Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-23 20:51:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branches 'arm/smmu', 'mediatek', 's390', 'ti/omap', 'riscv' and 'core' into next

Browse Source
This commit is contained in:
Joerg Roedel 2024-11-15 09:27:02 +01:00
commit ae3325f752
34 changed files with 3346 additions and 483 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Documentation/devicetree/bindings/iommu/arm,smmu.yaml
View File

@ -36,10 +36,12 @@ properties:
items:
- enum:
- qcom,qcm2290-smmu-500
- qcom,qcs615-smmu-500
- qcom,qcs8300-smmu-500
- qcom,qdu1000-smmu-500
- qcom,sa8255p-smmu-500
- qcom,sa8775p-smmu-500
- qcom,sar2130p-smmu-500
- qcom,sc7180-smmu-500
- qcom,sc7280-smmu-500
- qcom,sc8180x-smmu-500
@ -88,6 +90,7 @@ properties:
- qcom,qcm2290-smmu-500
- qcom,sa8255p-smmu-500
- qcom,sa8775p-smmu-500
- qcom,sar2130p-smmu-500
- qcom,sc7280-smmu-500
- qcom,sc8180x-smmu-500
- qcom,sc8280xp-smmu-500
@ -524,6 +527,7 @@ allOf:
compatible:
items:
- enum:
- qcom,sar2130p-smmu-500
- qcom,sm8550-smmu-500
- qcom,sm8650-smmu-500
- qcom,x1e80100-smmu-500
@ -555,6 +559,7 @@ allOf:
- cavium,smmu-v2
- marvell,ap806-smmu-500
- nvidia,smmu-500
- qcom,qcs615-smmu-500
- qcom,qcs8300-smmu-500
- qcom,qdu1000-smmu-500
- qcom,sa8255p-smmu-500

147
Documentation/devicetree/bindings/iommu/riscv,iommu.yaml Normal file
View File

@ -0,0 +1,147 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/iommu/riscv,iommu.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: RISC-V IOMMU Architecture Implementation
maintainers:
- Tomasz Jeznach <tjeznach@rivosinc.com>
description: |
The RISC-V IOMMU provides memory address translation and isolation for
input and output devices, supporting per-device translation context,
shared process address spaces including the ATS and PRI components of
the PCIe specification, two stage address translation and MSI remapping.
It supports identical translation table format to the RISC-V address
translation tables with page level access and protection attributes.
Hardware uses in-memory command and fault reporting queues with wired
interrupt or MSI notifications.
Visit https://github.com/riscv-non-isa/riscv-iommu for more details.
For information on assigning RISC-V IOMMU to its peripheral devices,
see generic IOMMU bindings.
properties:
# For PCIe IOMMU hardware compatible property should contain the vendor
# and device ID according to the PCI Bus Binding specification.
# Since PCI provides built-in identification methods, compatible is not
# actually required. For non-PCIe hardware implementations 'riscv,iommu'
# should be specified along with 'reg' property providing MMIO location.
compatible:
oneOf:
- items:
- enum:
- qemu,riscv-iommu
- const: riscv,iommu
- items:
- enum:
- pci1efd,edf1
- const: riscv,pci-iommu
reg:
maxItems: 1
description:
For non-PCI devices this represents base address and size of for the
IOMMU memory mapped registers interface.
For PCI IOMMU hardware implementation this should represent an address
of the IOMMU, as defined in the PCI Bus Binding reference.
'#iommu-cells':
const: 1
description:
The single cell describes the requester id emitted by a master to the
IOMMU.
interrupts:
minItems: 1
maxItems: 4
description:
Wired interrupt vectors available for RISC-V IOMMU to notify the
RISC-V HARTS. The cause to interrupt vector is software defined
using IVEC IOMMU register.
msi-parent: true
power-domains:
maxItems: 1
required:
- compatible
- reg
- '#iommu-cells'
additionalProperties: false
examples:
- |+
/* Example 1 (IOMMU device with wired interrupts) */
#include <dt-bindings/interrupt-controller/irq.h>
iommu1: iommu@1bccd000 {
compatible = "qemu,riscv-iommu", "riscv,iommu";
reg = <0x1bccd000 0x1000>;
interrupt-parent = <&aplic_smode>;
interrupts = <32 IRQ_TYPE_LEVEL_HIGH>,
<33 IRQ_TYPE_LEVEL_HIGH>,
<34 IRQ_TYPE_LEVEL_HIGH>,
<35 IRQ_TYPE_LEVEL_HIGH>;
#iommu-cells = <1>;
};
/* Device with two IOMMU device IDs, 0 and 7 */
master1 {
iommus = <&iommu1 0>, <&iommu1 7>;
};
- |+
/* Example 2 (IOMMU device with shared wired interrupt) */
#include <dt-bindings/interrupt-controller/irq.h>
iommu2: iommu@1bccd000 {
compatible = "qemu,riscv-iommu", "riscv,iommu";
reg = <0x1bccd000 0x1000>;
interrupt-parent = <&aplic_smode>;
interrupts = <32 IRQ_TYPE_LEVEL_HIGH>;
#iommu-cells = <1>;
};
- |+
/* Example 3 (IOMMU device with MSIs) */
iommu3: iommu@1bcdd000 {
compatible = "qemu,riscv-iommu", "riscv,iommu";
reg = <0x1bccd000 0x1000>;
msi-parent = <&imsics_smode>;
#iommu-cells = <1>;
};
- |+
/* Example 4 (IOMMU PCIe device with MSIs) */
bus {
#address-cells = <2>;
#size-cells = <2>;
pcie@30000000 {
device_type = "pci";
#address-cells = <3>;
#size-cells = <2>;
reg = <0x0 0x30000000 0x0 0x1000000>;
ranges = <0x02000000 0x0 0x41000000 0x0 0x41000000 0x0 0x0f000000>;
/*
* The IOMMU manages all functions in this PCI domain except
* itself. Omit BDF 00:01.0.
*/
iommu-map = <0x0 &iommu0 0x0 0x8>,
<0x9 &iommu0 0x9 0xfff7>;
/* The IOMMU programming interface uses slot 00:01.0 */
iommu0: iommu@1,0 {
compatible = "pci1efd,edf1", "riscv,pci-iommu";
reg = <0x800 0 0 0 0>;
#iommu-cells = <1>;
};
};
};

9
MAINTAINERS
View File

@ -19810,6 +19810,15 @@ F: arch/riscv/
N: riscv
K: riscv
RISC-V IOMMU
M: Tomasz Jeznach <tjeznach@rivosinc.com>
L: iommu@lists.linux.dev
L: linux-riscv@lists.infradead.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git
F: Documentation/devicetree/bindings/iommu/riscv,iommu.yaml
F: drivers/iommu/riscv/
RISC-V MICROCHIP FPGA SUPPORT
M: Conor Dooley <conor.dooley@microchip.com>
M: Daire McNamara <daire.mcnamara@microchip.com>

4
arch/s390/include/asm/pci.h
View File

@ -96,7 +96,6 @@ struct zpci_bar_struct {
u8 size; /* order 2 exponent */
};
struct s390_domain;
struct kvm_zdev;
#define ZPCI_FUNCTIONS_PER_BUS 256
@ -181,9 +180,10 @@ struct zpci_dev {
struct dentry *debugfs_dev;
/* IOMMU and passthrough */
struct s390_domain *s390_domain; /* s390 IOMMU domain data */
struct iommu_domain *s390_domain; /* attached IOMMU domain */
struct kvm_zdev *kzdev;
struct mutex kzdev_lock;
spinlock_t dom_lock; /* protect s390_domain change */
};
static inline bool zdev_enabled(struct zpci_dev *zdev)

3
arch/s390/pci/pci.c
View File

@ -160,6 +160,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE);
struct zpci_iommu_ctrs *ctrs;
struct zpci_fib fib = {0};
unsigned long flags;
u8 cc, status;
if (zdev->fmb || sizeof(*zdev->fmb) < zdev->fmb_length)
@ -171,6 +172,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
WARN_ON((u64) zdev->fmb & 0xf);
/* reset software counters */
spin_lock_irqsave(&zdev->dom_lock, flags);
ctrs = zpci_get_iommu_ctrs(zdev);
if (ctrs) {
atomic64_set(&ctrs->mapped_pages, 0);
@ -179,6 +181,7 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev)
atomic64_set(&ctrs->sync_map_rpcits, 0);
atomic64_set(&ctrs->sync_rpcits, 0);
}
spin_unlock_irqrestore(&zdev->dom_lock, flags);
fib.fmb_addr = virt_to_phys(zdev->fmb);

10
arch/s390/pci/pci_debug.c
View File

@ -71,17 +71,23 @@ static void pci_fmb_show(struct seq_file *m, char *name[], int length,
static void pci_sw_counter_show(struct seq_file *m)
{
struct zpci_iommu_ctrs *ctrs = zpci_get_iommu_ctrs(m->private);
struct zpci_dev *zdev = m->private;
struct zpci_iommu_ctrs *ctrs;
atomic64_t *counter;
unsigned long flags;
int i;
spin_lock_irqsave(&zdev->dom_lock, flags);
ctrs = zpci_get_iommu_ctrs(m->private);
if (!ctrs)
return;
goto unlock;
counter = &ctrs->mapped_pages;
for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
atomic64_read(counter));
unlock:
spin_unlock_irqrestore(&zdev->dom_lock, flags);
}
static int pci_perf_show(struct seq_file *m, void *v)

4
drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
View File

@ -120,8 +120,8 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
mutex_init(&tdev->iommu.mutex);
if (device_iommu_mapped(dev)) {
tdev->iommu.domain = iommu_domain_alloc(&platform_bus_type);
if (!tdev->iommu.domain)
tdev->iommu.domain = iommu_paging_domain_alloc(dev);
if (IS_ERR(tdev->iommu.domain))
goto error;
/*

1
drivers/iommu/Kconfig
View File

@ -195,6 +195,7 @@ config MSM_IOMMU
source "drivers/iommu/amd/Kconfig"
source "drivers/iommu/intel/Kconfig"
source "drivers/iommu/iommufd/Kconfig"
source "drivers/iommu/riscv/Kconfig"
config IRQ_REMAP
bool "Support for Interrupt Remapping"

2
drivers/iommu/Makefile
View File

@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
obj-y += amd/ intel/ arm/ iommufd/
obj-y += amd/ intel/ arm/ iommufd/ riscv/
obj-$(CONFIG_IOMMU_API) += iommu.o
obj-$(CONFIG_IOMMU_API) += iommu-traces.o
obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o

8
drivers/iommu/amd/amd_iommu.h
View File

@ -46,6 +46,7 @@ extern int amd_iommu_gpt_level;
extern unsigned long amd_iommu_pgsize_bitmap;
/* Protection domain ops */
void amd_iommu_init_identity_domain(void);
struct protection_domain *protection_domain_alloc(unsigned int type, int nid);
void protection_domain_free(struct protection_domain *domain);
struct iommu_domain *amd_iommu_domain_alloc_sva(struct device *dev,
@ -118,9 +119,14 @@ 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 (check_feature(FEATURE_GT) &&
return (amd_iommu_v2_pgtbl_supported() &&
check_feature(FEATURE_PPR) &&
check_feature(FEATURE_EPHSUP));
}

