guest.
> + *
> + * Copyright (c) 2014, Intel Corporation
> + * Author: Dongxiao Xu <dongxiao.xu@intel.com>
> + *
> + * This program is free software; you can redistribute it and/or modify it
> + * under the terms and conditions of the GNU General Public License,
> + * version 2, as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope it will be useful, but WITHOUT
> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
> + * more details.
> + */
> +#ifndef __ASM_PSR_H__
> +#define __ASM_PSR_H__
> +
> +/* Resource Type Enumeration */
> +#define PSR_RESOURCE_TYPE_L3 0x2
> +
> +/* L3 Monitoring Features */
> +#define PSR_CMT_L3_OCCUPANCY 0x1
> +
> +struct psr_cmt_l3 {
> + unsigned int features;
> + unsigned int upscaling_factor;
> + unsigned int rmid_max;
> +};
> +
> +struct psr_cmt {
> + unsigned long rmid_mask;
> + unsigned int rmid_max;
> + unsigned int features;
> + domid_t *rmid_to_dom;
> + struct psr_cmt_l3 l3;
> +};
> +
> +extern struct psr_cmt *psr_cmt;
> +
> +#endif /* __ASM_PSR_H__ */
> +
> +/*
> + * Local variables:
> + * mode: C
> + * c-file-style: "BSD"
> + * c-basic-offset: 4
> + * tab-width: 4
> + * indent-tabs-mode: nil
> + * End:
> + */
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 05/10] x86: dynamically attach/detach CMT service for a guest
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (3 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 04/10] x86: detect and initialize Cache Monitoring Technology feature Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 14:05 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 06/10] x86: collect global CMT information Chao Peng
` (4 subsequent siblings)
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Add hypervisor side support for dynamically attach and detach
Cache Monitoring Technology(CMT) services for a certain guest.
When attach CMT service for a guest, system will allocate an
RMID for it. When detach or guest is shutdown, the RMID will be
recycled for future use.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
xen/arch/x86/domain.c | 3 +++
xen/arch/x86/domctl.c | 29 ++++++++++++++++++++++++++
xen/arch/x86/psr.c | 46 ++++++++++++++++++++++++++++++++++++++++++
xen/include/asm-x86/domain.h | 2 ++
xen/include/asm-x86/psr.h | 10 +++++++++
xen/include/public/domctl.h | 12 +++++++++++
6 files changed, 102 insertions(+)
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 7b1dfe6..3cfd8f4 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -60,6 +60,7 @@
#include <xen/numa.h>
#include <xen/iommu.h>
#include <compat/vcpu.h>
+#include <asm/psr.h>
DEFINE_PER_CPU(struct vcpu *, curr_vcpu);
DEFINE_PER_CPU(unsigned long, cr4);
@@ -647,6 +648,8 @@ void arch_domain_destroy(struct domain *d)
free_xenheap_page(d->shared_info);
cleanup_domain_irq_mapping(d);
+
+ psr_free_rmid(d);
}
unsigned long pv_guest_cr4_fixup(const struct vcpu *v, unsigned long guest_cr4)
diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
index 7a5de43..6ed480a 100644
--- a/xen/arch/x86/domctl.c
+++ b/xen/arch/x86/domctl.c
@@ -35,6 +35,7 @@
#include <asm/mem_sharing.h>
#include <asm/xstate.h>
#include <asm/debugger.h>
+#include <asm/psr.h>
static int gdbsx_guest_mem_io(
domid_t domid, struct xen_domctl_gdbsx_memio *iop)
@@ -1319,6 +1320,34 @@ long arch_do_domctl(
}
break;
+ case XEN_DOMCTL_psr_cmt_op:
+ if ( !psr_cmt_enabled() )
+ {
+ ret = -ENODEV;
+ break;
+ }
+
+ switch ( domctl->u.psr_cmt_op.cmd )
+ {
+ case XEN_DOMCTL_PSR_CMT_OP_ATTACH:
+ ret = psr_alloc_rmid(d);
+ break;
+ case XEN_DOMCTL_PSR_CMT_OP_DETACH:
+ if ( d->arch.psr_rmid > 0 )
+ psr_free_rmid(d);
+ else
+ ret = -ENOENT;
+ break;
+ case XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID:
+ domctl->u.psr_cmt_op.data = d->arch.psr_rmid;
+ copyback = 1;
+ break;
+ default:
+ ret = -ENOSYS;
+ break;
+ }
+ break;
+
default:
ret = iommu_do_domctl(domctl, d, u_domctl);
break;
diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
index a4cbc0a..4b4a4cf 100644
--- a/xen/arch/x86/psr.c
+++ b/xen/arch/x86/psr.c
@@ -15,6 +15,7 @@
*/
#include <xen/init.h>
#include <xen/cpu.h>
+#include <xen/sched.h>
#include <asm/psr.h>
#define PSR_CMT (1<<0)
@@ -103,6 +104,51 @@ static int __init init_psr(void)
}
__initcall(init_psr);
+/* Called with domain lock held, no psr specific lock needed */
+int psr_alloc_rmid(struct domain *d)
+{
+ unsigned int rmid;
+
+ ASSERT(psr_cmt_enabled());
+
+ if ( d->arch.psr_rmid > 0 )
+ return -EEXIST;
+
+ for ( rmid = 1; rmid <= psr_cmt->rmid_max; rmid++ )
+ {
+ if ( psr_cmt->rmid_to_dom[rmid] != DOMID_INVALID )
+ continue;
+
+ psr_cmt->rmid_to_dom[rmid] = d->domain_id;
+ break;
+ }
+
+ /* No RMID available, assign RMID=0 by default. */
+ if ( rmid > psr_cmt->rmid_max )
+ {
+ d->arch.psr_rmid = 0;
+ return -EUSERS;
+ }
+
+ d->arch.psr_rmid = rmid;
+
+ return 0;
+}
+
+/* Called with domain lock held, no psr specific lock needed */
+void psr_free_rmid(struct domain *d)
+{
+ unsigned int rmid;
+
+ rmid = d->arch.psr_rmid;
+ /* We do not free system reserved "RMID=0". */
+ if ( rmid == 0 )
+ return;
+
+ psr_cmt->rmid_to_dom[rmid] = DOMID_INVALID;
+ d->arch.psr_rmid = 0;
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
index 7abe1b3..2be1d1e 100644
--- a/xen/include/asm-x86/domain.h
+++ b/xen/include/asm-x86/domain.h
@@ -314,6 +314,8 @@ struct arch_domain
/* Shared page for notifying that explicit PIRQ EOI is required. */
unsigned long *pirq_eoi_map;
unsigned long pirq_eoi_map_mfn;
+
+ unsigned int psr_rmid; /* RMID assigned to the domain for CMT */
} __cacheline_aligned;
#define has_arch_pdevs(d) (!list_empty(&(d)->arch.pdev_list))
diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
index 8a3803c..98cfa6d 100644
--- a/xen/include/asm-x86/psr.h
+++ b/xen/include/asm-x86/psr.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PSR_H__
#define __ASM_PSR_H__
+#include <xen/types.h>
+
/* Resource Type Enumeration */
#define PSR_RESOURCE_TYPE_L3 0x2
@@ -38,6 +40,14 @@ struct psr_cmt {
extern struct psr_cmt *psr_cmt;
+static inline bool_t psr_cmt_enabled(void)
+{
+ return !!psr_cmt;
+}
+
+int psr_alloc_rmid(struct domain *d);
+void psr_free_rmid(struct domain *d);
+
#endif /* __ASM_PSR_H__ */
/*
diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index cfa39b3..59220ed 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -965,6 +965,16 @@ struct xen_domctl_vnuma {
typedef struct xen_domctl_vnuma xen_domctl_vnuma_t;
DEFINE_XEN_GUEST_HANDLE(xen_domctl_vnuma_t);
+struct xen_domctl_psr_cmt_op {
+#define XEN_DOMCTL_PSR_CMT_OP_DETACH 0
+#define XEN_DOMCTL_PSR_CMT_OP_ATTACH 1
+#define XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID 2
+ uint32_t cmd;
+ uint32_t data;
+};
+typedef struct xen_domctl_psr_cmt_op xen_domctl_psr_cmt_op_t;
+DEFINE_XEN_GUEST_HANDLE(xen_domctl_psr_cmt_op_t);
+
struct xen_domctl {
uint32_t cmd;
#define XEN_DOMCTL_createdomain 1
@@ -1038,6 +1048,7 @@ struct xen_domctl {
#define XEN_DOMCTL_get_vcpu_msrs 72
#define XEN_DOMCTL_set_vcpu_msrs 73
#define XEN_DOMCTL_setvnumainfo 74
+#define XEN_DOMCTL_psr_cmt_op 75
#define XEN_DOMCTL_gdbsx_guestmemio 1000
#define XEN_DOMCTL_gdbsx_pausevcpu 1001
#define XEN_DOMCTL_gdbsx_unpausevcpu 1002
@@ -1099,6 +1110,7 @@ struct xen_domctl {
struct xen_domctl_gdbsx_pauseunp_vcpu gdbsx_pauseunp_vcpu;
struct xen_domctl_gdbsx_domstatus gdbsx_domstatus;
struct xen_domctl_vnuma vnuma;
+ struct xen_domctl_psr_cmt_op psr_cmt_op;
uint8_t pad[128];
} u;
};
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 05/10] x86: dynamically attach/detach CMT service for a guest
2014-09-29 10:40 ` [PATCH v17 05/10] x86: dynamically attach/detach CMT service for a guest Chao Peng
@ 2014-09-29 14:05 ` Andrew Cooper
0 siblings, 0 replies; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 14:05 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> Add hypervisor side support for dynamically attach and detach
> Cache Monitoring Technology(CMT) services for a certain guest.
