Skip to contentSkip to conversation

Intel IOMMU updates for Linux v6.3

GIT PULL New Lu Baolu 2 participants 14 messages Jan 31, 2023 – Feb 3, 2023

Subsystems (5)
lore
Share & tools
lore

Lu Baolu

author maintainer
#0 lore raw

Hi Joerg,

This includes patches queued for v6.3. It includes:

- Add Intel IOMMU performance monitoring support
- Set No Execute Enable bit in PASID table entry
- Cleanups

The whole series is based on v6.2-rc6 and also available at:
https://github.com/LuBaolu/intel-iommu/commits/vtd-update-for-v6.3

Please pull them for x86/vt-d branch.

Best regards,
Baolu

Kan Liang (7):
iommu/vt-d: Support size of the register set in DRHD iommu/vt-d: Retrieve IOMMU perfmon capability information iommu/vt-d: Support Enhanced Command Interface iommu/vt-d: Add IOMMU perfmon support iommu/vt-d: Support cpumask for IOMMU perfmon iommu/vt-d: Add IOMMU perfmon overflow handler support iommu/vt-d: Enable IOMMU perfmon support

Lu Baolu (5):
iommu/vt-d: Remove include/linux/intel-svm.h iommu/vt-d: Remove unused fields in svm structures iommu/vt-d: Remove users from intel_svm_dev iommu/vt-d: Remove sva from intel_svm_dev iommu/vt-d: Set No Execute Enable bit in PASID table entry

 include/linux/cpuhotplug.h                    |   1 +
 include/linux/dmar.h                          |   1 +
 include/linux/intel-svm.h                     |  16 -
 drivers/iommu/intel/iommu.h                   | 113 ++-
 drivers/iommu/intel/perfmon.h                 |  64 ++
 include/acpi/actbl1.h                         |   2 +-
 drivers/iommu/intel/dmar.c                    |  33 +-
 drivers/iommu/intel/iommu.c                   |  60 +-
 drivers/iommu/intel/pasid.c                   |  11 +
 drivers/iommu/intel/perfmon.c                 | 877 ++++++++++++++++++
 drivers/iommu/intel/svm.c                     |  90 +-
 .../sysfs-bus-event_source-devices-iommu      |  37 +
 MAINTAINERS                                   |   1 -
 drivers/iommu/intel/Kconfig                   |  11 +
 drivers/iommu/intel/Makefile                  |   1 +
 15 files changed, 1234 insertions(+), 84 deletions(-)
 delete mode 100644 include/linux/intel-svm.h
 create mode 100644 drivers/iommu/intel/perfmon.h
 create mode 100644 drivers/iommu/intel/perfmon.c
 create mode 100644 Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu
Signature · 1 line
2.34.1
author maintainer
#1 lore raw

PATCH 1/12 iommu/vt-d: Remove include/linux/intel-svm.h

There's no need to have a public header for Intel SVA implementation. The device driver should interact with Intel SVA implementation via the IOMMU generic APIs.

---
 include/linux/intel-svm.h   | 16 ----------------
 drivers/iommu/intel/iommu.h |  5 +++++
 drivers/iommu/intel/iommu.c |  1 -
 drivers/iommu/intel/svm.c   |  1 -
 MAINTAINERS                 |  1 -
 5 files changed, 5 insertions(+), 19 deletions(-)
 delete mode 100644 include/linux/intel-svm.h
include/linux/intel-svm.h deleted +0 -16
deleted file mode 100644
index f9a0d44f6fdb..000000000000
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright © 2015 Intel Corporation.
- *
- * Authors: David Woodhouse <[email protected]>
- */
-
-#ifndef __INTEL_SVM_H__
-#define __INTEL_SVM_H__
-
-/* Page Request Queue depth */
-#define PRQ_ORDER	4
-#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
-#define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
-
-#endif /* __INTEL_SVM_H__ */
drivers/iommu/intel/iommu.h +5 -0
index 06e61e474856..f89f63d7a72a 100644
@@ -438,6 +438,11 @@ struct q_inval {
 	int             free_cnt;
 };
 
+/* Page Request Queue depth */
+#define PRQ_ORDER	4
+#define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
+#define PRQ_DEPTH	((0x1000 << PRQ_ORDER) >> 5)
+
 struct dmar_pci_notify_info;
 
 #ifdef CONFIG_IRQ_REMAP
drivers/iommu/intel/iommu.c +0 -1
index 59df7e42fd53..317af67b6098 100644
@@ -16,7 +16,6 @@
 #include <linux/crash_dump.h>
 #include <linux/dma-direct.h>
 #include <linux/dmi.h>
-#include <linux/intel-svm.h>
 #include <linux/memory.h>
 #include <linux/pci.h>
 #include <linux/pci-ats.h>
drivers/iommu/intel/svm.c +0 -1
index c76b66263467..d38a54396c23 100644
@@ -9,7 +9,6 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/slab.h>
-#include <linux/intel-svm.h>
 #include <linux/rculist.h>
 #include <linux/pci.h>
 #include <linux/pci-ats.h>
MAINTAINERS +0 -1
index f781f936ae35..dbc36fa870d1 100644
@@ -10458,7 +10458,6 @@ L:	[email protected]
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
 F:	drivers/iommu/intel/
-F:	include/linux/intel-svm.h
 
 INTEL IPU3 CSI-2 CIO2 DRIVER
 M:	Yong Zhi <[email protected]>
Signature · 1 line
2.34.1
author maintainer
#2 lore raw

PATCH 2/12 iommu/vt-d: Remove unused fields in svm structures

In reply to Lu Baolu

They aren't used anywhere. Remove them to avoid dead code.