18
drivers/iommu/amd/init.c
View File

@ -2070,14 +2070,6 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
init_iommu_perf_ctr(iommu);
if (amd_iommu_pgtable == AMD_IOMMU_V2) {
if (!check_feature(FEATURE_GIOSUP) ||
!check_feature(FEATURE_GT)) {
pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
amd_iommu_pgtable = AMD_IOMMU_V1;
}
}
if (is_rd890_iommu(iommu->dev)) {
int i, j;
@ -2172,6 +2164,9 @@ static int __init amd_iommu_init_pci(void)
struct amd_iommu_pci_seg *pci_seg;
int ret;
/* Init global identity domain before registering IOMMU */
amd_iommu_init_identity_domain();
for_each_iommu(iommu) {
ret = iommu_init_pci(iommu);
if (ret) {
@ -3091,6 +3086,13 @@ static int __init early_amd_iommu_init(void)
FIELD_GET(FEATURE_GATS, amd_iommu_efr) == GUEST_PGTABLE_5_LEVEL)
amd_iommu_gpt_level = PAGE_MODE_5_LEVEL;
if (amd_iommu_pgtable == AMD_IOMMU_V2) {
if (!amd_iommu_v2_pgtbl_supported()) {
pr_warn("Cannot enable v2 page table for DMA-API. Fallback to v1.\n");
amd_iommu_pgtable = AMD_IOMMU_V1;
}
}
/* Disable any previously enabled IOMMUs */
if (!is_kdump_kernel() || amd_iommu_disabled)
disable_iommus();

145
drivers/iommu/amd/iommu.c
View File

@ -74,6 +74,9 @@ struct kmem_cache *amd_iommu_irq_cache;
static void detach_device(struct device *dev);
static int amd_iommu_attach_device(struct iommu_domain *dom,
struct device *dev);
static void set_dte_entry(struct amd_iommu *iommu,
struct iommu_dev_data *dev_data);
@ -2263,44 +2266,42 @@ void protection_domain_free(struct protection_domain *domain)
kfree(domain);
}
static void protection_domain_init(struct protection_domain *domain, int nid)
{
spin_lock_init(&domain->lock);
INIT_LIST_HEAD(&domain->dev_list);
INIT_LIST_HEAD(&domain->dev_data_list);
domain->iop.pgtbl.cfg.amd.nid = nid;
}
struct protection_domain *protection_domain_alloc(unsigned int type, int nid)
{
struct io_pgtable_ops *pgtbl_ops;
struct protection_domain *domain;
int pgtable;
domain = kzalloc(sizeof(*domain), GFP_KERNEL);
if (!domain)
return NULL;
domain->id = domain_id_alloc();
if (!domain->id)
goto err_free;
spin_lock_init(&domain->lock);
INIT_LIST_HEAD(&domain->dev_list);
INIT_LIST_HEAD(&domain->dev_data_list);
domain->iop.pgtbl.cfg.amd.nid = nid;
switch (type) {
/* No need to allocate io pgtable ops in passthrough mode */
case IOMMU_DOMAIN_IDENTITY:
case IOMMU_DOMAIN_SVA:
return domain;
case IOMMU_DOMAIN_DMA:
pgtable = amd_iommu_pgtable;
break;
/*
* Force IOMMU v1 page table when allocating
* domain for pass-through devices.
*/
case IOMMU_DOMAIN_UNMANAGED:
pgtable = AMD_IOMMU_V1;
break;
default:
goto err_id;
if (!domain->id) {
kfree(domain);
return NULL;
}
protection_domain_init(domain, nid);
return domain;
}
static int pdom_setup_pgtable(struct protection_domain *domain,
unsigned int type, int pgtable)
{
struct io_pgtable_ops *pgtbl_ops;
/* No need to allocate io pgtable ops in passthrough mode */
if (!(type & __IOMMU_DOMAIN_PAGING))
return 0;
switch (pgtable) {
case AMD_IOMMU_V1:
domain->pd_mode = PD_MODE_V1;
@ -2309,25 +2310,20 @@ struct protection_domain *protection_domain_alloc(unsigned int type, int nid)
domain->pd_mode = PD_MODE_V2;
break;
default:
goto err_id;
return -EINVAL;
}
pgtbl_ops =
alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl.cfg, domain);
if (!pgtbl_ops)
goto err_id;
return -ENOMEM;
return domain;
err_id:
domain_id_free(domain->id);
err_free:
kfree(domain);
return NULL;
return 0;
}
static inline u64 dma_max_address(void)
static inline u64 dma_max_address(int pgtable)
{
if (amd_iommu_pgtable == AMD_IOMMU_V1)
if (pgtable == AMD_IOMMU_V1)
return ~0ULL;
/* V2 with 4/5 level page table */
@ -2340,11 +2336,13 @@ static bool amd_iommu_hd_support(struct amd_iommu *iommu)
}
static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
struct device *dev, u32 flags)
struct device *dev,
u32 flags, int pgtable)
{
bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
struct protection_domain *domain;
struct amd_iommu *iommu = NULL;
int ret;
if (dev)
iommu = get_amd_iommu_from_dev(dev);
@ -2356,16 +2354,20 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY))
return ERR_PTR(-EINVAL);
if (dirty_tracking && !amd_iommu_hd_support(iommu))
return ERR_PTR(-EOPNOTSUPP);
domain = protection_domain_alloc(type,
dev ? dev_to_node(dev) : NUMA_NO_NODE);
if (!domain)
return ERR_PTR(-ENOMEM);
ret = pdom_setup_pgtable(domain, type, pgtable);
if (ret) {
domain_id_free(domain->id);
kfree(domain);
return ERR_PTR(ret);
}
domain->domain.geometry.aperture_start = 0;
domain->domain.geometry.aperture_end = dma_max_address();
domain->domain.geometry.aperture_end = dma_max_address(pgtable);
domain->domain.geometry.force_aperture = true;
domain->domain.pgsize_bitmap = domain->iop.pgtbl.cfg.pgsize_bitmap;
@ -2383,8 +2385,16 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type)
{
struct iommu_domain *domain;
int pgtable = amd_iommu_pgtable;
domain = do_iommu_domain_alloc(type, NULL, 0);
/*
* Force IOMMU v1 page table when allocating
* domain for pass-through devices.
*/
if (type == IOMMU_DOMAIN_UNMANAGED)
pgtable = AMD_IOMMU_V1;
domain = do_iommu_domain_alloc(type, NULL, 0, pgtable);
if (IS_ERR(domain))
return NULL;
@ -2398,11 +2408,36 @@ amd_iommu_domain_alloc_user(struct device *dev, u32 flags,
{
unsigned int type = IOMMU_DOMAIN_UNMANAGED;
struct amd_iommu *iommu = NULL;
const u32 supported_flags = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
IOMMU_HWPT_ALLOC_PASID;
if ((flags & ~IOMMU_HWPT_ALLOC_DIRTY_TRACKING) || parent || user_data)
if (dev)
iommu = get_amd_iommu_from_dev(dev);
if ((flags & ~supported_flags) || parent || user_data)
return ERR_PTR(-EOPNOTSUPP);
return do_iommu_domain_alloc(type, dev, flags);
/* Allocate domain with v2 page table if IOMMU supports PASID. */
if (flags & IOMMU_HWPT_ALLOC_PASID) {
if (!amd_iommu_pasid_supported())
return ERR_PTR(-EOPNOTSUPP);
return do_iommu_domain_alloc(type, dev, flags, AMD_IOMMU_V2);
}
/* Allocate domain with v1 page table for dirty tracking */
if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) {
if (iommu && amd_iommu_hd_support(iommu)) {
return do_iommu_domain_alloc(type, dev,
flags, AMD_IOMMU_V1);
}
return ERR_PTR(-EOPNOTSUPP);
}
/* If nothing specific is required use the kernel commandline default */
return do_iommu_domain_alloc(type, dev, 0, amd_iommu_pgtable);
}
void amd_iommu_domain_free(struct iommu_domain *dom)
@ -2444,6 +2479,25 @@ static struct iommu_domain blocked_domain = {
}
};
static struct protection_domain identity_domain;
static const struct iommu_domain_ops identity_domain_ops = {
.attach_dev = amd_iommu_attach_device,
};
void amd_iommu_init_identity_domain(void)
{
struct iommu_domain *domain = &identity_domain.domain;
domain->type = IOMMU_DOMAIN_IDENTITY;
domain->ops = &identity_domain_ops;
domain->owner = &amd_iommu_ops;
identity_domain.id = domain_id_alloc();
protection_domain_init(&identity_domain, NUMA_NO_NODE);
}
static int amd_iommu_attach_device(struct iommu_domain *dom,
struct device *dev)
{
@ -2842,6 +2896,7 @@ static int amd_iommu_dev_disable_feature(struct device *dev,
const struct iommu_ops amd_iommu_ops = {
.capable = amd_iommu_capable,
.blocked_domain = &blocked_domain,
.identity_domain = &identity_domain.domain,
.domain_alloc = amd_iommu_domain_alloc,
.domain_alloc_user = amd_iommu_domain_alloc_user,
.domain_alloc_sva = amd_iommu_domain_alloc_sva,

6
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
View File

@ -3084,7 +3084,8 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
const struct iommu_user_data *user_data)
{
struct arm_smmu_master *master = dev_iommu_priv_get(dev);
const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
IOMMU_HWPT_ALLOC_PASID;
struct arm_smmu_domain *smmu_domain;
int ret;
@ -3093,6 +3094,9 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
if (parent || user_data)
return ERR_PTR(-EOPNOTSUPP);
if (flags & IOMMU_HWPT_ALLOC_PASID)
return arm_smmu_domain_alloc_paging(dev);
smmu_domain = arm_smmu_domain_alloc();
if (IS_ERR(smmu_domain))
return ERR_CAST(smmu_domain);

7
drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
View File

@ -509,7 +509,8 @@ static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
snprintf(name, 16, "vcmdq%u", vcmdq->idx);
q->llq.max_n_shift = VCMDQ_LOG2SIZE_MAX;
/* Queue size, capped to ensure natural alignment */
q->llq.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT, VCMDQ_LOG2SIZE_MAX);
/* Use the common helper to init the VCMDQ, and then... */
ret = arm_smmu_init_one_queue(smmu, q, vcmdq->page0,
@ -800,7 +801,9 @@ out_fallback:
return 0;
}
struct dentry *cmdqv_debugfs_dir;
#ifdef CONFIG_IOMMU_DEBUGFS
static struct dentry *cmdqv_debugfs_dir;
#endif
static struct arm_smmu_device *
__tegra241_cmdqv_probe(struct arm_smmu_device *smmu, struct resource *res,

11
drivers/iommu/arm/arm-smmu/arm-smmu.c
View File

@ -1437,6 +1437,17 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
goto out_free;
} else {
smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
/*
* Defer probe if the relevant SMMU instance hasn't finished
* probing yet. This is a fragile hack and we'd ideally
* avoid this race in the core code. Until that's ironed
* out, however, this is the most pragmatic option on the
* table.
*/
if (!smmu)
return ERR_PTR(dev_err_probe(dev, -EPROBE_DEFER,
"smmu dev has not bound yet\n"));
}
ret = -EINVAL;

