Resguardo inicial

linux-7.2.3/drivers/iommu/amd/Kconfig

@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# AMD IOMMU support
+config AMD_IOMMU
+	bool "AMD IOMMU support"
+	select SWIOTLB
+	select PCI_MSI
+	select PCI_ATS
+	select PCI_PRI
+	select PCI_PASID
+	select IRQ_MSI_LIB
+	select MMU_NOTIFIER
+	select IOMMU_API
+	select IOMMU_IOVA
+	select IOMMU_SVA
+	select IOMMU_IOPF
+	select IOMMUFD_DRIVER if IOMMUFD
+	select GENERIC_PT
+	select IOMMU_PT
+	select IOMMU_PT_AMDV1
+	select IOMMU_PT_X86_64
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
+	help
+	  With this option you can enable support for AMD IOMMU hardware in
+	  your system. An IOMMU is a hardware component which provides
+	  remapping of DMA memory accesses from devices. With an AMD IOMMU you
+	  can isolate the DMA memory of different devices and protect the
+	  system from misbehaving device drivers or hardware.
+
+	  You can find out if your system has an AMD IOMMU if you look into
+	  your BIOS for an option to enable it or if you have an IVRS ACPI
+	  table.
+
+config AMD_IOMMU_IOMMUFD
+	bool "Enable IOMMUFD features for AMD IOMMU (EXPERIMENTAL)"
+	depends on IOMMUFD
+	depends on AMD_IOMMU
+	help
+	  Support for IOMMUFD features intended to support virtual machines
+	  with accelerated virtual IOMMUs.
+
+	  Say Y here if you are doing development and testing on this feature.
+
+config AMD_IOMMU_DEBUGFS
+	bool "Enable AMD IOMMU internals in DebugFS"
+	depends on AMD_IOMMU && IOMMU_DEBUGFS
+	help
+	  !!!WARNING!!!  !!!WARNING!!!  !!!WARNING!!!  !!!WARNING!!!
+
+	  DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!!
+	  Exposes AMD IOMMU device internals in DebugFS.
+
+	  This option is -NOT- intended for production environments, and should
+	  not generally be enabled.

linux-7.2.3/drivers/iommu/amd/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y += iommu.o init.o quirks.o ppr.o pasid.o
+obj-$(CONFIG_AMD_IOMMU_IOMMUFD) += iommufd.o nested.o
+obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += debugfs.o

linux-7.2.3/drivers/iommu/amd/amd_iommu.h

@@ -0,0 +1,228 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#ifndef AMD_IOMMU_H
+#define AMD_IOMMU_H
+
+#include <linux/iommu.h>
+
+#include "amd_iommu_types.h"
+
+extern int amd_iommu_evtlog_size;
+extern int amd_iommu_pprlog_size;
+
+irqreturn_t amd_iommu_int_thread(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_galog(int irq, void *data);
+void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type,
+			   u8 cntrl_intr, u8 cntrl_log,
+			   u32 status_run_mask, u32 status_overflow_mask);
+void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
+void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu);
+void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
+void iommu_feature_enable(struct amd_iommu *iommu, u8 bit);
+void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
+				  gfp_t gfp, size_t size);
+
+#ifdef CONFIG_AMD_IOMMU_DEBUGFS
+void amd_iommu_debugfs_setup(void);
+#else
+static inline void amd_iommu_debugfs_setup(void) {}
+#endif
+
+/* Needed for interrupt remapping */
+int amd_iommu_prepare(void);
+int amd_iommu_enable(void);
+void amd_iommu_disable(void);
+int amd_iommu_reenable(int mode);
+int amd_iommu_enable_faulting(unsigned int cpu);
+extern int amd_iommu_guest_ir;
+extern enum protection_domain_mode amd_iommu_pgtable;
+extern int amd_iommu_gpt_level;
+extern u8 amd_iommu_hpt_vasize;
+extern unsigned long amd_iommu_pgsize_bitmap;
+extern bool amd_iommu_hatdis;
+
+/* Protection domain ops */
+void amd_iommu_init_identity_domain(void);
+struct protection_domain *protection_domain_alloc(void);
+struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev,
+						struct mm_struct *mm);
+void amd_iommu_domain_free(struct iommu_domain *dom);
+int iommu_sva_set_dev_pasid(struct iommu_domain *domain,
+			    struct device *dev, ioasid_t pasid,
+			    struct iommu_domain *old);
+void amd_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid,
+				struct iommu_domain *domain);
+
+/* SVA/PASID */
+bool amd_iommu_pasid_supported(void);
+
+/* IOPF */
+int amd_iommu_iopf_init(struct amd_iommu *iommu);
+void amd_iommu_iopf_uninit(struct amd_iommu *iommu);
+void amd_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			     struct iommu_page_response *resp);
+int amd_iommu_iopf_add_device(struct amd_iommu *iommu,
+			      struct iommu_dev_data *dev_data);
+void amd_iommu_iopf_remove_device(struct amd_iommu *iommu,
+				  struct iommu_dev_data *dev_data);
+
+/* GCR3 setup */
+int amd_iommu_set_gcr3(struct iommu_dev_data *dev_data,
+		       ioasid_t pasid, unsigned long gcr3);
+int amd_iommu_clear_gcr3(struct iommu_dev_data *dev_data, ioasid_t pasid);
+
+/* PPR */
+int __init amd_iommu_alloc_ppr_log(struct amd_iommu *iommu);
+void __init amd_iommu_free_ppr_log(struct amd_iommu *iommu);
+void amd_iommu_enable_ppr_log(struct amd_iommu *iommu);
+void amd_iommu_poll_ppr_log(struct amd_iommu *iommu);
+int amd_iommu_complete_ppr(struct device *dev, u32 pasid, int status, int tag);
+
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, u64 last, u32 flags);
+void amd_iommu_dev_flush_pasid_pages(struct iommu_dev_data *dev_data,
+				     ioasid_t pasid, u64 address, u64 last);
+
+#ifdef CONFIG_IRQ_REMAP
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
+static inline bool is_rd890_iommu(struct pci_dev *pdev)
+{
+	return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
+	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
+}
+
+static inline bool check_feature(u64 mask)
+{
+	return (amd_iommu_efr & mask);
+}
+
+static inline bool check_feature2(u64 mask)
+{
+	return (amd_iommu_efr2 & mask);
+}
+
+static inline bool amd_iommu_v2_pgtbl_supported(void)
+{
+	return (check_feature(FEATURE_GIOSUP) && check_feature(FEATURE_GT));
+}
+
+static inline bool amd_iommu_gt_ppr_supported(void)
+{
+	return (amd_iommu_v2_pgtbl_supported() &&
+		check_feature(FEATURE_PPR) &&
+		check_feature(FEATURE_EPHSUP));
+}
+
+static inline u64 iommu_virt_to_phys(void *vaddr)
+{
+	return (u64)__sme_set(virt_to_phys(vaddr));
+}
+
+static inline void *iommu_phys_to_virt(unsigned long paddr)
+{
+	return phys_to_virt(__sme_clr(paddr));
+}
+
+static inline int get_pci_sbdf_id(struct pci_dev *pdev)
+{
+	int seg = pci_domain_nr(pdev->bus);
+	u16 devid = pci_dev_id(pdev);
+
+	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
+}
+
+bool amd_iommu_ht_range_ignore(void);
+
+/*
+ * This must be called after device probe completes. During probe
+ * use rlookup_amd_iommu() get the iommu.
+ */
+static inline struct amd_iommu *get_amd_iommu_from_dev(struct device *dev)
+{
+	return iommu_get_iommu_dev(dev, struct amd_iommu, iommu);
+}
+
+/* This must be called after device probe completes. */
+static inline struct amd_iommu *get_amd_iommu_from_dev_data(struct iommu_dev_data *dev_data)
+{
+	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);
+int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line);
+
+int amd_iommu_pdom_id_alloc(void);
+int amd_iommu_pdom_id_reserve(u16 id, gfp_t gfp);
+void amd_iommu_pdom_id_free(int id);
+void amd_iommu_pdom_id_destroy(void);
+
+#ifdef CONFIG_DMI
+void amd_iommu_apply_ivrs_quirks(void);
+#else
+static inline void amd_iommu_apply_ivrs_quirks(void) { }
+#endif
+struct dev_table_entry *amd_iommu_get_ivhd_dte_flags(u16 segid, u16 devid);
+
+void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+				  u64 *root, int mode);
+struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
+struct iommu_dev_data *search_dev_data(struct amd_iommu *iommu, u16 devid);
+
+void amd_iommu_set_dte_v1(struct iommu_dev_data *dev_data,
+			  struct protection_domain *domain, u16 domid,
+			  struct pt_iommu_amdv1_hw_info *pt_info,
+			  struct dev_table_entry *new);
+void amd_iommu_update_dte(struct amd_iommu *iommu,
+			  struct iommu_dev_data *dev_data,
+			  struct dev_table_entry *new);
+
+static inline void
+amd_iommu_make_clear_dte(struct iommu_dev_data *dev_data, struct dev_table_entry *new)
+{
+	struct dev_table_entry *initial_dte;
+	struct amd_iommu *iommu = get_amd_iommu_from_dev(dev_data->dev);
+
+	/* All existing DTE must have V bit set */
+	new->data128[0] = DTE_FLAG_V;
+	new->data128[1] = 0;
+
+	/*
+	 * Restore cached persistent DTE bits, which can be set by information
+	 * in IVRS table. See set_dev_entry_from_acpi().
+	 */
+	initial_dte = amd_iommu_get_ivhd_dte_flags(iommu->pci_seg->id, dev_data->devid);
+	if (initial_dte) {
+		new->data128[0] |= initial_dte->data128[0];
+		new->data128[1] |= initial_dte->data128[1];
+	}
+}
+
+/* NESTED */
+struct iommu_domain *
+amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags,
+			      const struct iommu_user_data *user_data);
+#endif /* AMD_IOMMU_H */