---
 drivers/iommu/intel/iommu.h | 4 ----
 drivers/iommu/intel/svm.c   | 2 --
 2 files changed, 6 deletions(-)
drivers/iommu/intel/iommu.h +0 -4
index f89f63d7a72a..e7c732979364 100644
@@ -762,18 +762,14 @@ struct intel_svm_dev {
 	struct device *dev;
 	struct intel_iommu *iommu;
 	struct iommu_sva sva;
-	u32 pasid;
 	int users;
 	u16 did;
-	u16 dev_iotlb:1;
 	u16 sid, qdep;
 };
 
 struct intel_svm {
 	struct mmu_notifier notifier;
 	struct mm_struct *mm;
-
-	unsigned int flags;
 	u32 pasid;
 	struct list_head devs;
 };
drivers/iommu/intel/svm.c +0 -2
index d38a54396c23..d1e445f03aa6 100644
@@ -351,11 +351,9 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 	sdev->users = 1;
-	sdev->pasid = svm->pasid;
 	sdev->sva.dev = dev;
 	init_rcu_head(&sdev->rcu);
 	if (info->ats_enabled) {
-		sdev->dev_iotlb = 1;
 		sdev->qdep = info->ats_qdep;
 		if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
 			sdev->qdep = 0;
Signature · 1 line
2.34.1
author maintainer
#3 lore raw

PATCH 3/12 iommu/vt-d: Remove users from intel_svm_dev

In reply to Lu Baolu

It was used as a reference counter of an existing bond between device and user application memory address. Commit be51b1d6bbff ("iommu/sva:
Refactoring iommu_sva_bind/unbind_device()") has added this in iommu core. Remove it to avoid duplicate code.

---
 drivers/iommu/intel/iommu.h |  1 -
 drivers/iommu/intel/svm.c   | 62 ++++++++++++++++---------------------
 2 files changed, 27 insertions(+), 36 deletions(-)
drivers/iommu/intel/iommu.h +0 -1
index e7c732979364..2a1619ff0d79 100644
@@ -762,7 +762,6 @@ struct intel_svm_dev {
 	struct device *dev;
 	struct intel_iommu *iommu;
 	struct iommu_sva sva;
-	int users;
 	u16 did;
 	u16 sid, qdep;
 };
drivers/iommu/intel/svm.c +27 -35

86 lines not on this page · raw message

Signature · 1 line
2.34.1
author maintainer
#4 lore raw

PATCH 4/12 iommu/vt-d: Remove sva from intel_svm_dev

In reply to Lu Baolu

After commit be51b1d6bbff ("iommu/sva: Refactoring iommu_sva_bind/unbind_device()"), the iommu driver doesn't need to return an iommu_sva pointer anymore. This removes the sva field from intel_svm_dev and cleanups the code accordingly.

---
 drivers/iommu/intel/iommu.h |  1 -
 drivers/iommu/intel/svm.c   | 23 +++++++++--------------
 2 files changed, 9 insertions(+), 15 deletions(-)
drivers/iommu/intel/iommu.h +0 -1
index 2a1619ff0d79..f0222ad38757 100644
@@ -761,7 +761,6 @@ struct intel_svm_dev {
 	struct rcu_head rcu;
 	struct device *dev;
 	struct intel_iommu *iommu;
-	struct iommu_sva sva;
 	u16 did;
 	u16 sid, qdep;
 };
drivers/iommu/intel/svm.c +9 -14
index c7dc53e40c26..e7b9bedebcc0 100644
@@ -298,9 +298,8 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 	return 0;
 }
 
-static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
-					   struct device *dev,
-					   struct mm_struct *mm)
+static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
+			     struct mm_struct *mm)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_svm_dev *sdev;
@@ -312,7 +311,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
-			return ERR_PTR(-ENOMEM);
+			return -ENOMEM;
 
 		svm->pasid = mm->pasid;
 		svm->mm = mm;
@@ -322,14 +321,14 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 		ret = mmu_notifier_register(&svm->notifier, mm);
 		if (ret) {
 			kfree(svm);
-			return ERR_PTR(ret);
+			return ret;
 		}
 
 		ret = pasid_private_add(svm->pasid, svm);
 		if (ret) {
 			mmu_notifier_unregister(&svm->notifier, mm);
 			kfree(svm);
-			return ERR_PTR(ret);
+			return ret;
 		}
 	}
 
@@ -343,7 +342,6 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	sdev->iommu = iommu;
 	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
-	sdev->sva.dev = dev;
 	init_rcu_head(&sdev->rcu);
 	if (info->ats_enabled) {
 		sdev->qdep = info->ats_qdep;
@@ -360,7 +358,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 
 	list_add_rcu(&sdev->list, &svm->devs);
 
-	return &sdev->sva;
+	return 0;
 
 free_sdev:
 	kfree(sdev);
@@ -371,7 +369,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 		kfree(svm);
 	}
 
-	return ERR_PTR(ret);
+	return ret;
 }
 
 /* Caller must hold pasid_mutex */
@@ -843,13 +841,10 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
 	struct mm_struct *mm = domain->mm;
-	struct iommu_sva *sva;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&pasid_mutex);
-	sva = intel_svm_bind_mm(iommu, dev, mm);
-	if (IS_ERR(sva))
-		ret = PTR_ERR(sva);
+	ret = intel_svm_bind_mm(iommu, dev, mm);
 	mutex_unlock(&pasid_mutex);
 
 	return ret;
Signature · 1 line
2.34.1
author maintainer
#5 lore raw

PATCH 5/12 iommu/vt-d: Set No Execute Enable bit in PASID table entry

In reply to Lu Baolu

Setup No Execute Enable bit (Bit 133) of a scalable mode PASID entry. This is to allow the use of XD bit of the first level page table.