>
> When attach CMT service for a guest, system will allocate an
> RMID for it. When detach or guest is shutdown, the RMID will be
> recycled for future use.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> xen/arch/x86/domain.c | 3 +++
> xen/arch/x86/domctl.c | 29 ++++++++++++++++++++++++++
> xen/arch/x86/psr.c | 46 ++++++++++++++++++++++++++++++++++++++++++
> xen/include/asm-x86/domain.h | 2 ++
> xen/include/asm-x86/psr.h | 10 +++++++++
> xen/include/public/domctl.h | 12 +++++++++++
> 6 files changed, 102 insertions(+)
>
> diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
> index 7b1dfe6..3cfd8f4 100644
> --- a/xen/arch/x86/domain.c
> +++ b/xen/arch/x86/domain.c
> @@ -60,6 +60,7 @@
> #include <xen/numa.h>
> #include <xen/iommu.h>
> #include <compat/vcpu.h>
> +#include <asm/psr.h>
>
> DEFINE_PER_CPU(struct vcpu *, curr_vcpu);
> DEFINE_PER_CPU(unsigned long, cr4);
> @@ -647,6 +648,8 @@ void arch_domain_destroy(struct domain *d)
>
> free_xenheap_page(d->shared_info);
> cleanup_domain_irq_mapping(d);
> +
> + psr_free_rmid(d);
> }
>
> unsigned long pv_guest_cr4_fixup(const struct vcpu *v, unsigned long guest_cr4)
> diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
> index 7a5de43..6ed480a 100644
> --- a/xen/arch/x86/domctl.c
> +++ b/xen/arch/x86/domctl.c
> @@ -35,6 +35,7 @@
> #include <asm/mem_sharing.h>
> #include <asm/xstate.h>
> #include <asm/debugger.h>
> +#include <asm/psr.h>
>
> static int gdbsx_guest_mem_io(
> domid_t domid, struct xen_domctl_gdbsx_memio *iop)
> @@ -1319,6 +1320,34 @@ long arch_do_domctl(
> }
> break;
>
> + case XEN_DOMCTL_psr_cmt_op:
> + if ( !psr_cmt_enabled() )
> + {
> + ret = -ENODEV;
> + break;
> + }
> +
> + switch ( domctl->u.psr_cmt_op.cmd )
> + {
> + case XEN_DOMCTL_PSR_CMT_OP_ATTACH:
> + ret = psr_alloc_rmid(d);
> + break;
> + case XEN_DOMCTL_PSR_CMT_OP_DETACH:
> + if ( d->arch.psr_rmid > 0 )
> + psr_free_rmid(d);
> + else
> + ret = -ENOENT;
> + break;
> + case XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID:
> + domctl->u.psr_cmt_op.data = d->arch.psr_rmid;
> + copyback = 1;
> + break;
> + default:
> + ret = -ENOSYS;
> + break;
> + }
> + break;
> +
> default:
> ret = iommu_do_domctl(domctl, d, u_domctl);
> break;
> diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
> index a4cbc0a..4b4a4cf 100644
> --- a/xen/arch/x86/psr.c
> +++ b/xen/arch/x86/psr.c
> @@ -15,6 +15,7 @@
> */
> #include <xen/init.h>
> #include <xen/cpu.h>
> +#include <xen/sched.h>
> #include <asm/psr.h>
>
> #define PSR_CMT (1<<0)
> @@ -103,6 +104,51 @@ static int __init init_psr(void)
> }
> __initcall(init_psr);
>
> +/* Called with domain lock held, no psr specific lock needed */
> +int psr_alloc_rmid(struct domain *d)
> +{
> + unsigned int rmid;
> +
> + ASSERT(psr_cmt_enabled());
> +
> + if ( d->arch.psr_rmid > 0 )
> + return -EEXIST;
> +
> + for ( rmid = 1; rmid <= psr_cmt->rmid_max; rmid++ )
> + {
> + if ( psr_cmt->rmid_to_dom[rmid] != DOMID_INVALID )
> + continue;
> +
> + psr_cmt->rmid_to_dom[rmid] = d->domain_id;
> + break;
> + }
> +
> + /* No RMID available, assign RMID=0 by default. */
> + if ( rmid > psr_cmt->rmid_max )
> + {
> + d->arch.psr_rmid = 0;
> + return -EUSERS;
> + }
> +
> + d->arch.psr_rmid = rmid;
> +
> + return 0;
> +}
> +
> +/* Called with domain lock held, no psr specific lock needed */
> +void psr_free_rmid(struct domain *d)
> +{
> + unsigned int rmid;
> +
> + rmid = d->arch.psr_rmid;
> + /* We do not free system reserved "RMID=0". */
> + if ( rmid == 0 )
> + return;
> +
> + psr_cmt->rmid_to_dom[rmid] = DOMID_INVALID;
> + d->arch.psr_rmid = 0;
> +}
> +
> /*
> * Local variables:
> * mode: C
> diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
> index 7abe1b3..2be1d1e 100644
> --- a/xen/include/asm-x86/domain.h
> +++ b/xen/include/asm-x86/domain.h
> @@ -314,6 +314,8 @@ struct arch_domain
> /* Shared page for notifying that explicit PIRQ EOI is required. */
> unsigned long *pirq_eoi_map;
> unsigned long pirq_eoi_map_mfn;
> +
> + unsigned int psr_rmid; /* RMID assigned to the domain for CMT */
> } __cacheline_aligned;
>
> #define has_arch_pdevs(d) (!list_empty(&(d)->arch.pdev_list))
> diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
> index 8a3803c..98cfa6d 100644
> --- a/xen/include/asm-x86/psr.h
> +++ b/xen/include/asm-x86/psr.h
> @@ -16,6 +16,8 @@
> #ifndef __ASM_PSR_H__
> #define __ASM_PSR_H__
>
> +#include <xen/types.h>
> +
> /* Resource Type Enumeration */
> #define PSR_RESOURCE_TYPE_L3 0x2
>
> @@ -38,6 +40,14 @@ struct psr_cmt {
>
> extern struct psr_cmt *psr_cmt;
>
> +static inline bool_t psr_cmt_enabled(void)
> +{
> + return !!psr_cmt;
> +}
> +
> +int psr_alloc_rmid(struct domain *d);
> +void psr_free_rmid(struct domain *d);
> +
> #endif /* __ASM_PSR_H__ */
>
> /*
> diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
> index cfa39b3..59220ed 100644
> --- a/xen/include/public/domctl.h
> +++ b/xen/include/public/domctl.h
> @@ -965,6 +965,16 @@ struct xen_domctl_vnuma {
> typedef struct xen_domctl_vnuma xen_domctl_vnuma_t;
> DEFINE_XEN_GUEST_HANDLE(xen_domctl_vnuma_t);
>
> +struct xen_domctl_psr_cmt_op {
> +#define XEN_DOMCTL_PSR_CMT_OP_DETACH 0
> +#define XEN_DOMCTL_PSR_CMT_OP_ATTACH 1
> +#define XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID 2
> + uint32_t cmd;
> + uint32_t data;
> +};
> +typedef struct xen_domctl_psr_cmt_op xen_domctl_psr_cmt_op_t;
> +DEFINE_XEN_GUEST_HANDLE(xen_domctl_psr_cmt_op_t);
> +
> struct xen_domctl {
> uint32_t cmd;
> #define XEN_DOMCTL_createdomain 1
> @@ -1038,6 +1048,7 @@ struct xen_domctl {
> #define XEN_DOMCTL_get_vcpu_msrs 72
> #define XEN_DOMCTL_set_vcpu_msrs 73
> #define XEN_DOMCTL_setvnumainfo 74
> +#define XEN_DOMCTL_psr_cmt_op 75
> #define XEN_DOMCTL_gdbsx_guestmemio 1000
> #define XEN_DOMCTL_gdbsx_pausevcpu 1001
> #define XEN_DOMCTL_gdbsx_unpausevcpu 1002
> @@ -1099,6 +1110,7 @@ struct xen_domctl {
> struct xen_domctl_gdbsx_pauseunp_vcpu gdbsx_pauseunp_vcpu;
> struct xen_domctl_gdbsx_domstatus gdbsx_domstatus;
> struct xen_domctl_vnuma vnuma;
> + struct xen_domctl_psr_cmt_op psr_cmt_op;
> uint8_t pad[128];
> } u;
> };
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 06/10] x86: collect global CMT information
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (4 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 05/10] x86: dynamically attach/detach CMT service for a guest Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 14:07 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 07/10] x86: enable CMT for each domain RMID Chao Peng
` (3 subsequent siblings)
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
This implementation tries to put all policies into user space, thus some
global CMT information needs to be exposed, such as the total RMID count,
L3 upscaling factor, etc.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
xen/arch/x86/cpu/intel_cacheinfo.c | 49 ++----------------------------------
xen/arch/x86/sysctl.c | 43 +++++++++++++++++++++++++++++++
xen/include/asm-x86/cpufeature.h | 45 +++++++++++++++++++++++++++++++++
xen/include/public/sysctl.h | 14 +++++++++++
4 files changed, 104 insertions(+), 47 deletions(-)
diff --git a/xen/arch/x86/cpu/intel_cacheinfo.c b/xen/arch/x86/cpu/intel_cacheinfo.c
index 430f939..48970c0 100644
--- a/xen/arch/x86/cpu/intel_cacheinfo.c
+++ b/xen/arch/x86/cpu/intel_cacheinfo.c
@@ -81,54 +81,9 @@ static struct _cache_table cache_table[] __cpuinitdata =
{ 0x00, 0, 0}
};
-
-enum _cache_type
-{
- CACHE_TYPE_NULL = 0,
- CACHE_TYPE_DATA = 1,
- CACHE_TYPE_INST = 2,
- CACHE_TYPE_UNIFIED = 3
-};
-
-union _cpuid4_leaf_eax {
- struct {
- enum _cache_type type:5;
- unsigned int level:3;
- unsigned int is_self_initializing:1;
- unsigned int is_fully_associative:1;
- unsigned int reserved:4;
- unsigned int num_threads_sharing:12;
- unsigned int num_cores_on_die:6;
- } split;
- u32 full;
-};
-
-union _cpuid4_leaf_ebx {
- struct {
- unsigned int coherency_line_size:12;
- unsigned int physical_line_partition:10;
- unsigned int ways_of_associativity:10;
- } split;
- u32 full;
-};
-
-union _cpuid4_leaf_ecx {
- struct {
- unsigned int number_of_sets:32;
- } split;
- u32 full;
-};
-
-struct _cpuid4_info {
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
- unsigned long size;
-};
-
unsigned short num_cache_leaves;
-static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+int cpuid4_cache_lookup(int index, struct cpuid4_info *this_leaf)
{
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
@@ -185,7 +140,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