149
drivers/iommu/io-pgtable-arm-v7s.c
View File

@ -166,7 +166,6 @@ struct arm_v7s_io_pgtable {
arm_v7s_iopte *pgd;
struct kmem_cache *l2_tables;
spinlock_t split_lock;
};
static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl);
@ -363,25 +362,6 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
return pte;
}
static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl)
{
int prot = IOMMU_READ;
arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
if (!(attr & ARM_V7S_PTE_AP_RDONLY))
prot |= IOMMU_WRITE;
if (!(attr & ARM_V7S_PTE_AP_UNPRIV))
prot |= IOMMU_PRIV;
if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
prot |= IOMMU_MMIO;
else if (pte & ARM_V7S_ATTR_C)
prot |= IOMMU_CACHE;
if (pte & ARM_V7S_ATTR_XN(lvl))
prot |= IOMMU_NOEXEC;
return prot;
}
static arm_v7s_iopte arm_v7s_pte_to_cont(arm_v7s_iopte pte, int lvl)
{
if (lvl == 1) {
@ -398,23 +378,6 @@ static arm_v7s_iopte arm_v7s_pte_to_cont(arm_v7s_iopte pte, int lvl)
return pte;
}
static arm_v7s_iopte arm_v7s_cont_to_pte(arm_v7s_iopte pte, int lvl)
{
if (lvl == 1) {
pte &= ~ARM_V7S_CONT_SECTION;
} else if (lvl == 2) {
arm_v7s_iopte xn = pte & BIT(ARM_V7S_CONT_PAGE_XN_SHIFT);
arm_v7s_iopte tex = pte & (ARM_V7S_CONT_PAGE_TEX_MASK <<
ARM_V7S_CONT_PAGE_TEX_SHIFT);
pte ^= xn | tex | ARM_V7S_PTE_TYPE_CONT_PAGE;
pte |= (xn >> ARM_V7S_CONT_PAGE_XN_SHIFT) |
(tex >> ARM_V7S_CONT_PAGE_TEX_SHIFT) |
ARM_V7S_PTE_TYPE_PAGE;
}
return pte;
}
static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
{
if (lvl == 1 && !ARM_V7S_PTE_IS_TABLE(pte, lvl))
@ -591,77 +554,6 @@ static void arm_v7s_free_pgtable(struct io_pgtable *iop)
kfree(data);
}
static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
unsigned long iova, int idx, int lvl,
arm_v7s_iopte *ptep)
{
struct io_pgtable *iop = &data->iop;
arm_v7s_iopte pte;
size_t size = ARM_V7S_BLOCK_SIZE(lvl);
int i;
/* Check that we didn't lose a race to get the lock */
pte = *ptep;
if (!arm_v7s_pte_is_cont(pte, lvl))
return pte;
ptep -= idx & (ARM_V7S_CONT_PAGES - 1);
pte = arm_v7s_cont_to_pte(pte, lvl);
for (i = 0; i < ARM_V7S_CONT_PAGES; i++)
ptep[i] = pte + i * size;
__arm_v7s_pte_sync(ptep, ARM_V7S_CONT_PAGES, &iop->cfg);
size *= ARM_V7S_CONT_PAGES;
io_pgtable_tlb_flush_walk(iop, iova, size, size);
return pte;
}
static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size,
arm_v7s_iopte blk_pte,
arm_v7s_iopte *ptep)
{
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_v7s_iopte pte, *tablep;
int i, unmap_idx, num_entries, num_ptes;
tablep = __arm_v7s_alloc_table(2, GFP_ATOMIC, data);
if (!tablep)
return 0; /* Bytes unmapped */
num_ptes = ARM_V7S_PTES_PER_LVL(2, cfg);
num_entries = size >> ARM_V7S_LVL_SHIFT(2);
unmap_idx = ARM_V7S_LVL_IDX(iova, 2, cfg);
pte = arm_v7s_prot_to_pte(arm_v7s_pte_to_prot(blk_pte, 1), 2, cfg);
if (num_entries > 1)
pte = arm_v7s_pte_to_cont(pte, 2);
for (i = 0; i < num_ptes; i += num_entries, pte += size) {
/* Unmap! */
if (i == unmap_idx)
continue;
__arm_v7s_set_pte(&tablep[i], pte, num_entries, cfg);
}
pte = arm_v7s_install_table(tablep, ptep, blk_pte, cfg);
if (pte != blk_pte) {
__arm_v7s_free_table(tablep, 2, data);
if (!ARM_V7S_PTE_IS_TABLE(pte, 1))
return 0;
tablep = iopte_deref(pte, 1, data);
return __arm_v7s_unmap(data, gather, iova, size, 2, tablep);
}
io_pgtable_tlb_add_page(&data->iop, gather, iova, size);
return size;
}
static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size, int lvl,
@ -694,11 +586,8 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
* case in a lock for the sake of correctness and be done with it.
*/
if (num_entries <= 1 && arm_v7s_pte_is_cont(pte[0], lvl)) {
unsigned long flags;
spin_lock_irqsave(&data->split_lock, flags);
pte[0] = arm_v7s_split_cont(data, iova, idx, lvl, ptep);
spin_unlock_irqrestore(&data->split_lock, flags);
WARN_ONCE(true, "Unmap of a partial large IOPTE is not allowed");
return 0;
}
/* If the size matches this level, we're in the right place */
@ -721,12 +610,8 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
}
return size;
} else if (lvl == 1 && !ARM_V7S_PTE_IS_TABLE(pte[0], lvl)) {
/*
* Insert a table at the next level to map the old region,
* minus the part we want to unmap
*/
return arm_v7s_split_blk_unmap(data, gather, iova, size, pte[0],
ptep);
WARN_ONCE(true, "Unmap of a partial large IOPTE is not allowed");
return 0;
}
/* Keep on walkin' */
@ -811,8 +696,6 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
if (!data)
return NULL;
spin_lock_init(&data->split_lock);
/*
* ARM_MTK_TTBR_EXT extend the translation table base support larger
* memory address.
@ -936,8 +819,8 @@ static int __init arm_v7s_do_selftests(void)
.quirks = IO_PGTABLE_QUIRK_ARM_NS,
.pgsize_bitmap = SZ_4K | SZ_64K | SZ_1M | SZ_16M,
};
unsigned int iova, size, iova_start;
unsigned int i, loopnr = 0;
unsigned int iova, size;
unsigned int i;
size_t mapped;
selftest_running = true;
@ -985,26 +868,6 @@ static int __init arm_v7s_do_selftests(void)
return __FAIL(ops);
iova += SZ_16M;
loopnr++;
}
/* Partial unmap */
i = 1;
size = 1UL << __ffs(cfg.pgsize_bitmap);
while (i < loopnr) {
iova_start = i * SZ_16M;
if (ops->unmap_pages(ops, iova_start + size, size, 1, NULL) != size)
return __FAIL(ops);
/* Remap of partial unmap */
if (ops->map_pages(ops, iova_start + size, size, size, 1,
IOMMU_READ, GFP_KERNEL, &mapped))
return __FAIL(ops);
if (ops->iova_to_phys(ops, iova_start + size + 42)
!= (size + 42))
return __FAIL(ops);
i++;
}
/* Full unmap */

114
drivers/iommu/io-pgtable-arm.c
View File

@ -199,6 +199,18 @@ static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte,
return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4);
}
/*
* Convert an index returned by ARM_LPAE_PGD_IDX(), which can point into
* a concatenated PGD, into the maximum number of entries that can be
* mapped in the same table page.
*/
static inline int arm_lpae_max_entries(int i, struct arm_lpae_io_pgtable *data)
{
int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data);
return ptes_per_table - (i & (ptes_per_table - 1));
}
static bool selftest_running = false;
static dma_addr_t __arm_lpae_dma_addr(void *pages)
@ -390,7 +402,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
/* If we can install a leaf entry at this level, then do so */
if (size == block_size) {
max_entries = ARM_LPAE_PTES_PER_TABLE(data) - map_idx_start;
max_entries = arm_lpae_max_entries(map_idx_start, data);
num_entries = min_t(int, pgcount, max_entries);
ret = arm_lpae_init_pte(data, iova, paddr, prot, lvl, num_entries, ptep);
if (!ret)
@ -569,66 +581,6 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
kfree(data);
}
static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size,
arm_lpae_iopte blk_pte, int lvl,
arm_lpae_iopte *ptep, size_t pgcount)
{
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_lpae_iopte pte, *tablep;
phys_addr_t blk_paddr;
size_t tablesz = ARM_LPAE_GRANULE(data);
size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data);
int i, unmap_idx_start = -1, num_entries = 0, max_entries;
if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
return 0;
tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
if (!tablep)
return 0; /* Bytes unmapped */
if (size == split_sz) {
unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data);
max_entries = ptes_per_table - unmap_idx_start;
num_entries = min_t(int, pgcount, max_entries);
}
blk_paddr = iopte_to_paddr(blk_pte, data);
pte = iopte_prot(blk_pte);
for (i = 0; i < ptes_per_table; i++, blk_paddr += split_sz) {
/* Unmap! */
if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries))
continue;
__arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
}
pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
if (pte != blk_pte) {
__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
/*
* We may race against someone unmapping another part of this
* block, but anything else is invalid. We can't misinterpret
* a page entry here since we're never at the last level.
*/
if (iopte_type(pte) != ARM_LPAE_PTE_TYPE_TABLE)
return 0;
tablep = iopte_deref(pte, data);
} else if (unmap_idx_start >= 0) {
for (i = 0; i < num_entries; i++)
io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size);
return num_entries * size;
}
return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl, tablep);
}
static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
struct iommu_iotlb_gather *gather,
unsigned long iova, size_t size, size_t pgcount,
@ -650,7 +602,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
/* If the size matches this level, we're in the right place */
if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
max_entries = ARM_LPAE_PTES_PER_TABLE(data) - unmap_idx_start;
max_entries = arm_lpae_max_entries(unmap_idx_start, data);
num_entries = min_t(int, pgcount, max_entries);
/* Find and handle non-leaf entries */
@ -678,12 +630,8 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
return i * size;
} else if (iopte_leaf(pte, lvl, iop->fmt)) {
/*
* Insert a table at the next level to map the old region,
* minus the part we want to unmap
*/
return arm_lpae_split_blk_unmap(data, gather, iova, size, pte,
lvl + 1, ptep, pgcount);
WARN_ONCE(true, "Unmap of a partial large IOPTE is not allowed");
return 0;
}
/* Keep on walkin' */
@ -1347,19 +1295,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
iova += SZ_1G;
}
/* Partial unmap */
size = 1UL << __ffs(cfg->pgsize_bitmap);
if (ops->unmap_pages(ops, SZ_1G + size, size, 1, NULL) != size)
return __FAIL(ops, i);
/* Remap of partial unmap */
if (ops->map_pages(ops, SZ_1G + size, size, size, 1,
IOMMU_READ, GFP_KERNEL, &mapped))
return __FAIL(ops, i);
if (ops->iova_to_phys(ops, SZ_1G + size + 42) != (size + 42))
return __FAIL(ops, i);
/* Full unmap */
iova = 0;
for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) {
@ -1382,6 +1317,23 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg)
iova += SZ_1G;
}
/*
* Map/unmap the last largest supported page of the IAS, this can
* trigger corner cases in the concatednated page tables.
*/
mapped = 0;
size = 1UL << __fls(cfg->pgsize_bitmap);
iova = (1UL << cfg->ias) - size;
if (ops->map_pages(ops, iova, iova, size, 1,
IOMMU_READ | IOMMU_WRITE |
IOMMU_NOEXEC | IOMMU_CACHE,
GFP_KERNEL, &mapped))
return __FAIL(ops, i);
if (mapped != size)
return __FAIL(ops, i);
if (ops->unmap_pages(ops, iova, size, 1, NULL) != size)
return __FAIL(ops, i);
free_io_pgtable_ops(ops);
}

