summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-20 14:46:05 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-20 14:46:05 -0700
commit16b3d851c0146123507fe864fdd97411ded51147 (patch)
tree8bfa3c0ca3a9e88f280bbd13de5549381db30fb5
parentcc1807b9158a909ffe829a5e222be756c57c9a90 (diff)
parentf52679b78877f17e95a317e18a4c9c46cc3d845a (diff)
downloadlinux-16b3d851c0146123507fe864fdd97411ded51147.tar.gz
linux-16b3d851c0146123507fe864fdd97411ded51147.tar.bz2
linux-16b3d851c0146123507fe864fdd97411ded51147.zip
Merge tag 'perf-tools-fixes-for-v6.0-2022-08-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tools fixes from Arnaldo Carvalho de Melo: - Fix alignment for cpu map masks in event encoding. - Support reading PERF_FORMAT_LOST, perf tool counterpart for a feature that was added in this merge window. - Sync perf tools copies of kernel headers: socket, msr-index, fscrypt, cpufeatures, i915_drm, kvm, vhost, perf_event. * tag 'perf-tools-fixes-for-v6.0-2022-08-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: perf tools: Support reading PERF_FORMAT_LOST libperf: Add a test case for read formats libperf: Handle read format in perf_evsel__read() tools headers UAPI: Sync linux/perf_event.h with the kernel sources tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources tools headers UAPI: Sync KVM's vmx.h header with the kernel sources tools include UAPI: Sync linux/vhost.h with the kernel sources tools headers kvm s390: Sync headers with the kernel sources tools headers UAPI: Sync linux/kvm.h with the kernel sources tools headers UAPI: Sync drm/i915_drm.h with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools headers UAPI: Sync linux/fscrypt.h with the kernel sources tools arch x86: Sync the msr-index.h copy with the kernel sources perf beauty: Update copy of linux/socket.h with the kernel sources perf cpumap: Fix alignment for masks in event encoding perf cpumap: Compute mask size in constant time perf cpumap: Synthetic events and const/static perf cpumap: Const map for max()
-rw-r--r--tools/arch/s390/include/uapi/asm/kvm.h1
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h6
-rw-r--r--tools/arch/x86/include/asm/msr-index.h8
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h10
-rw-r--r--tools/arch/x86/include/uapi/asm/vmx.h4
-rw-r--r--tools/include/uapi/drm/i915_drm.h387
-rw-r--r--tools/include/uapi/linux/fscrypt.h3
-rw-r--r--tools/include/uapi/linux/kvm.h108
-rw-r--r--tools/include/uapi/linux/perf_event.h5
-rw-r--r--tools/include/uapi/linux/vhost.h9
-rw-r--r--tools/lib/perf/cpumap.c2
-rw-r--r--tools/lib/perf/evsel.c79
-rw-r--r--tools/lib/perf/include/perf/cpumap.h2
-rw-r--r--tools/lib/perf/include/perf/event.h50
-rw-r--r--tools/lib/perf/include/perf/evsel.h4
-rw-r--r--tools/lib/perf/tests/test-evsel.c161
-rw-r--r--tools/perf/tests/cpumap.c19
-rw-r--r--tools/perf/tests/sample-parsing.c14
-rw-r--r--tools/perf/trace/beauty/include/linux/socket.h16
-rw-r--r--tools/perf/util/cpumap.c80
-rw-r--r--tools/perf/util/cpumap.h4
-rw-r--r--tools/perf/util/event.h25
-rw-r--r--tools/perf/util/evsel.c29
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c19
-rw-r--r--tools/perf/util/session.c65
-rw-r--r--tools/perf/util/synthetic-events.c99
-rw-r--r--tools/perf/util/synthetic-events.h2
27 files changed, 976 insertions, 235 deletions
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 7a6b14874d65..a73cf01a1606 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req {
#define KVM_S390_VM_CRYPTO 2
#define KVM_S390_VM_CPU_MODEL 3
#define KVM_S390_VM_MIGRATION 4
+#define KVM_S390_VM_CPU_TOPOLOGY 5
/* kvm attributes for mem_ctrl */
#define KVM_S390_VM_MEM_ENABLE_CMMA 0
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8323ac5b7eee..235dc85c91c3 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,7 +219,7 @@
#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */
#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */
#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
+#define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */
#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */
#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */
#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
@@ -303,7 +303,7 @@
#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */
#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */
#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */
-#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
+#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
@@ -354,6 +354,7 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
+#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
@@ -457,5 +458,6 @@
#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e057e039173c..6674bdb096f3 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -235,6 +235,12 @@
#define PERF_CAP_PT_IDX 16
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
+#define PERF_CAP_PEBS_TRAP BIT_ULL(6)
+#define PERF_CAP_ARCH_REG BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT 0xf00
+#define PERF_CAP_PEBS_BASELINE BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+ PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
#define MSR_IA32_RTIT_CTL 0x00000570
#define RTIT_CTL_TRACEEN BIT(0)
@@ -392,6 +398,7 @@
#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C
#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D
+#define MSR_SECONDARY_TURBO_RATIO_LIMIT 0x00000650
#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
@@ -1022,6 +1029,7 @@
#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f
#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490
#define MSR_IA32_VMX_VMFUNC 0x00000491
+#define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492
/* VMX_BASIC bits and bitmasks */
#define VMX_BASIC_VMCS_SIZE_SHIFT 32
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index ec53c9fa1da9..46de10a809ec 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -306,7 +306,8 @@ struct kvm_pit_state {
struct kvm_pit_channel_state channels[3];
};
-#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
struct kvm_pit_state2 {
struct kvm_pit_channel_state channels[3];
@@ -325,6 +326,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -359,7 +361,10 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
- __u8 reserved[27];
+ struct {
+ __u8 pending;
+ } triple_fault;
+ __u8 reserved[26];
__u8 exception_has_payload;
__u64 exception_payload;
};
@@ -434,6 +439,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 946d761adbd3..a5faf6d88f1b 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -91,6 +91,7 @@
#define EXIT_REASON_UMWAIT 67
#define EXIT_REASON_TPAUSE 68
#define EXIT_REASON_BUS_LOCK 74
+#define EXIT_REASON_NOTIFY 75
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -153,7 +154,8 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }, \
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }, \
- { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }
+ { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \
+ { EXIT_REASON_NOTIFY, "NOTIFY" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index b28ff5d88145..520ad2691a99 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -751,14 +751,27 @@ typedef struct drm_i915_irq_wait {
/* Must be kept compact -- no holes and well documented */
-typedef struct drm_i915_getparam {
+/**
+ * struct drm_i915_getparam - Driver parameter query structure.
+ */
+struct drm_i915_getparam {
+ /** @param: Driver parameter to query. */
__s32 param;
- /*
+
+ /**
+ * @value: Address of memory where queried value should be put.
+ *
* WARNING: Using pointers instead of fixed-size u64 means we need to write
* compat32 code. Don't repeat this mistake.
*/
int __user *value;
-} drm_i915_getparam_t;
+};
+
+/**
+ * typedef drm_i915_getparam_t - Driver parameter query structure.
+ * See struct drm_i915_getparam.
+ */
+typedef struct drm_i915_getparam drm_i915_getparam_t;
/* Ioctl to set kernel params:
*/
@@ -1239,76 +1252,119 @@ struct drm_i915_gem_exec_object2 {
__u64 rsvd2;
};
+/**
+ * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
+ * ioctl.
+ *
+ * The request will wait for input fence to signal before submission.
+ *
+ * The returned output fence will be signaled after the completion of the
+ * request.
+ */
struct drm_i915_gem_exec_fence {
- /**
- * User's handle for a drm_syncobj to wait on or signal.