- struct _cpuid4_info this_leaf;
+ struct cpuid4_info this_leaf;
int retval;
diff --git a/xen/arch/x86/sysctl.c b/xen/arch/x86/sysctl.c
index 15d4b91..b95408f 100644
--- a/xen/arch/x86/sysctl.c
+++ b/xen/arch/x86/sysctl.c
@@ -28,6 +28,7 @@
#include <xen/nodemask.h>
#include <xen/cpu.h>
#include <xsm/xsm.h>
+#include <asm/psr.h>
#define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0)
@@ -101,6 +102,48 @@ long arch_do_sysctl(
}
break;
+ case XEN_SYSCTL_psr_cmt_op:
+ if ( !psr_cmt_enabled() )
+ return -ENODEV;
+
+ if ( sysctl->u.psr_cmt_op.flags != 0 )
+ return -EINVAL;
+
+ switch ( sysctl->u.psr_cmt_op.cmd )
+ {
+ case XEN_SYSCTL_PSR_CMT_enabled:
+ sysctl->u.psr_cmt_op.data =
+ (psr_cmt->features & PSR_RESOURCE_TYPE_L3) &&
+ (psr_cmt->l3.features & PSR_CMT_L3_OCCUPANCY);
+ break;
+ case XEN_SYSCTL_PSR_CMT_get_total_rmid:
+ sysctl->u.psr_cmt_op.data = psr_cmt->rmid_max;
+ break;
+ case XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor:
+ sysctl->u.psr_cmt_op.data = psr_cmt->l3.upscaling_factor;
+ break;
+ case XEN_SYSCTL_PSR_CMT_get_l3_cache_size:
+ {
+ struct cpuid4_info info;
+
+ ret = cpuid4_cache_lookup(3, &info);
+ if ( ret < 0 )
+ break;
+
+ sysctl->u.psr_cmt_op.data = info.size / 1024; /* in KB unit */
+ }
+ break;
+ default:
+ sysctl->u.psr_cmt_op.data = 0;
+ ret = -ENOSYS;
+ break;
+ }
+
+ if ( __copy_to_guest(u_sysctl, sysctl, 1) )
+ ret = -EFAULT;
+
+ break;
+
default:
ret = -ENOSYS;
break;
diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
index 137d75c..d3bd14d 100644
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -215,6 +215,51 @@
#define cpu_has_vmx boot_cpu_has(X86_FEATURE_VMXE)
#define cpu_has_cpuid_faulting boot_cpu_has(X86_FEATURE_CPUID_FAULTING)
+
+enum _cache_type {
+ CACHE_TYPE_NULL = 0,
+ CACHE_TYPE_DATA = 1,
+ CACHE_TYPE_INST = 2,
+ CACHE_TYPE_UNIFIED = 3
+};
+
+union _cpuid4_leaf_eax {
+ struct {
+ enum _cache_type type:5;
+ unsigned int level:3;
+ unsigned int is_self_initializing:1;
+ unsigned int is_fully_associative:1;
+ unsigned int reserved:4;
+ unsigned int num_threads_sharing:12;
+ unsigned int num_cores_on_die:6;
+ } split;
+ u32 full;
+};
+
+union _cpuid4_leaf_ebx {
+ struct {
+ unsigned int coherency_line_size:12;
+ unsigned int physical_line_partition:10;
+ unsigned int ways_of_associativity:10;
+ } split;
+ u32 full;
+};
+
+union _cpuid4_leaf_ecx {
+ struct {
+ unsigned int number_of_sets:32;
+ } split;
+ u32 full;
+};
+
+struct cpuid4_info {
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ unsigned long size;
+};
+
+int cpuid4_cache_lookup(int index, struct cpuid4_info *this_leaf);
#endif
#endif /* __ASM_I386_CPUFEATURE_H */
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
index 3588698..66b6e47 100644
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -636,6 +636,18 @@ struct xen_sysctl_coverage_op {
typedef struct xen_sysctl_coverage_op xen_sysctl_coverage_op_t;
DEFINE_XEN_GUEST_HANDLE(xen_sysctl_coverage_op_t);
+#define XEN_SYSCTL_PSR_CMT_get_total_rmid 0
+#define XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor 1
+/* The L3 cache size is returned in KB unit */
+#define XEN_SYSCTL_PSR_CMT_get_l3_cache_size 2
+#define XEN_SYSCTL_PSR_CMT_enabled 3
+struct xen_sysctl_psr_cmt_op {
+ uint32_t cmd;
+ uint32_t flags; /* padding variable, may be extended for future use */
+ uint64_t data;
+};
+typedef struct xen_sysctl_psr_cmt_op xen_sysctl_psr_cmt_op_t;
+DEFINE_XEN_GUEST_HANDLE(xen_sysctl_psr_cmt_op_t);
struct xen_sysctl {
uint32_t cmd;
@@ -658,6 +670,7 @@ struct xen_sysctl {
#define XEN_SYSCTL_cpupool_op 18
#define XEN_SYSCTL_scheduler_op 19
#define XEN_SYSCTL_coverage_op 20
+#define XEN_SYSCTL_psr_cmt_op 21
uint32_t interface_version; /* XEN_SYSCTL_INTERFACE_VERSION */
union {
struct xen_sysctl_readconsole readconsole;
@@ -679,6 +692,7 @@ struct xen_sysctl {
struct xen_sysctl_cpupool_op cpupool_op;
struct xen_sysctl_scheduler_op scheduler_op;
struct xen_sysctl_coverage_op coverage_op;
+ struct xen_sysctl_psr_cmt_op psr_cmt_op;
uint8_t pad[128];
} u;
};
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 06/10] x86: collect global CMT information
2014-09-29 10:40 ` [PATCH v17 06/10] x86: collect global CMT information Chao Peng
@ 2014-09-29 14:07 ` Andrew Cooper
0 siblings, 0 replies; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 14:07 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> This implementation tries to put all policies into user space, thus some
> global CMT information needs to be exposed, such as the total RMID count,
> L3 upscaling factor, etc.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> xen/arch/x86/cpu/intel_cacheinfo.c | 49 ++----------------------------------
> xen/arch/x86/sysctl.c | 43 +++++++++++++++++++++++++++++++
> xen/include/asm-x86/cpufeature.h | 45 +++++++++++++++++++++++++++++++++
> xen/include/public/sysctl.h | 14 +++++++++++
> 4 files changed, 104 insertions(+), 47 deletions(-)
>
> diff --git a/xen/arch/x86/cpu/intel_cacheinfo.c b/xen/arch/x86/cpu/intel_cacheinfo.c
> index 430f939..48970c0 100644
> --- a/xen/arch/x86/cpu/intel_cacheinfo.c
> +++ b/xen/arch/x86/cpu/intel_cacheinfo.c
> @@ -81,54 +81,9 @@ static struct _cache_table cache_table[] __cpuinitdata =
> { 0x00, 0, 0}
> };
>
> -
> -enum _cache_type
> -{
> - CACHE_TYPE_NULL = 0,
> - CACHE_TYPE_DATA = 1,
> - CACHE_TYPE_INST = 2,
> - CACHE_TYPE_UNIFIED = 3
> -};
> -
> -union _cpuid4_leaf_eax {
> - struct {
> - enum _cache_type type:5;
> - unsigned int level:3;
> - unsigned int is_self_initializing:1;
> - unsigned int is_fully_associative:1;
> - unsigned int reserved:4;
> - unsigned int num_threads_sharing:12;
> - unsigned int num_cores_on_die:6;
> - } split;
> - u32 full;
> -};
> -
> -union _cpuid4_leaf_ebx {
> - struct {
> - unsigned int coherency_line_size:12;
> - unsigned int physical_line_partition:10;
> - unsigned int ways_of_associativity:10;
> - } split;
> - u32 full;
> -};
> -
> -union _cpuid4_leaf_ecx {
> - struct {
> - unsigned int number_of_sets:32;
> - } split;
> - u32 full;
> -};
> -
> -struct _cpuid4_info {
> - union _cpuid4_leaf_eax eax;
> - union _cpuid4_leaf_ebx ebx;
> - union _cpuid4_leaf_ecx ecx;
> - unsigned long size;
> -};
> -
> unsigned short num_cache_leaves;
>
> -static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
> +int cpuid4_cache_lookup(int index, struct cpuid4_info *this_leaf)
> {
> union _cpuid4_leaf_eax eax;
> union _cpuid4_leaf_ebx ebx;
> @@ -185,7 +140,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
> * parameters cpuid leaf to find the cache details
> */
> for (i = 0; i < num_cache_leaves; i++) {
> - struct _cpuid4_info this_leaf;
> + struct cpuid4_info this_leaf;
>
> int retval;
>
> diff --git a/xen/arch/x86/sysctl.c b/xen/arch/x86/sysctl.c
> index 15d4b91..b95408f 100644
> --- a/xen/arch/x86/sysctl.c
> +++ b/xen/arch/x86/sysctl.c
> @@ -28,6 +28,7 @@
> #include <xen/nodemask.h>
> #include <xen/cpu.h>
> #include <xsm/xsm.h>
> +#include <asm/psr.h>
>
> #define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0)
>
> @@ -101,6 +102,48 @@ long arch_do_sysctl(
> }
> break;
>
> + case XEN_SYSCTL_psr_cmt_op:
> + if ( !psr_cmt_enabled() )
> + return -ENODEV;
> +
> + if ( sysctl->u.psr_cmt_op.flags != 0 )
> + return -EINVAL;
> +
> + switch ( sysctl->u.psr_cmt_op.cmd )
> + {
> + case XEN_SYSCTL_PSR_CMT_enabled:
> + sysctl->u.psr_cmt_op.data =
> + (psr_cmt->features & PSR_RESOURCE_TYPE_L3) &&
> + (psr_cmt->l3.features & PSR_CMT_L3_OCCUPANCY);
> + break;
> + case XEN_SYSCTL_PSR_CMT_get_total_rmid:
> + sysctl->u.psr_cmt_op.data = psr_cmt->rmid_max;
> + break;
> + case XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor:
> + sysctl->u.psr_cmt_op.data = psr_cmt->l3.upscaling_factor;
> + break;
> + case XEN_SYSCTL_PSR_CMT_get_l3_cache_size:
> + {
> + struct cpuid4_info info;
> +
> + ret = cpuid4_cache_lookup(3, &info);
> + if ( ret < 0 )
> + break;
> +
> + sysctl->u.psr_cmt_op.data = info.size / 1024; /* in KB unit */
> + }
> + break;
> + default:
> + sysctl->u.psr_cmt_op.data = 0;
> + ret = -ENOSYS;
> + break;
> + }
> +
> + if ( __copy_to_guest(u_sysctl, sysctl, 1) )
> + ret = -EFAULT;
> +
> + break;
> +
> default:
> ret = -ENOSYS;
> break;
> diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
> index 137d75c..d3bd14d 100644
> --- a/xen/include/asm-x86/cpufeature.h
> +++ b/xen/include/asm-x86/cpufeature.h
> @@ -215,6 +215,51 @@
> #define cpu_has_vmx boot_cpu_has(X86_FEATURE_VMXE)
>
> #define cpu_has_cpuid_faulting boot_cpu_has(X86_FEATURE_CPUID_FAULTING)
> +
> +enum _cache_type {