2
drivers/iommu/iommu-sysfs.c
View File

@ -34,7 +34,7 @@ static void release_device(struct device *dev)
kfree(dev);
}
static struct class iommu_class = {
static const struct class iommu_class = {
.name = "iommu",
.dev_release = release_device,
.dev_groups = dev_groups,

270
drivers/iommu/iommu.c
View File

@ -32,6 +32,7 @@
#include <trace/events/iommu.h>
#include <linux/sched/mm.h>
#include <linux/msi.h>
#include <uapi/linux/iommufd.h>
#include "dma-iommu.h"
#include "iommu-priv.h"
@ -90,15 +91,17 @@ static const char * const iommu_group_resv_type_string[] = {
#define IOMMU_CMD_LINE_DMA_API BIT(0)
#define IOMMU_CMD_LINE_STRICT BIT(1)
static int bus_iommu_probe(const struct bus_type *bus);
static int iommu_bus_notifier(struct notifier_block *nb,
unsigned long action, void *data);
static void iommu_release_device(struct device *dev);
static struct iommu_domain *
__iommu_group_domain_alloc(struct iommu_group *group, unsigned int type);
static int __iommu_attach_device(struct iommu_domain *domain,
struct device *dev);
static int __iommu_attach_group(struct iommu_domain *domain,
struct iommu_group *group);
static struct iommu_domain *__iommu_paging_domain_alloc_flags(struct device *dev,
unsigned int type,
unsigned int flags);
enum {
IOMMU_SET_DOMAIN_MUST_SUCCEED = 1 << 0,
@ -133,6 +136,8 @@ static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
struct device *dev);
static void __iommu_group_free_device(struct iommu_group *group,
struct group_device *grp_dev);
static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
const struct iommu_ops *ops);
#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \
struct iommu_group_attribute iommu_group_attr_##_name = \
@ -1141,10 +1146,6 @@ map_end:
}
}
if (!list_empty(&mappings) && iommu_is_dma_domain(domain))
iommu_flush_iotlb_all(domain);
out:
iommu_put_resv_regions(dev, &mappings);
@ -1586,12 +1587,59 @@ struct iommu_group *fsl_mc_device_group(struct device *dev)
}
EXPORT_SYMBOL_GPL(fsl_mc_device_group);
static struct iommu_domain *__iommu_alloc_identity_domain(struct device *dev)
{
const struct iommu_ops *ops = dev_iommu_ops(dev);
struct iommu_domain *domain;
if (ops->identity_domain)
return ops->identity_domain;
/* Older drivers create the identity domain via ops->domain_alloc() */
if (!ops->domain_alloc)
return ERR_PTR(-EOPNOTSUPP);
domain = ops->domain_alloc(IOMMU_DOMAIN_IDENTITY);
if (IS_ERR(domain))
return domain;
if (!domain)
return ERR_PTR(-ENOMEM);
iommu_domain_init(domain, IOMMU_DOMAIN_IDENTITY, ops);
return domain;
}
static struct iommu_domain *
__iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
{
struct device *dev = iommu_group_first_dev(group);
struct iommu_domain *dom;
if (group->default_domain && group->default_domain->type == req_type)
return group->default_domain;
return __iommu_group_domain_alloc(group, req_type);
/*
* When allocating the DMA API domain assume that the driver is going to
* use PASID and make sure the RID's domain is PASID compatible.
*/
if (req_type & __IOMMU_DOMAIN_PAGING) {
dom = __iommu_paging_domain_alloc_flags(dev, req_type,
dev->iommu->max_pasids ? IOMMU_HWPT_ALLOC_PASID : 0);
/*
* If driver does not support PASID feature then
* try to allocate non-PASID domain
*/
if (PTR_ERR(dom) == -EOPNOTSUPP)
dom = __iommu_paging_domain_alloc_flags(dev, req_type, 0);
return dom;
}
if (req_type == IOMMU_DOMAIN_IDENTITY)
return __iommu_alloc_identity_domain(dev);
return ERR_PTR(-EINVAL);
}
/*
@ -1795,7 +1843,7 @@ static void iommu_group_do_probe_finalize(struct device *dev)
ops->probe_finalize(dev);
}
int bus_iommu_probe(const struct bus_type *bus)
static int bus_iommu_probe(const struct bus_type *bus)
{
struct iommu_group *group, *next;
LIST_HEAD(group_list);
@ -1840,31 +1888,6 @@ int bus_iommu_probe(const struct bus_type *bus)
return 0;
}
/**
* iommu_present() - make platform-specific assumptions about an IOMMU
* @bus: bus to check
*
* Do not use this function. You want device_iommu_mapped() instead.
*
* Return: true if some IOMMU is present and aware of devices on the given bus;
* in general it may not be the only IOMMU, and it may not have anything to do
* with whatever device you are ultimately interested in.
*/
bool iommu_present(const struct bus_type *bus)
{
bool ret = false;
for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
if (iommu_buses[i] == bus) {
spin_lock(&iommu_device_lock);
ret = !list_empty(&iommu_device_list);
spin_unlock(&iommu_device_lock);
}
}
return ret;
}
EXPORT_SYMBOL_GPL(iommu_present);
/**
* device_iommu_capable() - check for a general IOMMU capability
* @dev: device to which the capability would be relevant, if available
@ -1934,117 +1957,67 @@ void iommu_set_fault_handler(struct iommu_domain *domain,
}
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
struct device *dev,
unsigned int type)
static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
const struct iommu_ops *ops)
{
struct iommu_domain *domain;
unsigned int alloc_type = type & IOMMU_DOMAIN_ALLOC_FLAGS;
if (alloc_type == IOMMU_DOMAIN_IDENTITY && ops->identity_domain)
return ops->identity_domain;
else if (alloc_type == IOMMU_DOMAIN_BLOCKED && ops->blocked_domain)
return ops->blocked_domain;
else if (type & __IOMMU_DOMAIN_PAGING && ops->domain_alloc_paging)
domain = ops->domain_alloc_paging(dev);
else if (ops->domain_alloc)
domain = ops->domain_alloc(alloc_type);
else
return ERR_PTR(-EOPNOTSUPP);
/*
* Many domain_alloc ops now return ERR_PTR, make things easier for the
* driver by accepting ERR_PTR from all domain_alloc ops instead of
* having two rules.
*/
if (IS_ERR(domain))
return domain;
if (!domain)
return ERR_PTR(-ENOMEM);
domain->type = type;
domain->owner = ops;
if (!domain->ops)
domain->ops = ops->default_domain_ops;
/*
* If not already set, assume all sizes by default; the driver
* may override this later
*/
if (!domain->pgsize_bitmap)
domain->pgsize_bitmap = ops->pgsize_bitmap;
if (!domain->ops)
domain->ops = ops->default_domain_ops;
if (iommu_is_dma_domain(domain)) {
int rc;
rc = iommu_get_dma_cookie(domain);
if (rc) {
iommu_domain_free(domain);
return ERR_PTR(rc);
}
}
return domain;
}
static struct iommu_domain *
__iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
__iommu_paging_domain_alloc_flags(struct device *dev, unsigned int type,
unsigned int flags)
{
struct device *dev = iommu_group_first_dev(group);
return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
}
static int __iommu_domain_alloc_dev(struct device *dev, void *data)
{
const struct iommu_ops **ops = data;
if (!dev_has_iommu(dev))
return 0;
if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
"Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
dev_bus_name(dev)))
return -EBUSY;
*ops = dev_iommu_ops(dev);
return 0;
}
/*
* The iommu ops in bus has been retired. Do not use this interface in
* new drivers.
*/
struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
{
const struct iommu_ops *ops = NULL;
int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
const struct iommu_ops *ops;
struct iommu_domain *domain;
if (err || !ops)
return NULL;
domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
if (IS_ERR(domain))
return NULL;
return domain;
}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);
/**
* iommu_paging_domain_alloc() - Allocate a paging domain
* @dev: device for which the domain is allocated
*
* Allocate a paging domain which will be managed by a kernel driver. Return
* allocated domain if successful, or a ERR pointer for failure.
*/
struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
{
if (!dev_has_iommu(dev))
return ERR_PTR(-ENODEV);
return __iommu_domain_alloc(dev_iommu_ops(dev), dev, IOMMU_DOMAIN_UNMANAGED);
ops = dev_iommu_ops(dev);
if (ops->domain_alloc_paging && !flags)
domain = ops->domain_alloc_paging(dev);
else if (ops->domain_alloc_user)
domain = ops->domain_alloc_user(dev, flags, NULL, NULL);
else if (ops->domain_alloc && !flags)
domain = ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
else
return ERR_PTR(-EOPNOTSUPP);
if (IS_ERR(domain))
return domain;
if (!domain)
return ERR_PTR(-ENOMEM);
iommu_domain_init(domain, type, ops);
return domain;
}
EXPORT_SYMBOL_GPL(iommu_paging_domain_alloc);
/**
* iommu_paging_domain_alloc_flags() - Allocate a paging domain
* @dev: device for which the domain is allocated
* @flags: Bitmap of iommufd_hwpt_alloc_flags
*
* Allocate a paging domain which will be managed by a kernel driver. Return
* allocated domain if successful, or an ERR pointer for failure.
*/
struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev,
unsigned int flags)
{
return __iommu_paging_domain_alloc_flags(dev,
IOMMU_DOMAIN_UNMANAGED, flags);
}
EXPORT_SYMBOL_GPL(iommu_paging_domain_alloc_flags);
void iommu_domain_free(struct iommu_domain *domain)
{
@ -2216,8 +2189,8 @@ EXPORT_SYMBOL_GPL(iommu_attach_group);
/**
* iommu_group_replace_domain - replace the domain that a group is attached to
* @new_domain: new IOMMU domain to replace with
* @group: IOMMU group that will be attached to the new domain
* @new_domain: new IOMMU domain to replace with
*
* This API allows the group to switch domains without being forced to go to
* the blocking domain in-between.
@ -2586,6 +2559,20 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
return unmapped;
}
/**
* iommu_unmap() - Remove mappings from a range of IOVA
* @domain: Domain to manipulate
* @iova: IO virtual address to start
* @size: Length of the range starting from @iova
*
* iommu_unmap() will remove a translation created by iommu_map(). It cannot
* subdivide a mapping created by iommu_map(), so it should be called with IOVA
* ranges that match what was passed to iommu_map(). The range can aggregate
* contiguous iommu_map() calls so long as no individual range is split.
*
* Returns: Number of bytes of IOVA unmapped. iova + res will be the point
* unmapping stopped.
*/
size_t iommu_unmap(struct iommu_domain *domain,
unsigned long iova, size_t size)
{
@ -2965,6 +2952,14 @@ static int iommu_setup_default_domain(struct iommu_group *group,
if (group->default_domain == dom)
return 0;
if (iommu_is_dma_domain(dom)) {
ret = iommu_get_dma_cookie(dom);
if (ret) {
iommu_domain_free(dom);
return ret;
}
}
/*
* IOMMU_RESV_DIRECT and IOMMU_RESV_DIRECT_RELAXABLE regions must be
* mapped before their device is attached, in order to guarantee
@ -3152,22 +3147,25 @@ void iommu_device_unuse_default_domain(struct device *dev)
static int __iommu_group_alloc_blocking_domain(struct iommu_group *group)
{
struct device *dev = iommu_group_first_dev(group);
const struct iommu_ops *ops = dev_iommu_ops(dev);
struct iommu_domain *domain;
if (group->blocking_domain)
return 0;
domain = __iommu_group_domain_alloc(group, IOMMU_DOMAIN_BLOCKED);
if (IS_ERR(domain)) {
/*
* For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED
* create an empty domain instead.
*/
domain = __iommu_group_domain_alloc(group,
IOMMU_DOMAIN_UNMANAGED);
if (IS_ERR(domain))
return PTR_ERR(domain);
if (ops->blocked_domain) {
group->blocking_domain = ops->blocked_domain;
return 0;
}
/*
* For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED create an
* empty PAGING domain instead.
*/
domain = iommu_paging_domain_alloc(dev);
if (IS_ERR(domain))
return PTR_ERR(domain);
group->blocking_domain = domain;
return 0;
}

