iommu/amd: Initial SVA support for AMD IOMMU

This includes :
  - Add data structure to track per protection domain dev/pasid binding details
    protection_domain->dev_data_list will track attached list of
    dev_data/PASIDs.

  - Move 'to_pdomain()' to header file

  - Add iommu_sva_set_dev_pasid(). It will check whether PASID is supported
    or not. Also adds PASID to SVA protection domain list as well as to
    device GCR3 table.

  - Add iommu_ops.remove_dev_pasid support. It will unbind PASID from
    device. Also remove pasid data from protection domain device list.

  - Add IOMMU_SVA as dependency to AMD_IOMMU driver

For a given PASID, iommu_set_dev_pasid() will bind all devices to same
SVA protection domain (1 PASID : 1 SVA protection domain : N devices).
This protection domain is different from device protection domain (one
that's mapped in attach_device() path). IOMMU uses domain ID for caching,
invalidation, etc. In SVA mode it will use per-device-domain-ID. Hence in
invalidation path we retrieve domain ID from gcr3_info_table structure and
use that for invalidation.

Co-developed-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20240418103400.6229-14-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

Author: hegdevasant

drivers/iommu/amd/Kconfig

@@ -10,6 +10,7 @@ config AMD_IOMMU
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IOMMU_IO_PGTABLE
+	select IOMMU_SVA
 	select IOMMU_IOPF
 	select IOMMUFD_DRIVER if IOMMUFD
 	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE

drivers/iommu/amd/Makefile

@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o ppr.o
+obj-$(CONFIG_AMD_IOMMU) += iommu.o init.o quirks.o io_pgtable.o io_pgtable_v2.o ppr.o pasid.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o

drivers/iommu/amd/amd_iommu.h

@@ -44,6 +44,12 @@ extern int amd_iommu_guest_ir;
 extern enum io_pgtable_fmt amd_iommu_pgtable;
 extern int amd_iommu_gpt_level;
 
+/* Protection domain ops */
+int iommu_sva_set_dev_pasid(struct iommu_domain *domain,
+			    struct device *dev, ioasid_t pasid);
+void amd_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid);
+
+/* SVA/PASID */
 bool amd_iommu_pasid_supported(void);
 
 /* IOPF */
@@ -174,6 +180,11 @@ static inline struct amd_iommu *get_amd_iommu_from_dev_data(struct iommu_dev_dat
 	return iommu_get_iommu_dev(dev_data->dev, struct amd_iommu, iommu);
 }
 
+static inline struct protection_domain *to_pdomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct protection_domain, domain);
+}
+
 bool translation_pre_enabled(struct amd_iommu *iommu);
 bool amd_iommu_is_attach_deferred(struct device *dev);
 int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line);

drivers/iommu/amd/amd_iommu_types.h

@@ -8,7 +8,9 @@
 #ifndef _ASM_X86_AMD_IOMMU_TYPES_H
 #define _ASM_X86_AMD_IOMMU_TYPES_H
 
+#include <linux/iommu.h>
 #include <linux/types.h>
+#include <linux/mmu_notifier.h>
 #include <linux/mutex.h>
 #include <linux/msi.h>
 #include <linux/list.h>
@@ -511,6 +513,11 @@ extern struct kmem_cache *amd_iommu_irq_cache;
 	list_for_each_entry((iommu), &amd_iommu_list, list)
 #define for_each_iommu_safe(iommu, next) \
 	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+/* Making iterating over protection_domain->dev_data_list easier */
+#define for_each_pdom_dev_data(pdom_dev_data, pdom) \
+	list_for_each_entry(pdom_dev_data, &pdom->dev_data_list, list)
+#define for_each_pdom_dev_data_safe(pdom_dev_data, next, pdom) \
+	list_for_each_entry_safe((pdom_dev_data), (next), &pdom->dev_data_list, list)
 
 struct amd_iommu;
 struct iommu_domain;
@@ -552,6 +559,16 @@ enum protection_domain_mode {
 	PD_MODE_V2,
 };
 
+/* Track dev_data/PASID list for the protection domain */
+struct pdom_dev_data {
+	/* Points to attached device data */
+	struct iommu_dev_data *dev_data;
+	/* PASID attached to the protection domain */
+	ioasid_t pasid;
+	/* For protection_domain->dev_data_list */
+	struct list_head list;
+};
+
 /*
  * This structure contains generic data for  IOMMU protection domains
  * independent of their use.
@@ -568,6 +585,8 @@ struct protection_domain {
 	bool dirty_tracking;	/* dirty tracking is enabled in the domain */
 	unsigned dev_cnt;	/* devices assigned to this domain */
 	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
+
+	struct list_head dev_data_list; /* List of pdom_dev_data */
 };
 
 /*

drivers/iommu/amd/iommu.c

@@ -194,11 +194,6 @@ static struct amd_iommu *rlookup_amd_iommu(struct device *dev)
 	return __rlookup_amd_iommu(seg, PCI_SBDF_TO_DEVID(devid));
 }
 