> + CACHE_TYPE_NULL = 0,
> + CACHE_TYPE_DATA = 1,
> + CACHE_TYPE_INST = 2,
> + CACHE_TYPE_UNIFIED = 3
> +};
> +
> +union _cpuid4_leaf_eax {
> + struct {
> + enum _cache_type type:5;
> + unsigned int level:3;
> + unsigned int is_self_initializing:1;
> + unsigned int is_fully_associative:1;
> + unsigned int reserved:4;
> + unsigned int num_threads_sharing:12;
> + unsigned int num_cores_on_die:6;
> + } split;
> + u32 full;
> +};
> +
> +union _cpuid4_leaf_ebx {
> + struct {
> + unsigned int coherency_line_size:12;
> + unsigned int physical_line_partition:10;
> + unsigned int ways_of_associativity:10;
> + } split;
> + u32 full;
> +};
> +
> +union _cpuid4_leaf_ecx {
> + struct {
> + unsigned int number_of_sets:32;
> + } split;
> + u32 full;
> +};
> +
> +struct cpuid4_info {
> + union _cpuid4_leaf_eax eax;
> + union _cpuid4_leaf_ebx ebx;
> + union _cpuid4_leaf_ecx ecx;
> + unsigned long size;
> +};
> +
> +int cpuid4_cache_lookup(int index, struct cpuid4_info *this_leaf);
> #endif
>
> #endif /* __ASM_I386_CPUFEATURE_H */
> diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
> index 3588698..66b6e47 100644
> --- a/xen/include/public/sysctl.h
> +++ b/xen/include/public/sysctl.h
> @@ -636,6 +636,18 @@ struct xen_sysctl_coverage_op {
> typedef struct xen_sysctl_coverage_op xen_sysctl_coverage_op_t;
> DEFINE_XEN_GUEST_HANDLE(xen_sysctl_coverage_op_t);
>
> +#define XEN_SYSCTL_PSR_CMT_get_total_rmid 0
> +#define XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor 1
> +/* The L3 cache size is returned in KB unit */
> +#define XEN_SYSCTL_PSR_CMT_get_l3_cache_size 2
> +#define XEN_SYSCTL_PSR_CMT_enabled 3
> +struct xen_sysctl_psr_cmt_op {
> + uint32_t cmd;
> + uint32_t flags; /* padding variable, may be extended for future use */
> + uint64_t data;
> +};
> +typedef struct xen_sysctl_psr_cmt_op xen_sysctl_psr_cmt_op_t;
> +DEFINE_XEN_GUEST_HANDLE(xen_sysctl_psr_cmt_op_t);
>
> struct xen_sysctl {
> uint32_t cmd;
> @@ -658,6 +670,7 @@ struct xen_sysctl {
> #define XEN_SYSCTL_cpupool_op 18
> #define XEN_SYSCTL_scheduler_op 19
> #define XEN_SYSCTL_coverage_op 20
> +#define XEN_SYSCTL_psr_cmt_op 21
> uint32_t interface_version; /* XEN_SYSCTL_INTERFACE_VERSION */
> union {
> struct xen_sysctl_readconsole readconsole;
> @@ -679,6 +692,7 @@ struct xen_sysctl {
> struct xen_sysctl_cpupool_op cpupool_op;
> struct xen_sysctl_scheduler_op scheduler_op;
> struct xen_sysctl_coverage_op coverage_op;
> + struct xen_sysctl_psr_cmt_op psr_cmt_op;
> uint8_t pad[128];
> } u;
> };
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 07/10] x86: enable CMT for each domain RMID
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (5 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 06/10] x86: collect global CMT information Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 14:08 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 08/10] x86: add CMT related MSRs in allowed list Chao Peng
` (2 subsequent siblings)
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
If the CMT service is attached to a domain, its related RMID
will be set to hardware for monitoring when the domain's vcpu is
scheduled in. When the domain's vcpu is scheduled out, RMID 0
(system reserved) will be set for monitoring.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
---
xen/arch/x86/domain.c | 5 +++++
xen/arch/x86/psr.c | 27 +++++++++++++++++++++++++++
xen/include/asm-x86/msr-index.h | 3 +++
xen/include/asm-x86/psr.h | 1 +
4 files changed, 36 insertions(+)
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 3cfd8f4..04a6719 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1418,6 +1418,8 @@ static void __context_switch(void)
{
memcpy(&p->arch.user_regs, stack_regs, CTXT_SWITCH_STACK_BYTES);
vcpu_save_fpu(p);
+ if ( psr_cmt_enabled() )
+ psr_assoc_rmid(0);
p->arch.ctxt_switch_from(p);
}
@@ -1442,6 +1444,9 @@ static void __context_switch(void)
}
vcpu_restore_fpu_eager(n);
n->arch.ctxt_switch_to(n);
+
+ if ( psr_cmt_enabled() && n->domain->arch.psr_rmid > 0 )
+ psr_assoc_rmid(n->domain->arch.psr_rmid);
}
gdt = !is_pv_32on64_vcpu(n) ? per_cpu(gdt_table, cpu) :
diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
index 4b4a4cf..c5ee16e 100644
--- a/xen/arch/x86/psr.c
+++ b/xen/arch/x86/psr.c
@@ -20,9 +20,15 @@
#define PSR_CMT (1<<0)
+struct pqr_assoc {
+ uint64_t val;
+ bool_t initialized;
+};
+
struct psr_cmt *__read_mostly psr_cmt;
static bool_t __initdata opt_psr;
static unsigned int __initdata opt_rmid_max = 255;
+static DEFINE_PER_CPU(struct pqr_assoc, pqr_assoc);
static void __init parse_psr_param(char *s)
{
@@ -149,6 +155,27 @@ void psr_free_rmid(struct domain *d)
d->arch.psr_rmid = 0;
}
+void psr_assoc_rmid(unsigned int rmid)
+{
+ uint64_t val;
+ uint64_t new_val;
+ struct pqr_assoc *pqr = &this_cpu(pqr_assoc);
+
+ if ( !pqr->initialized )
+ {
+ rdmsrl(MSR_IA32_PQR_ASSOC, pqr->val);
+ pqr->initialized = 1;
+ }
+ val = pqr->val;
+
+ new_val = (val & ~psr_cmt->rmid_mask) | (rmid & psr_cmt->rmid_mask);
+ if ( val != new_val )
+ {
+ wrmsrl(MSR_IA32_PQR_ASSOC, new_val);
+ pqr->val = new_val;
+ }
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h
index 542222e..dcb2b87 100644
--- a/xen/include/asm-x86/msr-index.h
+++ b/xen/include/asm-x86/msr-index.h
@@ -323,6 +323,9 @@
#define MSR_IA32_TSC_DEADLINE 0x000006E0
#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
+/* Platform Shared Resource MSRs */
+#define MSR_IA32_PQR_ASSOC 0x00000c8f
+
/* Intel Model 6 */
#define MSR_P6_PERFCTR(n) (0x000000c1 + (n))
#define MSR_P6_EVNTSEL(n) (0x00000186 + (n))
diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
index 98cfa6d..b544306 100644
--- a/xen/include/asm-x86/psr.h
+++ b/xen/include/asm-x86/psr.h
@@ -47,6 +47,7 @@ static inline bool_t psr_cmt_enabled(void)
int psr_alloc_rmid(struct domain *d);
void psr_free_rmid(struct domain *d);
+void psr_assoc_rmid(unsigned int rmid);
#endif /* __ASM_PSR_H__ */
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 07/10] x86: enable CMT for each domain RMID
2014-09-29 10:40 ` [PATCH v17 07/10] x86: enable CMT for each domain RMID Chao Peng
@ 2014-09-29 14:08 ` Andrew Cooper
0 siblings, 0 replies; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 14:08 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> If the CMT service is attached to a domain, its related RMID
> will be set to hardware for monitoring when the domain's vcpu is
> scheduled in. When the domain's vcpu is scheduled out, RMID 0
> (system reserved) will be set for monitoring.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
> Acked-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> xen/arch/x86/domain.c | 5 +++++
> xen/arch/x86/psr.c | 27 +++++++++++++++++++++++++++
> xen/include/asm-x86/msr-index.h | 3 +++
> xen/include/asm-x86/psr.h | 1 +
> 4 files changed, 36 insertions(+)
>
> diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
> index 3cfd8f4..04a6719 100644
> --- a/xen/arch/x86/domain.c
> +++ b/xen/arch/x86/domain.c
> @@ -1418,6 +1418,8 @@ static void __context_switch(void)
> {
> memcpy(&p->arch.user_regs, stack_regs, CTXT_SWITCH_STACK_BYTES);
> vcpu_save_fpu(p);
> + if ( psr_cmt_enabled() )
> + psr_assoc_rmid(0);
> p->arch.ctxt_switch_from(p);
> }
>
> @@ -1442,6 +1444,9 @@ static void __context_switch(void)
> }
> vcpu_restore_fpu_eager(n);
> n->arch.ctxt_switch_to(n);
> +
> + if ( psr_cmt_enabled() && n->domain->arch.psr_rmid > 0 )
> + psr_assoc_rmid(n->domain->arch.psr_rmid);
> }
>
> gdt = !is_pv_32on64_vcpu(n) ? per_cpu(gdt_table, cpu) :
> diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
> index 4b4a4cf..c5ee16e 100644
> --- a/xen/arch/x86/psr.c
> +++ b/xen/arch/x86/psr.c
> @@ -20,9 +20,15 @@
>
> #define PSR_CMT (1<<0)
>
> +struct pqr_assoc {
> + uint64_t val;
> + bool_t initialized;
> +};
> +
> struct psr_cmt *__read_mostly psr_cmt;
> static bool_t __initdata opt_psr;
> static unsigned int __initdata opt_rmid_max = 255;
> +static DEFINE_PER_CPU(struct pqr_assoc, pqr_assoc);
>
> static void __init parse_psr_param(char *s)
> {
> @@ -149,6 +155,27 @@ void psr_free_rmid(struct domain *d)
> d->arch.psr_rmid = 0;
> }
>
> +void psr_assoc_rmid(unsigned int rmid)
> +{
> + uint64_t val;
> + uint64_t new_val;
> + struct pqr_assoc *pqr = &this_cpu(pqr_assoc);
> +
> + if ( !pqr->initialized )
> + {
> + rdmsrl(MSR_IA32_PQR_ASSOC, pqr->val);
> + pqr->initialized = 1;
> + }
> + val = pqr->val;
> +
> + new_val = (val & ~psr_cmt->rmid_mask) | (rmid & psr_cmt->rmid_mask);
> + if ( val != new_val )
> + {
> + wrmsrl(MSR_IA32_PQR_ASSOC, new_val);