2
drivers/iommu/iova.c
View File

@ -506,7 +506,7 @@ __adjust_overlap_range(struct iova *iova,
* reserve_iova - reserves an iova in the given range
* @iovad: - iova domain pointer
* @pfn_lo: - lower page frame address
* @pfn_hi:- higher pfn adderss
* @pfn_hi:- higher pfn address
* This function allocates reserves the address range from pfn_lo to pfn_hi so
* that this address is not dished out as part of alloc_iova.
*/

2
drivers/iommu/mtk_iommu.c
View File

@ -1599,7 +1599,7 @@ static const unsigned int mt8186_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK
static const struct mtk_iommu_plat_data mt8186_data_mm = {
.m4u_plat = M4U_MT8186,
.flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM | PGTABLE_PA_35_EN,
.larbid_remap = {{0}, {1, MTK_INVALID_LARBID, 8}, {4}, {7}, {2}, {9, 11, 19, 20},
{MTK_INVALID_LARBID, 14, 16},
{MTK_INVALID_LARBID, 13, MTK_INVALID_LARBID, 17}},

26
drivers/iommu/omap-iommu.c
View File

@ -1230,25 +1230,24 @@ static int omap_iommu_probe(struct platform_device *pdev)
if (err)
return err;
err = iommu_device_register(&obj->iommu, &omap_iommu_ops, &pdev->dev);
if (err)
goto out_sysfs;
obj->has_iommu_driver = true;
}
err = iommu_device_register(&obj->iommu, &omap_iommu_ops, &pdev->dev);
if (err)
goto out_sysfs;
pm_runtime_enable(obj->dev);
omap_iommu_debugfs_add(obj);
dev_info(&pdev->dev, "%s registered\n", obj->name);
/* Re-probe bus to probe device attached to this IOMMU */
bus_iommu_probe(&platform_bus_type);
return 0;
out_sysfs:
iommu_device_sysfs_remove(&obj->iommu);
if (obj->has_iommu_driver)
iommu_device_sysfs_remove(&obj->iommu);
return err;
}
@ -1256,10 +1255,10 @@ static void omap_iommu_remove(struct platform_device *pdev)
{
struct omap_iommu *obj = platform_get_drvdata(pdev);
if (obj->has_iommu_driver) {
if (obj->has_iommu_driver)
iommu_device_sysfs_remove(&obj->iommu);
iommu_device_unregister(&obj->iommu);
}
iommu_device_unregister(&obj->iommu);
omap_iommu_debugfs_remove(obj);
@ -1723,12 +1722,19 @@ static void omap_iommu_release_device(struct device *dev)
}
static int omap_iommu_of_xlate(struct device *dev, const struct of_phandle_args *args)
{
/* TODO: collect args->np to save re-parsing in probe above */
return 0;
}
static const struct iommu_ops omap_iommu_ops = {
.identity_domain = &omap_iommu_identity_domain,
.domain_alloc_paging = omap_iommu_domain_alloc_paging,
.probe_device = omap_iommu_probe_device,
.release_device = omap_iommu_release_device,
.device_group = generic_single_device_group,
.of_xlate = omap_iommu_of_xlate,
.pgsize_bitmap = OMAP_IOMMU_PGSIZES,
.default_domain_ops = &(const struct iommu_domain_ops) {
.attach_dev = omap_iommu_attach_dev,

20
drivers/iommu/riscv/Kconfig Normal file
View File

@ -0,0 +1,20 @@
# SPDX-License-Identifier: GPL-2.0-only
# RISC-V IOMMU support
config RISCV_IOMMU
bool "RISC-V IOMMU Support"
depends on RISCV && 64BIT
default y
select IOMMU_API
help
Support for implementations of the RISC-V IOMMU architecture that
complements the RISC-V MMU capabilities, providing similar address
translation and protection functions for accesses from I/O devices.
Say Y here if your SoC includes an IOMMU device implementing
the RISC-V IOMMU architecture.
config RISCV_IOMMU_PCI
def_bool y if RISCV_IOMMU && PCI_MSI
help
Support for the PCIe implementation of RISC-V IOMMU architecture.

3
drivers/iommu/riscv/Makefile Normal file
View File

@ -0,0 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_RISCV_IOMMU) += iommu.o iommu-platform.o
obj-$(CONFIG_RISCV_IOMMU_PCI) += iommu-pci.o