linux-7.2.3/drivers/iommu/amd/debugfs.c

@@ -0,0 +1,392 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD IOMMU driver
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ *
+ * Author: Gary R Hook <gary.hook@amd.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/pci.h>
+
+#include "amd_iommu.h"
+#include "../irq_remapping.h"
+
+static struct dentry *amd_iommu_debugfs;
+
+#define	MAX_NAME_LEN	20
+#define	OFS_IN_SZ	8
+#define	DEVID_IN_SZ	16
+
+static int sbdf = -1;
+
+static ssize_t iommu_mmio_write(struct file *filp, const char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct amd_iommu *iommu = m->private;
+	int ret, dbg_mmio_offset = iommu->dbg_mmio_offset = -1;
+
+	if (cnt > OFS_IN_SZ)
+		return -EINVAL;
+
+	ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_mmio_offset);
+	if (ret)
+		return ret;
+
+	if (dbg_mmio_offset < 0 || dbg_mmio_offset >
+			iommu->mmio_phys_end - sizeof(u64))
+		return -EINVAL;
+
+	iommu->dbg_mmio_offset = dbg_mmio_offset;
+	return cnt;
+}
+
+static int iommu_mmio_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	u64 value;
+	int dbg_mmio_offset = iommu->dbg_mmio_offset;
+
+	if (dbg_mmio_offset < 0 || dbg_mmio_offset >
+			iommu->mmio_phys_end - sizeof(u64)) {
+		seq_puts(m, "Please provide mmio register's offset\n");
+		return 0;
+	}
+
+	value = readq(iommu->mmio_base + dbg_mmio_offset);
+	seq_printf(m, "Offset:0x%x Value:0x%016llx\n", dbg_mmio_offset, value);
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(iommu_mmio);
+
+static ssize_t iommu_capability_write(struct file *filp, const char __user *ubuf,
+				      size_t cnt, loff_t *ppos)
+{
+	struct seq_file *m = filp->private_data;
+	struct amd_iommu *iommu = m->private;
+	int ret, dbg_cap_offset = iommu->dbg_cap_offset = -1;
+
+	if (cnt > OFS_IN_SZ)
+		return -EINVAL;
+
+	ret = kstrtos32_from_user(ubuf, cnt, 0, &dbg_cap_offset);
+	if (ret)
+		return ret;
+
+	/* Capability register at offset 0x14 is the last IOMMU capability register. */
+	if (dbg_cap_offset < 0 || dbg_cap_offset > 0x14)
+		return -EINVAL;
+
+	iommu->dbg_cap_offset = dbg_cap_offset;
+	return cnt;
+}
+
+static int iommu_capability_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	u32 value;
+	int err, dbg_cap_offset = iommu->dbg_cap_offset;
+
+	if (dbg_cap_offset < 0 || dbg_cap_offset > 0x14) {
+		seq_puts(m, "Please provide capability register's offset in the range [0x00 - 0x14]\n");
+		return 0;
+	}
+
+	err = pci_read_config_dword(iommu->dev, iommu->cap_ptr + dbg_cap_offset, &value);
+	if (err) {
+		seq_printf(m, "Not able to read capability register at 0x%x\n",
+			   dbg_cap_offset);
+		return 0;
+	}
+
+	seq_printf(m, "Offset:0x%x Value:0x%08x\n", dbg_cap_offset, value);
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(iommu_capability);
+
+static int iommu_cmdbuf_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	struct iommu_cmd *cmd;
+	unsigned long flag;
+	u32 head, tail;
+	int i;
+
+	raw_spin_lock_irqsave(&iommu->lock, flag);
+	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	seq_printf(m, "CMD Buffer Head Offset:%d Tail Offset:%d\n",
+		   (head >> 4) & 0x7fff, (tail >> 4) & 0x7fff);
+	for (i = 0; i < CMD_BUFFER_ENTRIES; i++) {
+		cmd = (struct iommu_cmd *)(iommu->cmd_buf + i * sizeof(*cmd));
+		seq_printf(m, "%3d: %08x %08x %08x %08x\n", i, cmd->data[0],
+			   cmd->data[1], cmd->data[2], cmd->data[3]);
+	}
+	raw_spin_unlock_irqrestore(&iommu->lock, flag);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_cmdbuf);
+
+static ssize_t devid_write(struct file *filp, const char __user *ubuf,
+			   size_t cnt, loff_t *ppos)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	int seg, bus, slot, func;
+	struct amd_iommu *iommu;
+	char *srcid_ptr;
+	u16 devid;
+	int i;
+
+	sbdf = -1;
+
+	if (cnt >= DEVID_IN_SZ)
+		return -EINVAL;
+
+	srcid_ptr = memdup_user_nul(ubuf, cnt);
+	if (IS_ERR(srcid_ptr))
+		return PTR_ERR(srcid_ptr);
+
+	i = sscanf(srcid_ptr, "%x:%x:%x.%x", &seg, &bus, &slot, &func);
+	if (i != 4) {
+		i = sscanf(srcid_ptr, "%x:%x.%x", &bus, &slot, &func);
+		if (i != 3) {
+			kfree(srcid_ptr);
+			return -EINVAL;
+		}
+		seg = 0;
+	}
+
+	devid = PCI_DEVID(bus, PCI_DEVFN(slot, func));
+
+	/* Check if user device id input is a valid input */
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		if (devid > pci_seg->last_bdf) {
+			kfree(srcid_ptr);
+			return -EINVAL;
+		}
+		iommu = pci_seg->rlookup_table[devid];
+		if (!iommu) {
+			kfree(srcid_ptr);
+			return -ENODEV;
+		}
+		break;
+	}
+
+	if (pci_seg->id != seg) {
+		kfree(srcid_ptr);
+		return -EINVAL;
+	}
+
+	sbdf = PCI_SEG_DEVID_TO_SBDF(seg, devid);
+
+	kfree(srcid_ptr);
+
+	return cnt;
+}
+
+static int devid_show(struct seq_file *m, void *unused)
+{
+	u16 devid;
+	int sbdf_shadow = sbdf;
+
+	if (sbdf_shadow >= 0) {
+		devid = PCI_SBDF_TO_DEVID(sbdf_shadow);
+		seq_printf(m, "%04x:%02x:%02x.%x\n", PCI_SBDF_TO_SEGID(sbdf_shadow),
+			   PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid));
+	} else
