Skip to contentSkip to conversation

Intel Processor Trace virtualization enabling

PATCH Superseded Luwei Kang 4 participants 48 messages May 3, 2018 – May 7, 2018

Subsystems (4)

v7 of 13 Superseded Latest is v13 →

lore
Share & tools
lore

Luwei Kang

author
#0 lore raw

v7 cover Intel Processor Trace virtualization enabling

Hi All,

Here is a patch-series which adding Processor Trace enabling in KVM guest. You can get It's software developer manuals from:
https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
In Chapter 4 INTEL PROCESSOR TRACE: VMX IMPROVEMENTS.

Introduction:
Intel Processor Trace (Intel PT) is an extension of Intel Architecture that captures information about software execution using dedicated hardware facilities that cause only minimal performance perturbation to the software being traced. Details on the Intel PT infrastructure and trace capabilities can be found in the Intel 64 and IA-32 Architectures Software Developer’s Manual, Volume 3C.

The suite of architecture changes serve to simplify the process of virtualizing Intel PT for use by a guest software. There are two primary elements to this new architecture support for VMX support improvements made for Intel PT.
1. Addition of a new guest IA32_RTIT_CTL value field to the VMCS.
— This serves to speed and simplify the process of disabling trace on VM exit, and restoring it on VM entry.
2. Enabling use of EPT to redirect PT output.
— This enables the VMM to elect to virtualize the PT output buffer using EPT. In this mode, the CPU will treat PT output addresses as Guest Physical Addresses (GPAs) and translate them using EPT. This means that Intel PT output reads (of the ToPA table) and writes (of trace output) can cause EPT violations, and other output events.

Processor Trace virtualization can be work in one of 3 possible modes by set new option "pt_mode". Default value is system mode.
a. system-wide: trace both host/guest and output to host buffer;
b. host-only: only trace host and output to host buffer;
c. host-guest: trace host/guest simultaneous and output to their respective buffer.

Quoted 1 line

From V6:

- split pathes 1~2 to four separate patches (these patches do 2 things) and add more descriptions.

Quoted 1 line

From V5:

- rename the function from pt_cap_get_ex() to __pt_cap_get();
- replace the most of function from vmx_pt_supported() to "pt_mode == PT_MODE_HOST_GUEST"(or !=).

Quoted 1 line

From V4:

- add data check when setting the value of MSR_IA32_RTIT_CTL;
- Invoke new interface to set the intercept of MSRs read/write after "MSR bitmap per-vcpu" patches.

Quoted 1 line

From V3:

- change default mode to SYSTEM mode;
- add a new patch to move PT out of scattered features;
- add a new fucntion kvm_get_pt_addr_cnt() to get the number of address ranges;
- add a new function vmx_set_rtit_ctl() to set the value of guest RTIT_CTL, GUEST_IA32_RTIT_CTL and MSRs intercept.

Quoted 1 line

From v2:

- replace *_PT_SUPPRESS_PIP to *_PT_CONCEAL_PIP;
- clean SECONDARY_EXEC_PT_USE_GPA, VM_EXIT_CLEAR_IA32_RTIT_CTL and VM_ENTRY_LOAD_IA32_RTIT_CTL in SYSTEM mode. These bits must be all set or all clean;
- move processor tracing out of scattered features;
- add a new function to enable/disable intercept MSRs read/write;
- add all Intel PT MSRs read/write and disable intercept when PT is enabled in guest;
- disable Intel PT and enable intercept MSRs when L1 guest VMXON;
- performance optimization.
In Host only mode. we just need to save host RTIT_CTL before vm-entry and restore host RTIT_CTL after vm-exit;
In HOST_GUEST mode. we need to save and restore all MSRs only when PT has enabled in guest.
- use XSAVES/XRESTORES implement context switch.
Haven't implementation in this version and still in debuging. will make a separate patch work on this.

Quoted 1 line

From v1:

- remove guest-only mode because guest-only mode can be covered by host-guest mode;
- always set "use GPA for processor tracing" in secondary execution control if it can be;
- trap RTIT_CTL read/write. Forbid write this msr when VMXON in L1 hypervisor.

Chao Peng (8):
perf/x86/intel/pt: Move Intel-PT MSRs bit definitions to a public
header
perf/x86/intel/pt: Change pt_cap_get() to a public function
KVM: x86: Add Intel Processor Trace virtualization mode
KVM: x86: Add Intel Processor Trace cpuid emulation
KVM: x86: Add Intel processor trace context for each vcpu
KVM: x86: Implement Intel Processor Trace context switch
KVM: x86: Implement Intel Processor Trace MSRs read/write
KVM: x86: Set intercept for Intel PT MSRs read/write

Luwei Kang (5):
perf/x86/intel/pt: Add new bit definitions for Intel PT MSRs perf/x86/intel/pt: add new capability for Intel PT perf/x86/intel/pt: Introduce a new function to get capability of Intel
PT
KVM: x86: Introduce a function to initialize the PT configuration
KVM: x86: Disable Intel Processor Trace when VMXON in L1 guest

 arch/x86/events/intel/pt.c       |  12 +-
 arch/x86/events/intel/pt.h       |  58 ------
 arch/x86/include/asm/intel_pt.h  |  40 ++++
 arch/x86/include/asm/kvm_host.h  |   1 +
 arch/x86/include/asm/msr-index.h |  38 ++++
 arch/x86/include/asm/vmx.h       |   8 +
 arch/x86/kvm/cpuid.c             |  22 ++-
 arch/x86/kvm/svm.c               |   6 +
 arch/x86/kvm/vmx.c               | 412 ++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/x86.c               |  33 +++-
 10 files changed, 563 insertions(+), 67 deletions(-)
Signature · 1 line
1.8.3.1
author
#1 lore raw

PATCH v7 1/13 perf/x86/intel/pt: Move Intel-PT MSRs bit definitions to a public header

From: Chao Peng <[email protected]>

Intel Processor Trace virtualization enabling in KVM guest need to access these MSRs bit definitions, so move them to public header file msr-index.h.

---
 arch/x86/events/intel/pt.h       | 37 -------------------------------------
 arch/x86/include/asm/msr-index.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 37 deletions(-)
arch/x86/events/intel/pt.h +0 -37
index 0eb41d0..0050ca1 100644
@@ -20,43 +20,6 @@
 #define __INTEL_PT_H__
 
 /*
- * PT MSR bit definitions
- */
-#define RTIT_CTL_TRACEEN		BIT(0)
-#define RTIT_CTL_CYCLEACC		BIT(1)
-#define RTIT_CTL_OS			BIT(2)
-#define RTIT_CTL_USR			BIT(3)
-#define RTIT_CTL_PWR_EVT_EN		BIT(4)
-#define RTIT_CTL_FUP_ON_PTW		BIT(5)
-#define RTIT_CTL_CR3EN			BIT(7)
-#define RTIT_CTL_TOPA			BIT(8)
-#define RTIT_CTL_MTC_EN			BIT(9)
-#define RTIT_CTL_TSC_EN			BIT(10)
-#define RTIT_CTL_DISRETC		BIT(11)
-#define RTIT_CTL_PTW_EN			BIT(12)
-#define RTIT_CTL_BRANCH_EN		BIT(13)
-#define RTIT_CTL_MTC_RANGE_OFFSET	14
-#define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
-#define RTIT_CTL_CYC_THRESH_OFFSET	19
-#define RTIT_CTL_CYC_THRESH		(0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
-#define RTIT_CTL_PSB_FREQ_OFFSET	24
-#define RTIT_CTL_PSB_FREQ      		(0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
-#define RTIT_CTL_ADDR0_OFFSET		32
-#define RTIT_CTL_ADDR0      		(0x0full << RTIT_CTL_ADDR0_OFFSET)
-#define RTIT_CTL_ADDR1_OFFSET		36
-#define RTIT_CTL_ADDR1      		(0x0full << RTIT_CTL_ADDR1_OFFSET)
-#define RTIT_CTL_ADDR2_OFFSET		40
-#define RTIT_CTL_ADDR2      		(0x0full << RTIT_CTL_ADDR2_OFFSET)
-#define RTIT_CTL_ADDR3_OFFSET		44
-#define RTIT_CTL_ADDR3      		(0x0full << RTIT_CTL_ADDR3_OFFSET)
-#define RTIT_STATUS_FILTEREN		BIT(0)
-#define RTIT_STATUS_CONTEXTEN		BIT(1)
-#define RTIT_STATUS_TRIGGEREN		BIT(2)
-#define RTIT_STATUS_BUFFOVF		BIT(3)
-#define RTIT_STATUS_ERROR		BIT(4)
-#define RTIT_STATUS_STOPPED		BIT(5)
-
-/*
  * Single-entry ToPA: when this close to region boundary, switch
  * buffers to avoid losing data.
  */
arch/x86/include/asm/msr-index.h +34 -0
index 53d5b1b..c168e26 100644
@@ -106,7 +106,40 @@
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
 