Fixes ddf09b6d43ec ("iommu/vt-d: Setup pasid entries for iova over first level")
---
 drivers/iommu/intel/pasid.c | 11 +++++++++++
 1 file changed, 11 insertions(+)
drivers/iommu/intel/pasid.c +11 -0
index fb3c7020028d..ec964ac7d797 100644
@@ -364,6 +364,16 @@ static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
 	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
 }
 
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
 /*
  * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
  * PASID entry.
@@ -557,6 +567,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	pasid_set_nxe(pte);
 
 	/* Setup Present and PASID Granular Transfer Type: */
 	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
Signature · 1 line
2.34.1
author maintainer
#6 lore raw

PATCH 6/12 iommu/vt-d: Support size of the register set in DRHD

In reply to Lu Baolu

From: Kan Liang <[email protected]>

A new field, which indicates the size of the remapping hardware register set for this remapping unit, is introduced in the DMA-remapping hardware unit definition (DRHD) structure with the VT-d Spec 4.0. With this information, SW doesn't need to 'guess' the size of the register set anymore.

Update the struct acpi_dmar_hardware_unit to reflect the field. Store the size of the register set in struct dmar_drhd_unit for each dmar device.

The 'size' information is ResvZ for the old BIOS and platforms. Fall back to the old guessing method. There is nothing changed.

---
 include/linux/dmar.h       |  1 +
 include/acpi/actbl1.h      |  2 +-
 drivers/iommu/intel/dmar.c | 11 +++++++----
 3 files changed, 9 insertions(+), 5 deletions(-)
include/linux/dmar.h +1 -0
index d81a51978d01..725d5e6acec0 100644
@@ -39,6 +39,7 @@ struct dmar_drhd_unit {
 	struct list_head list;		/* list of drhd units	*/
 	struct  acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	reg_base_addr;		/* register base address*/
+	unsigned long reg_size;		/* size of register set */
 	struct	dmar_dev_scope *devices;/* target device array	*/
 	int	devices_cnt;		/* target device count	*/
 	u16	segment;		/* PCI domain		*/
include/acpi/actbl1.h +1 -1
index 4175dce3967c..bdded0ac46eb 100644
@@ -802,7 +802,7 @@ struct acpi_dmar_pci_path {
 struct acpi_dmar_hardware_unit {
 	struct acpi_dmar_header header;
 	u8 flags;
-	u8 reserved;
+	u8 size;		/* Size of the register set */
 	u16 segment;
 	u64 address;		/* Register Base Address */
 };
drivers/iommu/intel/dmar.c +7 -4
index b00a0ceb2d13..3a40fef1ec1b 100644
@@ -427,6 +427,8 @@ static int dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
 	memcpy(dmaru->hdr, header, header->length);
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
+	/* The size of the register set is 2 ^ N 4 KB pages. */
+	dmaru->reg_size = 1UL << (drhd->size + 12);
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
 	dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
 					      ((void *)drhd) + drhd->header.length,
@@ -956,17 +958,18 @@ static void unmap_iommu(struct intel_iommu *iommu)
 /**
  * map_iommu: map the iommu's registers
  * @iommu: the iommu to map
- * @phys_addr: the physical address of the base resgister
+ * @drhd: DMA remapping hardware definition structure
  *
  * Memory map the iommu's registers.  Start w/ a single page, and
  * possibly expand if that turns out to be insufficent.
  */
-static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
+static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd)
 {
+	u64 phys_addr = drhd->reg_base_addr;
 	int map_size, err=0;
 
 	iommu->reg_phys = phys_addr;
-	iommu->reg_size = VTD_PAGE_SIZE;
+	iommu->reg_size = drhd->reg_size;
 
 	if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) {
 		pr_err("Can't reserve memory\n");
@@ -1050,7 +1053,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 	sprintf(iommu->name, "dmar%d", iommu->seq_id);
 
-	err = map_iommu(iommu, drhd->reg_base_addr);
+	err = map_iommu(iommu, drhd);
 	if (err) {
 		pr_err("Failed to map %s\n", iommu->name);
 		goto error_free_seq_id;
Signature · 1 line
2.34.1
author maintainer
#7 lore raw

PATCH 7/12 iommu/vt-d: Retrieve IOMMU perfmon capability information

In reply to Lu Baolu

From: Kan Liang <[email protected]>

The performance monitoring infrastructure, perfmon, is to support collection of information about key events occurring during operation of the remapping hardware, to aid performance tuning and debug. Each remapping hardware unit has capability registers that indicate support for performance monitoring features and enumerate the capabilities.

Add alloc_iommu_pmu() to retrieve IOMMU perfmon capability information for each iommu unit. The information is stored in the iommu->pmu data structure. Capability registers are read-only, so it's safe to prefetch and store them in the pmu structure. This could avoid unnecessary VMEXIT when this code is running in the virtualization environment.

Add free_iommu_pmu() to free the saved capability information when freeing the iommu unit.

Add a kernel config option for the IOMMU perfmon feature. Unless a user explicitly uses the perf tool to monitor the IOMMU perfmon event, there isn't any impact for the existing IOMMU. Enable it by default.

---
 drivers/iommu/intel/iommu.h   |  43 ++++++++-
 drivers/iommu/intel/perfmon.h |  40 ++++++++
 drivers/iommu/intel/dmar.c    |   7 ++
 drivers/iommu/intel/perfmon.c | 172 ++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/Kconfig   |  11 +++
 drivers/iommu/intel/Makefile  |   1 +
 6 files changed, 273 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/intel/perfmon.h
 create mode 100644 drivers/iommu/intel/perfmon.c
drivers/iommu/intel/iommu.h +42 -1
index f0222ad38757..f03d4b6bf49a 100644
@@ -125,6 +125,11 @@
 #define DMAR_MTRR_PHYSMASK8_REG 0x208
 #define DMAR_MTRR_PHYSBASE9_REG 0x210
 #define DMAR_MTRR_PHYSMASK9_REG 0x218
+#define DMAR_PERFCAP_REG	0x300
+#define DMAR_PERFCFGOFF_REG	0x310
+#define DMAR_PERFOVFOFF_REG	0x318
+#define DMAR_PERFCNTROFF_REG	0x31c
+#define DMAR_PERFEVNTCAP_REG	0x380
 #define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
 #define DMAR_VCMD_REG		0xe00 /* Virtual command register */
 #define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
@@ -148,6 +153,7 @@
  */
 #define cap_esrtps(c)		(((c) >> 63) & 1)
 #define cap_esirtps(c)		(((c) >> 62) & 1)
+#define cap_ecmds(c)		(((c) >> 61) & 1)
 #define cap_fl5lp_support(c)	(((c) >> 60) & 1)
 #define cap_pi_support(c)	(((c) >> 59) & 1)
 #define cap_fl1gp_support(c)	(((c) >> 56) & 1)
@@ -179,7 +185,8 @@
  * Extended Capability Register
  */
 