+		seq_puts(m, "No or Invalid input provided\n");
+
+	return 0;
+}
+DEFINE_SHOW_STORE_ATTRIBUTE(devid);
+
+static void dump_dte(struct seq_file *m, struct amd_iommu_pci_seg *pci_seg, u16 devid)
+{
+	struct dev_table_entry *dev_table;
+	struct amd_iommu *iommu;
+
+	iommu = pci_seg->rlookup_table[devid];
+	if (!iommu)
+		return;
+
+	dev_table = get_dev_table(iommu);
+	if (!dev_table) {
+		seq_puts(m, "Device table not found");
+		return;
+	}
+
+	seq_printf(m, "%-12s %16s %16s %16s %16s iommu\n", "DeviceId",
+		   "QWORD[3]", "QWORD[2]", "QWORD[1]", "QWORD[0]");
+	seq_printf(m, "%04x:%02x:%02x.%x ", pci_seg->id, PCI_BUS_NUM(devid),
+		   PCI_SLOT(devid), PCI_FUNC(devid));
+	for (int i = 3; i >= 0; --i)
+		seq_printf(m, "%016llx ", dev_table[devid].data[i]);
+	seq_printf(m, "iommu%d\n", iommu->index);
+}
+
+static int iommu_devtbl_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	u16 seg, devid;
+	int sbdf_shadow = sbdf;
+
+	if (sbdf_shadow < 0) {
+		seq_puts(m, "Enter a valid device ID to 'devid' file\n");
+		return 0;
+	}
+	seg = PCI_SBDF_TO_SEGID(sbdf_shadow);
+	devid = PCI_SBDF_TO_DEVID(sbdf_shadow);
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		dump_dte(m, pci_seg, devid);
+		break;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_devtbl);
+
+static void dump_128_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len)
+{
+	struct irte_ga *ptr, *irte;
+	int index;
+
+	for (index = 0; index < int_tab_len; index++) {
+		ptr = (struct irte_ga *)table->table;
+		irte = &ptr[index];
+
+		if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+		    !irte->lo.fields_vapic.valid)
+			continue;
+		else if (!irte->lo.fields_remap.valid)
+			continue;
+		seq_printf(m, "IRT[%04d] %016llx %016llx\n", index, irte->hi.val, irte->lo.val);
+	}
+}
+
+static void dump_32_irte(struct seq_file *m, struct irq_remap_table *table, u16 int_tab_len)
+{
+	union irte *ptr, *irte;
+	int index;
+
+	for (index = 0; index < int_tab_len; index++) {
+		ptr = (union irte *)table->table;
+		irte = &ptr[index];
+
+		if (!irte->fields.valid)
+			continue;
+		seq_printf(m, "IRT[%04d] %08x\n", index, irte->val);
+	}
+}
+
+static void dump_irte(struct seq_file *m, u16 devid, struct amd_iommu_pci_seg *pci_seg)
+{
+	struct dev_table_entry *dev_table;
+	struct irq_remap_table *table;
+	struct amd_iommu *iommu;
+	unsigned long flags;
+	u16 int_tab_len;
+
+	table = pci_seg->irq_lookup_table[devid];
+	if (!table) {
+		seq_printf(m, "IRQ lookup table not set for %04x:%02x:%02x:%x\n",
+			   pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid));
+		return;
+	}
+
+	iommu = pci_seg->rlookup_table[devid];
+	if (!iommu)
+		return;
+
+	dev_table = get_dev_table(iommu);
+	if (!dev_table) {
+		seq_puts(m, "Device table not found");
+		return;
+	}
+
+	int_tab_len = dev_table[devid].data[2] & DTE_INTTABLEN_MASK;
+	if (int_tab_len != DTE_INTTABLEN_512 && int_tab_len != DTE_INTTABLEN_2K) {
+		seq_puts(m, "The device's DTE contains an invalid IRT length value.");
+		return;
+	}
+
+	seq_printf(m, "DeviceId %04x:%02x:%02x.%x\n", pci_seg->id, PCI_BUS_NUM(devid),
+		   PCI_SLOT(devid), PCI_FUNC(devid));
+
+	raw_spin_lock_irqsave(&table->lock, flags);
+	if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+		dump_128_irte(m, table, BIT(int_tab_len >> 1));
+	else
+		dump_32_irte(m, table, BIT(int_tab_len >> 1));
+	seq_puts(m, "\n");
+	raw_spin_unlock_irqrestore(&table->lock, flags);
+}
+
+static int iommu_irqtbl_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu_pci_seg *pci_seg;
+	u16 devid, seg;
+	int sbdf_shadow = sbdf;
+
+	if (!irq_remapping_enabled) {
+		seq_puts(m, "Interrupt remapping is disabled\n");
+		return 0;
+	}
+
+	if (sbdf_shadow < 0) {
+		seq_puts(m, "Enter a valid device ID to 'devid' file\n");
+		return 0;
+	}
+
+	seg = PCI_SBDF_TO_SEGID(sbdf_shadow);
+	devid = PCI_SBDF_TO_DEVID(sbdf_shadow);
+
+	for_each_pci_segment(pci_seg) {
+		if (pci_seg->id != seg)
+			continue;
+		dump_irte(m, devid, pci_seg);
+		break;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_irqtbl);
+
+void amd_iommu_debugfs_setup(void)
+{
+	struct amd_iommu *iommu;
+	char name[MAX_NAME_LEN + 1];
+
+	amd_iommu_debugfs = debugfs_create_dir("amd", iommu_debugfs_dir);
+
+	for_each_iommu(iommu) {
+		iommu->dbg_mmio_offset = -1;
+		iommu->dbg_cap_offset = -1;
+
+		snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index);
+		iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs);
+
+		debugfs_create_file("mmio", 0644, iommu->debugfs, iommu,
+				    &iommu_mmio_fops);
+		debugfs_create_file("capability", 0644, iommu->debugfs, iommu,
+				    &iommu_capability_fops);
+		debugfs_create_file("cmdbuf", 0444, iommu->debugfs, iommu,
+				    &iommu_cmdbuf_fops);
+	}
+
+	debugfs_create_file("devid", 0644, amd_iommu_debugfs, NULL,
+			    &devid_fops);
+	debugfs_create_file("devtbl", 0444, amd_iommu_debugfs, NULL,
+			    &iommu_devtbl_fops);
+	debugfs_create_file("irqtbl", 0444, amd_iommu_debugfs, NULL,
+			    &iommu_irqtbl_fops);
+}