784
drivers/iommu/riscv/iommu-bits.h Normal file
View File

@ -0,0 +1,784 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright © 2022-2024 Rivos Inc.
* Copyright © 2023 FORTH-ICS/CARV
* Copyright © 2023 RISC-V IOMMU Task Group
*
* RISC-V IOMMU - Register Layout and Data Structures.
*
* Based on the 'RISC-V IOMMU Architecture Specification', Version 1.0
* Published at https://github.com/riscv-non-isa/riscv-iommu
*
*/
#ifndef _RISCV_IOMMU_BITS_H_
#define _RISCV_IOMMU_BITS_H_
#include <linux/types.h>
#include <linux/bitfield.h>
#include <linux/bits.h>
/*
* Chapter 5: Memory Mapped register interface
*/
/* Common field positions */
#define RISCV_IOMMU_PPN_FIELD GENMASK_ULL(53, 10)
#define RISCV_IOMMU_QUEUE_LOG2SZ_FIELD GENMASK_ULL(4, 0)
#define RISCV_IOMMU_QUEUE_INDEX_FIELD GENMASK_ULL(31, 0)
#define RISCV_IOMMU_QUEUE_ENABLE BIT(0)
#define RISCV_IOMMU_QUEUE_INTR_ENABLE BIT(1)
#define RISCV_IOMMU_QUEUE_MEM_FAULT BIT(8)
#define RISCV_IOMMU_QUEUE_OVERFLOW BIT(9)
#define RISCV_IOMMU_QUEUE_ACTIVE BIT(16)
#define RISCV_IOMMU_QUEUE_BUSY BIT(17)
#define RISCV_IOMMU_ATP_PPN_FIELD GENMASK_ULL(43, 0)
#define RISCV_IOMMU_ATP_MODE_FIELD GENMASK_ULL(63, 60)
/* 5.3 IOMMU Capabilities (64bits) */
#define RISCV_IOMMU_REG_CAPABILITIES 0x0000
#define RISCV_IOMMU_CAPABILITIES_VERSION GENMASK_ULL(7, 0)
#define RISCV_IOMMU_CAPABILITIES_SV32 BIT_ULL(8)
#define RISCV_IOMMU_CAPABILITIES_SV39 BIT_ULL(9)
#define RISCV_IOMMU_CAPABILITIES_SV48 BIT_ULL(10)
#define RISCV_IOMMU_CAPABILITIES_SV57 BIT_ULL(11)
#define RISCV_IOMMU_CAPABILITIES_SVPBMT BIT_ULL(15)
#define RISCV_IOMMU_CAPABILITIES_SV32X4 BIT_ULL(16)
#define RISCV_IOMMU_CAPABILITIES_SV39X4 BIT_ULL(17)
#define RISCV_IOMMU_CAPABILITIES_SV48X4 BIT_ULL(18)
#define RISCV_IOMMU_CAPABILITIES_SV57X4 BIT_ULL(19)
#define RISCV_IOMMU_CAPABILITIES_AMO_MRIF BIT_ULL(21)
#define RISCV_IOMMU_CAPABILITIES_MSI_FLAT BIT_ULL(22)
#define RISCV_IOMMU_CAPABILITIES_MSI_MRIF BIT_ULL(23)
#define RISCV_IOMMU_CAPABILITIES_AMO_HWAD BIT_ULL(24)
#define RISCV_IOMMU_CAPABILITIES_ATS BIT_ULL(25)
#define RISCV_IOMMU_CAPABILITIES_T2GPA BIT_ULL(26)
#define RISCV_IOMMU_CAPABILITIES_END BIT_ULL(27)
#define RISCV_IOMMU_CAPABILITIES_IGS GENMASK_ULL(29, 28)
#define RISCV_IOMMU_CAPABILITIES_HPM BIT_ULL(30)
#define RISCV_IOMMU_CAPABILITIES_DBG BIT_ULL(31)
#define RISCV_IOMMU_CAPABILITIES_PAS GENMASK_ULL(37, 32)
#define RISCV_IOMMU_CAPABILITIES_PD8 BIT_ULL(38)
#define RISCV_IOMMU_CAPABILITIES_PD17 BIT_ULL(39)
#define RISCV_IOMMU_CAPABILITIES_PD20 BIT_ULL(40)
/**
* enum riscv_iommu_igs_settings - Interrupt Generation Support Settings
* @RISCV_IOMMU_CAPABILITIES_IGS_MSI: IOMMU supports only MSI generation
* @RISCV_IOMMU_CAPABILITIES_IGS_WSI: IOMMU supports only Wired-Signaled interrupt
* @RISCV_IOMMU_CAPABILITIES_IGS_BOTH: IOMMU supports both MSI and WSI generation
* @RISCV_IOMMU_CAPABILITIES_IGS_RSRV: Reserved for standard use
*/
enum riscv_iommu_igs_settings {
RISCV_IOMMU_CAPABILITIES_IGS_MSI = 0,
RISCV_IOMMU_CAPABILITIES_IGS_WSI = 1,
RISCV_IOMMU_CAPABILITIES_IGS_BOTH = 2,
RISCV_IOMMU_CAPABILITIES_IGS_RSRV = 3
};
/* 5.4 Features control register (32bits) */
#define RISCV_IOMMU_REG_FCTL 0x0008
#define RISCV_IOMMU_FCTL_BE BIT(0)
#define RISCV_IOMMU_FCTL_WSI BIT(1)
#define RISCV_IOMMU_FCTL_GXL BIT(2)
/* 5.5 Device-directory-table pointer (64bits) */
#define RISCV_IOMMU_REG_DDTP 0x0010
#define RISCV_IOMMU_DDTP_IOMMU_MODE GENMASK_ULL(3, 0)
#define RISCV_IOMMU_DDTP_BUSY BIT_ULL(4)
#define RISCV_IOMMU_DDTP_PPN RISCV_IOMMU_PPN_FIELD
/**
* enum riscv_iommu_ddtp_modes - IOMMU translation modes
* @RISCV_IOMMU_DDTP_IOMMU_MODE_OFF: No inbound transactions allowed
* @RISCV_IOMMU_DDTP_IOMMU_MODE_BARE: Pass-through mode
* @RISCV_IOMMU_DDTP_IOMMU_MODE_1LVL: One-level DDT
* @RISCV_IOMMU_DDTP_IOMMU_MODE_2LVL: Two-level DDT
* @RISCV_IOMMU_DDTP_IOMMU_MODE_3LVL: Three-level DDT
* @RISCV_IOMMU_DDTP_IOMMU_MODE_MAX: Max value allowed by specification
*/
enum riscv_iommu_ddtp_modes {
RISCV_IOMMU_DDTP_IOMMU_MODE_OFF = 0,
RISCV_IOMMU_DDTP_IOMMU_MODE_BARE = 1,
RISCV_IOMMU_DDTP_IOMMU_MODE_1LVL = 2,
RISCV_IOMMU_DDTP_IOMMU_MODE_2LVL = 3,
RISCV_IOMMU_DDTP_IOMMU_MODE_3LVL = 4,
RISCV_IOMMU_DDTP_IOMMU_MODE_MAX = 4
};
/* 5.6 Command Queue Base (64bits) */
#define RISCV_IOMMU_REG_CQB 0x0018
#define RISCV_IOMMU_CQB_ENTRIES RISCV_IOMMU_QUEUE_LOG2SZ_FIELD
#define RISCV_IOMMU_CQB_PPN RISCV_IOMMU_PPN_FIELD
/* 5.7 Command Queue head (32bits) */
#define RISCV_IOMMU_REG_CQH 0x0020
#define RISCV_IOMMU_CQH_INDEX RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.8 Command Queue tail (32bits) */
#define RISCV_IOMMU_REG_CQT 0x0024
#define RISCV_IOMMU_CQT_INDEX RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.9 Fault Queue Base (64bits) */
#define RISCV_IOMMU_REG_FQB 0x0028
#define RISCV_IOMMU_FQB_ENTRIES RISCV_IOMMU_QUEUE_LOG2SZ_FIELD
#define RISCV_IOMMU_FQB_PPN RISCV_IOMMU_PPN_FIELD
/* 5.10 Fault Queue Head (32bits) */
#define RISCV_IOMMU_REG_FQH 0x0030
#define RISCV_IOMMU_FQH_INDEX RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.11 Fault Queue tail (32bits) */
#define RISCV_IOMMU_REG_FQT 0x0034
#define RISCV_IOMMU_FQT_INDEX RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.12 Page Request Queue base (64bits) */
#define RISCV_IOMMU_REG_PQB 0x0038
#define RISCV_IOMMU_PQB_ENTRIES RISCV_IOMMU_QUEUE_LOG2SZ_FIELD
#define RISCV_IOMMU_PQB_PPN RISCV_IOMMU_PPN_FIELD
/* 5.13 Page Request Queue head (32bits) */
#define RISCV_IOMMU_REG_PQH 0x0040
#define RISCV_IOMMU_PQH_INDEX RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.14 Page Request Queue tail (32bits) */
#define RISCV_IOMMU_REG_PQT 0x0044
#define RISCV_IOMMU_PQT_INDEX_MASK RISCV_IOMMU_QUEUE_INDEX_FIELD
/* 5.15 Command Queue CSR (32bits) */
#define RISCV_IOMMU_REG_CQCSR 0x0048
#define RISCV_IOMMU_CQCSR_CQEN RISCV_IOMMU_QUEUE_ENABLE
#define RISCV_IOMMU_CQCSR_CIE RISCV_IOMMU_QUEUE_INTR_ENABLE
#define RISCV_IOMMU_CQCSR_CQMF RISCV_IOMMU_QUEUE_MEM_FAULT
#define RISCV_IOMMU_CQCSR_CMD_TO BIT(9)
#define RISCV_IOMMU_CQCSR_CMD_ILL BIT(10)
#define RISCV_IOMMU_CQCSR_FENCE_W_IP BIT(11)
#define RISCV_IOMMU_CQCSR_CQON RISCV_IOMMU_QUEUE_ACTIVE
#define RISCV_IOMMU_CQCSR_BUSY RISCV_IOMMU_QUEUE_BUSY
/* 5.16 Fault Queue CSR (32bits) */
#define RISCV_IOMMU_REG_FQCSR 0x004C
#define RISCV_IOMMU_FQCSR_FQEN RISCV_IOMMU_QUEUE_ENABLE
#define RISCV_IOMMU_FQCSR_FIE RISCV_IOMMU_QUEUE_INTR_ENABLE
#define RISCV_IOMMU_FQCSR_FQMF RISCV_IOMMU_QUEUE_MEM_FAULT
#define RISCV_IOMMU_FQCSR_FQOF RISCV_IOMMU_QUEUE_OVERFLOW
#define RISCV_IOMMU_FQCSR_FQON RISCV_IOMMU_QUEUE_ACTIVE
#define RISCV_IOMMU_FQCSR_BUSY RISCV_IOMMU_QUEUE_BUSY
/* 5.17 Page Request Queue CSR (32bits) */
#define RISCV_IOMMU_REG_PQCSR 0x0050
#define RISCV_IOMMU_PQCSR_PQEN RISCV_IOMMU_QUEUE_ENABLE
#define RISCV_IOMMU_PQCSR_PIE RISCV_IOMMU_QUEUE_INTR_ENABLE
#define RISCV_IOMMU_PQCSR_PQMF RISCV_IOMMU_QUEUE_MEM_FAULT
#define RISCV_IOMMU_PQCSR_PQOF RISCV_IOMMU_QUEUE_OVERFLOW
#define RISCV_IOMMU_PQCSR_PQON RISCV_IOMMU_QUEUE_ACTIVE
#define RISCV_IOMMU_PQCSR_BUSY RISCV_IOMMU_QUEUE_BUSY
/* 5.18 Interrupt Pending Status (32bits) */
#define RISCV_IOMMU_REG_IPSR 0x0054
#define RISCV_IOMMU_INTR_CQ 0
#define RISCV_IOMMU_INTR_FQ 1
#define RISCV_IOMMU_INTR_PM 2
#define RISCV_IOMMU_INTR_PQ 3
#define RISCV_IOMMU_INTR_COUNT 4
#define RISCV_IOMMU_IPSR_CIP BIT(RISCV_IOMMU_INTR_CQ)
#define RISCV_IOMMU_IPSR_FIP BIT(RISCV_IOMMU_INTR_FQ)
#define RISCV_IOMMU_IPSR_PMIP BIT(RISCV_IOMMU_INTR_PM)
#define RISCV_IOMMU_IPSR_PIP BIT(RISCV_IOMMU_INTR_PQ)
/* 5.19 Performance monitoring counter overflow status (32bits) */
#define RISCV_IOMMU_REG_IOCOUNTOVF 0x0058
#define RISCV_IOMMU_IOCOUNTOVF_CY BIT(0)
#define RISCV_IOMMU_IOCOUNTOVF_HPM GENMASK_ULL(31, 1)
/* 5.20 Performance monitoring counter inhibits (32bits) */
#define RISCV_IOMMU_REG_IOCOUNTINH 0x005C
#define RISCV_IOMMU_IOCOUNTINH_CY BIT(0)
#define RISCV_IOMMU_IOCOUNTINH_HPM GENMASK(31, 1)
/* 5.21 Performance monitoring cycles counter (64bits) */
#define RISCV_IOMMU_REG_IOHPMCYCLES 0x0060
#define RISCV_IOMMU_IOHPMCYCLES_COUNTER GENMASK_ULL(62, 0)
#define RISCV_IOMMU_IOHPMCYCLES_OF BIT_ULL(63)