-#define	ecap_rps(e)		(((e) >> 49) & 0x1)
+#define ecap_pms(e)		(((e) >> 51) & 0x1)
+#define ecap_rps(e)		(((e) >> 49) & 0x1)
 #define ecap_smpwc(e)		(((e) >> 48) & 0x1)
 #define ecap_flts(e)		(((e) >> 47) & 0x1)
 #define ecap_slts(e)		(((e) >> 46) & 0x1)
@@ -210,6 +217,22 @@
 #define ecap_max_handle_mask(e) (((e) >> 20) & 0xf)
 #define ecap_sc_support(e)	(((e) >> 7) & 0x1) /* Snooping Control */
 
+/*
+ * Decoding Perf Capability Register
+ */
+#define pcap_num_cntr(p)	((p) & 0xffff)
+#define pcap_cntr_width(p)	(((p) >> 16) & 0x7f)
+#define pcap_num_event_group(p)	(((p) >> 24) & 0x1f)
+#define pcap_filters_mask(p)	(((p) >> 32) & 0x1f)
+#define pcap_interrupt(p)	(((p) >> 50) & 0x1)
+/* The counter stride is calculated as 2 ^ (x+10) bytes */
+#define pcap_cntr_stride(p)	(1ULL << ((((p) >> 52) & 0x7) + 10))
+
+/*
+ * Decoding Perf Event Capability Register
+ */
+#define pecap_es(p)		((p) & 0xfffffff)
+
 /* Virtual command interface capability */
 #define vccap_pasid(v)		(((v) & DMA_VCS_PAS)) /* PASID allocation */
 
@@ -559,6 +582,22 @@ struct dmar_domain {
 					   iommu core */
 };
 
+struct iommu_pmu {
+	struct intel_iommu	*iommu;
+	u32			num_cntr;	/* Number of counters */
+	u32			num_eg;		/* Number of event group */
+	u32			cntr_width;	/* Counter width */
+	u32			cntr_stride;	/* Counter Stride */
+	u32			filter;		/* Bitmask of filter support */
+	void __iomem		*base;		/* the PerfMon base address */
+	void __iomem		*cfg_reg;	/* counter configuration base address */
+	void __iomem		*cntr_reg;	/* counter 0 address*/
+	void __iomem		*overflow;	/* overflow status register */
+
+	u64			*evcap;		/* Indicates all supported events */
+	u32			**cntr_evcap;	/* Supported events of each counter. */
+};
+
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64 		reg_phys; /* physical address of hw register set */
@@ -605,6 +644,8 @@ struct intel_iommu {
 
 	struct dmar_drhd_unit *drhd;
 	void *perf_statistic;
+
+	struct iommu_pmu *pmu;
 };
 
 /* PCI domain-device relationship */
drivers/iommu/intel/perfmon.h new file +40 -0
new file mode 100644
index 000000000000..4b0d9c1fea6f
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * PERFCFGOFF_REG, PERFFRZOFF_REG
+ * PERFOVFOFF_REG, PERFCNTROFF_REG
+ */
+#define IOMMU_PMU_NUM_OFF_REGS			4
+#define IOMMU_PMU_OFF_REGS_STEP			4
+
+#define IOMMU_PMU_CFG_OFFSET			0x100
+#define IOMMU_PMU_CFG_CNTRCAP_OFFSET		0x80
+#define IOMMU_PMU_CFG_CNTREVCAP_OFFSET		0x84
+#define IOMMU_PMU_CFG_SIZE			0x8
+#define IOMMU_PMU_CFG_FILTERS_OFFSET		0x4
+
+#define IOMMU_PMU_CAP_REGS_STEP			8
+
+#define iommu_cntrcap_pcc(p)			((p) & 0x1)
+#define iommu_cntrcap_cw(p)			(((p) >> 8) & 0xff)
+#define iommu_cntrcap_ios(p)			(((p) >> 16) & 0x1)
+#define iommu_cntrcap_egcnt(p)			(((p) >> 28) & 0xf)
+
+#define iommu_event_select(p)			((p) & 0xfffffff)
+#define iommu_event_group(p)			(((p) >> 28) & 0xf)
+
+#ifdef CONFIG_INTEL_IOMMU_PERF_EVENTS
+int alloc_iommu_pmu(struct intel_iommu *iommu);
+void free_iommu_pmu(struct intel_iommu *iommu);
+#else
+static inline int
+alloc_iommu_pmu(struct intel_iommu *iommu)
+{
+	return 0;
+}
+
+static inline void
+free_iommu_pmu(struct intel_iommu *iommu)
+{
+}
+#endif /* CONFIG_INTEL_IOMMU_PERF_EVENTS */
drivers/iommu/intel/dmar.c +7 -0
index 3a40fef1ec1b..7a03cadb13ff 100644
@@ -34,6 +34,7 @@
 #include "../irq_remapping.h"
 #include "perf.h"
 #include "trace.h"
+#include "perfmon.h"
 
 typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
 struct dmar_res_callback {
@@ -1106,6 +1107,9 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	if (sts & DMA_GSTS_QIES)
 		iommu->gcmd |= DMA_GCMD_QIE;
 