 #define MSR_IA32_RTIT_CTL		0x00000570
+#define RTIT_CTL_TRACEEN		BIT(0)
+#define RTIT_CTL_CYCLEACC		BIT(1)
+#define RTIT_CTL_OS			BIT(2)
+#define RTIT_CTL_USR			BIT(3)
+#define RTIT_CTL_PWR_EVT_EN		BIT(4)
+#define RTIT_CTL_FUP_ON_PTW		BIT(5)
+#define RTIT_CTL_CR3EN			BIT(7)
+#define RTIT_CTL_TOPA			BIT(8)
+#define RTIT_CTL_MTC_EN			BIT(9)
+#define RTIT_CTL_TSC_EN			BIT(10)
+#define RTIT_CTL_DISRETC		BIT(11)
+#define RTIT_CTL_PTW_EN			BIT(12)
+#define RTIT_CTL_BRANCH_EN		BIT(13)
+#define RTIT_CTL_MTC_RANGE_OFFSET	14
+#define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
+#define RTIT_CTL_CYC_THRESH_OFFSET	19
+#define RTIT_CTL_CYC_THRESH		(0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
+#define RTIT_CTL_PSB_FREQ_OFFSET	24
+#define RTIT_CTL_PSB_FREQ      		(0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
+#define RTIT_CTL_ADDR0_OFFSET		32
+#define RTIT_CTL_ADDR0      		(0x0full << RTIT_CTL_ADDR0_OFFSET)
+#define RTIT_CTL_ADDR1_OFFSET		36
+#define RTIT_CTL_ADDR1      		(0x0full << RTIT_CTL_ADDR1_OFFSET)
+#define RTIT_CTL_ADDR2_OFFSET		40
+#define RTIT_CTL_ADDR2      		(0x0full << RTIT_CTL_ADDR2_OFFSET)
+#define RTIT_CTL_ADDR3_OFFSET		44
+#define RTIT_CTL_ADDR3      		(0x0full << RTIT_CTL_ADDR3_OFFSET)
 #define MSR_IA32_RTIT_STATUS		0x00000571
+#define RTIT_STATUS_FILTEREN		BIT(0)
+#define RTIT_STATUS_CONTEXTEN		BIT(1)
+#define RTIT_STATUS_TRIGGEREN		BIT(2)
+#define RTIT_STATUS_BUFFOVF		BIT(3)
+#define RTIT_STATUS_ERROR		BIT(4)
+#define RTIT_STATUS_STOPPED		BIT(5)
 #define MSR_IA32_RTIT_ADDR0_A		0x00000580
 #define MSR_IA32_RTIT_ADDR0_B		0x00000581
 #define MSR_IA32_RTIT_ADDR1_A		0x00000582
@@ -115,6 +148,7 @@
 #define MSR_IA32_RTIT_ADDR2_B		0x00000585
 #define MSR_IA32_RTIT_ADDR3_A		0x00000586
 #define MSR_IA32_RTIT_ADDR3_B		0x00000587
+#define MSR_IA32_RTIT_ADDR_COUNT	8
 #define MSR_IA32_RTIT_CR3_MATCH		0x00000572
 #define MSR_IA32_RTIT_OUTPUT_BASE	0x00000560
 #define MSR_IA32_RTIT_OUTPUT_MASK	0x00000561
Signature · 1 line
1.8.3.1
author
#2 lore raw

PATCH v7 2/13 perf/x86/intel/pt: Change pt_cap_get() to a public function

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Change pt_cap_get() to a public function that KVM can access this function to check if specific feature is supported on hardware.

---
 arch/x86/events/intel/pt.c      |  3 ++-
 arch/x86/events/intel/pt.h      | 21 ---------------------
 arch/x86/include/asm/intel_pt.h | 23 +++++++++++++++++++++++
 3 files changed, 25 insertions(+), 22 deletions(-)
arch/x86/events/intel/pt.c +2 -1
index 81fd41d..a5a7e44 100644
@@ -75,7 +75,7 @@
 	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
-static u32 pt_cap_get(enum pt_capabilities cap)
+u32 pt_cap_get(enum pt_capabilities cap)
 {
 	struct pt_cap_desc *cd = &pt_caps[cap];
 	u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
@@ -83,6 +83,7 @@ static u32 pt_cap_get(enum pt_capabilities cap)
 
 	return (c & cd->mask) >> shift;
 }
+EXPORT_SYMBOL_GPL(pt_cap_get);
 
 static ssize_t pt_cap_show(struct device *cdev,
 			   struct device_attribute *attr,
arch/x86/events/intel/pt.h +0 -21
index 0050ca1..269e15a 100644
@@ -45,30 +45,9 @@ struct topa_entry {
 	u64	rsvd4	: 16;
 };
 
-#define PT_CPUID_LEAVES		2
-#define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
-
 /* TSC to Core Crystal Clock Ratio */
 #define CPUID_TSC_LEAF		0x15
 
-enum pt_capabilities {
-	PT_CAP_max_subleaf = 0,
-	PT_CAP_cr3_filtering,
-	PT_CAP_psb_cyc,
-	PT_CAP_ip_filtering,
-	PT_CAP_mtc,
-	PT_CAP_ptwrite,
-	PT_CAP_power_event_trace,
-	PT_CAP_topa_output,
-	PT_CAP_topa_multiple_entries,
-	PT_CAP_single_range_output,
-	PT_CAP_payloads_lip,
-	PT_CAP_num_address_ranges,
-	PT_CAP_mtc_periods,
-	PT_CAP_cycle_thresholds,
-	PT_CAP_psb_periods,
-};
-
 struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
arch/x86/include/asm/intel_pt.h +23 -0
index b523f51..4270421 100644
@@ -2,10 +2,33 @@
 #ifndef _ASM_X86_INTEL_PT_H
 #define _ASM_X86_INTEL_PT_H
 
+#define PT_CPUID_LEAVES		2
+#define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
+
+enum pt_capabilities {
+	PT_CAP_max_subleaf = 0,
+	PT_CAP_cr3_filtering,
+	PT_CAP_psb_cyc,
+	PT_CAP_ip_filtering,
+	PT_CAP_mtc,
+	PT_CAP_ptwrite,
+	PT_CAP_power_event_trace,
+	PT_CAP_topa_output,
+	PT_CAP_topa_multiple_entries,
+	PT_CAP_single_range_output,
+	PT_CAP_payloads_lip,
+	PT_CAP_num_address_ranges,
+	PT_CAP_mtc_periods,
+	PT_CAP_cycle_thresholds,
+	PT_CAP_psb_periods,
+};
+
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 void cpu_emergency_stop_pt(void);
+extern u32 pt_cap_get(enum pt_capabilities cap);
 #else
 static inline void cpu_emergency_stop_pt(void) {}
+static inline u32 pt_cap_get(enum pt_capabilities cap) { return 0; }
 #endif
 
 #endif /* _ASM_X86_INTEL_PT_H */
Signature · 1 line
1.8.3.1
author
#3 lore raw

PATCH v7 3/13 perf/x86/intel/pt: Add new bit definitions for Intel PT MSRs

In reply to Luwei Kang

These new bit definitions are use for emulate MSRs read/write for KVM. For example, IA32_RTIT_CTL.FabricEn[bit 6] is available only when CPUID.(EAX=14H, ECX=0):ECX[bit 3] = 1. If KVM guest try to set this bit with CPUID.(EAX=14H, ECX=0):ECX[bit3] = 0 a #GP would be injected to KVM guest.

---
 arch/x86/include/asm/msr-index.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/msr-index.h +3 -0
index c168e26..cc9e681 100644
@@ -112,6 +112,7 @@
 #define RTIT_CTL_USR			BIT(3)
 #define RTIT_CTL_PWR_EVT_EN		BIT(4)
 #define RTIT_CTL_FUP_ON_PTW		BIT(5)
+#define RTIT_CTL_FABRIC_EN		BIT(6)
 #define RTIT_CTL_CR3EN			BIT(7)
 #define RTIT_CTL_TOPA			BIT(8)
 #define RTIT_CTL_MTC_EN			BIT(9)
@@ -140,6 +141,8 @@
 #define RTIT_STATUS_BUFFOVF		BIT(3)
 #define RTIT_STATUS_ERROR		BIT(4)
 #define RTIT_STATUS_STOPPED		BIT(5)
+#define RTIT_STATUS_BYTECNT_OFFSET	32
+#define RTIT_STATUS_BYTECNT		(0x1ffffull << RTIT_STATUS_BYTECNT_OFFSET)
 #define MSR_IA32_RTIT_ADDR0_A		0x00000580
 #define MSR_IA32_RTIT_ADDR0_B		0x00000581
 #define MSR_IA32_RTIT_ADDR1_A		0x00000582
Signature · 1 line
1.8.3.1
author
#4 lore raw

PATCH v7 4/13 perf/x86/intel/pt: add new capability for Intel PT

In reply to Luwei Kang

CPUID(EAX=14H,ECX=0):EBX[bit 3] = 1 indicates support of output to Trace Transport subsystem.
MSR IA32_RTIT_CTL.FabricEn[bit 6] is reserved if CPUID.(EAX=14H, ECX=0):ECX[bit 3] = 0.
This is use for emulate IA32_RTIT_CTL MSR read/write in KVM. KVM guest write IA32_RTIT_CTL will trap to root mode and a #GP would be injected to guest if set IA32_RTIT_CTL.FabricEn with
CPUID.(EAX=14H, ECX=0):ECX[bit 3] = 0.