linux-7.2.3/drivers/iommu/amd/iommufd.c

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/iommu.h>
+
+#include "iommufd.h"
+#include "amd_iommu.h"
+#include "amd_iommu_types.h"
+
+static const struct iommufd_viommu_ops amd_viommu_ops;
+
+void *amd_iommufd_hw_info(struct device *dev, u32 *length, enum iommu_hw_info_type *type)
+{
+	struct iommu_hw_info_amd *hwinfo;
+
+	if (*type != IOMMU_HW_INFO_TYPE_DEFAULT &&
+	    *type != IOMMU_HW_INFO_TYPE_AMD)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	hwinfo = kzalloc_obj(*hwinfo);
+	if (!hwinfo)
+		return ERR_PTR(-ENOMEM);
+
+	*length = sizeof(*hwinfo);
+	*type = IOMMU_HW_INFO_TYPE_AMD;
+
+	hwinfo->efr = amd_iommu_efr;
+	hwinfo->efr2 = amd_iommu_efr2;
+
+	return hwinfo;
+}
+
+size_t amd_iommufd_get_viommu_size(struct device *dev, enum iommu_viommu_type viommu_type)
+{
+	return VIOMMU_STRUCT_SIZE(struct amd_iommu_viommu, core);
+}
+
+int amd_iommufd_viommu_init(struct iommufd_viommu *viommu, struct iommu_domain *parent,
+			    const struct iommu_user_data *user_data)
+{
+	unsigned long flags;
+	struct protection_domain *pdom = to_pdomain(parent);
+	struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core);
+
+	xa_init_flags(&aviommu->gdomid_array, XA_FLAGS_ALLOC1);
+	aviommu->parent = pdom;
+
+	viommu->ops = &amd_viommu_ops;
+
+	spin_lock_irqsave(&pdom->lock, flags);
+	list_add(&aviommu->pdom_list, &pdom->viommu_list);
+	spin_unlock_irqrestore(&pdom->lock, flags);
+
+	return 0;
+}
+
+static void amd_iommufd_viommu_destroy(struct iommufd_viommu *viommu)
+{
+	unsigned long flags;
+	struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core);
+	struct protection_domain *pdom = aviommu->parent;
+
+	spin_lock_irqsave(&pdom->lock, flags);
+	list_del(&aviommu->pdom_list);
+	spin_unlock_irqrestore(&pdom->lock, flags);
+	xa_destroy(&aviommu->gdomid_array);
+}
+
+/*
+ * See include/linux/iommufd.h
+ * struct iommufd_viommu_ops - vIOMMU specific operations
+ */
+static const struct iommufd_viommu_ops amd_viommu_ops = {
+	.destroy = amd_iommufd_viommu_destroy,
+};