+	if (alloc_iommu_pmu(iommu))
+		pr_debug("Cannot alloc PMU for iommu (seq_id = %d)\n", iommu->seq_id);
+
 	raw_spin_lock_init(&iommu->register_lock);
 
 	/*
@@ -1140,6 +1144,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 err_sysfs:
 	iommu_device_sysfs_remove(&iommu->iommu);
 err_unmap:
+	free_iommu_pmu(iommu);
 	unmap_iommu(iommu);
 error_free_seq_id:
 	ida_free(&dmar_seq_ids, iommu->seq_id);
@@ -1155,6 +1160,8 @@ static void free_iommu(struct intel_iommu *iommu)
 		iommu_device_sysfs_remove(&iommu->iommu);
 	}
 
+	free_iommu_pmu(iommu);
+
 	if (iommu->irq) {
 		if (iommu->pr_irq) {
 			free_irq(iommu->pr_irq, iommu);
drivers/iommu/intel/perfmon.c new file +172 -0

172 lines not on this page · raw message

drivers/iommu/intel/Kconfig +11 -0
index b7dff5092fd2..12e1e90fdae1 100644
@@ -96,4 +96,15 @@ config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
 	  passing intel_iommu=sm_on to the kernel. If not sure, please use
 	  the default value.
 
+config INTEL_IOMMU_PERF_EVENTS
+	def_bool y
+	bool "Intel IOMMU performance events"
+	depends on INTEL_IOMMU && PERF_EVENTS
+	help
+	  Selecting this option will enable the performance monitoring
+	  infrastructure in the Intel IOMMU. It collects information about
+	  key events occurring during operation of the remapping hardware,
+	  to aid performance tuning and debug. These are available on modern
+	  processors which support Intel VT-d 4.0 and later.
+
 endif # INTEL_IOMMU
drivers/iommu/intel/Makefile +1 -0
index fa0dae16441c..7af3b8a4f2a0 100644
@@ -6,3 +6,4 @@ obj-$(CONFIG_DMAR_PERF) += perf.o
 obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += debugfs.o
 obj-$(CONFIG_INTEL_IOMMU_SVM) += svm.o
 obj-$(CONFIG_IRQ_REMAP) += irq_remapping.o
+obj-$(CONFIG_INTEL_IOMMU_PERF_EVENTS) += perfmon.o
Signature · 1 line
2.34.1
author maintainer
#8 lore raw

PATCH 8/12 iommu/vt-d: Support Enhanced Command Interface

In reply to Lu Baolu

From: Kan Liang <[email protected]>

The Enhanced Command Register is to submit command and operand of enhanced commands to DMA Remapping hardware. It can supports up to 256 enhanced commands.

There is a HW register to indicate the availability of all 256 enhanced commands. Each bit stands for each command. But there isn't an existing interface to read/write all 256 bits. Introduce the u64 ecmdcap[4] to store the existence of each enhanced command. Read 4 times to get all of them in map_iommu().

Add a helper to facilitate an enhanced command launch. Make sure hardware complete the command. Also add a helper to facilitate the check of PMU essentials. These helpers will be used later.

---
 drivers/iommu/intel/iommu.h | 33 ++++++++++++++++++++++
 drivers/iommu/intel/dmar.c  | 10 +++++++
 drivers/iommu/intel/iommu.c | 56 +++++++++++++++++++++++++++++++++++++
 3 files changed, 99 insertions(+)
drivers/iommu/intel/iommu.h +33 -0
index f03d4b6bf49a..f918e83bf91c 100644
@@ -130,6 +130,10 @@
 #define DMAR_PERFOVFOFF_REG	0x318
 #define DMAR_PERFCNTROFF_REG	0x31c
 #define DMAR_PERFEVNTCAP_REG	0x380
+#define DMAR_ECMD_REG		0x400
+#define DMAR_ECEO_REG		0x408
+#define DMAR_ECRSP_REG		0x410
+#define DMAR_ECCAP_REG		0x430
 #define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
 #define DMAR_VCMD_REG		0xe00 /* Virtual command register */
 #define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
@@ -304,6 +308,26 @@
 #define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16)
 #define DMA_CCMD_DID(d) ((u64)((d) & 0xffff))
 
+/* ECMD_REG */
+#define DMA_MAX_NUM_ECMD		256
+#define DMA_MAX_NUM_ECMDCAP		(DMA_MAX_NUM_ECMD / 64)
+#define DMA_ECMD_REG_STEP		8
+#define DMA_ECMD_ENABLE			0xf0
+#define DMA_ECMD_DISABLE		0xf1
+#define DMA_ECMD_FREEZE			0xf4
+#define DMA_ECMD_UNFREEZE		0xf5
+#define DMA_ECMD_OA_SHIFT		16
+#define DMA_ECMD_ECRSP_IP		0x1
+#define DMA_ECMD_ECCAP3			3
+#define DMA_ECMD_ECCAP3_ECNTS		BIT_ULL(48)
+#define DMA_ECMD_ECCAP3_DCNTS		BIT_ULL(49)
+#define DMA_ECMD_ECCAP3_FCNTS		BIT_ULL(52)
+#define DMA_ECMD_ECCAP3_UFCNTS		BIT_ULL(53)
+#define DMA_ECMD_ECCAP3_ESSENTIAL	(DMA_ECMD_ECCAP3_ECNTS |	\
+					 DMA_ECMD_ECCAP3_DCNTS |	\
+					 DMA_ECMD_ECCAP3_FCNTS |	\
+					 DMA_ECMD_ECCAP3_UFCNTS)
+
 /* FECTL_REG */
 #define DMA_FECTL_IM (((u32)1) << 31)
 