/* 5.22 Performance monitoring event counters (31 * 64bits) */
#define RISCV_IOMMU_REG_IOHPMCTR_BASE 0x0068
#define RISCV_IOMMU_REG_IOHPMCTR(_n) (RISCV_IOMMU_REG_IOHPMCTR_BASE + ((_n) * 0x8))
/* 5.23 Performance monitoring event selectors (31 * 64bits) */
#define RISCV_IOMMU_REG_IOHPMEVT_BASE 0x0160
#define RISCV_IOMMU_REG_IOHPMEVT(_n) (RISCV_IOMMU_REG_IOHPMEVT_BASE + ((_n) * 0x8))
#define RISCV_IOMMU_IOHPMEVT_EVENTID GENMASK_ULL(14, 0)
#define RISCV_IOMMU_IOHPMEVT_DMASK BIT_ULL(15)
#define RISCV_IOMMU_IOHPMEVT_PID_PSCID GENMASK_ULL(35, 16)
#define RISCV_IOMMU_IOHPMEVT_DID_GSCID GENMASK_ULL(59, 36)
#define RISCV_IOMMU_IOHPMEVT_PV_PSCV BIT_ULL(60)
#define RISCV_IOMMU_IOHPMEVT_DV_GSCV BIT_ULL(61)
#define RISCV_IOMMU_IOHPMEVT_IDT BIT_ULL(62)
#define RISCV_IOMMU_IOHPMEVT_OF BIT_ULL(63)
/* Number of defined performance-monitoring event selectors */
#define RISCV_IOMMU_IOHPMEVT_CNT 31
/**
* enum riscv_iommu_hpmevent_id - Performance-monitoring event identifier
*
* @RISCV_IOMMU_HPMEVENT_INVALID: Invalid event, do not count
* @RISCV_IOMMU_HPMEVENT_URQ: Untranslated requests
* @RISCV_IOMMU_HPMEVENT_TRQ: Translated requests
* @RISCV_IOMMU_HPMEVENT_ATS_RQ: ATS translation requests
* @RISCV_IOMMU_HPMEVENT_TLB_MISS: TLB misses
* @RISCV_IOMMU_HPMEVENT_DD_WALK: Device directory walks
* @RISCV_IOMMU_HPMEVENT_PD_WALK: Process directory walks
* @RISCV_IOMMU_HPMEVENT_S_VS_WALKS: First-stage page table walks
* @RISCV_IOMMU_HPMEVENT_G_WALKS: Second-stage page table walks
* @RISCV_IOMMU_HPMEVENT_MAX: Value to denote maximum Event IDs
*/
enum riscv_iommu_hpmevent_id {
RISCV_IOMMU_HPMEVENT_INVALID = 0,
RISCV_IOMMU_HPMEVENT_URQ = 1,
RISCV_IOMMU_HPMEVENT_TRQ = 2,
RISCV_IOMMU_HPMEVENT_ATS_RQ = 3,
RISCV_IOMMU_HPMEVENT_TLB_MISS = 4,
RISCV_IOMMU_HPMEVENT_DD_WALK = 5,
RISCV_IOMMU_HPMEVENT_PD_WALK = 6,
RISCV_IOMMU_HPMEVENT_S_VS_WALKS = 7,
RISCV_IOMMU_HPMEVENT_G_WALKS = 8,
RISCV_IOMMU_HPMEVENT_MAX = 9
};
/* 5.24 Translation request IOVA (64bits) */
#define RISCV_IOMMU_REG_TR_REQ_IOVA 0x0258
#define RISCV_IOMMU_TR_REQ_IOVA_VPN GENMASK_ULL(63, 12)
/* 5.25 Translation request control (64bits) */
#define RISCV_IOMMU_REG_TR_REQ_CTL 0x0260
#define RISCV_IOMMU_TR_REQ_CTL_GO_BUSY BIT_ULL(0)
#define RISCV_IOMMU_TR_REQ_CTL_PRIV BIT_ULL(1)
#define RISCV_IOMMU_TR_REQ_CTL_EXE BIT_ULL(2)
#define RISCV_IOMMU_TR_REQ_CTL_NW BIT_ULL(3)
#define RISCV_IOMMU_TR_REQ_CTL_PID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_TR_REQ_CTL_PV BIT_ULL(32)
#define RISCV_IOMMU_TR_REQ_CTL_DID GENMASK_ULL(63, 40)
/* 5.26 Translation request response (64bits) */
#define RISCV_IOMMU_REG_TR_RESPONSE 0x0268
#define RISCV_IOMMU_TR_RESPONSE_FAULT BIT_ULL(0)
#define RISCV_IOMMU_TR_RESPONSE_PBMT GENMASK_ULL(8, 7)
#define RISCV_IOMMU_TR_RESPONSE_SZ BIT_ULL(9)
#define RISCV_IOMMU_TR_RESPONSE_PPN RISCV_IOMMU_PPN_FIELD
/* 5.27 Interrupt cause to vector (64bits) */
#define RISCV_IOMMU_REG_ICVEC 0x02F8
#define RISCV_IOMMU_ICVEC_CIV GENMASK_ULL(3, 0)
#define RISCV_IOMMU_ICVEC_FIV GENMASK_ULL(7, 4)
#define RISCV_IOMMU_ICVEC_PMIV GENMASK_ULL(11, 8)
#define RISCV_IOMMU_ICVEC_PIV GENMASK_ULL(15, 12)
/* 5.28 MSI Configuration table (32 * 64bits) */
#define RISCV_IOMMU_REG_MSI_CFG_TBL 0x0300
#define RISCV_IOMMU_REG_MSI_CFG_TBL_ADDR(_n) \
(RISCV_IOMMU_REG_MSI_CFG_TBL + ((_n) * 0x10))
#define RISCV_IOMMU_MSI_CFG_TBL_ADDR GENMASK_ULL(55, 2)
#define RISCV_IOMMU_REG_MSI_CFG_TBL_DATA(_n) \
(RISCV_IOMMU_REG_MSI_CFG_TBL + ((_n) * 0x10) + 0x08)
#define RISCV_IOMMU_MSI_CFG_TBL_DATA GENMASK_ULL(31, 0)
#define RISCV_IOMMU_REG_MSI_CFG_TBL_CTRL(_n) \
(RISCV_IOMMU_REG_MSI_CFG_TBL + ((_n) * 0x10) + 0x0C)
#define RISCV_IOMMU_MSI_CFG_TBL_CTRL_M BIT_ULL(0)
#define RISCV_IOMMU_REG_SIZE 0x1000
/*
* Chapter 2: Data structures
*/
/*
* Device Directory Table macros for non-leaf nodes
*/
#define RISCV_IOMMU_DDTE_V BIT_ULL(0)
#define RISCV_IOMMU_DDTE_PPN RISCV_IOMMU_PPN_FIELD
/**
* struct riscv_iommu_dc - Device Context
* @tc: Translation Control
* @iohgatp: I/O Hypervisor guest address translation and protection
* (Second stage context)
* @ta: Translation Attributes
* @fsc: First stage context
* @msiptp: MSI page table pointer
* @msi_addr_mask: MSI address mask
* @msi_addr_pattern: MSI address pattern
* @_reserved: Reserved for future use, padding
*
* This structure is used for leaf nodes on the Device Directory Table,
* in case RISCV_IOMMU_CAPABILITIES_MSI_FLAT is not set, the bottom 4 fields
* are not present and are skipped with pointer arithmetic to avoid
* casting, check out riscv_iommu_get_dc().
* See section 2.1 for more details
*/
struct riscv_iommu_dc {
u64 tc;
u64 iohgatp;
u64 ta;
u64 fsc;
u64 msiptp;
u64 msi_addr_mask;
u64 msi_addr_pattern;
u64 _reserved;
};
/* Translation control fields */
#define RISCV_IOMMU_DC_TC_V BIT_ULL(0)
#define RISCV_IOMMU_DC_TC_EN_ATS BIT_ULL(1)
#define RISCV_IOMMU_DC_TC_EN_PRI BIT_ULL(2)
#define RISCV_IOMMU_DC_TC_T2GPA BIT_ULL(3)
#define RISCV_IOMMU_DC_TC_DTF BIT_ULL(4)
#define RISCV_IOMMU_DC_TC_PDTV BIT_ULL(5)
#define RISCV_IOMMU_DC_TC_PRPR BIT_ULL(6)
#define RISCV_IOMMU_DC_TC_GADE BIT_ULL(7)
#define RISCV_IOMMU_DC_TC_SADE BIT_ULL(8)
#define RISCV_IOMMU_DC_TC_DPE BIT_ULL(9)
#define RISCV_IOMMU_DC_TC_SBE BIT_ULL(10)
#define RISCV_IOMMU_DC_TC_SXL BIT_ULL(11)
/* Second-stage (aka G-stage) context fields */
#define RISCV_IOMMU_DC_IOHGATP_PPN RISCV_IOMMU_ATP_PPN_FIELD
#define RISCV_IOMMU_DC_IOHGATP_GSCID GENMASK_ULL(59, 44)
#define RISCV_IOMMU_DC_IOHGATP_MODE RISCV_IOMMU_ATP_MODE_FIELD
/**
* enum riscv_iommu_dc_iohgatp_modes - Guest address translation/protection modes
* @RISCV_IOMMU_DC_IOHGATP_MODE_BARE: No translation/protection
* @RISCV_IOMMU_DC_IOHGATP_MODE_SV32X4: Sv32x4 (2-bit extension of Sv32), when fctl.GXL == 1
* @RISCV_IOMMU_DC_IOHGATP_MODE_SV39X4: Sv39x4 (2-bit extension of Sv39), when fctl.GXL == 0
* @RISCV_IOMMU_DC_IOHGATP_MODE_SV48X4: Sv48x4 (2-bit extension of Sv48), when fctl.GXL == 0
* @RISCV_IOMMU_DC_IOHGATP_MODE_SV57X4: Sv57x4 (2-bit extension of Sv57), when fctl.GXL == 0
*/
enum riscv_iommu_dc_iohgatp_modes {
RISCV_IOMMU_DC_IOHGATP_MODE_BARE = 0,
RISCV_IOMMU_DC_IOHGATP_MODE_SV32X4 = 8,
RISCV_IOMMU_DC_IOHGATP_MODE_SV39X4 = 8,
RISCV_IOMMU_DC_IOHGATP_MODE_SV48X4 = 9,
RISCV_IOMMU_DC_IOHGATP_MODE_SV57X4 = 10
};
/* Translation attributes fields */
#define RISCV_IOMMU_DC_TA_PSCID GENMASK_ULL(31, 12)
/* First-stage context fields */
#define RISCV_IOMMU_DC_FSC_PPN RISCV_IOMMU_ATP_PPN_FIELD
#define RISCV_IOMMU_DC_FSC_MODE RISCV_IOMMU_ATP_MODE_FIELD
/**
* enum riscv_iommu_dc_fsc_atp_modes - First stage address translation/protection modes
* @RISCV_IOMMU_DC_FSC_MODE_BARE: No translation/protection
* @RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV32: Sv32, when dc.tc.SXL == 1
* @RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV39: Sv39, when dc.tc.SXL == 0
* @RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV48: Sv48, when dc.tc.SXL == 0
* @RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV57: Sv57, when dc.tc.SXL == 0
* @RISCV_IOMMU_DC_FSC_PDTP_MODE_PD8: 1lvl PDT, 8bit process ids
* @RISCV_IOMMU_DC_FSC_PDTP_MODE_PD17: 2lvl PDT, 17bit process ids
* @RISCV_IOMMU_DC_FSC_PDTP_MODE_PD20: 3lvl PDT, 20bit process ids
*
* FSC holds IOSATP when RISCV_IOMMU_DC_TC_PDTV is 0 and PDTP otherwise.
* IOSATP controls the first stage address translation (same as the satp register on
* the RISC-V MMU), and PDTP holds the process directory table, used to select a
* first stage page table based on a process id (for devices that support multiple
* process ids).
*/
enum riscv_iommu_dc_fsc_atp_modes {
RISCV_IOMMU_DC_FSC_MODE_BARE = 0,
RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV32 = 8,
RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV39 = 8,
RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV48 = 9,
RISCV_IOMMU_DC_FSC_IOSATP_MODE_SV57 = 10,
RISCV_IOMMU_DC_FSC_PDTP_MODE_PD8 = 1,
RISCV_IOMMU_DC_FSC_PDTP_MODE_PD17 = 2,
RISCV_IOMMU_DC_FSC_PDTP_MODE_PD20 = 3
};
/* MSI page table pointer */
#define RISCV_IOMMU_DC_MSIPTP_PPN RISCV_IOMMU_ATP_PPN_FIELD
#define RISCV_IOMMU_DC_MSIPTP_MODE RISCV_IOMMU_ATP_MODE_FIELD