> + pqr->val = new_val;
> + }
> +}
> +
> /*
> * Local variables:
> * mode: C
> diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h
> index 542222e..dcb2b87 100644
> --- a/xen/include/asm-x86/msr-index.h
> +++ b/xen/include/asm-x86/msr-index.h
> @@ -323,6 +323,9 @@
> #define MSR_IA32_TSC_DEADLINE 0x000006E0
> #define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
>
> +/* Platform Shared Resource MSRs */
> +#define MSR_IA32_PQR_ASSOC 0x00000c8f
> +
> /* Intel Model 6 */
> #define MSR_P6_PERFCTR(n) (0x000000c1 + (n))
> #define MSR_P6_EVNTSEL(n) (0x00000186 + (n))
> diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
> index 98cfa6d..b544306 100644
> --- a/xen/include/asm-x86/psr.h
> +++ b/xen/include/asm-x86/psr.h
> @@ -47,6 +47,7 @@ static inline bool_t psr_cmt_enabled(void)
>
> int psr_alloc_rmid(struct domain *d);
> void psr_free_rmid(struct domain *d);
> +void psr_assoc_rmid(unsigned int rmid);
>
> #endif /* __ASM_PSR_H__ */
>
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 08/10] x86: add CMT related MSRs in allowed list
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (6 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 07/10] x86: enable CMT for each domain RMID Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 14:09 ` Andrew Cooper
2014-09-29 10:40 ` [PATCH v17 09/10] xsm: add CMT related xsm policies Chao Peng
2014-09-29 10:40 ` [PATCH v17 10/10] tools: CMDs and APIs for Cache Monitoring Technology Chao Peng
9 siblings, 1 reply; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Tool stack will try to access the two MSRs to perform CMT
related operations, thus added them in the allowed list.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
xen/arch/x86/platform_hypercall.c | 8 ++++++++
xen/include/asm-x86/msr-index.h | 2 ++
2 files changed, 10 insertions(+)
diff --git a/xen/arch/x86/platform_hypercall.c b/xen/arch/x86/platform_hypercall.c
index 4b92b56..c049499 100644
--- a/xen/arch/x86/platform_hypercall.c
+++ b/xen/arch/x86/platform_hypercall.c
@@ -69,6 +69,14 @@ struct xen_resource_access {
static bool_t allow_access_msr(unsigned int msr)
{
+ switch ( msr )
+ {
+ /* MSR for CMT, refer to chapter 17.14 of Intel SDM. */
+ case MSR_IA32_QOSEVTSEL:
+ case MSR_IA32_QMC:
+ return 1;
+ }
+
return 0;
}
diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h
index dcb2b87..ae089fb 100644
--- a/xen/include/asm-x86/msr-index.h
+++ b/xen/include/asm-x86/msr-index.h
@@ -324,6 +324,8 @@
#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
/* Platform Shared Resource MSRs */
+#define MSR_IA32_QOSEVTSEL 0x00000c8d
+#define MSR_IA32_QMC 0x00000c8e
#define MSR_IA32_PQR_ASSOC 0x00000c8f
/* Intel Model 6 */
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH v17 08/10] x86: add CMT related MSRs in allowed list
2014-09-29 10:40 ` [PATCH v17 08/10] x86: add CMT related MSRs in allowed list Chao Peng
@ 2014-09-29 14:09 ` Andrew Cooper
0 siblings, 0 replies; 18+ messages in thread
From: Andrew Cooper @ 2014-09-29 14:09 UTC (permalink / raw)
To: Chao Peng, xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
Ian.Jackson, JBeulich, dgdegra
On 29/09/14 11:40, Chao Peng wrote:
> Tool stack will try to access the two MSRs to perform CMT
> related operations, thus added them in the allowed list.
>
> Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
> Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> xen/arch/x86/platform_hypercall.c | 8 ++++++++
> xen/include/asm-x86/msr-index.h | 2 ++
> 2 files changed, 10 insertions(+)
>
> diff --git a/xen/arch/x86/platform_hypercall.c b/xen/arch/x86/platform_hypercall.c
> index 4b92b56..c049499 100644
> --- a/xen/arch/x86/platform_hypercall.c
> +++ b/xen/arch/x86/platform_hypercall.c
> @@ -69,6 +69,14 @@ struct xen_resource_access {
>
> static bool_t allow_access_msr(unsigned int msr)
> {
> + switch ( msr )
> + {
> + /* MSR for CMT, refer to chapter 17.14 of Intel SDM. */
> + case MSR_IA32_QOSEVTSEL:
> + case MSR_IA32_QMC:
> + return 1;
> + }
> +
> return 0;
> }
>
> diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h
> index dcb2b87..ae089fb 100644
> --- a/xen/include/asm-x86/msr-index.h
> +++ b/xen/include/asm-x86/msr-index.h
> @@ -324,6 +324,8 @@
> #define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
>
> /* Platform Shared Resource MSRs */
> +#define MSR_IA32_QOSEVTSEL 0x00000c8d
> +#define MSR_IA32_QMC 0x00000c8e
> #define MSR_IA32_PQR_ASSOC 0x00000c8f
>
> /* Intel Model 6 */
^ permalink raw reply [flat|nested] 18+ messages in thread
* [PATCH v17 09/10] xsm: add CMT related xsm policies
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (7 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 08/10] x86: add CMT related MSRs in allowed list Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
2014-09-29 10:40 ` [PATCH v17 10/10] tools: CMDs and APIs for Cache Monitoring Technology Chao Peng
9 siblings, 0 replies; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Add xsm policies for CMT related hypercalls.
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Acked-by: Daniel De Graaf <dgdegra@tycho.nsa.gov>
---
tools/flask/policy/policy/modules/xen/xen.if | 2 +-
tools/flask/policy/policy/modules/xen/xen.te | 3 ++-
xen/xsm/flask/hooks.c | 6 ++++++
xen/xsm/flask/policy/access_vectors | 4 ++++
4 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/tools/flask/policy/policy/modules/xen/xen.if b/tools/flask/policy/policy/modules/xen/xen.if
index 32b51b6..641c797 100644
--- a/tools/flask/policy/policy/modules/xen/xen.if
+++ b/tools/flask/policy/policy/modules/xen/xen.if
@@ -49,7 +49,7 @@ define(`create_domain_common', `
getdomaininfo hypercall setvcpucontext setextvcpucontext
getscheduler getvcpuinfo getvcpuextstate getaddrsize
getaffinity setaffinity };
- allow $1 $2:domain2 { set_cpuid settsc setscheduler setclaim set_max_evtchn set_vnumainfo get_vnumainfo };
+ allow $1 $2:domain2 { set_cpuid settsc setscheduler setclaim set_max_evtchn set_vnumainfo get_vnumainfo psr_cmt_op };
allow $1 $2:security check_context;
allow $1 $2:shadow enable;
allow $1 $2:mmu { map_read map_write adjust memorymap physmap pinpage mmuext_op };
diff --git a/tools/flask/policy/policy/modules/xen/xen.te b/tools/flask/policy/policy/modules/xen/xen.te
index 6cecf97..d214470 100644
--- a/tools/flask/policy/policy/modules/xen/xen.te
+++ b/tools/flask/policy/policy/modules/xen/xen.te
@@ -66,6 +66,7 @@ allow dom0_t xen_t:xen {
};
allow dom0_t xen_t:xen2 {
resource_op
+ psr_cmt_op
};
allow dom0_t xen_t:mmu memorymap;
@@ -79,7 +80,7 @@ allow dom0_t dom0_t:domain {
getpodtarget setpodtarget set_misc_info set_virq_handler
};
allow dom0_t dom0_t:domain2 {
- set_cpuid gettsc settsc setscheduler set_max_evtchn set_vnumainfo get_vnumainfo
+ set_cpuid gettsc settsc setscheduler set_max_evtchn set_vnumainfo get_vnumainfo psr_cmt_op
};
allow dom0_t dom0_t:resource { add remove };
diff --git a/xen/xsm/flask/hooks.c b/xen/xsm/flask/hooks.c
index 9f36503..1bb3c00 100644
--- a/xen/xsm/flask/hooks.c
+++ b/xen/xsm/flask/hooks.c
@@ -722,6 +722,8 @@ static int flask_domctl(struct domain *d, int cmd)
case XEN_DOMCTL_setvnumainfo:
return current_has_perm(d, SECCLASS_DOMAIN, DOMAIN2__SET_VNUMAINFO);
+ case XEN_DOMCTL_psr_cmt_op:
+ return current_has_perm(d, SECCLASS_DOMAIN2, DOMAIN2__PSR_CMT_OP);
default:
printk("flask_domctl: Unknown op %d\n", cmd);
@@ -778,6 +780,10 @@ static int flask_sysctl(int cmd)
case XEN_SYSCTL_numainfo:
return domain_has_xen(current->domain, XEN__PHYSINFO);
+ case XEN_SYSCTL_psr_cmt_op:
+ return avc_current_has_perm(SECINITSID_XEN, SECCLASS_XEN2,
+ XEN2__PSR_CMT_OP, NULL);
+
default:
printk("flask_sysctl: Unknown op %d\n", cmd);
return -EPERM;
diff --git a/xen/xsm/flask/policy/access_vectors b/xen/xsm/flask/policy/access_vectors
index daf0de5..de0c707 100644
--- a/xen/xsm/flask/policy/access_vectors
+++ b/xen/xsm/flask/policy/access_vectors
@@ -81,6 +81,8 @@ class xen2
{
# XENPF_resource_op
resource_op
+# XEN_SYSCTL_psr_cmt_op
+ psr_cmt_op
}
# Classes domain and domain2 consist of operations that a domain performs on
@@ -212,6 +214,8 @@ class domain2
set_vnumainfo
# XENMEM_getvnumainfo
get_vnumainfo
+# XEN_DOMCTL_psr_cmt_op
+ psr_cmt_op
}
# Similar to class domain, but primarily contains domctls related to HVM domains
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread* [PATCH v17 10/10] tools: CMDs and APIs for Cache Monitoring Technology
2014-09-29 10:40 [PATCH v17 00/10] enable Cache Monitoring Technology (CMT) feature Chao Peng
` (8 preceding siblings ...)