- */
+ /** @handle: User's handle for a drm_syncobj to wait on or signal. */
__u32 handle;
+ /**
+ * @flags: Supported flags are:
+ *
+ * I915_EXEC_FENCE_WAIT:
+ * Wait for the input fence before request submission.
+ *
+ * I915_EXEC_FENCE_SIGNAL:
+ * Return request completion fence as output
+ */
+ __u32 flags;
#define I915_EXEC_FENCE_WAIT (1<<0)
#define I915_EXEC_FENCE_SIGNAL (1<<1)
#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
- __u32 flags;
};
-/*
- * See drm_i915_gem_execbuffer_ext_timeline_fences.
- */
-#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
-
-/*
+/**
+ * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
+ * for execbuf ioctl.
+ *
* This structure describes an array of drm_syncobj and associated points for
* timeline variants of drm_syncobj. It is invalid to append this structure to
* the execbuf if I915_EXEC_FENCE_ARRAY is set.
*/
struct drm_i915_gem_execbuffer_ext_timeline_fences {
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+ /** @base: Extension link. See struct i915_user_extension. */
struct i915_user_extension base;
/**
- * Number of element in the handles_ptr & value_ptr arrays.
+ * @fence_count: Number of elements in the @handles_ptr & @value_ptr
+ * arrays.
*/
__u64 fence_count;
/**
- * Pointer to an array of struct drm_i915_gem_exec_fence of length
- * fence_count.
+ * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
+ * of length @fence_count.
*/
__u64 handles_ptr;
/**
- * Pointer to an array of u64 values of length fence_count. Values
- * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
- * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+ * @values_ptr: Pointer to an array of u64 values of length
+ * @fence_count.
+ * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
+ * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
+ * binary one.
*/
__u64 values_ptr;
};
+/**
+ * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
+ * ioctl.
+ */
struct drm_i915_gem_execbuffer2 {
- /**
- * List of gem_exec_object2 structs
- */
+ /** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
__u64 buffers_ptr;
+
+ /** @buffer_count: Number of elements in @buffers_ptr array */
__u32 buffer_count;
- /** Offset in the batchbuffer to start execution from. */
+ /**
+ * @batch_start_offset: Offset in the batchbuffer to start execution
+ * from.
+ */
__u32 batch_start_offset;
- /** Bytes used in batchbuffer from batch_start_offset */
+
+ /**
+ * @batch_len: Length in bytes of the batch buffer, starting from the
+ * @batch_start_offset. If 0, length is assumed to be the batch buffer
+ * object size.
+ */
__u32 batch_len;
+
+ /** @DR1: deprecated */
__u32 DR1;
+
+ /** @DR4: deprecated */
__u32 DR4;
+
+ /** @num_cliprects: See @cliprects_ptr */
__u32 num_cliprects;
+
/**
- * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
- * & I915_EXEC_USE_EXTENSIONS are not set.
+ * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
+ *
+ * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
+ * I915_EXEC_USE_EXTENSIONS flags are not set.
*
* If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
- * of struct drm_i915_gem_exec_fence and num_cliprects is the length
- * of the array.
+ * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
+ * array.
*
* If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
- * single struct i915_user_extension and num_cliprects is 0.
+ * single &i915_user_extension and num_cliprects is 0.
*/
__u64 cliprects_ptr;
+
+ /** @flags: Execbuf flags */
+ __u64 flags;
#define I915_EXEC_RING_MASK (0x3f)
#define I915_EXEC_DEFAULT (0<<0)
#define I915_EXEC_RENDER (1<<0)
@@ -1326,10 +1382,6 @@ struct drm_i915_gem_execbuffer2 {
#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
#define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6)
#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
- __u64 flags;
- __u64 rsvd1; /* now used for context info */
- __u64 rsvd2;
-};
/** Resets the SO write offset registers for transform feedback on gen7. */
#define I915_EXEC_GEN7_SOL_RESET (1<<8)
@@ -1432,9 +1484,23 @@ struct drm_i915_gem_execbuffer2 {
* drm_i915_gem_execbuffer_ext enum.