@@ -605,6 +629,7 @@ struct intel_iommu {
 	u64		cap;
 	u64		ecap;
 	u64		vccap;
+	u64		ecmdcap[DMA_MAX_NUM_ECMDCAP];
 	u32		gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
 	raw_spinlock_t	register_lock; /* protect register handling */
 	int		seq_id;	/* sequence id of the iommu */
@@ -840,6 +865,14 @@ extern const struct iommu_ops intel_iommu_ops;
 extern int intel_iommu_sm;
 extern int iommu_calculate_agaw(struct intel_iommu *iommu);
 extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
+int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob);
+
+static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu)
+{
+	return (iommu->ecmdcap[DMA_ECMD_ECCAP3] & DMA_ECMD_ECCAP3_ESSENTIAL) ==
+		DMA_ECMD_ECCAP3_ESSENTIAL;
+}
+
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
 #else
drivers/iommu/intel/dmar.c +10 -0
index 7a03cadb13ff..0e429bab436f 100644
@@ -1017,6 +1017,16 @@ static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd)
 			goto release;
 		}
 	}
+
+	if (cap_ecmds(iommu->cap)) {
+		int i;
+
+		for (i = 0; i < DMA_MAX_NUM_ECMDCAP; i++) {
+			iommu->ecmdcap[i] = dmar_readq(iommu->reg + DMAR_ECCAP_REG +
+						       i * DMA_ECMD_REG_STEP);
+		}
+	}
+
 	err = 0;
 	goto out;
 
drivers/iommu/intel/iommu.c +56 -0

59 lines not on this page · raw message

Signature · 1 line
2.34.1
author maintainer
#9 lore raw

PATCH 9/12 iommu/vt-d: Add IOMMU perfmon support

In reply to Lu Baolu

From: Kan Liang <[email protected]>

Implement the IOMMU performance monitor capability, which supports the collection of information about key events occurring during operation of the remapping hardware, to aid performance tuning and debug.

The IOMMU perfmon support is implemented as part of the IOMMU driver and interfaces with the Linux perf subsystem.

The IOMMU PMU has the following unique features compared with the other PMUs.
- Support counting. Not support sampling.
- Does not support per-thread counting. The scope is system-wide.
- Support per-counter capability register. The event constraints can be enumerated.
- The available event and event group can also be enumerated.
- Extra Enhanced Commands are introduced to control the counters.

Add a new variable, struct iommu_pmu *pmu, to in the struct intel_iommu to track the PMU related information.

Add iommu_pmu_register() and iommu_pmu_unregister() to register and unregister a IOMMU PMU. The register function setup the IOMMU PMU ops and invoke the standard perf_pmu_register() interface to register a PMU in the perf subsystem. This patch only exposes the functions. The following patch will enable them in the IOMMU driver.

The IOMMU PMUs can be found under /sys/bus/event_source/devices/dmar*

The available filters and event format can be found at the format folder

 $ ls /sys/bus/event_source/devices/dmar1/format/
 event  event_group  filter_ats  filter_ats_en  filter_page_table
 filter_page_table_en

The supported events can be found at the events folder

 $ ls /sys/bus/event_source/devices/dmar1/events/
 ats_blocked        fs_nonleaf_hit           int_cache_hit_posted
 iommu_mem_blocked  iotlb_hit        pasid_cache_lookup  ss_nonleaf_hit
 ctxt_cache_hit     fs_nonleaf_lookup        int_cache_lookup
 iommu_mrds         iotlb_lookup     pg_req_posted    ss_nonleaf_lookup
 ctxt_cache_lookup  int_cache_hit_nonposted  iommu_clocks
 iommu_requests     pasid_cache_hit  pw_occupancy

The command below illustrates filter usage with a simple example.

 $ perf stat -e dmar1/iommu_requests,filter_ats_en=0x1,filter_ats=0x1/
   -a sleep 1

Performance counter stats for 'system wide':

368,947 dmar1/iommu_requests,filter_ats_en=0x1,filter_ats=0x1/

1.002592074 seconds time elapsed

---
 drivers/iommu/intel/iommu.h                   |  15 +
 drivers/iommu/intel/perfmon.h                 |  24 +
 drivers/iommu/intel/perfmon.c                 | 526 ++++++++++++++++++
 .../sysfs-bus-event_source-devices-iommu      |  29 +
 4 files changed, 594 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu
drivers/iommu/intel/iommu.h +15 -0
index f918e83bf91c..d56b3c386366 100644
@@ -22,6 +22,7 @@
 #include <linux/ioasid.h>
 #include <linux/bitfield.h>
 #include <linux/xarray.h>
+#include <linux/perf_event.h>
 
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
@@ -606,6 +607,16 @@ struct dmar_domain {
 					   iommu core */
 };
 
+/*
+ * In theory, the VT-d 4.0 spec can support up to 2 ^ 16 counters.
+ * But in practice, there are only 14 counters for the existing
+ * platform. Setting the max number of counters to 64 should be good
+ * enough for a long time. Also, supporting more than 64 counters
+ * requires more extras, e.g., extra freeze and overflow registers,
+ * which is not necessary for now.
+ */
+#define IOMMU_PMU_IDX_MAX		64
+
 struct iommu_pmu {
 	struct intel_iommu	*iommu;
 	u32			num_cntr;	/* Number of counters */
@@ -620,6 +631,10 @@ struct iommu_pmu {
 
 	u64			*evcap;		/* Indicates all supported events */
 	u32			**cntr_evcap;	/* Supported events of each counter. */
+
+	struct pmu		pmu;
+	DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX);
+	struct perf_event	*event_list[IOMMU_PMU_IDX_MAX];
 };
 
 struct intel_iommu {
drivers/iommu/intel/perfmon.h +24 -0
index 4b0d9c1fea6f..58606af9a2b9 100644
@@ -7,6 +7,14 @@
 #define IOMMU_PMU_NUM_OFF_REGS			4
 #define IOMMU_PMU_OFF_REGS_STEP			4
 