linux-7.2.3/drivers/iommu/amd/iommufd.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#ifndef AMD_IOMMUFD_H
+#define AMD_IOMMUFD_H
+
+#if IS_ENABLED(CONFIG_AMD_IOMMU_IOMMUFD)
+void *amd_iommufd_hw_info(struct device *dev, u32 *length, enum iommu_hw_info_type *type);
+size_t amd_iommufd_get_viommu_size(struct device *dev, enum iommu_viommu_type viommu_type);
+int amd_iommufd_viommu_init(struct iommufd_viommu *viommu, struct iommu_domain *parent,
+			    const struct iommu_user_data *user_data);
+#else
+#define amd_iommufd_hw_info NULL
+#define amd_iommufd_viommu_init NULL
+#define amd_iommufd_get_viommu_size NULL
+#endif /* CONFIG_AMD_IOMMU_IOMMUFD */
+
+#endif /* AMD_IOMMUFD_H */

linux-7.2.3/drivers/iommu/amd/nested.c

@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#define dev_fmt(fmt)	"AMD-Vi: " fmt
+
+#include <linux/iommu.h>
+#include <linux/refcount.h>
+#include <uapi/linux/iommufd.h>
+
+#include "amd_iommu.h"
+
+static const struct iommu_domain_ops nested_domain_ops;
+
+static inline struct nested_domain *to_ndomain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct nested_domain, domain);
+}
+
+/*
+ * Validate guest DTE to make sure that configuration for host (v1)
+ * and guest (v2) page tables are valid when allocating nested domain.
+ */
+static int validate_gdte_nested(struct iommu_hwpt_amd_guest *gdte)
+{
+	u32 gpt_level = FIELD_GET(DTE_GPT_LEVEL_MASK, gdte->dte[2]);
+
+	/* Must be zero: Mode, Host-TPR */
+	if (FIELD_GET(DTE_MODE_MASK, gdte->dte[0]) != 0 ||
+	    FIELD_GET(DTE_HOST_TRP, gdte->dte[0]) != 0)
+		return -EINVAL;
+
+	/* GCR3 TRP must be non-zero if V, GV is set */
+	if (FIELD_GET(DTE_FLAG_V, gdte->dte[0]) == 1 &&
+	    FIELD_GET(DTE_FLAG_GV, gdte->dte[0]) == 1 &&
+	    FIELD_GET(DTE_GCR3_14_12, gdte->dte[0]) == 0 &&
+	    FIELD_GET(DTE_GCR3_30_15, gdte->dte[1]) == 0 &&
+	    FIELD_GET(DTE_GCR3_51_31, gdte->dte[1]) == 0)
+		return -EINVAL;
+
+	/* Valid Guest Paging Mode values are 0 and 1 */
+	if (gpt_level != GUEST_PGTABLE_4_LEVEL &&
+	    gpt_level != GUEST_PGTABLE_5_LEVEL)
+		return -EINVAL;
+
+	/* GLX = 3 is reserved */
+	if (FIELD_GET(DTE_GLX, gdte->dte[0]) == 3)
+		return -EINVAL;
+
+	/*
+	 * We need to check host capability before setting
+	 * the Guest Paging Mode
+	 */
+	if (gpt_level == GUEST_PGTABLE_5_LEVEL &&
+	    amd_iommu_gpt_level < PAGE_MODE_5_LEVEL)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void *gdom_info_load_or_alloc_locked(struct xarray *xa,
+					    unsigned long index,
+					    unsigned long *flags)
+{
+	struct guest_domain_mapping_info *elm, *res;
+
+	elm = xa_load(xa, index);
+	if (elm)
+		return elm;
+
+	xa_unlock_irqrestore(xa, *flags);
+	elm = kzalloc_obj(struct guest_domain_mapping_info);
+	xa_lock_irqsave(xa, *flags);
+	if (!elm)
+		return ERR_PTR(-ENOMEM);
+
+	res = __xa_cmpxchg(xa, index, NULL, elm, GFP_ATOMIC);
+	if (xa_is_err(res))
+		res = ERR_PTR(xa_err(res));
+
+	if (res) {
+		kfree(elm);
+		return res;
+	}
+
+	refcount_set(&elm->users, 0);
+	return elm;
+}
+
+/*
+ * This function is assigned to struct iommufd_viommu_ops.alloc_domain_nested()
+ * during the call to struct iommu_ops.viommu_init().
+ */
+struct iommu_domain *
+amd_iommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags,
+			      const struct iommu_user_data *user_data)
+{
+	int ret;
+	unsigned long irqflags;
+	struct nested_domain *ndom;
+	struct guest_domain_mapping_info *gdom_info;
+	struct amd_iommu_viommu *aviommu = container_of(viommu, struct amd_iommu_viommu, core);
+
+	if (user_data->type != IOMMU_HWPT_DATA_AMD_GUEST)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	ndom = kzalloc_obj(*ndom);
+	if (!ndom)
+		return ERR_PTR(-ENOMEM);
+
+	ret = iommu_copy_struct_from_user(&ndom->gdte, user_data,
+					  IOMMU_HWPT_DATA_AMD_GUEST,
+					  dte);
+	if (ret)
+		goto out_err;
+
+	ret = validate_gdte_nested(&ndom->gdte);
+	if (ret)
+		goto out_err;
+
+	ndom->gdom_id = FIELD_GET(DTE_DOMID_MASK, ndom->gdte.dte[1]);
+	ndom->domain.ops = &nested_domain_ops;
+	ndom->domain.type = IOMMU_DOMAIN_NESTED;
+	ndom->viommu = aviommu;
+
+	/*
+	 * Normally, when a guest has multiple pass-through devices,
+	 * the IOMMU driver setup DTEs with the same stage-2 table and
+	 * use the same host domain ID (hDomId). In case of nested translation,
+	 * if the guest setup different stage-1 tables with same PASID,
+	 * IOMMU would use the same TLB tag. This will results in TLB
+	 * aliasing issue.
+	 *
+	 * The guest is assigning gDomIDs based on its own algorithm for managing
+	 * cache tags of (DomID, PASID). Within a single viommu, the nest parent domain
+	 * (w/ S2 table) is used by all DTEs. But we need to consistently map the gDomID