*/
#define I915_EXEC_USE_EXTENSIONS (1 << 21)
-
#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
+ /** @rsvd1: Context id */
+ __u64 rsvd1;
+
+ /**
+ * @rsvd2: in and out sync_file file descriptors.
+ *
+ * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
+ * lower 32 bits of this field will have the in sync_file fd (input).
+ *
+ * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
+ * field will have the out sync_file fd (output).
+ */
+ __u64 rsvd2;
+};
+
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
@@ -1814,19 +1880,58 @@ struct drm_i915_gem_context_create {
__u32 pad;
};
+/**
+ * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
+ */
struct drm_i915_gem_context_create_ext {
- __u32 ctx_id; /* output: id of new context*/
+ /** @ctx_id: Id of the created context (output) */
+ __u32 ctx_id;
+
+ /**
+ * @flags: Supported flags are:
+ *
+ * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
+ *
+ * Extensions may be appended to this structure and driver must check
+ * for those. See @extensions.
+ *
+ * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
+ *
+ * Created context will have single timeline.
+ */
__u32 flags;
#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0)
#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1)
#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
+
+ /**
+ * @extensions: Zero-terminated chain of extensions.
+ *
+ * I915_CONTEXT_CREATE_EXT_SETPARAM:
+ * Context parameter to set or query during context creation.
+ * See struct drm_i915_gem_context_create_ext_setparam.
+ *
+ * I915_CONTEXT_CREATE_EXT_CLONE:
+ * This extension has been removed. On the off chance someone somewhere
+ * has attempted to use it, never re-use this extension number.
+ */
__u64 extensions;
+#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
};
+/**
+ * struct drm_i915_gem_context_param - Context parameter to set or query.
+ */
struct drm_i915_gem_context_param {
+ /** @ctx_id: Context id */
__u32 ctx_id;
+
+ /** @size: Size of the parameter @value */
__u32 size;
+
+ /** @param: Parameter to set or query */
__u64 param;
#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1
/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance
@@ -1973,6 +2078,7 @@ struct drm_i915_gem_context_param {
#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd
/* Must be kept compact -- no holes and well documented */
+ /** @value: Context parameter value to be set or queried */
__u64 value;
};
@@ -2371,23 +2477,29 @@ struct i915_context_param_engines {
struct i915_engine_class_instance engines[N__]; \
} __attribute__((packed)) name__
+/**
+ * struct drm_i915_gem_context_create_ext_setparam - Context parameter
+ * to set or query during context creation.
+ */
struct drm_i915_gem_context_create_ext_setparam {
-#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+ /** @base: Extension link. See struct i915_user_extension. */
struct i915_user_extension base;
+
+ /**
+ * @param: Context parameter to set or query.
+ * See struct drm_i915_gem_context_param.
+ */
struct drm_i915_gem_context_param param;
};
-/* This API has been removed. On the off chance someone somewhere has
- * attempted to use it, never re-use this extension number.
- */
-#define I915_CONTEXT_CREATE_EXT_CLONE 1
-
struct drm_i915_gem_context_destroy {
__u32 ctx_id;
__u32 pad;
};
-/*
+/**
+ * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
+ *
* DRM_I915_GEM_VM_CREATE -
*
* Create a new virtual memory address space (ppGTT) for use within a context
@@ -2397,20 +2509,23 @@ struct drm_i915_gem_context_destroy {
* The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
* returned in the outparam @id.
*
- * No flags are defined, with all bits reserved and must be zero.
- *
* An extension chain maybe provided, starting with @extensions, and terminated
* by the @next_extension being 0. Currently, no extensions are defined.
*
* DRM_I915_GEM_VM_DESTROY -
*
- * Destroys a previously created VM id, specified in @id.
+ * Destroys a previously created VM id, specified in @vm_id.
*
* No extensions or flags are allowed currently, and so must be zero.