+#define IOMMU_PMU_FILTER_REQUESTER_ID		0x01
+#define IOMMU_PMU_FILTER_DOMAIN			0x02
+#define IOMMU_PMU_FILTER_PASID			0x04
+#define IOMMU_PMU_FILTER_ATS			0x08
+#define IOMMU_PMU_FILTER_PAGE_TABLE		0x10
+
+#define IOMMU_PMU_FILTER_EN			BIT(31)
+
 #define IOMMU_PMU_CFG_OFFSET			0x100
 #define IOMMU_PMU_CFG_CNTRCAP_OFFSET		0x80
 #define IOMMU_PMU_CFG_CNTREVCAP_OFFSET		0x84
@@ -20,12 +28,18 @@
 #define iommu_cntrcap_ios(p)			(((p) >> 16) & 0x1)
 #define iommu_cntrcap_egcnt(p)			(((p) >> 28) & 0xf)
 
+#define IOMMU_EVENT_CFG_EGI_SHIFT		8
+#define IOMMU_EVENT_CFG_ES_SHIFT		32
+#define IOMMU_EVENT_CFG_INT			BIT_ULL(1)
+
 #define iommu_event_select(p)			((p) & 0xfffffff)
 #define iommu_event_group(p)			(((p) >> 28) & 0xf)
 
 #ifdef CONFIG_INTEL_IOMMU_PERF_EVENTS
 int alloc_iommu_pmu(struct intel_iommu *iommu);
 void free_iommu_pmu(struct intel_iommu *iommu);
+void iommu_pmu_register(struct intel_iommu *iommu);
+void iommu_pmu_unregister(struct intel_iommu *iommu);
 #else
 static inline int
 alloc_iommu_pmu(struct intel_iommu *iommu)
@@ -37,4 +51,14 @@ static inline void
 free_iommu_pmu(struct intel_iommu *iommu)
 {
 }
+
+static inline void
+iommu_pmu_register(struct intel_iommu *iommu)
+{
+}
+
+static inline void
+iommu_pmu_unregister(struct intel_iommu *iommu)
+{
+}
 #endif /* CONFIG_INTEL_IOMMU_PERF_EVENTS */
drivers/iommu/intel/perfmon.c +526 -0

546 lines not on this page · raw message

Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu new file +29 -0
new file mode 100644
index 000000000000..988210a0e8ce
@@ -0,0 +1,29 @@
+What:		/sys/bus/event_source/devices/dmar*/format
+Date:		Jan 2023
+KernelVersion:  6.3
+Contact:	Kan Liang <[email protected]>
+Description:	Read-only.  Attribute group to describe the magic bits
+		that go into perf_event_attr.config,
+		perf_event_attr.config1 or perf_event_attr.config2 for
+		the IOMMU pmu.  (See also
+		ABI/testing/sysfs-bus-event_source-devices-format).
+
+		Each attribute in this group defines a bit range in
+		perf_event_attr.config, perf_event_attr.config1,
+		or perf_event_attr.config2. All supported attributes
+		are listed below (See the VT-d Spec 4.0 for possible
+		attribute values)::
+
+		    event		= "config:0-27"   - event ID
+		    event_group		= "config:28-31"  - event group ID
+
+		    filter_requester_en	= "config1:0"     - Enable Requester ID filter
+		    filter_domain_en	= "config1:1"     - Enable Domain ID filter
+		    filter_pasid_en	= "config1:2"     - Enable PASID filter
+		    filter_ats_en	= "config1:3"     - Enable Address Type filter
+		    filter_page_table_en= "config1:4"     - Enable Page Table Level filter
+		    filter_requester_id	= "config1:16-31" - Requester ID filter
+		    filter_domain	= "config1:32-47" - Domain ID filter
+		    filter_pasid	= "config2:0-21"  - PASID filter
+		    filter_ats		= "config2:24-28" - Address Type filter
+		    filter_page_table	= "config2:32-36" - Page Table Level filter
Signature · 1 line
2.34.1
author maintainer
#10 lore raw

PATCH 10/12 iommu/vt-d: Support cpumask for IOMMU perfmon

In reply to Lu Baolu

From: Kan Liang <[email protected]>

The perf subsystem assumes that all counters are by default per-CPU. So the user space tool reads a counter from each CPU. However, the IOMMU counters are system-wide and can be read from any CPU. Here we use a CPU mask to restrict counting to one CPU to handle the issue. (with CPU hotplug notifier to choose a different CPU if the chosen one is taken off-line).

The CPU is exposed to /sys/bus/event_source/devices/dmar*/cpumask for the user space perf tool.

---
 include/linux/cpuhotplug.h                    |   1 +
 drivers/iommu/intel/perfmon.c                 | 113 ++++++++++++++++--
 .../sysfs-bus-event_source-devices-iommu      |   8 ++
 3 files changed, 114 insertions(+), 8 deletions(-)
include/linux/cpuhotplug.h +1 -0
index 6c6859bfc454..f2ea348ce3b0 100644
@@ -221,6 +221,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_CQM_ONLINE,
 	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
 	CPUHP_AP_PERF_X86_IDXD_ONLINE,
+	CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
drivers/iommu/intel/perfmon.c +105 -8

134 lines not on this page · raw message

Documentation/ABI/testing/sysfs-bus-event_source-devices-iommu +8 -0
index 988210a0e8ce..d7af4919302e 100644
@@ -27,3 +27,11 @@ Description:	Read-only.  Attribute group to describe the magic bits
 		    filter_pasid	= "config2:0-21"  - PASID filter
 		    filter_ats		= "config2:24-28" - Address Type filter
 		    filter_page_table	= "config2:32-36" - Page Table Level filter
+
+What:		/sys/bus/event_source/devices/dmar*/cpumask
+Date:		Jan 2023
+KernelVersion:	6.3
+Contact:	Kan Liang <[email protected]>
+Description:	Read-only. This file always returns the CPU to which the
+		IOMMU pmu is bound for access to all IOMMU pmu performance
+		monitoring events.
Signature · 1 line
2.34.1
author maintainer
#11 lore raw

PATCH 11/12 iommu/vt-d: Add IOMMU perfmon overflow handler support

In reply to Lu Baolu

From: Kan Liang <[email protected]>

While enabled to count events and an event occurrence causes the counter value to increment and roll over to or past zero, this is termed a counter overflow. The overflow can trigger an interrupt. The IOMMU perfmon needs to handle the case properly.