---
 arch/x86/events/intel/pt.c      | 1 +
 arch/x86/include/asm/intel_pt.h | 1 +
 2 files changed, 2 insertions(+)
arch/x86/events/intel/pt.c +1 -0
index a5a7e44..d5819a2 100644
@@ -68,6 +68,7 @@
 	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
 	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
 	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
+	PT_CAP(output_subsys,		0, CPUID_ECX, BIT(3)),
 	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
 	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
 	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
arch/x86/include/asm/intel_pt.h +1 -0
index 4270421..2de4db0 100644
@@ -16,6 +16,7 @@ enum pt_capabilities {
 	PT_CAP_topa_output,
 	PT_CAP_topa_multiple_entries,
 	PT_CAP_single_range_output,
+	PT_CAP_output_subsys,
 	PT_CAP_payloads_lip,
 	PT_CAP_num_address_ranges,
 	PT_CAP_mtc_periods,
Signature · 1 line
1.8.3.1
author
#5 lore raw

PATCH v7 5/13 perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

In reply to Luwei Kang

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest. Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

---
 arch/x86/events/intel/pt.c      | 10 ++++++++--
 arch/x86/include/asm/intel_pt.h |  2 ++
 2 files changed, 10 insertions(+), 2 deletions(-)
arch/x86/events/intel/pt.c +8 -2
index d5819a2..a1fe6ff 100644
@@ -76,14 +76,20 @@
 	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
-u32 pt_cap_get(enum pt_capabilities cap)
+u32 __pt_cap_get(u32 *caps, enum pt_capabilities cap)
 {
 	struct pt_cap_desc *cd = &pt_caps[cap];
-	u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
+	u32 c = caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
 	unsigned int shift = __ffs(cd->mask);
 
 	return (c & cd->mask) >> shift;
 }
+EXPORT_SYMBOL_GPL(__pt_cap_get);
+
+u32 pt_cap_get(enum pt_capabilities cap)
+{
+	return __pt_cap_get(pt_pmu.caps, cap);
+}
 EXPORT_SYMBOL_GPL(pt_cap_get);
 
 static ssize_t pt_cap_show(struct device *cdev,
arch/x86/include/asm/intel_pt.h +2 -0
index 2de4db0..3a4f524 100644
@@ -27,9 +27,11 @@ enum pt_capabilities {
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 void cpu_emergency_stop_pt(void);
 extern u32 pt_cap_get(enum pt_capabilities cap);
+extern u32 __pt_cap_get(u32 *caps, enum pt_capabilities cap);
 #else
 static inline void cpu_emergency_stop_pt(void) {}
 static inline u32 pt_cap_get(enum pt_capabilities cap) { return 0; }
+static u32 __pt_cap_get(u32 *caps, enum pt_capabilities cap) { return 0; }
 #endif
 
 #endif /* _ASM_X86_INTEL_PT_H */
Signature · 1 line
1.8.3.1
#6 lore raw

Re: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 5 lines · Luwei Kang

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest. Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

Do we really need both in KVM?

arch/x86/include/asm/intel_pt.h enum pt_capabilities { · line 30

Quoted 9 lines
arch/x86/include/asm/intel_pt.h +1 -0
index 2de4db0..3a4f524 100644
@@ -27,9 +27,11 @@ enum pt_capabilities {
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 void cpu_emergency_stop_pt(void);
 extern u32 pt_cap_get(enum pt_capabilities cap);
+extern u32 __pt_cap_get(u32 *caps, enum pt_capabilities cap);

I'd call it something like pt_cap_decode().

#7 lore raw

RE: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 7 lines
Quoted 5 lines

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest.
Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

Do we really need both in KVM?

Yes, KVM need get host capability to estimate if can expose this feature to guest and get guest capability to confirm if some bits of MSRs are accessible.

Thanks,
Luwei Kang

Quoted 12 lines
Quoted 10 lines
(quoted diff) +0 -0

b/arch/x86/include/asm/intel_pt.h index 2de4db0..3a4f524 100644

arch/x86/include/asm/intel_pt.h +0 -0
@@ -27,9 +27,11 @@ enum pt_capabilities {  #if

defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) void cpu_emergency_stop_pt(void); extern u32 pt_cap_get(enum pt_capabilities cap);
+extern u32 __pt_cap_get(u32 *caps, enum pt_capabilities cap);

I'd call it something like pt_cap_decode().

#8 lore raw

Re: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 10 lines · Luwei
Quoted 7 lines
Quoted 5 lines

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest.
Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

Do we really need both in KVM?

Yes, KVM need get host capability to estimate if can expose this feature to guest

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

Thanks,
--
Alex

maintainer
#9 lore raw

Re: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 10 lines · Alexander Shishkin
Quoted 8 lines
Quoted 6 lines
Quoted 5 lines

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest.
Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

Do we really need both in KVM?

Yes, KVM need get host capability to estimate if can expose this feature to guest

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

It needs all the CPUID data, and it's nice to query it in a more manageable form than with bit shifts.

Paolo

#10 lore raw

RE: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

In reply to Alexander Shishkin
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
Quoted 5 lines

New function __pt_cap_get() will be invoked in KVM to check if a specific capability is availiable in KVM guest. Another function pt_cap_get() can only check the hardware capabilities but this may different with KVM guest because some features may not be exposed to guest.

Quoted 6 lines
Quoted 4 lines
Quoted 1 line

Do we really need both in KVM?

Yes, KVM need get host capability to estimate if can expose this feature to guest

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

Enable Intel PT in guest depend on SECONDARY_EXEC_PT_USE_GPA, EPT, MSR_IA32_VMX_MISC[14] and the capability of " PT_CAP_topa_output" on hardware. PT driver will return " -ENODEV" if hardware not support "PT_CAP_topa_output".

Thanks,
Luwei Kang

Quoted 4 lines

Thanks,
--
Alex

maintainer
#11 lore raw

Re: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 7 lines · Luwei
Quoted 2 lines

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

Enable Intel PT in guest depend on SECONDARY_EXEC_PT_USE_GPA, EPT, MSR_IA32_VMX_MISC[14] and the capability of " PT_CAP_topa_output" on hardware. PT driver will return " -ENODEV" if hardware not support "PT_CAP_topa_output".

I actually don't understand why PT_CAP_topa_output matters for the purpose of enabling PT in the guest. However you still need __pt_cap_get() in the CPUID checks.

Paolo

#12 lore raw

RE: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 10 lines
Quoted 7 lines
Quoted 2 lines

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

Enable Intel PT in guest depend on SECONDARY_EXEC_PT_USE_GPA, EPT, MSR_IA32_VMX_MISC[14] and the capability of " PT_CAP_topa_output" on hardware. PT driver will return " -ENODEV" if hardware not support "PT_CAP_topa_output".

I actually don't understand why PT_CAP_topa_output matters for the purpose of enabling PT in the guest. However you still need __pt_cap_get() in the CPUID checks.

Hi Paolo,
I think we should expose Intel Processor Trace to guest that can be detected and initialized. But without "PT_CAP_topa_output" Intel PT can't work in Linux. So I add this feature as precondition. About why need this check in driver I think Alexander may know the reason.

Thanks,
Luwei Kang

Quoted 2 lines

Paolo

#13 lore raw

Re: [PATCH v7 05/13] perf/x86/intel/pt: Introduce a new function to get capability of Intel PT

Quoted 8 lines · Luwei
Quoted 8 lines
Quoted 7 lines
Quoted 2 lines

Can you elaborate on this, what information do we need besides MSR_IA32_VMX_MISC[14]?

Enable Intel PT in guest depend on SECONDARY_EXEC_PT_USE_GPA, EPT, MSR_IA32_VMX_MISC[14] and the capability of " PT_CAP_topa_output" on hardware. PT driver will return " -ENODEV" if hardware not support "PT_CAP_topa_output".

Quoted 6 lines
Quoted 2 lines

I actually don't understand why PT_CAP_topa_output matters for the purpose of enabling PT in the guest. However you still need __pt_cap_get() in the CPUID checks.

Hi Paolo,
I think we should expose Intel Processor Trace to guest that can be detected and initialized. But without "PT_CAP_topa_output" Intel PT can't work in Linux. So I add this feature as precondition. About why need this check in driver I think Alexander may know the reason.

The driver only operates on ToPA at the moment, so if PT doesn't support it, there's nothing for the driver to do. But other things, such as simple_pt, might still be functional without CAP_topa_output, so it still makes sense to virtualize it.

Regards,
--
Alex

author
#14 lore raw

PATCH v7 6/13 KVM: x86: Add Intel Processor Trace virtualization mode

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Intel PT virtualization can be work in one of 3 possible modes:
a. system-wide: trace both host/guest and output to host buffer; b. host-only: only trace host and output to host buffer; c. host-guest: trace host/guest simultaneous and output to their
respective buffer.