*/
struct drm_i915_gem_vm_control {
+ /** @extensions: Zero-terminated chain of extensions. */
__u64 extensions;
+
+ /** @flags: reserved for future usage, currently MBZ */
__u32 flags;
+
+ /** @vm_id: Id of the VM created or to be destroyed */
__u32 vm_id;
};
@@ -3207,36 +3322,6 @@ struct drm_i915_gem_memory_class_instance {
* struct drm_i915_memory_region_info - Describes one region as known to the
* driver.
*
- * Note that we reserve some stuff here for potential future work. As an example
- * we might want expose the capabilities for a given region, which could include
- * things like if the region is CPU mappable/accessible, what are the supported
- * mapping types etc.
- *
- * Note that to extend struct drm_i915_memory_region_info and struct
- * drm_i915_query_memory_regions in the future the plan is to do the following:
- *
- * .. code-block:: C
- *
- * struct drm_i915_memory_region_info {
- * struct drm_i915_gem_memory_class_instance region;
- * union {
- * __u32 rsvd0;
- * __u32 new_thing1;
- * };
- * ...
- * union {
- * __u64 rsvd1[8];
- * struct {
- * __u64 new_thing2;
- * __u64 new_thing3;
- * ...
- * };
- * };
- * };
- *
- * With this things should remain source compatible between versions for
- * userspace, even as we add new fields.
- *
* Note this is using both struct drm_i915_query_item and struct drm_i915_query.
* For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
* at &drm_i915_query_item.query_id.
@@ -3248,14 +3333,81 @@ struct drm_i915_memory_region_info {
/** @rsvd0: MBZ */
__u32 rsvd0;
- /** @probed_size: Memory probed by the driver (-1 = unknown) */
+ /**
+ * @probed_size: Memory probed by the driver
+ *
+ * Note that it should not be possible to ever encounter a zero value
+ * here, also note that no current region type will ever return -1 here.
+ * Although for future region types, this might be a possibility. The
+ * same applies to the other size fields.
+ */
__u64 probed_size;
- /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */
+ /**
+ * @unallocated_size: Estimate of memory remaining
+ *
+ * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
+ * Without this (or if this is an older kernel) the value here will
+ * always equal the @probed_size. Note this is only currently tracked
+ * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
+ * will always equal the @probed_size).
+ */
__u64 unallocated_size;
- /** @rsvd1: MBZ */
- __u64 rsvd1[8];
+ union {
+ /** @rsvd1: MBZ */
+ __u64 rsvd1[8];
+ struct {
+ /**
+ * @probed_cpu_visible_size: Memory probed by the driver
+ * that is CPU accessible.
+ *
+ * This will be always be <= @probed_size, and the
+ * remainder (if there is any) will not be CPU
+ * accessible.
+ *
+ * On systems without small BAR, the @probed_size will
+ * always equal the @probed_cpu_visible_size, since all
+ * of it will be CPU accessible.
+ *
+ * Note this is only tracked for
+ * I915_MEMORY_CLASS_DEVICE regions (for other types the
+ * value here will always equal the @probed_size).
+ *
+ * Note that if the value returned here is zero, then
+ * this must be an old kernel which lacks the relevant
+ * small-bar uAPI support (including
+ * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
+ * such systems we should never actually end up with a
+ * small BAR configuration, assuming we are able to load
+ * the kernel module. Hence it should be safe to treat
+ * this the same as when @probed_cpu_visible_size ==
+ * @probed_size.
+ */
+ __u64 probed_cpu_visible_size;
+
+ /**
+ * @unallocated_cpu_visible_size: Estimate of CPU
+ * visible memory remaining.
+ *
+ * Note this is only tracked for
+ * I915_MEMORY_CLASS_DEVICE regions (for other types the
+ * value here will always equal the
+ * @probed_cpu_visible_size).
+ *
+ * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+ * accounting. Without this the value here will always
+ * equal the @probed_cpu_visible_size. Note this is only
+ * currently tracked for I915_MEMORY_CLASS_DEVICE
+ * regions (for other types the value here will also
+ * always equal the @probed_cpu_visible_size).