+	 * to a single hDomID. This is done using an xarray in the vIOMMU to
+	 * keep track of the gDomID mapping. When the S2 is changed, the INVALIDATE_IOMMU_PAGES
+	 * command must be issued for each hDomID in the xarray.
+	 */
+	xa_lock_irqsave(&aviommu->gdomid_array, irqflags);
+
+	gdom_info = gdom_info_load_or_alloc_locked(&aviommu->gdomid_array,
+						   ndom->gdom_id, &irqflags);
+	if (IS_ERR(gdom_info)) {
+		xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+		ret = PTR_ERR(gdom_info);
+		goto out_err;
+	}
+
+	/* Check if gDomID exist */
+	if (refcount_inc_not_zero(&gdom_info->users)) {
+		ndom->gdom_info = gdom_info;
+		xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+
+		pr_debug("%s: Found gdom_id=%#x, hdom_id=%#x\n",
+			  __func__, ndom->gdom_id, gdom_info->hdom_id);
+
+		return &ndom->domain;
+	}
+
+	/* The gDomID does not exist. We allocate new hdom_id */
+	gdom_info->hdom_id = amd_iommu_pdom_id_alloc();
+	if (gdom_info->hdom_id <= 0) {
+		__xa_cmpxchg(&aviommu->gdomid_array,
+			     ndom->gdom_id, gdom_info, NULL, GFP_ATOMIC);
+		xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+		ret = -ENOSPC;
+		goto out_err_gdom_info;
+	}
+
+	ndom->gdom_info = gdom_info;
+	refcount_set(&gdom_info->users, 1);
+
+	xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+
+	pr_debug("%s: Allocate gdom_id=%#x, hdom_id=%#x\n",
+		 __func__, ndom->gdom_id, gdom_info->hdom_id);
+
+	return &ndom->domain;
+
+out_err_gdom_info:
+	kfree(gdom_info);
+out_err:
+	kfree(ndom);
+	return ERR_PTR(ret);
+}
+
+static void set_dte_nested(struct amd_iommu *iommu, struct iommu_domain *dom,
+			   struct iommu_dev_data *dev_data, struct dev_table_entry *new)
+{
+	struct protection_domain *parent;
+	struct nested_domain *ndom = to_ndomain(dom);
+	struct iommu_hwpt_amd_guest *gdte = &ndom->gdte;
+	struct pt_iommu_amdv1_hw_info pt_info;
+
+	/*
+	 * The nest parent domain is attached during the call to the
+	 * struct iommu_ops.viommu_init(), which will be stored as part
+	 * of the struct amd_iommu_viommu.parent.
+	 */
+	if (WARN_ON(!ndom->viommu || !ndom->viommu->parent))
+		return;
+
+	parent = ndom->viommu->parent;
+	amd_iommu_make_clear_dte(dev_data, new);
+
+	/* Retrieve the current pagetable info via the IOMMU PT API. */
+	pt_iommu_amdv1_hw_info(&parent->amdv1, &pt_info);
+
+	/*
+	 * Use domain ID from nested domain to program DTE.
+	 * See amd_iommu_alloc_domain_nested().
+	 */
+	amd_iommu_set_dte_v1(dev_data, parent, ndom->gdom_info->hdom_id,
+			     &pt_info, new);
+
+	/* GV is required for nested page table */
+	new->data[0] |= DTE_FLAG_GV;
+
+	/* Guest PPR */
+	new->data[0] |= gdte->dte[0] & DTE_FLAG_PPR;
+
+	/* Guest translation stuff */
+	new->data[0] |= gdte->dte[0] & (DTE_GLX | DTE_FLAG_GIOV);
+
+	/* GCR3 table */
+	new->data[0] |= gdte->dte[0] & DTE_GCR3_14_12;
+	new->data[1] |= gdte->dte[1] & (DTE_GCR3_30_15 | DTE_GCR3_51_31);
+
+	/* Guest paging mode */
+	new->data[2] |= gdte->dte[2] & DTE_GPT_LEVEL_MASK;
+}
+
+static int nested_attach_device(struct iommu_domain *dom, struct device *dev,
+				struct iommu_domain *old)
+{
+	struct dev_table_entry new = {0};
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
+	struct amd_iommu *iommu = get_amd_iommu_from_dev_data(dev_data);
+	int ret = 0;
+
+	/*
+	 * Needs to make sure PASID is not enabled
+	 * for this attach path.
+	 */
+	if (WARN_ON(dev_data->pasid_enabled))
+		return -EINVAL;
+
+	mutex_lock(&dev_data->mutex);
+
+	set_dte_nested(iommu, dom, dev_data, &new);
+
+	amd_iommu_update_dte(iommu, dev_data, &new);
+
+	mutex_unlock(&dev_data->mutex);
+
+	return ret;
+}
+
+static void nested_domain_free(struct iommu_domain *dom)
+{
+	unsigned long irqflags;
+	struct guest_domain_mapping_info *curr;
+	struct nested_domain *ndom __free(kfree) = to_ndomain(dom);
+	struct amd_iommu_viommu *aviommu = ndom->viommu;
+
+	xa_lock_irqsave(&aviommu->gdomid_array, irqflags);
+
+	if (!refcount_dec_and_test(&ndom->gdom_info->users)) {
+		xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+		return;
+	}
+
+	/*
+	 * The refcount for the gdom_id to hdom_id mapping is zero.
+	 * It is now safe to remove the mapping.
+	 */
+	curr = __xa_cmpxchg(&aviommu->gdomid_array, ndom->gdom_id,
+			    ndom->gdom_info, NULL, GFP_ATOMIC);
+
+	xa_unlock_irqrestore(&aviommu->gdomid_array, irqflags);
+	if (WARN_ON(!curr || xa_err(curr)))
+		return;
+
+	/* success */
+	pr_debug("%s: Free gdom_id=%#x, hdom_id=%#x\n",
+		__func__, ndom->gdom_id, curr->hdom_id);
+
+	amd_iommu_pdom_id_free(ndom->gdom_info->hdom_id);
+	kfree(curr);
+}
+
+static const struct iommu_domain_ops nested_domain_ops = {
+	.attach_dev = nested_attach_device,
+	.free = nested_domain_free,
+};