---
 arch/x86/include/asm/intel_pt.h  |  6 ++++
 arch/x86/include/asm/msr-index.h |  1 +
 arch/x86/include/asm/vmx.h       |  8 +++++
 arch/x86/kvm/vmx.c               | 68 +++++++++++++++++++++++++++++++++++++---
 4 files changed, 79 insertions(+), 4 deletions(-)
arch/x86/include/asm/intel_pt.h +6 -0
index 3a4f524..43ad260 100644
@@ -5,6 +5,12 @@
 #define PT_CPUID_LEAVES		2
 #define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
+enum pt_mode {
+	PT_MODE_SYSTEM = 0,
+	PT_MODE_HOST,
+	PT_MODE_HOST_GUEST,
+};
+
 enum pt_capabilities {
 	PT_CAP_max_subleaf = 0,
 	PT_CAP_cr3_filtering,
arch/x86/include/asm/msr-index.h +1 -0
index cc9e681..c813507 100644
@@ -790,6 +790,7 @@
 #define VMX_BASIC_INOUT		0x0040000000000000LLU
 
 /* MSR_IA32_VMX_MISC bits */
+#define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)
 #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
 #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
 /* AMD-V MSRs */
arch/x86/include/asm/vmx.h +8 -0
index 8b67807..9e828d4 100644
@@ -76,7 +76,9 @@
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
+#define SECONDARY_EXEC_PT_CONCEAL_VMX		0x00080000
 #define SECONDARY_EXEC_XSAVES			0x00100000
+#define SECONDARY_EXEC_PT_USE_GPA		0x01000000
 #define SECONDARY_EXEC_TSC_SCALING              0x02000000
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -97,6 +99,8 @@
 #define VM_EXIT_LOAD_IA32_EFER                  0x00200000
 #define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER       0x00400000
 #define VM_EXIT_CLEAR_BNDCFGS                   0x00800000
+#define VM_EXIT_PT_CONCEAL_PIP			0x01000000
+#define VM_EXIT_CLEAR_IA32_RTIT_CTL		0x02000000
 
 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
 
@@ -108,6 +112,8 @@
 #define VM_ENTRY_LOAD_IA32_PAT			0x00004000
 #define VM_ENTRY_LOAD_IA32_EFER                 0x00008000
 #define VM_ENTRY_LOAD_BNDCFGS                   0x00010000
+#define VM_ENTRY_PT_CONCEAL_PIP			0x00020000
+#define VM_ENTRY_LOAD_IA32_RTIT_CTL		0x00040000
 
 #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
 
@@ -234,6 +240,8 @@ enum vmcs_field {
 	GUEST_PDPTR3_HIGH               = 0x00002811,
 	GUEST_BNDCFGS                   = 0x00002812,
 	GUEST_BNDCFGS_HIGH              = 0x00002813,
+	GUEST_IA32_RTIT_CTL		= 0x00002814,
+	GUEST_IA32_RTIT_CTL_HIGH	= 0x00002815,
 	HOST_IA32_PAT			= 0x00002c00,
 	HOST_IA32_PAT_HIGH		= 0x00002c01,
 	HOST_IA32_EFER			= 0x00002c02,
arch/x86/kvm/vmx.c +64 -4

134 lines not on this page · raw message

Signature · 1 line
1.8.3.1
#15 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 7 lines · Luwei Kang

From: Chao Peng <[email protected]>

Intel PT virtualization can be work in one of 3 possible modes:
a. system-wide: trace both host/guest and output to host buffer; b. host-only: only trace host and output to host buffer; c. host-guest: trace host/guest simultaneous and output to their
respective buffer.

You also need to explain what this patch is doing, how and why. I think I figured it out from reading the rest of the patch, but it should really be mentioned in the description.

Quoted 14 lines
arch/x86/include/asm/intel_pt.h +6 -0
@@ -5,6 +5,12 @@
 #define PT_CPUID_LEAVES		2
 #define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
+enum pt_mode {
+	PT_MODE_SYSTEM = 0,
+	PT_MODE_HOST,
+	PT_MODE_HOST_GUEST,
+};
+
 enum pt_capabilities {
 	PT_CAP_max_subleaf = 0,
 	PT_CAP_cr3_filtering,

arch/x86/include/asm/intel_pt.h line 193

Quoted 6 lines
arch/x86/include/asm/intel_pt.h +3 -0
@@ -187,6 +188,10 @@
 static unsigned int ple_window_max        = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
 module_param(ple_window_max, uint, 0444);
 
+/* Default is SYSTEM mode. */
+static int __read_mostly pt_mode = PT_MODE_SYSTEM;
+module_param(pt_mode, int, S_IRUGO);

So, it's an explicit module parameter? One apparent problem with this is that one would need to reload kvm module(s) to be able to use PT, which is not ideal.

Quoted 5 lines
arch/x86/kvm/vmx.c +1 -0
+
 extern const ulong vmx_return;
 
 struct kvm_vmx {

arch/x86/kvm/vmx.c static inline bool cpu_has_vmx_vmfunc(void) · line 1501

Quoted 9 lines
arch/x86/kvm/vmx.c +6 -0
@@ -1488,6 +1493,19 @@ static inline bool cpu_has_vmx_vmfunc(void)
 		SECONDARY_EXEC_ENABLE_VMFUNC;
 }
 
+static inline bool cpu_has_vmx_intel_pt(void)
+{
+	u64 vmx_msr;
+
+	rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+	return vmx_msr & MSR_IA32_VMX_MISC_INTEL_PT;

This is an implicit cast. return !!(...) would clarify your intention.

Also, does it make sense to write an accessor to pt_pmu.vmx instead?

arch/x86/kvm/vmx.c static inline bool cpu_has_vmx_vmfunc(void) · line 1507

Quoted 6 lines
arch/x86/kvm/vmx.c +6 -0
+}
+
+static inline bool cpu_has_vmx_pt_use_gpa(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA;
+}

I can deduce the meaning of the previous one, but not this one, and there's no explanation.

arch/x86/kvm/vmx.c static u32 vmx_exec_control(struct vcpu_vmx *vmx) · line 5819

Quoted 11 lines
arch/x86/kvm/vmx.c +7 -0
@@ -5780,6 +5810,28 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	return exec_control;
 }
 
+static u32 vmx_vmexit_control(struct vcpu_vmx *vmx)
+{
+	u32 vmexit_control = vmcs_config.vmexit_ctrl;
+
+	if (pt_mode == PT_MODE_SYSTEM)
+		vmexit_control &= ~(VM_EXIT_CLEAR_IA32_RTIT_CTL |
+				    VM_EXIT_PT_CONCEAL_PIP);

Ok, so what we really want to know is: is there an encompassing PT event on this cpu when we go into VMLAUNCH/VMRESTORE, right? We can find this out from the pt_ctx and avoid the pt_mode entirely. IOW, instead of having the 3 modes that you describe at the top, you can use something like the following:

1. Do we have an event in pt_ctx?
* No -> Set up the context for VMX.
* Yes -> 2. Is attr.exclude_guest set?
* No -> Guest trace goes to the host's buffer, do nothing.
* Yes -> Set up/switch the context for VMX.

Regards,
--
Alex

maintainer
#16 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 7 lines · Alexander Shishkin

arch/x86/kvm/vmx.c line 193

Quoted 4 lines
arch/x86/kvm/vmx.c +3 -0
+/* Default is SYSTEM mode. */
+static int __read_mostly pt_mode = PT_MODE_SYSTEM;
+module_param(pt_mode, int, S_IRUGO);

So, it's an explicit module parameter? One apparent problem with this is that one would need to reload kvm module(s) to be able to use PT, which is not ideal.

If you want to do tracing system-wide, that by definition must disable guest tracing, so I think the module parameter is appropriate. The question is more, what is the best default.

Paolo

#17 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 11 lines · Paolo Bonzini
Quoted 7 lines · Alexander Shishkin

arch/x86/kvm/vmx.c line 193

Quoted 4 lines
arch/x86/kvm/vmx.c +3 -0
+/* Default is SYSTEM mode. */
+static int __read_mostly pt_mode = PT_MODE_SYSTEM;
+module_param(pt_mode, int, S_IRUGO);

So, it's an explicit module parameter? One apparent problem with this is that one would need to reload kvm module(s) to be able to use PT, which is not ideal.

If you want to do tracing system-wide, that by definition must disable guest tracing,

Sure.

Quoted 1 line

so I think the module parameter is appropriate.

I don't see why. System-wide tracing takes place while perf record is running. When it's done, it's done and we can un-disable the guest tracing, without requiring the user to kill all their VMs and reload modules.

Regards,
--
Alex

maintainer
#18 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 4 lines · Alexander Shishkin

I don't see why. System-wide tracing takes place while perf record is running. When it's done, it's done and we can un-disable the guest tracing, without requiring the user to kill all their VMs and reload modules.