+ *
+ * If this is an older kernel the value here will be
+ * zero, see also @probed_cpu_visible_size.
+ */
+ __u64 unallocated_cpu_visible_size;
+ };
+ };
};
/**
@@ -3329,11 +3481,11 @@ struct drm_i915_query_memory_regions {
* struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
* extension support using struct i915_user_extension.
*
- * Note that in the future we want to have our buffer flags here, at least for
- * the stuff that is immutable. Previously we would have two ioctls, one to
- * create the object with gem_create, and another to apply various parameters,
- * however this creates some ambiguity for the params which are considered
- * immutable. Also in general we're phasing out the various SET/GET ioctls.
+ * Note that new buffer flags should be added here, at least for the stuff that
+ * is immutable. Previously we would have two ioctls, one to create the object
+ * with gem_create, and another to apply various parameters, however this
+ * creates some ambiguity for the params which are considered immutable. Also in
+ * general we're phasing out the various SET/GET ioctls.
*/
struct drm_i915_gem_create_ext {
/**
@@ -3341,7 +3493,6 @@ struct drm_i915_gem_create_ext {
*
* The (page-aligned) allocated size for the object will be returned.
*
- *
* DG2 64K min page size implications:
*
* On discrete platforms, starting from DG2, we have to contend with GTT
@@ -3353,7 +3504,9 @@ struct drm_i915_gem_create_ext {
*
* Note that the returned size here will always reflect any required
* rounding up done by the kernel, i.e 4K will now become 64K on devices
- * such as DG2.
+ * such as DG2. The kernel will always select the largest minimum
+ * page-size for the set of possible placements as the value to use when
+ * rounding up the @size.
*
* Special DG2 GTT address alignment requirement:
*
@@ -3377,14 +3530,58 @@ struct drm_i915_gem_create_ext {
* is deemed to be a good compromise.
*/
__u64 size;
+
/**
* @handle: Returned handle for the object.
*
* Object handles are nonzero.
*/
__u32 handle;
- /** @flags: MBZ */
+
+ /**
+ * @flags: Optional flags.
+ *
+ * Supported values:
+ *
+ * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
+ * the object will need to be accessed via the CPU.
+ *
+ * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
+ * strictly required on configurations where some subset of the device
+ * memory is directly visible/mappable through the CPU (which we also
+ * call small BAR), like on some DG2+ systems. Note that this is quite
+ * undesirable, but due to various factors like the client CPU, BIOS etc
+ * it's something we can expect to see in the wild. See
+ * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
+ * determine if this system applies.
+ *
+ * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
+ * ensure the kernel can always spill the allocation to system memory,
+ * if the object can't be allocated in the mappable part of
+ * I915_MEMORY_CLASS_DEVICE.
+ *
+ * Also note that since the kernel only supports flat-CCS on objects
+ * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
+ * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
+ * flat-CCS.
+ *
+ * Without this hint, the kernel will assume that non-mappable
+ * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
+ * kernel can still migrate the object to the mappable part, as a last
+ * resort, if userspace ever CPU faults this object, but this might be
+ * expensive, and so ideally should be avoided.
+ *
+ * On older kernels which lack the relevant small-bar uAPI support (see
+ * also &drm_i915_memory_region_info.probed_cpu_visible_size),
+ * usage of the flag will result in an error, but it should NEVER be
+ * possible to end up with a small BAR configuration, assuming we can
+ * also successfully load the i915 kernel module. In such cases the
+ * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
+ * such there are zero restrictions on where the object can be placed.
+ */
+#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
__u32 flags;
+
/**
* @extensions: The chain of extensions to apply to this object.
*
@@ -3443,6 +3640,22 @@ struct drm_i915_gem_create_ext {
* At which point we get the object handle in &drm_i915_gem_create_ext.handle,
* along with the final object size in &drm_i915_gem_create_ext.size, which
* should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Fla