linux-7.2.3/drivers/iommu/amd/pasid.c

@@ -0,0 +1,203 @@
+// 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;
+		}
+	}
+}
+
+static void sva_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
+				    struct mm_struct *mm,
+				    unsigned long start, unsigned long end)
+{
+	struct pdom_dev_data *pdom_dev_data;
+	struct protection_domain *sva_pdom;
+	unsigned long flags;
+
+	sva_pdom = container_of(mn, struct protection_domain, mn);
+
+	spin_lock_irqsave(&sva_pdom->lock, flags);
+
+	for_each_pdom_dev_data(pdom_dev_data, sva_pdom) {
+		amd_iommu_dev_flush_pasid_pages(pdom_dev_data->dev_data,
+						pdom_dev_data->pasid,
+						start, end - 1);
+	}
+
+	spin_unlock_irqrestore(&sva_pdom->lock, flags);
+}
+
+static void sva_mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct pdom_dev_data *pdom_dev_data, *next;
+	struct protection_domain *sva_pdom;
+	unsigned long flags;
+
+	sva_pdom = container_of(mn, struct protection_domain, mn);
+
+	spin_lock_irqsave(&sva_pdom->lock, flags);
+
+	/* Assume dev_data_list contains same PASID with different devices */
+	for_each_pdom_dev_data_safe(pdom_dev_data, next, sva_pdom)
+		remove_dev_pasid(pdom_dev_data);
+
+	spin_unlock_irqrestore(&sva_pdom->lock, flags);
+}
+
+static const struct mmu_notifier_ops sva_mn = {
+	.arch_invalidate_secondary_tlbs = sva_arch_invalidate_secondary_tlbs,
+	.release = sva_mn_release,
+};
+
+int iommu_sva_set_dev_pasid(struct iommu_domain *domain,
+			    struct device *dev, ioasid_t pasid,
+			    struct iommu_domain *old)
+{
+	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;
+
+	if (old)
+		return -EOPNOTSUPP;
+
+	/* 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_obj(*pdom_dev_data);
+	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 iommu_domain *domain)
+{
+	struct protection_domain *sva_pdom;
+	unsigned long flags;
+
+	if (!is_pasid_valid(dev_iommu_priv_get(dev), pasid))
+		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);
+}
+
+static void iommu_sva_domain_free(struct iommu_domain *domain)
+{
+	struct protection_domain *sva_pdom = to_pdomain(domain);
+
+	if (sva_pdom->mn.ops)
+		mmu_notifier_unregister(&sva_pdom->mn, domain->mm);
+
+	amd_iommu_domain_free(domain);
+}
+
+static const struct iommu_domain_ops amd_sva_domain_ops = {
+	.set_dev_pasid = iommu_sva_set_dev_pasid,
+	.free	       = iommu_sva_domain_free
+};
+
+struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev,
+						struct mm_struct *mm)
+{
+	struct protection_domain *pdom;
+	int ret;
+
+	pdom = protection_domain_alloc();
+	if (!pdom)
+		return ERR_PTR(-ENOMEM);
+
+	pdom->domain.ops = &amd_sva_domain_ops;
+	pdom->mn.ops = &sva_mn;
+	pdom->domain.type = IOMMU_DOMAIN_SVA;
+
+	ret = mmu_notifier_register(&pdom->mn, mm);
+	if (ret) {
+		amd_iommu_domain_free(&pdom->domain);
+		return ERR_PTR(ret);
+	}
+
+	return &pdom->domain;
+}