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

Paolo

#19 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 10 lines · Paolo Bonzini
Quoted 4 lines · Alexander Shishkin

I don't see why. System-wide tracing takes place while perf record is running. When it's done, it's done and we can un-disable the guest tracing, without requiring the user to kill all their VMs and reload modules.

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

CPUID is immaterial here; the real trick is to disallow the use of PT at runtime when the host suddenly decides to trace the guest, in such a way that the guest user is informed that their trace is incomplete due to the host activity.

Side note: the "system-wide tracing" is a misnomer here, all that matters is that there's a perf event on the host that wants to trace the guest, it can very well be a per-task event.

Regards,
--
Alex

maintainer
#20 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 9 lines · Alexander Shishkin
Quoted 4 lines

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

CPUID is immaterial here; the real trick is to disallow the use of PT at runtime when the host suddenly decides to trace the guest, in such a way that the guest user is informed that their trace is incomplete due to the host activity.

How do you do that? And you still need the module parameter to decide whether the host is _allowed_ to cause incomplete traces in the guest.

Paolo

Quoted 3 lines

Side note: the "system-wide tracing" is a misnomer here, all that matters is that there's a perf event on the host that wants to trace the guest, it can very well be a per-task event.

#21 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 6 lines · Paolo Bonzini
Quoted 5 lines · Alexander Shishkin
Quoted 4 lines

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

Quoted 6 lines
Quoted 4 lines

CPUID is immaterial here; the real trick is to disallow the use of PT at runtime when the host suddenly decides to trace the guest, in such a way that the guest user is informed that their trace is incomplete due to the host activity.

How do you do that?

Off the top of my head:
* you don't;
* you write something to the PT stream;
* you signal an error via RTIT_STATUS;
* guest always prevails: host gets PARTIAL records in case of a conflict.

Quoted 2 lines

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

Regards,
--
Alex

maintainer
#22 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 20 lines · Alexander Shishkin
Quoted 6 lines · Paolo Bonzini
Quoted 5 lines · Alexander Shishkin
Quoted 4 lines

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

Quoted 6 lines
Quoted 4 lines

CPUID is immaterial here; the real trick is to disallow the use of PT at runtime when the host suddenly decides to trace the guest, in such a way that the guest user is informed that their trace is incomplete due to the host activity.

How do you do that?

Off the top of my head:
* you don't;
* you write something to the PT stream;
* you signal an error via RTIT_STATUS;
* guest always prevails: host gets PARTIAL records in case of a conflict.

Quoted 6 lines
Quoted 2 lines

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

It's not different versions; it's having PT vs. not having PT at all. I don't really see it as a big issue. The nice thing about this series is that the interactions between PT code and KVM code are minimal.

Paolo

#23 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 24 lines · Paolo Bonzini
Quoted 23 lines · Alexander Shishkin
Quoted 6 lines · Paolo Bonzini
Quoted 5 lines · Alexander Shishkin
Quoted 4 lines

Guest tracing can only be enabled at boot time, because the guest's CPUID changes depending on whether it's enabled. And likewise if perf record can do system-wide tracing at any time during the guest's execution, we need to know it at boot time in order to set the guest CPUID.

Quoted 6 lines
Quoted 4 lines

CPUID is immaterial here; the real trick is to disallow the use of PT at runtime when the host suddenly decides to trace the guest, in such a way that the guest user is informed that their trace is incomplete due to the host activity.

How do you do that?

Off the top of my head:
* you don't;
* you write something to the PT stream;
* you signal an error via RTIT_STATUS;
* guest always prevails: host gets PARTIAL records in case of a conflict.

Quoted 2 lines

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Quoted 7 lines
Quoted 3 lines

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

It's not different versions; it's having PT vs. not having PT at all. I don't really see it as a big issue. The nice thing about this series is that the interactions between PT code and KVM code are minimal.

Unfortunately, it gets it wrong. Like I just said in another email, if you switch off host's PT, you need to let them know, which this patchset doesn't do. And when it does, it would be the same amount of interaction with PT code as what would be required to get the dynamic guest PT right.

Regards,
--
Alex

maintainer
#24 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 10 lines · Alexander Shishkin
Quoted 6 lines
Quoted 3 lines

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

It's not different versions; it's having PT vs. not having PT at all. I don't really see it as a big issue. The nice thing about this series is that the interactions between PT code and KVM code are minimal.

Unfortunately, it gets it wrong. Like I just said in another email, if you switch off host's PT, you need to let them know, which this patchset doesn't do. And when it does, it would be the same amount of interaction with PT code as what would be required to get the dynamic guest PT right.

Two issues:

1) Is there a fast (10 clock cycles, better if less) way for KVM to know "PT is enabled on the host", or a callback that KVM can register when e.g. RTIT_CTL is written?

2) We'd have to write trace records into the guest. That does not sound that easy. Does it entail parsing the ToPA and all that?

Thanks,

Paolo

maintainer
#25 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

In reply to Alexander Shishkin
Quoted 8 lines · Alexander Shishkin
Quoted 2 lines · Paolo Bonzini

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

Yes, that sounds like a much better approach.

maintainer
#26 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 11 lines · Peter Zijlstra
Quoted 8 lines · Alexander Shishkin
Quoted 2 lines · Paolo Bonzini

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

Yes, that sounds like a much better approach.

I don't think so. The possibility that the host would lose tracing data just because the guest starts using PT seems hideous to me...

Paolo

maintainer
#27 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 7 lines · Paolo Bonzini
Quoted 6 lines · Peter Zijlstra
Quoted 5 lines · Alexander Shishkin
Quoted 2 lines · Paolo Bonzini

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

Yes, that sounds like a much better approach.

I don't think so. The possibility that the host would lose tracing data just because the guest starts using PT seems hideous to me...

Well, either way around is a fairly crap situation, the modparam at least lets the admin pick which it goes. But if you want to always let the host win, that's fine with me too, less knobs is better.

maintainer
#28 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 12 lines · Peter Zijlstra
Quoted 11 lines · Paolo Bonzini
Quoted 10 lines · Peter Zijlstra
Quoted 8 lines · Alexander Shishkin
Quoted 2 lines · Paolo Bonzini

And you still need the module parameter to decide
whether the host is _allowed_ to cause incomplete traces in the guest.

Or rather a parameter to decide who wins in case both host and guest want to trace the guest. That's arguably better than having different versions of PT in the guest depending on a module parameter setting.

Quoted 8 lines
Quoted 4 lines
Quoted 1 line

Yes, that sounds like a much better approach.

I don't think so. The possibility that the host would lose tracing data just because the guest starts using PT seems hideous to me...

Well, either way around is a fairly crap situation, the modparam at least lets the admin pick which it goes. But if you want to always let the host win, that's fine with me too, less knobs is better.

I expect that the default "system-wide" host wins will be used almost always, with "host-guest" being used in case someone actually wants to use PT in guests.

I agree that "Host-only, drop guest events" should be removed, since it can be emulated by perf code. Luwei, can you change that?

Paolo

maintainer
#29 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

In reply to Alexander Shishkin
Quoted 7 lines · Alexander Shishkin

arch/x86/kvm/vmx.c static inline bool cpu_has_vmx_vmfunc(void) · line 1507

Quoted 4 lines
arch/x86/kvm/vmx.c +4 -0
+static inline bool cpu_has_vmx_pt_use_gpa(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA;
+}

I can deduce the meaning of the previous one, but not this one, and there's no explanation.

Within KVM, GPA always means guest physical address.

Quoted 10 lines

arch/x86/kvm/vmx.c static u32 vmx_exec_control(struct vcpu_vmx *vmx) · line 5819

Quoted 3 lines
arch/x86/kvm/vmx.c +3 -0
+	if (pt_mode == PT_MODE_SYSTEM)
+		vmexit_control &= ~(VM_EXIT_CLEAR_IA32_RTIT_CTL |
+				    VM_EXIT_PT_CONCEAL_PIP);

Ok, so what we really want to know is: is there an encompassing PT event on this cpu when we go into VMLAUNCH/VMRESTORE, right? We can find this out from the pt_ctx and avoid the pt_mode entirely. IOW, instead of having the 3 modes that you describe at the top, you can use something like the following:

Quoted 5 lines

1. Do we have an event in pt_ctx?
* No -> Set up the context for VMX.
* Yes -> 2. Is attr.exclude_guest set?
* No -> Guest trace goes to the host's buffer, do nothing.
* Yes -> Set up/switch the context for VMX.

Can you explain this more clearly?

Thanks,

Paolo

#30 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 10 lines · Paolo Bonzini
Quoted 7 lines · Alexander Shishkin

arch/x86/kvm/vmx.c static inline bool cpu_has_vmx_vmfunc(void) · line 1507

Quoted 4 lines
arch/x86/kvm/vmx.c +4 -0
+static inline bool cpu_has_vmx_pt_use_gpa(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA;
+}

I can deduce the meaning of the previous one, but not this one, and there's no explanation.

Within KVM, GPA always means guest physical address.

I see, thanks.