2014-09-29 10:40 ` [PATCH v17 09/10] xsm: add CMT related xsm policies Chao Peng
@ 2014-09-29 10:40 ` Chao Peng
9 siblings, 0 replies; 18+ messages in thread
From: Chao Peng @ 2014-09-29 10:40 UTC (permalink / raw)
To: xen-devel
Cc: keir, Ian.Campbell, stefano.stabellini, George.Dunlap,
andrew.cooper3, Ian.Jackson, JBeulich, dgdegra
Introduced some new xl commands to enable/disable Cache Monitoring
Technology(CMT) feature.
The following two commands is to attach/detach the CMT feature
to/from a certain domain.
$ xl psr-cmt-attach domid
$ xl psr-cmt-detach domid
This command is to display the CMT information, such as L3 cache
occupancy.
$ xl psr-cmt-show cache_occupancy <domid>
Signed-off-by: Dongxiao Xu <dongxiao.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
docs/man/xl.pod.1 | 25 +++++
tools/libxc/Makefile | 1 +
tools/libxc/xc_msr_x86.h | 36 ++++++++
tools/libxc/xc_psr.c | 214 +++++++++++++++++++++++++++++++++++++++++++
tools/libxc/xenctrl.h | 17 ++++
tools/libxl/Makefile | 2 +-
tools/libxl/libxl.h | 19 ++++
tools/libxl/libxl_psr.c | 184 +++++++++++++++++++++++++++++++++++++
tools/libxl/libxl_types.idl | 4 +
tools/libxl/libxl_utils.c | 28 ++++++
tools/libxl/xl.h | 3 +
tools/libxl/xl_cmdimpl.c | 132 ++++++++++++++++++++++++++
tools/libxl/xl_cmdtable.c | 17 ++++
13 files changed, 681 insertions(+), 1 deletion(-)
create mode 100644 tools/libxc/xc_msr_x86.h
create mode 100644 tools/libxc/xc_psr.c
create mode 100644 tools/libxl/libxl_psr.c
diff --git a/docs/man/xl.pod.1 b/docs/man/xl.pod.1
index f1e95db..ef8cd24 100644
--- a/docs/man/xl.pod.1
+++ b/docs/man/xl.pod.1
@@ -1387,6 +1387,31 @@ Load FLASK policy from the given policy file. The initial policy is provided to
the hypervisor as a multiboot module; this command allows runtime updates to the
policy. Loading new security policy will reset runtime changes to device labels.
+=head1 Cache Monitoring Technology
+
+Some new hardware may offer monitoring capability in each logical processor to
+measure specific platform shared resource metric, for example, L3 cache
+occupancy. In Xen implementation, the monitoring granularity is domain level.
+To monitor a specific domain, just attach the domain id with the monitoring
+service. When the domain doesn't need to be monitored any more, detach the
+domain id from the monitoring service.
+
+=over 4
+
+=item B<psr-cmt-attach> [I<domain-id>]
+
+attach: Attach the platform shared resource monitoring service to a domain.
+
+=item B<psr-cmt-detach> [I<domain-id>]
+
+detach: Detach the platform shared resource monitoring service from a domain.
+
+=item B<psr-cmt-show> [I<psr-monitor-type>] [I<domain-id>]
+
+Show monitoring data for a certain domain or all domains. Current supported
+monitor types are:
+ - "cache-occupancy": showing the L3 cache occupancy.
+
=back
=head1 TO BE DOCUMENTED
diff --git a/tools/libxc/Makefile b/tools/libxc/Makefile
index dde6109..d8cc21b 100644
--- a/tools/libxc/Makefile
+++ b/tools/libxc/Makefile
@@ -35,6 +35,7 @@ CTRL_SRCS-y += xc_kexec.c
CTRL_SRCS-y += xtl_core.c
CTRL_SRCS-y += xtl_logger_stdio.c
CTRL_SRCS-y += xc_resource.c
+CTRL_SRCS-y += xc_psr.c
CTRL_SRCS-$(CONFIG_X86) += xc_pagetab.c
CTRL_SRCS-$(CONFIG_Linux) += xc_linux.c xc_linux_osdep.c
CTRL_SRCS-$(CONFIG_FreeBSD) += xc_freebsd.c xc_freebsd_osdep.c
diff --git a/tools/libxc/xc_msr_x86.h b/tools/libxc/xc_msr_x86.h
new file mode 100644
index 0000000..1e0ee99
--- /dev/null
+++ b/tools/libxc/xc_msr_x86.h
@@ -0,0 +1,36 @@
+/*
+ * xc_msr_x86.h
+ *
+ * MSR definition macros
+ *
+ * Copyright (C) 2014 Intel Corporation
+ * Author Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#ifndef XC_MSR_X86_H
+#define XC_MSR_X86_H
+
+#define MSR_IA32_QOSEVTSEL 0x00000c8d
+#define MSR_IA32_QMC 0x00000c8e
+
+#endif
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/tools/libxc/xc_psr.c b/tools/libxc/xc_psr.c
new file mode 100644
index 0000000..e333ea4
--- /dev/null
+++ b/tools/libxc/xc_psr.c
@@ -0,0 +1,214 @@
+/*
+ * xc_psr.c
+ *
+ * platform shared resource related API functions.