linux-7.2.3/drivers/iommu/amd/ppr.c

@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/amd-iommu.h>
+#include <linux/delay.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/iommu.h>
+
+#include "amd_iommu.h"
+#include "amd_iommu_types.h"
+
+#include "../iommu-pages.h"
+
+int __init amd_iommu_alloc_ppr_log(struct amd_iommu *iommu)
+{
+	iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      amd_iommu_pprlog_size);
+	return iommu->ppr_log ? 0 : -ENOMEM;
+}
+
+void amd_iommu_enable_ppr_log(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+
+	entry = iommu_virt_to_phys(iommu->ppr_log);
+	entry |= (amd_iommu_pprlog_size == PPRLOG_SIZE_DEF) ?
+			PPRLOG_LEN_MASK_DEF : PPRLOG_LEN_MASK_MAX;
+
+	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* set head and tail to zero manually */
+	writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
+	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
+}
+
+void __init amd_iommu_free_ppr_log(struct amd_iommu *iommu)
+{
+	iommu_free_pages(iommu->ppr_log);
+}
+
+/*
+ * This function restarts ppr logging in case the IOMMU experienced
+ * PPR log overflow.
+ */
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu)
+{
+	amd_iommu_restart_log(iommu, "PPR", CONTROL_PPRINT_EN,
+			      CONTROL_PPRLOG_EN, MMIO_STATUS_PPR_RUN_MASK,
+			      MMIO_STATUS_PPR_OVERFLOW_MASK);
+}
+
+static inline u32 ppr_flag_to_fault_perm(u16 flag)
+{
+	int perm = 0;
+
+	if (flag & PPR_FLAG_READ)
+		perm |= IOMMU_FAULT_PERM_READ;
+	if (flag & PPR_FLAG_WRITE)
+		perm |= IOMMU_FAULT_PERM_WRITE;
+	if (flag & PPR_FLAG_EXEC)
+		perm |= IOMMU_FAULT_PERM_EXEC;
+	if (!(flag & PPR_FLAG_US))
+		perm |= IOMMU_FAULT_PERM_PRIV;
+
+	return perm;
+}
+
+static bool ppr_is_valid(struct amd_iommu *iommu, u64 *raw)
+{
+	struct device *dev = iommu->iommu.dev;
+	u16 devid = PPR_DEVID(raw[0]);
+
+	if (!(PPR_FLAGS(raw[0]) & PPR_FLAG_GN)) {
+		dev_dbg(dev, "PPR logged [Request ignored due to GN=0 (device=%04x:%02x:%02x.%x "
+			"pasid=0x%05llx address=0x%llx flags=0x%04llx tag=0x%03llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			PPR_PASID(raw[0]), raw[1], PPR_FLAGS(raw[0]), PPR_TAG(raw[0]));
+		return false;
+	}
+
+	if (PPR_FLAGS(raw[0]) & PPR_FLAG_RVSD) {
+		dev_dbg(dev, "PPR logged [Invalid request format (device=%04x:%02x:%02x.%x "
+			"pasid=0x%05llx address=0x%llx flags=0x%04llx tag=0x%03llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			PPR_PASID(raw[0]), raw[1], PPR_FLAGS(raw[0]), PPR_TAG(raw[0]));
+		return false;
+	}
+
+	return true;
+}
+
+static void iommu_call_iopf_notifier(struct amd_iommu *iommu, u64 *raw)
+{
+	struct iommu_dev_data *dev_data;
+	struct iopf_fault event;
+	struct pci_dev *pdev;
+	u16 devid = PPR_DEVID(raw[0]);
+
+	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
+		pr_info_ratelimited("Unknown PPR request received\n");
+		return;
+	}
+
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+					   PCI_BUS_NUM(devid), devid & 0xff);
+	if (!pdev)
+		return;
+
+	if (!ppr_is_valid(iommu, raw))
+		goto out;
+
+	memset(&event, 0, sizeof(struct iopf_fault));
+
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.perm = ppr_flag_to_fault_perm(PPR_FLAGS(raw[0]));
+	event.fault.prm.addr = (u64)(raw[1] & PAGE_MASK);
+	event.fault.prm.pasid = PPR_PASID(raw[0]);
+	event.fault.prm.grpid = PPR_TAG(raw[0]) & 0x1FF;
+
+	/*
+	 * PASID zero is used for requests from the I/O device without
+	 * a PASID
+	 */
+	dev_data = dev_iommu_priv_get(&pdev->dev);
+	if (event.fault.prm.pasid == 0 ||
+	    event.fault.prm.pasid >= dev_data->max_pasids) {
+		pr_info_ratelimited("Invalid PASID : 0x%x, device : 0x%x\n",
+				    event.fault.prm.pasid, pdev->dev.id);
+		goto out;
+	}
+
+	event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+	event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	if (PPR_TAG(raw[0]) & 0x200)
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	/* Submit event */
+	iommu_report_device_fault(&pdev->dev, &event);
+
+	return;
+
+out:
+	/* Nobody cared, abort */
+	amd_iommu_complete_ppr(&pdev->dev, PPR_PASID(raw[0]),
+			       IOMMU_PAGE_RESP_FAILURE,
+			       PPR_TAG(raw[0]) & 0x1FF);
+}
+
+void amd_iommu_poll_ppr_log(struct amd_iommu *iommu)
+{
+	u32 head, tail;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	while (head != tail) {
+		volatile u64 *raw;
+		u64 entry[2];
+		int i;
+
+		raw = (u64 *)(iommu->ppr_log + head);
+
+		/*
+		 * Hardware bug: Interrupt may arrive before the entry is
+		 * written to memory. If this happens we need to wait for the
+		 * entry to arrive.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			if (PPR_REQ_TYPE(raw[0]) != 0)
+				break;
+			udelay(1);
+		}
+
+		/* Avoid memcpy function-call overhead */
+		entry[0] = raw[0];
+		entry[1] = raw[1];
+
+		/*
+		 * To detect the hardware errata 733 we need to clear the
+		 * entry back to zero. This issue does not exist on SNP
+		 * enabled system. Also this buffer is not writeable on
+		 * SNP enabled system.
+		 */
+		if (!amd_iommu_snp_en)
+			raw[0] = raw[1] = 0UL;
+
+		/* Update head pointer of hardware ring-buffer */
+		head = (head + PPRLOG_ENTRY_SIZE) % amd_iommu_pprlog_size;
+		writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+		/* Handle PPR entry */
+		iommu_call_iopf_notifier(iommu, entry);
+	}
+}
+
+/**************************************************************
+ *
+ * IOPF handling stuff
+ */
+
+/* Setup per-IOMMU IOPF queue if not exist. */
+int amd_iommu_iopf_init(struct amd_iommu *iommu)
+{
+	int ret = 0;
+
+	if (iommu->iopf_queue)
+		return ret;
+
+	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name), "amdvi-%#x",
+		 PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->id, iommu->devid));
+
+	iommu->iopf_queue = iopf_queue_alloc(iommu->iopfq_name);
+	if (!iommu->iopf_queue)
+		ret = -ENOMEM;
+
+	return ret;
+}
+
+/* Destroy per-IOMMU IOPF queue if no longer needed. */
+void amd_iommu_iopf_uninit(struct amd_iommu *iommu)
+{
+	iopf_queue_free(iommu->iopf_queue);
+	iommu->iopf_queue = NULL;
+}
+
+void amd_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			     struct iommu_page_response *resp)
+{
+	amd_iommu_complete_ppr(dev, resp->pasid, resp->code, resp->grpid);
+}
+
+int amd_iommu_iopf_add_device(struct amd_iommu *iommu,
+			      struct iommu_dev_data *dev_data)
+{
+	int ret = 0;
+
+	if (!dev_data->pri_enabled)
+		return ret;
+
+	if (!iommu->iopf_queue)
+		return -EINVAL;
+
+	ret = iopf_queue_add_device(iommu->iopf_queue, dev_data->dev);
+	if (ret)
+		return ret;
+
+	dev_data->ppr = true;
+	return 0;
+}
+
+/* Its assumed that caller has verified that device was added to iopf queue */
+void amd_iommu_iopf_remove_device(struct amd_iommu *iommu,
+				  struct iommu_dev_data *dev_data)
+{
+	iopf_queue_remove_device(iommu->iopf_queue, dev_data->dev);
+	dev_data->ppr = false;
+}

linux-7.2.3/drivers/iommu/amd/quirks.c

@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * Quirks for AMD IOMMU
+ *
+ * Copyright (C) 2019 Kai-Heng Feng <kai.heng.feng@canonical.com>
+ */
+
+#ifdef CONFIG_DMI
+#include <linux/dmi.h>
+
+#include "amd_iommu.h"
+
+#define IVHD_SPECIAL_IOAPIC		1
+
+struct ivrs_quirk_entry {
+	u8 id;
+	u32 devid;
+};
+
+enum {
+	DELL_INSPIRON_7375 = 0,
+	DELL_LATITUDE_5495,
+	LENOVO_IDEAPAD_330S_15ARR,
+};
+
+static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = {
+	/* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */
+	[DELL_INSPIRON_7375] = {
+		{ .id = 4, .devid = 0xa0 },
+		{ .id = 5, .devid = 0x2 },
+		{}
+	},
+	/* ivrs_ioapic[4]=00:14.0 */
+	[DELL_LATITUDE_5495] = {
+		{ .id = 4, .devid = 0xa0 },
+		{}
+	},
+	/* ivrs_ioapic[32]=00:14.0 */
+	[LENOVO_IDEAPAD_330S_15ARR] = {
+		{ .id = 32, .devid = 0xa0 },
+		{}
+	},
+	{}
+};
+
+static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d)
+{
+	const struct ivrs_quirk_entry *i;
+
+	for (i = d->driver_data; i->id != 0 && i->devid != 0; i++)
+		add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u32 *)&i->devid, 0);
+
+	return 0;
+}
+
+static const struct dmi_system_id ivrs_quirks[] __initconst = {
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Inspiron 7375",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Latitude 5495",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
+		/*
+		 * Acer Aspire A315-41 requires the very same workaround as
+		 * Dell Latitude 5495
+		 */
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Acer Aspire A315-41",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Lenovo ideapad 330S-15ARR",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "81FB"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR],
+	},
+	{}
+};
+
+void __init amd_iommu_apply_ivrs_quirks(void)
+{
+	dmi_check_system(ivrs_quirks);
+}
+#endif