New HW IRQs are allocated for each IOMMU device for perfmon. The IRQ IDs are after the SVM range.

In the overflow handler, the counter is not frozen. It's very unlikely that the same counter overflows again during the period. But it's possible that other counters overflow at the same time. Read the overflow register at the end of the handler and check whether there are more.

---
 drivers/iommu/intel/iommu.h   | 11 ++++-
 drivers/iommu/intel/dmar.c    |  2 +
 drivers/iommu/intel/perfmon.c | 82 +++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/svm.c     |  2 +-
 4 files changed, 95 insertions(+), 2 deletions(-)
drivers/iommu/intel/iommu.h +10 -1
index d56b3c386366..d7c61eb20f6f 100644
@@ -130,6 +130,8 @@
 #define DMAR_PERFCFGOFF_REG	0x310
 #define DMAR_PERFOVFOFF_REG	0x318
 #define DMAR_PERFCNTROFF_REG	0x31c
+#define DMAR_PERFINTRSTS_REG	0x324
+#define DMAR_PERFINTRCTL_REG	0x328
 #define DMAR_PERFEVNTCAP_REG	0x380
 #define DMAR_ECMD_REG		0x400
 #define DMAR_ECEO_REG		0x408
@@ -357,6 +359,9 @@
 
 #define DMA_VCS_PAS	((u64)1)
 
+/* PERFINTRSTS_REG */
+#define DMA_PERFINTRSTS_PIS	((u32)1)
+
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
 do {									\
 	cycles_t start_time = get_cycles();				\
@@ -635,8 +640,12 @@ struct iommu_pmu {
 	struct pmu		pmu;
 	DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX);
 	struct perf_event	*event_list[IOMMU_PMU_IDX_MAX];
+	unsigned char		irq_name[16];
 };
 
+#define IOMMU_IRQ_ID_OFFSET_PRQ		(DMAR_UNITS_SUPPORTED)
+#define IOMMU_IRQ_ID_OFFSET_PERF	(2 * DMAR_UNITS_SUPPORTED)
+
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64 		reg_phys; /* physical address of hw register set */
@@ -650,7 +659,7 @@ struct intel_iommu {
 	int		seq_id;	/* sequence id of the iommu */
 	int		agaw; /* agaw of this iommu */
 	int		msagaw; /* max sagaw of this iommu */
-	unsigned int 	irq, pr_irq;
+	unsigned int	irq, pr_irq, perf_irq;
 	u16		segment;     /* PCI segment# */
 	unsigned char 	name[13];    /* Device Name */
 
drivers/iommu/intel/dmar.c +2 -0
index 0e429bab436f..43db6ebe8b57 100644
@@ -1879,6 +1879,8 @@ static inline int dmar_msi_reg(struct intel_iommu *iommu, int irq)
 		return DMAR_FECTL_REG;
 	else if (iommu->pr_irq == irq)
 		return DMAR_PECTL_REG;
+	else if (iommu->perf_irq == irq)
+		return DMAR_PERFINTRCTL_REG;
 	else
 		BUG();
 }
drivers/iommu/intel/perfmon.c +82 -0

108 lines not on this page · raw message

drivers/iommu/intel/svm.c +1 -1
index e7b9bedebcc0..7367f56c3bad 100644
@@ -78,7 +78,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 	}
 	iommu->prq = page_address(pages);
 
-	irq = dmar_alloc_hwirq(DMAR_UNITS_SUPPORTED + iommu->seq_id, iommu->node, iommu);
+	irq = dmar_alloc_hwirq(IOMMU_IRQ_ID_OFFSET_PRQ + iommu->seq_id, iommu->node, iommu);
 	if (irq <= 0) {
 		pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n",
 		       iommu->name);
Signature · 1 line
2.34.1
author maintainer
#12 lore raw

PATCH 12/12 iommu/vt-d: Enable IOMMU perfmon support

In reply to Lu Baolu

From: Kan Liang <[email protected]>

Register and enable an IOMMU perfmon for each active IOMMU device.

The failure of IOMMU perfmon registration doesn't impact other functionalities of an IOMMU device.

---
 drivers/iommu/intel/dmar.c  | 3 +++
 drivers/iommu/intel/iommu.c | 3 +++
 2 files changed, 6 insertions(+)
drivers/iommu/intel/dmar.c +3 -0
index 43db6ebe8b57..6acfe879589c 100644
@@ -1144,6 +1144,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 		err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
 		if (err)
 			goto err_sysfs;
+
+		iommu_pmu_register(iommu);
 	}
 
 	drhd->iommu = iommu;
@@ -1166,6 +1168,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 static void free_iommu(struct intel_iommu *iommu)
 {
 	if (intel_iommu_enabled && !iommu->drhd->ignored) {
+		iommu_pmu_unregister(iommu);
 		iommu_device_unregister(&iommu->iommu);
 		iommu_device_sysfs_remove(&iommu->iommu);
 	}
drivers/iommu/intel/iommu.c +3 -0
index e314c30d371a..691b306fada5 100644
@@ -29,6 +29,7 @@
 #include "../iommu-sva.h"
 #include "pasid.h"
 #include "cap_audit.h"
+#include "perfmon.h"
 
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
@@ -4012,6 +4013,8 @@ int __init intel_iommu_init(void)
 				       intel_iommu_groups,
 				       "%s", iommu->name);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+
+		iommu_pmu_register(iommu);
 	}
 	up_read(&dmar_global_lock);
 
Signature · 1 line
2.34.1