Quoted 10 lines
Quoted 10 lines

arch/x86/kvm/vmx.c static u32 vmx_exec_control(struct vcpu_vmx *vmx) · line 5819

Quoted 3 lines
arch/x86/kvm/vmx.c +3 -0
+	if (pt_mode == PT_MODE_SYSTEM)
+		vmexit_control &= ~(VM_EXIT_CLEAR_IA32_RTIT_CTL |
+				    VM_EXIT_PT_CONCEAL_PIP);

Ok, so what we really want to know is: is there an encompassing PT event on this cpu when we go into VMLAUNCH/VMRESTORE, right? We can find this out from the pt_ctx and avoid the pt_mode entirely. IOW, instead of having the 3 modes that you describe at the top, you can use something like the following:

Quoted 7 lines
Quoted 5 lines

1. Do we have an event in pt_ctx?
* No -> Set up the context for VMX.
* Yes -> 2. Is attr.exclude_guest set?
* No -> Guest trace goes to the host's buffer, do nothing.
* Yes -> Set up/switch the context for VMX.

Can you explain this more clearly?

Let's see; in the intel_pt driver we have a per-cpu PT "context", from which we can tell if there is a host event that wants to trace the guest. This should provide enough information to make a decision whether we want to context switch PT MSRs or not on the spot, instead of having a module parameter.

Regards,
--
Alex

maintainer
#31 lore raw

Re: [PATCH v7 06/13] KVM: x86: Add Intel Processor Trace virtualization mode

Quoted 11 lines · Alexander Shishkin
Quoted 6 lines
Quoted 5 lines

1. Do we have an event in pt_ctx?
* No -> Set up the context for VMX.
* Yes -> 2. Is attr.exclude_guest set?
* No -> Guest trace goes to the host's buffer, do nothing.
* Yes -> Set up/switch the context for VMX.

Can you explain this more clearly?

Let's see; in the intel_pt driver we have a per-cpu PT "context", from which we can tell if there is a host event that wants to trace the guest. This should provide enough information to make a decision whether we want to context switch PT MSRs or not on the spot, instead of having a module parameter.

I still don't understand how the host event is useful...

Paolo

author
#32 lore raw

PATCH v7 7/13 KVM: x86: Add Intel Processor Trace cpuid emulation

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Expose Intel Processor Trace to guest only when PT work in HOST_GUEST mode.

---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/cpuid.c            | 22 ++++++++++++++++++++--
 arch/x86/kvm/svm.c              |  6 ++++++
 arch/x86/kvm/vmx.c              |  6 ++++++
 4 files changed, 33 insertions(+), 2 deletions(-)
arch/x86/include/asm/kvm_host.h +1 -0
index c25775f..03875aa 100644
@@ -1025,6 +1025,7 @@ struct kvm_x86_ops {
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
 	bool (*umip_emulated)(void);
+	bool (*pt_supported)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
arch/x86/kvm/cpuid.c +20 -2
index 82055b9..e04bf67 100644
@@ -336,6 +336,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
 	unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
 	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
+	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
 
 	/* cpuid 1.edx */
 	const u32 kvm_cpuid_1_edx_x86_features =
@@ -393,7 +394,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
 		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
-		F(SHA_NI) | F(AVX512BW) | F(AVX512VL);
+		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt;
 
 	/* cpuid 0xD.1.eax */
 	const u32 kvm_cpuid_D_1_eax_x86_features =
@@ -423,7 +424,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	switch (function) {
 	case 0:
-		entry->eax = min(entry->eax, (u32)0xd);
+		entry->eax = min(entry->eax, (u32)(f_intel_pt ? 0x14 : 0xd));
 		break;
 	case 1:
 		entry->edx &= kvm_cpuid_1_edx_x86_features;
@@ -595,6 +596,23 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
+	/* Intel PT */
+	case 0x14: {
+		int t, times = entry->eax;
+
+		if (!f_intel_pt)
+			break;
+
+		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+		for (t = 1; t <= times; ++t) {
+			if (*nent >= maxnent)
+				goto out;
+			do_cpuid_1_ent(&entry[t], function, t);
+			entry[t].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+			++*nent;
+		}
+		break;
+	}
 	case KVM_CPUID_SIGNATURE: {
 		static const char signature[12] = "KVMKVMKVM\0\0";
 		const u32 *sigptr = (const u32 *)signature;
arch/x86/kvm/svm.c +6 -0
index 80ea262..23a1ef9 100644
@@ -5877,6 +5877,11 @@ static bool svm_umip_emulated(void)
 	return false;
 }
 
+static bool svm_pt_supported(void)
+{
+	return false;
+}
+
 static bool svm_has_wbinvd_exit(void)
 {
 	return true;
@@ -7102,6 +7107,7 @@ static int svm_unregister_enc_region(struct kvm *kvm,
 	.mpx_supported = svm_mpx_supported,
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
+	.pt_supported = svm_pt_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
arch/x86/kvm/vmx.c +6 -0
index 8680cd5..27cf417 100644
@@ -9563,6 +9563,11 @@ static bool vmx_umip_emulated(void)
 		SECONDARY_EXEC_DESC;
 }
 
+static bool vmx_pt_supported(void)
+{
+	return (pt_mode == PT_MODE_HOST_GUEST);
+}
+
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -12790,6 +12795,7 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	.mpx_supported = vmx_mpx_supported,
 	.xsaves_supported = vmx_xsaves_supported,
 	.umip_emulated = vmx_umip_emulated,
+	.pt_supported = vmx_pt_supported,
 
 	.check_nested_events = vmx_check_nested_events,
 
Signature · 1 line
1.8.3.1
author
#33 lore raw

PATCH v7 8/13 KVM: x86: Add Intel processor trace context for each vcpu

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Add a data structure to save Intel Processor Trace context. It mainly include the value of Intel PT host/guest MSRs and guest CPUID information.

---
 arch/x86/kvm/vmx.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
arch/x86/kvm/vmx.c +19 -0
index 27cf417..9a5c26d 100644
@@ -597,6 +597,23 @@ static inline int pi_test_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+struct pt_ctx {
+	u64 ctl;
+	u64 status;
+	u64 output_base;
+	u64 output_mask;
+	u64 cr3_match;
+	u64 addrs[MSR_IA32_RTIT_ADDR_COUNT];
+};
+
+struct pt_desc {
+	u64 ctl_bitmask;
+	u32 range_cnt;
+	u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	struct pt_ctx host;
+	struct pt_ctx guest;
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -693,6 +710,8 @@ struct vcpu_vmx {
 	 */
 	u64 msr_ia32_feature_control;
 	u64 msr_ia32_feature_control_valid_bits;
+
+	struct pt_desc pt_desc;
 };
 
 enum segment_cache_field {
Signature · 1 line
1.8.3.1
#34 lore raw

Re: [PATCH v7 08/13] KVM: x86: Add Intel processor trace context for each vcpu

Quoted 5 lines · Luwei Kang

From: Chao Peng <[email protected]>

Add a data structure to save Intel Processor Trace context. It mainly include the value of Intel PT host/guest MSRs and guest CPUID information.

I'd say that code and data should be in the same patch.

Quoted 46 lines
---
 arch/x86/kvm/vmx.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
arch/x86/kvm/vmx.c +19 -0
index 27cf417..9a5c26d 100644
@@ -597,6 +597,23 @@ static inline int pi_test_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+struct pt_ctx {
+	u64 ctl;
+	u64 status;
+	u64 output_base;
+	u64 output_mask;
+	u64 cr3_match;
+	u64 addrs[MSR_IA32_RTIT_ADDR_COUNT];
+};
+
+struct pt_desc {
+	u64 ctl_bitmask;
+	u32 range_cnt;
+	u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	struct pt_ctx host;
+	struct pt_ctx guest;
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -693,6 +710,8 @@ struct vcpu_vmx {
 	 */
 	u64 msr_ia32_feature_control;
 	u64 msr_ia32_feature_control_valid_bits;
+
+	struct pt_desc pt_desc;
 };
 
 enum segment_cache_field {
Signature · 1 line
1.8.3.1
maintainer
#35 lore raw

Re: [PATCH v7 08/13] KVM: x86: Add Intel processor trace context for each vcpu

Quoted 8 lines · Alexander Shishkin
Quoted 5 lines · Luwei Kang

From: Chao Peng <[email protected]>

Add a data structure to save Intel Processor Trace context. It mainly include the value of Intel PT host/guest MSRs and guest CPUID information.

I'd say that code and data should be in the same patch.

Yeah, it's okay to merge this with patch 9.

Paolo

author
#36 lore raw

PATCH v7 9/13 KVM: x86: Implement Intel Processor Trace context switch

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Load/Store Intel processor trace register in context switch. MSR IA32_RTIT_CTL is loaded/stored automatically from VMCS. In HOST mode, we just need to restore the status of IA32_RTIT_CTL. In HOST_GUEST mode, we need load/resore PT MSRs only when PT is enabled in guest.