+ *
+ * Copyright (C) 2014 Intel Corporation
+ * Author Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#include "xc_private.h"
+#include "xc_msr_x86.h"
+
+#define IA32_QM_CTR_ERROR_MASK (0x3ull << 62)
+
+#define EVTID_L3_OCCUPANCY 0x1
+
+int xc_psr_cmt_attach(xc_interface *xch, uint32_t domid)
+{
+ DECLARE_DOMCTL;
+
+ domctl.cmd = XEN_DOMCTL_psr_cmt_op;
+ domctl.domain = (domid_t)domid;
+ domctl.u.psr_cmt_op.cmd = XEN_DOMCTL_PSR_CMT_OP_ATTACH;
+
+ return do_domctl(xch, &domctl);
+}
+
+int xc_psr_cmt_detach(xc_interface *xch, uint32_t domid)
+{
+ DECLARE_DOMCTL;
+
+ domctl.cmd = XEN_DOMCTL_psr_cmt_op;
+ domctl.domain = (domid_t)domid;
+ domctl.u.psr_cmt_op.cmd = XEN_DOMCTL_PSR_CMT_OP_DETACH;
+
+ return do_domctl(xch, &domctl);
+}
+
+int xc_psr_cmt_get_domain_rmid(xc_interface *xch, uint32_t domid,
+ uint32_t *rmid)
+{
+ int rc;
+ DECLARE_DOMCTL;
+
+ domctl.cmd = XEN_DOMCTL_psr_cmt_op;
+ domctl.domain = (domid_t)domid;
+ domctl.u.psr_cmt_op.cmd = XEN_DOMCTL_PSR_CMT_OP_QUERY_RMID;
+
+ rc = do_domctl(xch, &domctl);
+
+ if ( !rc )
+ *rmid = domctl.u.psr_cmt_op.data;
+
+ return rc;
+}
+
+int xc_psr_cmt_get_total_rmid(xc_interface *xch, uint32_t *total_rmid)
+{
+ static int val = 0;
+ int rc;
+ DECLARE_SYSCTL;
+
+ if ( val )
+ {
+ *total_rmid = val;
+ return 0;
+ }
+
+ sysctl.cmd = XEN_SYSCTL_psr_cmt_op;
+ sysctl.u.psr_cmt_op.cmd = XEN_SYSCTL_PSR_CMT_get_total_rmid;
+ sysctl.u.psr_cmt_op.flags = 0;
+
+ rc = xc_sysctl(xch, &sysctl);
+ if ( !rc )
+ val = *total_rmid = sysctl.u.psr_cmt_op.data;
+
+ return rc;
+}
+
+int xc_psr_cmt_get_l3_upscaling_factor(xc_interface *xch,
+ uint32_t *upscaling_factor)
+{
+ static int val = 0;
+ int rc;
+ DECLARE_SYSCTL;
+
+ if ( val )
+ {
+ *upscaling_factor = val;
+ return 0;
+ }
+
+ sysctl.cmd = XEN_SYSCTL_psr_cmt_op;
+ sysctl.u.psr_cmt_op.cmd =
+ XEN_SYSCTL_PSR_CMT_get_l3_upscaling_factor;
+ sysctl.u.psr_cmt_op.flags = 0;
+
+ rc = xc_sysctl(xch, &sysctl);
+ if ( !rc )
+ val = *upscaling_factor = sysctl.u.psr_cmt_op.data;
+
+ return rc;
+}
+
+int xc_psr_cmt_get_l3_cache_size(xc_interface *xch,
+ uint32_t *l3_cache_size)
+{
+ static int val = 0;
+ int rc;
+ DECLARE_SYSCTL;
+
+ if ( val )
+ {
+ *l3_cache_size = val;
+ return 0;
+ }
+
+ sysctl.cmd = XEN_SYSCTL_psr_cmt_op;
+ sysctl.u.psr_cmt_op.cmd =
+ XEN_SYSCTL_PSR_CMT_get_l3_cache_size;
+ sysctl.u.psr_cmt_op.flags = 0;
+
+ rc = xc_sysctl(xch, &sysctl);
+ if ( !rc )
+ val = *l3_cache_size= sysctl.u.psr_cmt_op.data;
+
+ return rc;
+}
+
+int xc_psr_cmt_get_data(xc_interface *xch, uint32_t rmid,
+ uint32_t cpu, xc_psr_cmt_type type, uint64_t *monitor_data)
+{
+ xc_resource_op_t op;
+ xc_resource_entry_t entries[2];
+ uint32_t evtid;
+ int rc;
+
+ switch ( type )
+ {
+ case XC_PSR_CMT_L3_OCCUPANCY:
+ evtid = EVTID_L3_OCCUPANCY;
+ break;
+ default:
+ return -1;
+ }
+
+ entries[0].cmd = XEN_RESOURCE_OP_MSR_WRITE;
+ entries[0].idx = MSR_IA32_QOSEVTSEL;
+ entries[0].val = (uint64_t)rmid << 32 | evtid;
+ entries[0].rsvd = 0;
+
+ entries[1].cmd = XEN_RESOURCE_OP_MSR_READ;
+ entries[1].idx = MSR_IA32_QMC;
+ entries[1].val = 0;
+ entries[1].rsvd = 0;
+
+ op.cpu = cpu;
+ op.nr_entries = 2;
+ op.entries = entries;
+
+ rc = xc_resource_op(xch, 1, &op);
+ if ( rc )
+ return rc;
+
+ if ( op.result || entries[1].val & IA32_QM_CTR_ERROR_MASK )
+ return -1;
+
+ *monitor_data = entries[1].val;
+
+ return 0;
+}
+
+int xc_psr_cmt_enabled(xc_interface *xch)
+{
+ static int val = -1;
+ int rc;
+ DECLARE_SYSCTL;
+
+ if ( val >= 0 )
+ return val;
+
+ sysctl.cmd = XEN_SYSCTL_psr_cmt_op;
+ sysctl.u.psr_cmt_op.cmd = XEN_SYSCTL_PSR_CMT_enabled;
+ sysctl.u.psr_cmt_op.flags = 0;
+
+ rc = do_sysctl(xch, &sysctl);
+ if ( !rc )
+ {
+ val = sysctl.u.psr_cmt_op.data;
+ return val;
+ }
+
+ return 0;
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h
index 6edb738..b0ab6f4 100644
--- a/tools/libxc/xenctrl.h
+++ b/tools/libxc/xenctrl.h
@@ -2672,6 +2672,23 @@ struct xc_resource_op {
typedef struct xc_resource_op xc_resource_op_t;
int xc_resource_op(xc_interface *xch, uint32_t nr_ops, xc_resource_op_t *ops);
+enum xc_psr_cmt_type {
+ XC_PSR_CMT_L3_OCCUPANCY,
+};
+typedef enum xc_psr_cmt_type xc_psr_cmt_type;
+int xc_psr_cmt_attach(xc_interface *xch, uint32_t domid);
+int xc_psr_cmt_detach(xc_interface *xch, uint32_t domid);
+int xc_psr_cmt_get_domain_rmid(xc_interface *xch, uint32_t domid,
+ uint32_t *rmid);
+int xc_psr_cmt_get_total_rmid(xc_interface *xch, uint32_t *total_rmid);
+int xc_psr_cmt_get_l3_upscaling_factor(xc_interface *xch,
+ uint32_t *upscaling_factor);
+int xc_psr_cmt_get_l3_cache_size(xc_interface *xch,
+ uint32_t *l3_cache_size);
+int xc_psr_cmt_get_data(xc_interface *xch, uint32_t rmid,
+ uint32_t cpu, uint32_t psr_cmt_type, uint64_t *monitor_data);
+int xc_psr_cmt_enabled(xc_interface *xch);
+
#endif /* XENCTRL_H */
/*
diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index 990414b..fd9ae28 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -43,7 +43,7 @@ LIBXL_OBJS-y += libxl_blktap2.o
else
LIBXL_OBJS-y += libxl_noblktap2.o
endif
-LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o
+LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o libxl_psr.o
LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o libxl_arm.o
ifeq ($(CONFIG_NetBSD),y)
diff --git a/tools/libxl/libxl.h b/tools/libxl/libxl.h
index bc68cac..5acc933 100644
--- a/tools/libxl/libxl.h
+++ b/tools/libxl/libxl.h
@@ -640,6 +640,13 @@ typedef uint8_t libxl_mac[6];
#define LIBXL_MAC_BYTES(mac) mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]
void libxl_mac_copy(libxl_ctx *ctx, libxl_mac *dst, libxl_mac *src);
+/*
+ * LIBXL_HAVE_PSR_CMT
+ *
+ * If this is defined, the Cache Monitoring Technology feature is supported.
+ */
+#define LIBXL_HAVE_PSR_CMT 1
+
typedef char **libxl_string_list;
void libxl_string_list_dispose(libxl_string_list *sl);
int libxl_string_list_length(const libxl_string_list *sl);
@@ -1380,6 +1387,18 @@ bool libxl_ms_vm_genid_is_zero(const libxl_ms_vm_genid *id);
void libxl_ms_vm_genid_copy(libxl_ctx *ctx, libxl_ms_vm_genid *dst,
libxl_ms_vm_genid *src);
+int libxl_get_socket_cpu(libxl_ctx *ctx, uint32_t socketid);
+
+int libxl_psr_cmt_attach(libxl_ctx *ctx, uint32_t domid);
+int libxl_psr_cmt_detach(libxl_ctx *ctx, uint32_t domid);
+int libxl_psr_cmt_domain_attached(libxl_ctx *ctx, uint32_t domid);
+int libxl_psr_cmt_enabled(libxl_ctx *ctx);
+int libxl_psr_cmt_get_total_rmid(libxl_ctx *ctx, uint32_t *total_rmid);
+int libxl_psr_cmt_get_l3_cache_size(libxl_ctx *ctx,
+ uint32_t *l3_cache_size);
+int libxl_psr_cmt_get_cache_occupancy(libxl_ctx *ctx, uint32_t domid,
+ uint32_t socketid, uint32_t *l3_cache_occupancy);
+
/* misc */
/* Each of these sets or clears the flag according to whether the
diff --git a/tools/libxl/libxl_psr.c b/tools/libxl/libxl_psr.c
new file mode 100644
index 0000000..5551be8
--- /dev/null
+++ b/tools/libxl/libxl_psr.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2014 Intel Corporation
+ * Author Dongxiao Xu <dongxiao.xu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#include "libxl_osdeps.h" /* must come before any other headers */
+#include "libxl_internal.h"
+
+
+#define IA32_QM_CTR_ERROR_MASK (0x3ul << 62)
+
+static void libxl_psr_cmt_err_msg(libxl_ctx *ctx, int err)
+{
+ GC_INIT(ctx);
+
+ char *msg;
+
+ switch (err) {
+ case ENOSYS:
+ msg = "unsupported operation";
+ break;
+ case ENODEV:
+ msg = "Cache Monitoring Technology is not supported in this system";
+ break;
+ case EEXIST:
+ msg = "Cache Monitoring Technology is already attached to this domain";
+ break;
+ case ENOENT:
+ msg = "Cache Monitoring Technology is not attached to this domain";
+ break;
+ case EUSERS:
+ msg = "there is no free RMID available";
+ break;
+ case ESRCH:
+ msg = "is this Domain ID valid?";
+ break;
+ case EFAULT:
+ msg = "failed to exchange data with Xen";
+ break;
+ default:
+ msg = "unknown error";
+ break;
+ }
+
+ LOGE(ERROR, "%s", msg);
+
+ GC_FREE;
+}
+
+int libxl_psr_cmt_attach(libxl_ctx *ctx, uint32_t domid)
+{
+ int rc;
+
+ rc = xc_psr_cmt_attach(ctx->xch, domid);
+ if (rc < 0) {
+ libxl_psr_cmt_err_msg(ctx, errno);
+ return ERROR_FAIL;