-static struct protection_domain *to_pdomain(struct iommu_domain *dom)
-{
-	return container_of(dom, struct protection_domain, domain);
-}
-
 static struct iommu_dev_data *alloc_dev_data(struct amd_iommu *iommu, u16 devid)
 {
 	struct iommu_dev_data *dev_data;
@@ -2345,6 +2340,7 @@ static struct protection_domain *protection_domain_alloc(unsigned int type)
 
 	spin_lock_init(&domain->lock);
 	INIT_LIST_HEAD(&domain->dev_list);
+	INIT_LIST_HEAD(&domain->dev_data_list);
 	domain->nid = NUMA_NO_NODE;
 
 	switch (type) {
@@ -2874,6 +2870,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.def_domain_type = amd_iommu_def_domain_type,
 	.dev_enable_feat = amd_iommu_dev_enable_feature,
 	.dev_disable_feat = amd_iommu_dev_disable_feature,
+	.remove_dev_pasid = amd_iommu_remove_dev_pasid,
 	.page_response = amd_iommu_page_response,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev	= amd_iommu_attach_device,

drivers/iommu/amd/pasid.c

@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/iommu.h>
+#include <linux/mm_types.h>
+
+#include "amd_iommu.h"
+
+static inline bool is_pasid_enabled(struct iommu_dev_data *dev_data)
+{
+	if (dev_data->pasid_enabled && dev_data->max_pasids &&
+	    dev_data->gcr3_info.gcr3_tbl != NULL)
+		return true;
+
+	return false;
+}
+
+static inline bool is_pasid_valid(struct iommu_dev_data *dev_data,
+				  ioasid_t pasid)
+{
+	if (pasid > 0 && pasid < dev_data->max_pasids)
+		return true;
+
+	return false;
+}
+
+static void remove_dev_pasid(struct pdom_dev_data *pdom_dev_data)
+{
+	/* Update GCR3 table and flush IOTLB */
+	amd_iommu_clear_gcr3(pdom_dev_data->dev_data, pdom_dev_data->pasid);
+
+	list_del(&pdom_dev_data->list);
+	kfree(pdom_dev_data);
+}
+
+/* Clear PASID from device GCR3 table and remove pdom_dev_data from list */
+static void remove_pdom_dev_pasid(struct protection_domain *pdom,
+				  struct device *dev, ioasid_t pasid)
+{
+	struct pdom_dev_data *pdom_dev_data;
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
+
+	lockdep_assert_held(&pdom->lock);
+
+	for_each_pdom_dev_data(pdom_dev_data, pdom) {
+		if (pdom_dev_data->dev_data == dev_data &&
+		    pdom_dev_data->pasid == pasid) {
+			remove_dev_pasid(pdom_dev_data);
+			break;
+		}
+	}
+}
+
+int iommu_sva_set_dev_pasid(struct iommu_domain *domain,
+			    struct device *dev, ioasid_t pasid)
+{
+	struct pdom_dev_data *pdom_dev_data;
+	struct protection_domain *sva_pdom = to_pdomain(domain);
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	/* PASID zero is used for requests from the I/O device without PASID */
+	if (!is_pasid_valid(dev_data, pasid))
+		return ret;
+
+	/* Make sure PASID is enabled */
+	if (!is_pasid_enabled(dev_data))
+		return ret;
+
+	/* Add PASID to protection domain pasid list */
+	pdom_dev_data = kzalloc(sizeof(*pdom_dev_data), GFP_KERNEL);
+	if (pdom_dev_data == NULL)
+		return ret;
+
+	pdom_dev_data->pasid = pasid;
+	pdom_dev_data->dev_data = dev_data;
+
+	spin_lock_irqsave(&sva_pdom->lock, flags);
+
+	/* Setup GCR3 table */
+	ret = amd_iommu_set_gcr3(dev_data, pasid,
+				 iommu_virt_to_phys(domain->mm->pgd));
+	if (ret) {
+		kfree(pdom_dev_data);
+		goto out_unlock;
+	}
+
+	list_add(&pdom_dev_data->list, &sva_pdom->dev_data_list);
+
+out_unlock:
+	spin_unlock_irqrestore(&sva_pdom->lock, flags);
+	return ret;
+}
+
+void amd_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
+{
+	struct protection_domain *sva_pdom;
+	struct iommu_domain *domain;
+	unsigned long flags;
+
+	if (!is_pasid_valid(dev_iommu_priv_get(dev), pasid))
+		return;
+
+	/* Get protection domain */
+	domain = iommu_get_domain_for_dev_pasid(dev, pasid, IOMMU_DOMAIN_SVA);
+	if (!domain)
+		return;
+	sva_pdom = to_pdomain(domain);
+
+	spin_lock_irqsave(&sva_pdom->lock, flags);
+
+	/* Remove PASID from dev_data_list */
+	remove_pdom_dev_pasid(sva_pdom, dev, pasid);
+
+	spin_unlock_irqrestore(&sva_pdom->lock, flags);
+}