---
 arch/x86/kvm/vmx.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
arch/x86/kvm/vmx.c +60 -0
index 9a5c26d..a08c61b 100644
@@ -2385,6 +2385,55 @@ static unsigned long segment_base(u16 selector)
 }
 #endif
 
+static inline void pt_load_msr(struct pt_ctx *ctx, u32 range_cnt)
+{
+	u32 i;
+
+	wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < range_cnt; i++)
+		wrmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
+}
+
+static inline void pt_save_msr(struct pt_ctx *ctx, u32 range_cnt)
+{
+	u32 i;
+
+	rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+	rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+	rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+	for (i = 0; i < range_cnt; i++)
+		rdmsrl(MSR_IA32_RTIT_ADDR0_A + i, ctx->addrs[i]);
+}
+
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+	}
+
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}
+
 static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6119,6 +6168,13 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
 		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 	}
+
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		memset(&vmx->pt_desc, 0, sizeof(vmx->pt_desc));
+		/* Bit[6~0] are forced to 1, writes are ignored. */
+		vmx->pt_desc.guest.output_mask = 0x7F;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
+	}
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9794,6 +9850,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	    vcpu->arch.pkru != vmx->host_pkru)
 		__write_pkru(vcpu->arch.pkru);
 
+	pt_guest_enter(vmx);
+
 	atomic_switch_perf_msrs(vmx);
 
 	vmx_arm_hv_timer(vcpu);
@@ -9988,6 +10046,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 				  | (1 << VCPU_EXREG_CR3));
 	vcpu->arch.regs_dirty = 0;
 
+	pt_guest_exit(vmx);
+
 	/*
 	 * eager fpu is enabled if PKEY is supported and CR4 is switched
 	 * back on host, so it is safe to read guest PKRU from current
Signature · 1 line
1.8.3.1
#37 lore raw

Re: [PATCH v7 09/13] KVM: x86: Implement Intel Processor Trace context switch

Quoted 14 lines · Luwei Kang
arch/x86/kvm/vmx.c +14 -0
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)

arch/x86/kvm/vmx.c static unsigned long segment_base(u16 selector) · line 2435

Quoted 10 lines
arch/x86/kvm/vmx.c +10 -0
+{
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+	}
+
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}

This means that a host PT event won't get the guest traces and won't get any notification as to what'd happened or why. At the minimum we need to send a PARTIAL AUX record at the pt_guest_enter(), when we turn the host tracing off.

Regards,
--
Alex

maintainer
#38 lore raw

Re: [PATCH v7 09/13] KVM: x86: Implement Intel Processor Trace context switch

Quoted 22 lines · Alexander Shishkin
Quoted 21 lines · Luwei Kang
arch/x86/kvm/vmx.c +21 -0
+static void pt_guest_enter(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		wrmsrl(MSR_IA32_RTIT_CTL, 0);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+	}
+}
+
+static void pt_guest_exit(struct vcpu_vmx *vmx)
+{
+	if (pt_mode == PT_MODE_HOST_GUEST &&
+		vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.range_cnt);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.range_cnt);
+	}
+
Quoted 8 lines

arch/x86/kvm/vmx.c static unsigned long segment_base(u16 selector) · line 2435

Quoted 3 lines
arch/x86/kvm/vmx.c +3 -0
+	if (pt_mode == PT_MODE_HOST || pt_mode == PT_MODE_HOST_GUEST)
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+}

This means that a host PT event won't get the guest traces and won't get any notification as to what'd happened or why. At the minimum we need to send a PARTIAL AUX record at the pt_guest_enter(), when we turn the host tracing off.

How do you do that? :)

Paolo

author
#39 lore raw

PATCH v7 10/13 KVM: x86: Introduce a function to initialize the PT configuration

In reply to Luwei Kang

Initialize the Intel PT configuration when cpuid update. Include cpuid inforamtion, rtit_ctl bit mask and the number of address ranges.

---
 arch/x86/kvm/vmx.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
arch/x86/kvm/vmx.c +69 -0
index a08c61b..3ed02a8 100644
@@ -10371,6 +10371,71 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 #undef cr4_fixed1_update
 }
 
+static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_cpuid_entry2 *best = NULL;
+	int i;
+
+	for (i = 0; i < PT_CPUID_LEAVES; i++) {
+		best = kvm_find_cpuid_entry(vcpu, 0x14, i);
+		if (!best)
+			return;
+		vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax;
+		vmx->pt_desc.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM] = best->ebx;
+		vmx->pt_desc.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM] = best->ecx;
+		vmx->pt_desc.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM] = best->edx;
+	}
+
+	/* Get the number of configurable Address Ranges for filtering */
+	vmx->pt_desc.range_cnt = __pt_cap_get(vmx->pt_desc.caps,
+						PT_CAP_num_address_ranges);
+
+	/* Clear the no dependency bits */
+	vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS |
+			RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC);
+
+	/* If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_cr3_filtering))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_CR3EN;
+
+	/*
+	 * If CPUID.(EAX=14H,ECX=0):EBX[1]=1 CYCEn, CycThresh and
+	 * PSBFreq can be set
+	 */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_psb_cyc))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_CYCLEACC |
+			RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ);
+
+	/*
+	 * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and
+	 * MTCFreq can be set
+	 */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_mtc))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN |
+			RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE);
+
+	/* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_ptwrite))
+		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_FUP_ON_PTW |
+						RTIT_CTL_PTW_EN);
+
+	/* If CPUID.(EAX=14H,ECX=0):EBX[5]=1 PwrEvEn can be set */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_power_event_trace))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_PWR_EVT_EN;
+
+	/* If CPUID.(EAX=14H,ECX=0):ECX[0]=1 ToPA can be set */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_topa_output))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA;
+	/* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */
+	if (__pt_cap_get(vmx->pt_desc.caps, PT_CAP_output_subsys))
+		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN;
+
+	/* unmask address range configure area */
+	for (i = 0; i < vmx->pt_desc.range_cnt; i++)
+		vmx->pt_desc.ctl_bitmask &= ~(0xf << (32 + i*4));
+}
+
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -10389,6 +10454,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 
 	if (nested_vmx_allowed(vcpu))
 		nested_vmx_cr_fixed1_bits_update(vcpu);
+
+	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
+		guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
+		update_intel_pt_cfg(vcpu);
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
Signature · 1 line
1.8.3.1
author
#40 lore raw

PATCH v7 11/13 KVM: x86: Implement Intel Processor Trace MSRs read/write

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Implement Intel Processor Trace MSRs read/write.

---
 arch/x86/include/asm/intel_pt.h |   8 ++
 arch/x86/kvm/vmx.c              | 163 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c              |  33 +++++++-
 3 files changed, 203 insertions(+), 1 deletion(-)
arch/x86/include/asm/intel_pt.h +8 -0
index 43ad260..dc0f3f0 100644
@@ -5,6 +5,14 @@
 #define PT_CPUID_LEAVES		2
 #define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
+#define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \
+		RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \
+		RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \
+		RTIT_STATUS_BYTECNT))
+
+#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \
+	(~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f)
+
 enum pt_mode {
 	PT_MODE_SYSTEM = 0,
 	PT_MODE_HOST,
arch/x86/kvm/vmx.c +163 -0

181 lines not on this page · raw message

arch/x86/kvm/x86.c +32 -1
index 51ecd38..cea0ee2 100644
@@ -69,6 +69,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
+#include <asm/intel_pt.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -1023,7 +1024,13 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu)
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
-	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
+	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES,
+	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
+	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
+	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
+	MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
+	MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
+	MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
 };
 
 static unsigned num_msrs_to_save;
@@ -4592,6 +4599,30 @@ static void kvm_init_msr_list(void)
 			if (!kvm_x86_ops->rdtscp_supported())
 				continue;
 			break;
+		case MSR_IA32_RTIT_CTL:
+		case MSR_IA32_RTIT_STATUS:
+			if (!kvm_x86_ops->pt_supported())
+				continue;
+			break;
+		case MSR_IA32_RTIT_CR3_MATCH:
+			if (!kvm_x86_ops->pt_supported() ||
+					!pt_cap_get(PT_CAP_cr3_filtering))
+				continue;
+			break;
+		case MSR_IA32_RTIT_OUTPUT_BASE:
+		case MSR_IA32_RTIT_OUTPUT_MASK:
+			if (!kvm_x86_ops->pt_supported() ||
+				(!pt_cap_get(PT_CAP_topa_output) &&
+				 !pt_cap_get(PT_CAP_single_range_output)))
+				continue;
+			break;
+		case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
+			if (!kvm_x86_ops->pt_supported() ||
+				msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+				2 * pt_cap_get(PT_CAP_num_address_ranges))
+				continue;
+			break;
+		}
 		default:
 			break;
 		}
Signature · 1 line
1.8.3.1
#41 lore raw

Re: [PATCH v7 11/13] KVM: x86: Implement Intel Processor Trace MSRs read/write

Quoted 3 lines · Luwei Kang

From: Chao Peng <[email protected]>

Implement Intel Processor Trace MSRs read/write.

There needs to be a commit message here.