+ }
+
+ return 0;
+}
+
+int libxl_psr_cmt_detach(libxl_ctx *ctx, uint32_t domid)
+{
+ int rc;
+
+ rc = xc_psr_cmt_detach(ctx->xch, domid);
+ if (rc < 0) {
+ libxl_psr_cmt_err_msg(ctx, errno);
+ return ERROR_FAIL;
+ }
+
+ return 0;
+}
+
+int libxl_psr_cmt_domain_attached(libxl_ctx *ctx, uint32_t domid)
+{
+ int rc;
+ uint32_t rmid;
+
+ rc = xc_psr_cmt_get_domain_rmid(ctx->xch, domid, &rmid);
+ if (rc < 0)
+ return 0;
+
+ return !!rmid;
+}
+
+int libxl_psr_cmt_enabled(libxl_ctx *ctx)
+{
+ return xc_psr_cmt_enabled(ctx->xch);
+}
+
+int libxl_psr_cmt_get_total_rmid(libxl_ctx *ctx, uint32_t *total_rmid)
+{
+ int rc;
+
+ rc = xc_psr_cmt_get_total_rmid(ctx->xch, total_rmid);
+ if (rc < 0) {
+ libxl_psr_cmt_err_msg(ctx, errno);
+ return ERROR_FAIL;
+ }
+
+ return 0;
+}
+
+int libxl_psr_cmt_get_l3_cache_size(libxl_ctx *ctx,
+ uint32_t *l3_cache_size)
+{
+ int rc;
+
+ rc = xc_psr_cmt_get_l3_cache_size(ctx->xch, l3_cache_size);
+ if (rc < 0) {
+ libxl_psr_cmt_err_msg(ctx, errno);
+ return ERROR_FAIL;
+ }
+
+ return 0;
+}
+
+int libxl_psr_cmt_get_cache_occupancy(libxl_ctx *ctx, uint32_t domid,
+ uint32_t socketid, uint32_t *l3_cache_occupancy)
+{
+ GC_INIT(ctx);
+
+ unsigned int rmid;
+ uint32_t upscaling_factor;
+ uint64_t monitor_data;
+ int cpu, rc;
+ xc_psr_cmt_type type;
+
+ rc = xc_psr_cmt_get_domain_rmid(ctx->xch, domid, &rmid);
+ if (rc < 0 || rmid == 0) {
+ LOGE(ERROR, "fail to get the domain rmid, "
+ "or domain is not attached with platform QoS monitoring service");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ cpu = libxl_get_socket_cpu(ctx, socketid);
+ if (cpu < 0) {
+ LOGE(ERROR, "failed to get socket cpu");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ type = XC_PSR_CMT_L3_OCCUPANCY;
+ rc = xc_psr_cmt_get_data(ctx->xch, rmid, cpu, type, &monitor_data);
+ if (rc < 0) {
+ LOGE(ERROR, "failed to get monitoring data");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ rc = xc_psr_cmt_get_l3_upscaling_factor(ctx->xch, &upscaling_factor);
+ if (rc < 0) {
+ LOGE(ERROR, "failed to get L3 upscaling factor");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
+ *l3_cache_occupancy = upscaling_factor * monitor_data / 1024;
+ rc = 0;
+out:
+ GC_FREE;
+ return 0;
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index f1fcbc3..27a5022 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -635,3 +635,7 @@ libxl_event = Struct("event",[
])),
("domain_create_console_available", None),
]))])
+
+libxl_psr_cmt_type = Enumeration("psr_cmt_type", [
+ (1, "CACHE_OCCUPANCY"),
+ ])
diff --git a/tools/libxl/libxl_utils.c b/tools/libxl/libxl_utils.c
index 58df4f3..318a996 100644
--- a/tools/libxl/libxl_utils.c
+++ b/tools/libxl/libxl_utils.c
@@ -1065,6 +1065,34 @@ int libxl__random_bytes(libxl__gc *gc, uint8_t *buf, size_t len)
return ret;
}
+int libxl_get_socket_cpu(libxl_ctx *ctx, uint32_t socketid)
+{
+ int i, j, cpu, nr_cpus;
+ libxl_cputopology *topology;
+ int *socket_cpus;
+
+ topology = libxl_get_cpu_topology(ctx, &nr_cpus);
+ if (!topology)
+ return ERROR_FAIL;
+
+ socket_cpus = malloc(sizeof(int) * nr_cpus);
+ if (!socket_cpus) {
+ libxl_cputopology_list_free(topology, nr_cpus);
+ return ERROR_FAIL;
+ }
+
+ for (i = 0, j = 0; i < nr_cpus; i++)
+ if (topology[i].socket == socketid)
+ socket_cpus[j++] = i;
+
+ /* load balance among cpus in the same socket. */
+ cpu = socket_cpus[rand() % j];
+
+ free(socket_cpus);
+ libxl_cputopology_list_free(topology, nr_cpus);
+ return cpu;
+}
+
/*
* Local variables:
* mode: C
diff --git a/tools/libxl/xl.h b/tools/libxl/xl.h
index 10a2e66..abb1fac 100644
--- a/tools/libxl/xl.h
+++ b/tools/libxl/xl.h
@@ -110,6 +110,9 @@ int main_loadpolicy(int argc, char **argv);
int main_remus(int argc, char **argv);
#endif
int main_devd(int argc, char **argv);
+int main_psr_cmt_attach(int argc, char **argv);
+int main_psr_cmt_detach(int argc, char **argv);
+int main_psr_cmt_show(int argc, char **argv);
void help(const char *command);
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 698b3bc..77f19d7 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -7428,6 +7428,138 @@ out:
return ret;
}
+static int psr_cmt_show_cache_occupancy(uint32_t domid)
+{
+ uint32_t i, socketid, nr_sockets, total_rmid;
+ uint32_t l3_cache_size, l3_cache_occupancy;
+ libxl_physinfo info;
+ char *domain_name;
+ int rc, print_header, nr_domains;
+ libxl_dominfo *dominfo;
+
+ if (!libxl_psr_cmt_enabled(ctx)) {
+ printf("CMT is disabled in the system\n");
+ return -1;
+ }
+
+ rc = libxl_get_physinfo(ctx, &info);
+ if (rc < 0) {
+ printf("Failed getting physinfo, rc: %d\n", rc);
+ return -1;
+ }
+ nr_sockets = info.nr_cpus / info.threads_per_core / info.cores_per_socket;
+
+ rc = libxl_psr_cmt_get_total_rmid(ctx, &total_rmid);
+ if (rc < 0) {
+ printf("Failed to get max RMID value\n");
+ return -1;
+ }
+
+ rc = libxl_psr_cmt_get_l3_cache_size(ctx, &l3_cache_size);
+ if (rc < 0) {
+ printf("Failed to get system l3 cache size\n");
+ return -1;
+ }
+
+ printf("Total RMID: %d\n", total_rmid);
+ printf("Per-Socket L3 Cache Size: %d KB\n", l3_cache_size);
+
+ print_header = 1;
+ if (!(dominfo = libxl_list_domain(ctx, &nr_domains))) {
+ fprintf(stderr, "libxl_list_domain failed.\n");
+ return -1;
+ }
+ for (i = 0; i < nr_domains; i++) {
+ if (domid != ~0 && dominfo[i].domid != domid)
+ continue;
+ if (!libxl_psr_cmt_domain_attached(ctx, dominfo[i].domid))
+ continue;
+ if (print_header) {
+ printf("%-40s %5s", "Name", "ID");
+ for (socketid = 0; socketid < nr_sockets; socketid++)
+ printf("%14s %d", "Socket", socketid);
+ printf("\n");
+ print_header = 0;
+ }
+ domain_name = libxl_domid_to_name(ctx, dominfo[i].domid);
+ printf("%-40s %5d", domain_name, dominfo[i].domid);
+ free(domain_name);
+ for (socketid = 0; socketid < nr_sockets; socketid++) {
+ rc = libxl_psr_cmt_get_cache_occupancy(ctx, dominfo[i].domid,
+ socketid, &l3_cache_occupancy);
+ if ( !rc )
+ printf("%13u KB", l3_cache_occupancy);
+ }
+ printf("\n");
+ }
+ libxl_dominfo_list_free(dominfo, nr_domains);
+
+ return 0;
+}
+
+int main_psr_cmt_attach(int argc, char **argv)
+{
+ uint32_t domid;
+ int opt, ret = 0;
+
+ SWITCH_FOREACH_OPT(opt, "", NULL, "psr-cmt-attach", 1) {
+ /* No options */
+ }
+
+ domid = find_domain(argv[optind]);
+ ret = libxl_psr_cmt_attach(ctx, domid);
+
+ return ret;
+}
+
+int main_psr_cmt_detach(int argc, char **argv)
+{
+ uint32_t domid;
+ int opt, ret = 0;
+
+ SWITCH_FOREACH_OPT(opt, "", NULL, "psr-cmt-detach", 1) {
+ /* No options */
+ }
+
+ domid = find_domain(argv[optind]);
+ ret = libxl_psr_cmt_detach(ctx, domid);
+
+ return ret;
+}
+
+int main_psr_cmt_show(int argc, char **argv)
+{
+ int opt, ret = 0;
+ uint32_t domid;
+ libxl_psr_cmt_type type;
+
+ SWITCH_FOREACH_OPT(opt, "", NULL, "psr-cmt-show", 1) {
+ /* No options */
+ }
+
+ libxl_psr_cmt_type_from_string(argv[optind], &type);
+
+ if (optind + 1 >= argc)
+ domid = ~0;
+ else if (optind + 1 == argc - 1)
+ domid = find_domain(argv[optind + 1]);
+ else {
+ help("psr-cmt-show");
+ return 2;
+ }
+
+ switch (type) {
+ case LIBXL_PSR_CMT_TYPE_CACHE_OCCUPANCY:
+ ret = psr_cmt_show_cache_occupancy(domid);
+ break;
+ default:
+ help("psr-cmt-show");
+ return 2;
+ }
+
+ return ret;
+}
+
/*
* Local variables:
* mode: C
diff --git a/tools/libxl/xl_cmdtable.c b/tools/libxl/xl_cmdtable.c
index 35f02c4..da25c3f 100644
--- a/tools/libxl/xl_cmdtable.c
+++ b/tools/libxl/xl_cmdtable.c
@@ -502,6 +502,23 @@ struct cmd_spec cmd_table[] = {
"[options]",
"-F Run in the foreground",
},
+ { "psr-cmt-attach",
+ &main_psr_cmt_attach, 0, 1,
+ "Attach Cache Monitoring Technology service to a domain",
+ "<Domain>",
+ },
+ { "psr-cmt-detach",
+ &main_psr_cmt_detach, 0, 1,
+ "Detach Cache Monitoring Technology service from a domain",
+ "<Domain>",
+ },
+ { "psr-cmt-show",
+ &main_psr_cmt_show, 0, 1,
+ "Show Cache Monitoring Technology information",
+ "<PSR-CMT-Type> <Domain>",
+ "Available monitor types:\n"
+ "\"cache_occupancy\": Show L3 cache occupancy\n",
+ },
};
int cmdtable_len = sizeof(cmd_table)/sizeof(struct cmd_spec);
--
1.7.9.5
^ permalink raw reply related [flat|nested] 18+ messages in thread