Quoted 13 lines
---
 arch/x86/include/asm/intel_pt.h |   8 ++
 arch/x86/kvm/vmx.c              | 163 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c              |  33 +++++++-
 3 files changed, 203 insertions(+), 1 deletion(-)
arch/x86/include/asm/intel_pt.h +0 -0
index 43ad260..dc0f3f0 100644

arch/x86/include/asm/intel_pt.h line 14

Quoted 10 lines
arch/x86/include/asm/intel_pt.h +7 -0
@@ -5,6 +5,14 @@
 #define PT_CPUID_LEAVES		2
 #define PT_CPUID_REGS_NUM	4 /* number of regsters (eax, ebx, ecx, edx) */
 
+#define MSR_IA32_RTIT_STATUS_MASK (~(RTIT_STATUS_FILTEREN | \
+		RTIT_STATUS_CONTEXTEN | RTIT_STATUS_TRIGGEREN | \
+		RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \
+		RTIT_STATUS_BYTECNT))
+
+#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \
+	(~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f)

How does this macro make sense in the intel_pt.h? It also relies on vcpu being in the scope.

Quoted 29 lines
arch/x86/include/asm/intel_pt.h +0 -0
 enum pt_mode {
 	PT_MODE_SYSTEM = 0,
 	PT_MODE_HOST,
arch/x86/kvm/vmx.c +18 -0
index 3ed02a8..2a29ab9 100644
@@ -2769,6 +2769,77 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, interruptibility);
 }
 
+static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long value;
+
+	/*
+	 * Any MSR write that attempts to change bits marked reserved will
+	 * case a #GP fault.
+	 */
+	if (data & vmx->pt_desc.ctl_bitmask)
+		return 1;
+
+	/*
+	 * Any attempt to modify IA32_RTIT_CTL while TraceEn is set will
+	 * result in a #GP unless the same write also clears TraceEn.
+	 */
+	if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) &&
+		((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN))

arch/x86/kvm/vmx.c static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) · line 2799

Quoted 10 lines
arch/x86/kvm/vmx.c +10 -0
+		return 1;
+
+	/*
+	 * WRMSR to IA32_RTIT_CTL that sets TraceEn but clears this bit
+	 * and FabricEn would cause #GP, if
+	 * CPUID.(EAX=14H, ECX=0):ECX.SNGLRGNOUT[bit 2] = 0
+	 */
+	if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) &&
+		!(data & RTIT_CTL_FABRIC_EN) &&
+		!__pt_cap_get(vmx->pt_desc.caps, PT_CAP_single_range_output))

You seem to be doing a lot of __pt_cap_get()s on each wrmsr. Did you consider decoding the capabilities once and storing the decoded values instead, so that in functions like these you can access them by

if (vmx->pt_desc.caps[PT_CAP_single_range_output]) ...

?

Regards,
--
Alex

maintainer
#42 lore raw

Re: [PATCH v7 11/13] KVM: x86: Implement Intel Processor Trace MSRs read/write

Quoted 11 lines · Alexander Shishkin

arch/x86/kvm/vmx.c static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) · line 2799

Quoted 4 lines
arch/x86/kvm/vmx.c +4 -0
+	 */
+	if ((data & RTIT_CTL_TRACEEN) && !(data & RTIT_CTL_TOPA) &&
+		!(data & RTIT_CTL_FABRIC_EN) &&
+		!__pt_cap_get(vmx->pt_desc.caps, PT_CAP_single_range_output))

You seem to be doing a lot of __pt_cap_get()s on each wrmsr. Did you consider decoding the capabilities once and storing the decoded values instead, so that in functions like these you can access them by

   if (vmx->pt_desc.caps[PT_CAP_single_range_output]) ...

?

Or pt_cap_get could use a switch statement in pt_cap_get and make it __always_inline. The argument is always a constant except for pt_cap_show.

What you say is also a possibility though. Are you okay with adding a PT_CAP_first_unused at the end of enum pt_capabilities, so that the array can be sized?

Thanks,

Paolo

author
#43 lore raw

PATCH v7 12/13 KVM: x86: Set intercept for Intel PT MSRs read/write

In reply to Luwei Kang

From: Chao Peng <[email protected]>

Disable intercept Intel PT MSRs only when Intel PT is enabled in guest. But MSR_IA32_RTIT_CTL will alway be intercept.

---
 arch/x86/kvm/vmx.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
arch/x86/kvm/vmx.c +20 -0
index 2a29ab9..c125fb1 100644
@@ -947,6 +947,7 @@ static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
 static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
 static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
 							  u32 msr, int type);
+static void pt_set_intercept_for_msr(struct vcpu_vmx *vmx, bool flag);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -3954,6 +3955,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			vmx_rtit_ctl_check(vcpu, data))
 			return 1;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
+		pt_set_intercept_for_msr(vmx, !(data & RTIT_CTL_TRACEEN));
 		vmx->pt_desc.guest.ctl = data;
 		break;
 	case MSR_IA32_RTIT_STATUS:
@@ -5761,6 +5763,24 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 	vmx->msr_bitmap_mode = mode;
 }
 
+static void pt_set_intercept_for_msr(struct vcpu_vmx *vmx, bool flag)
+{
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	u32 i;
+
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
+							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
+							MSR_TYPE_RW, flag);
+	for (i = 0; i < vmx->pt_desc.range_cnt; i++)
+		vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_ADDR0_A + i,
+							MSR_TYPE_RW, flag);
+}
+
 static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
 {
 	return enable_apicv;
Signature · 1 line
1.8.3.1
author
#44 lore raw

PATCH v7 13/13 KVM: x86: Disable Intel Processor Trace when VMXON in L1 guest

In reply to Luwei Kang

Currently, Intel Processor Trace do not support tracing in L1 guest VMX operation(IA32_VMX_MISC[bit 14] is 0). As mentioned in SDM, on these type of processors, execution of the VMXON instruction will clears IA32_RTIT_CTL.TraceEn and any attempt to write IA32_RTIT_CTL causes a general-protection exception (#GP).

---
 arch/x86/kvm/vmx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
arch/x86/kvm/vmx.c +8 -1
index c125fb1..1e800d0 100644
@@ -3952,7 +3952,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			vmx_rtit_ctl_check(vcpu, data))
+			vmx_rtit_ctl_check(vcpu, data) ||
+			vmx->nested.vmxon)
 			return 1;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
 		pt_set_intercept_for_msr(vmx, !(data & RTIT_CTL_TRACEEN));
@@ -8029,6 +8030,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		vmx->pt_desc.guest.ctl = 0;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
+		pt_set_intercept_for_msr(vmx, 1);
+	}
+
 	nested_vmx_succeed(vcpu);
 	return kvm_skip_emulated_instruction(vcpu);
 }
Signature · 1 line
1.8.3.1
#45 lore raw

Re: [PATCH v7 13/13] KVM: x86: Disable Intel Processor Trace when VMXON in L1 guest

Quoted 2 lines · Luwei Kang

Currently, Intel Processor Trace do not support tracing in L1 guest VMX operation(IA32_VMX_MISC[bit 14] is 0). As mentioned in SDM,

I don't understand this patch. You mention VMX_MISC[14] here, but I can't see anything related to it in the code.

Also, the description should probably say "...does not support tracing in VMX *if* IA32_VMX_MISC[bit 14] is 0."

Quoted 39 lines

on these type of processors, execution of the VMXON instruction will clears IA32_RTIT_CTL.TraceEn and any attempt to write IA32_RTIT_CTL causes a general-protection exception (#GP).

---
 arch/x86/kvm/vmx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
arch/x86/kvm/vmx.c +8 -1
index c125fb1..1e800d0 100644
@@ -3952,7 +3952,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			vmx_rtit_ctl_check(vcpu, data))
+			vmx_rtit_ctl_check(vcpu, data) ||
+			vmx->nested.vmxon)
 			return 1;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
 		pt_set_intercept_for_msr(vmx, !(data & RTIT_CTL_TRACEEN));
@@ -8029,6 +8030,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
+	if (pt_mode == PT_MODE_HOST_GUEST) {
+		vmx->pt_desc.guest.ctl = 0;
+		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
+		pt_set_intercept_for_msr(vmx, 1);
+	}
+
 	nested_vmx_succeed(vcpu);
 	return kvm_skip_emulated_instruction(vcpu);
 }
Signature · 1 line
1.8.3.1
maintainer
#46 lore raw

Re: [PATCH v7 13/13] KVM: x86: Disable Intel Processor Trace when VMXON in L1 guest

Quoted 4 lines · Alexander Shishkin
Quoted 2 lines

Currently, Intel Processor Trace do not support tracing in L1 guest VMX operation(IA32_VMX_MISC[bit 14] is 0). As mentioned in SDM,

I don't understand this patch. You mention VMX_MISC[14] here, but I can't see anything related to it in the code.

This is talking about the _guest_'s view of IA32_VMX_MISC. The code does nothing to set it, so the patch does what the commit message says below:

Quoted 5 lines
Quoted 5 lines

on these type of processors, execution of the VMXON instruction will clears IA32_RTIT_CTL.TraceEn and any attempt to write IA32_RTIT_CTL causes a general-protection exception (#GP).

Thanks,

Paolo