#define RISCV_IOMMU_DC_MSIPTP_MODE_OFF 0
#define RISCV_IOMMU_DC_MSIPTP_MODE_FLAT 1
/* MSI address mask */
#define RISCV_IOMMU_DC_MSI_ADDR_MASK GENMASK_ULL(51, 0)
/* MSI address pattern */
#define RISCV_IOMMU_DC_MSI_PATTERN GENMASK_ULL(51, 0)
/**
* struct riscv_iommu_pc - Process Context
* @ta: Translation Attributes
* @fsc: First stage context
*
* This structure is used for leaf nodes on the Process Directory Table
* See section 2.3 for more details
*/
struct riscv_iommu_pc {
u64 ta;
u64 fsc;
};
/* Translation attributes fields */
#define RISCV_IOMMU_PC_TA_V BIT_ULL(0)
#define RISCV_IOMMU_PC_TA_ENS BIT_ULL(1)
#define RISCV_IOMMU_PC_TA_SUM BIT_ULL(2)
#define RISCV_IOMMU_PC_TA_PSCID GENMASK_ULL(31, 12)
/* First stage context fields */
#define RISCV_IOMMU_PC_FSC_PPN RISCV_IOMMU_ATP_PPN_FIELD
#define RISCV_IOMMU_PC_FSC_MODE RISCV_IOMMU_ATP_MODE_FIELD
/*
* Chapter 3: In-memory queue interface
*/
/**
* struct riscv_iommu_command - Generic IOMMU command structure
* @dword0: Includes the opcode and the function identifier
* @dword1: Opcode specific data
*
* The commands are interpreted as two 64bit fields, where the first
* 7bits of the first field are the opcode which also defines the
* command's format, followed by a 3bit field that specifies the
* function invoked by that command, and the rest is opcode-specific.
* This is a generic struct which will be populated differently
* according to each command. For more infos on the commands and
* the command queue check section 3.1.
*/
struct riscv_iommu_command {
u64 dword0;
u64 dword1;
};
/* Fields on dword0, common for all commands */
#define RISCV_IOMMU_CMD_OPCODE GENMASK_ULL(6, 0)
#define RISCV_IOMMU_CMD_FUNC GENMASK_ULL(9, 7)
/* 3.1.1 IOMMU Page-table cache invalidation */
/* Fields on dword0 */
#define RISCV_IOMMU_CMD_IOTINVAL_OPCODE 1
#define RISCV_IOMMU_CMD_IOTINVAL_FUNC_VMA 0
#define RISCV_IOMMU_CMD_IOTINVAL_FUNC_GVMA 1
#define RISCV_IOMMU_CMD_IOTINVAL_AV BIT_ULL(10)
#define RISCV_IOMMU_CMD_IOTINVAL_PSCID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_CMD_IOTINVAL_PSCV BIT_ULL(32)
#define RISCV_IOMMU_CMD_IOTINVAL_GV BIT_ULL(33)
#define RISCV_IOMMU_CMD_IOTINVAL_GSCID GENMASK_ULL(59, 44)
/* dword1[61:10] is the 4K-aligned page address */
#define RISCV_IOMMU_CMD_IOTINVAL_ADDR GENMASK_ULL(61, 10)
/* 3.1.2 IOMMU Command Queue Fences */
/* Fields on dword0 */
#define RISCV_IOMMU_CMD_IOFENCE_OPCODE 2
#define RISCV_IOMMU_CMD_IOFENCE_FUNC_C 0
#define RISCV_IOMMU_CMD_IOFENCE_AV BIT_ULL(10)
#define RISCV_IOMMU_CMD_IOFENCE_WSI BIT_ULL(11)
#define RISCV_IOMMU_CMD_IOFENCE_PR BIT_ULL(12)
#define RISCV_IOMMU_CMD_IOFENCE_PW BIT_ULL(13)
#define RISCV_IOMMU_CMD_IOFENCE_DATA GENMASK_ULL(63, 32)
/* dword1 is the address, word-size aligned and shifted to the right by two bits. */
/* 3.1.3 IOMMU Directory cache invalidation */
/* Fields on dword0 */
#define RISCV_IOMMU_CMD_IODIR_OPCODE 3
#define RISCV_IOMMU_CMD_IODIR_FUNC_INVAL_DDT 0
#define RISCV_IOMMU_CMD_IODIR_FUNC_INVAL_PDT 1
#define RISCV_IOMMU_CMD_IODIR_PID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_CMD_IODIR_DV BIT_ULL(33)
#define RISCV_IOMMU_CMD_IODIR_DID GENMASK_ULL(63, 40)
/* dword1 is reserved for standard use */
/* 3.1.4 IOMMU PCIe ATS */
/* Fields on dword0 */
#define RISCV_IOMMU_CMD_ATS_OPCODE 4
#define RISCV_IOMMU_CMD_ATS_FUNC_INVAL 0
#define RISCV_IOMMU_CMD_ATS_FUNC_PRGR 1
#define RISCV_IOMMU_CMD_ATS_PID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_CMD_ATS_PV BIT_ULL(32)
#define RISCV_IOMMU_CMD_ATS_DSV BIT_ULL(33)
#define RISCV_IOMMU_CMD_ATS_RID GENMASK_ULL(55, 40)
#define RISCV_IOMMU_CMD_ATS_DSEG GENMASK_ULL(63, 56)
/* dword1 is the ATS payload, two different payload types for INVAL and PRGR */
/* ATS.INVAL payload*/
#define RISCV_IOMMU_CMD_ATS_INVAL_G BIT_ULL(0)
/* Bits 1 - 10 are zeroed */
#define RISCV_IOMMU_CMD_ATS_INVAL_S BIT_ULL(11)
#define RISCV_IOMMU_CMD_ATS_INVAL_UADDR GENMASK_ULL(63, 12)
/* ATS.PRGR payload */
/* Bits 0 - 31 are zeroed */
#define RISCV_IOMMU_CMD_ATS_PRGR_PRG_INDEX GENMASK_ULL(40, 32)
/* Bits 41 - 43 are zeroed */
#define RISCV_IOMMU_CMD_ATS_PRGR_RESP_CODE GENMASK_ULL(47, 44)
#define RISCV_IOMMU_CMD_ATS_PRGR_DST_ID GENMASK_ULL(63, 48)
/**
* struct riscv_iommu_fq_record - Fault/Event Queue Record
* @hdr: Header, includes fault/event cause, PID/DID, transaction type etc
* @_reserved: Low 32bits for custom use, high 32bits for standard use
* @iotval: Transaction-type/cause specific format
* @iotval2: Cause specific format
*
* The fault/event queue reports events and failures raised when
* processing transactions. Each record is a 32byte structure where
* the first dword has a fixed format for providing generic infos
* regarding the fault/event, and two more dwords are there for
* fault/event-specific information. For more details see section
* 3.2.
*/
struct riscv_iommu_fq_record {
u64 hdr;
u64 _reserved;
u64 iotval;
u64 iotval2;
};
/* Fields on header */
#define RISCV_IOMMU_FQ_HDR_CAUSE GENMASK_ULL(11, 0)
#define RISCV_IOMMU_FQ_HDR_PID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_FQ_HDR_PV BIT_ULL(32)
#define RISCV_IOMMU_FQ_HDR_PRIV BIT_ULL(33)
#define RISCV_IOMMU_FQ_HDR_TTYP GENMASK_ULL(39, 34)
#define RISCV_IOMMU_FQ_HDR_DID GENMASK_ULL(63, 40)
/**
* enum riscv_iommu_fq_causes - Fault/event cause values
* @RISCV_IOMMU_FQ_CAUSE_INST_FAULT: Instruction access fault
* @RISCV_IOMMU_FQ_CAUSE_RD_ADDR_MISALIGNED: Read address misaligned
* @RISCV_IOMMU_FQ_CAUSE_RD_FAULT: Read load fault
* @RISCV_IOMMU_FQ_CAUSE_WR_ADDR_MISALIGNED: Write/AMO address misaligned
* @RISCV_IOMMU_FQ_CAUSE_WR_FAULT: Write/AMO access fault
* @RISCV_IOMMU_FQ_CAUSE_INST_FAULT_S: Instruction page fault
* @RISCV_IOMMU_FQ_CAUSE_RD_FAULT_S: Read page fault
* @RISCV_IOMMU_FQ_CAUSE_WR_FAULT_S: Write/AMO page fault
* @RISCV_IOMMU_FQ_CAUSE_INST_FAULT_VS: Instruction guest page fault
* @RISCV_IOMMU_FQ_CAUSE_RD_FAULT_VS: Read guest page fault
* @RISCV_IOMMU_FQ_CAUSE_WR_FAULT_VS: Write/AMO guest page fault
* @RISCV_IOMMU_FQ_CAUSE_DMA_DISABLED: All inbound transactions disallowed
* @RISCV_IOMMU_FQ_CAUSE_DDT_LOAD_FAULT: DDT entry load access fault
* @RISCV_IOMMU_FQ_CAUSE_DDT_INVALID: DDT entry invalid
* @RISCV_IOMMU_FQ_CAUSE_DDT_MISCONFIGURED: DDT entry misconfigured
* @RISCV_IOMMU_FQ_CAUSE_TTYP_BLOCKED: Transaction type disallowed
* @RISCV_IOMMU_FQ_CAUSE_MSI_LOAD_FAULT: MSI PTE load access fault
* @RISCV_IOMMU_FQ_CAUSE_MSI_INVALID: MSI PTE invalid
* @RISCV_IOMMU_FQ_CAUSE_MSI_MISCONFIGURED: MSI PTE misconfigured
* @RISCV_IOMMU_FQ_CAUSE_MRIF_FAULT: MRIF access fault
* @RISCV_IOMMU_FQ_CAUSE_PDT_LOAD_FAULT: PDT entry load access fault
* @RISCV_IOMMU_FQ_CAUSE_PDT_INVALID: PDT entry invalid
* @RISCV_IOMMU_FQ_CAUSE_PDT_MISCONFIGURED: PDT entry misconfigured
* @RISCV_IOMMU_FQ_CAUSE_DDT_CORRUPTED: DDT data corruption
* @RISCV_IOMMU_FQ_CAUSE_PDT_CORRUPTED: PDT data corruption
* @RISCV_IOMMU_FQ_CAUSE_MSI_PT_CORRUPTED: MSI page table data corruption
* @RISCV_IOMMU_FQ_CAUSE_MRIF_CORRUIPTED: MRIF data corruption
* @RISCV_IOMMU_FQ_CAUSE_INTERNAL_DP_ERROR: Internal data path error
* @RISCV_IOMMU_FQ_CAUSE_MSI_WR_FAULT: IOMMU MSI write access fault
* @RISCV_IOMMU_FQ_CAUSE_PT_CORRUPTED: First/second stage page table data corruption
*
* Values are on table 11 of the spec, encodings 275 - 2047 are reserved for standard
* use, and 2048 - 4095 for custom use.
*/
enum riscv_iommu_fq_causes {
RISCV_IOMMU_FQ_CAUSE_INST_FAULT = 1,
RISCV_IOMMU_FQ_CAUSE_RD_ADDR_MISALIGNED = 4,
RISCV_IOMMU_FQ_CAUSE_RD_FAULT = 5,
RISCV_IOMMU_FQ_CAUSE_WR_ADDR_MISALIGNED = 6,
RISCV_IOMMU_FQ_CAUSE_WR_FAULT = 7,
RISCV_IOMMU_FQ_CAUSE_INST_FAULT_S = 12,
RISCV_IOMMU_FQ_CAUSE_RD_FAULT_S = 13,
RISCV_IOMMU_FQ_CAUSE_WR_FAULT_S = 15,
RISCV_IOMMU_FQ_CAUSE_INST_FAULT_VS = 20,
RISCV_IOMMU_FQ_CAUSE_RD_FAULT_VS = 21,
RISCV_IOMMU_FQ_CAUSE_WR_FAULT_VS = 23,
RISCV_IOMMU_FQ_CAUSE_DMA_DISABLED = 256,
RISCV_IOMMU_FQ_CAUSE_DDT_LOAD_FAULT = 257,
RISCV_IOMMU_FQ_CAUSE_DDT_INVALID = 258,
RISCV_IOMMU_FQ_CAUSE_DDT_MISCONFIGURED = 259,
RISCV_IOMMU_FQ_CAUSE_TTYP_BLOCKED = 260,
RISCV_IOMMU_FQ_CAUSE_MSI_LOAD_FAULT = 261,
RISCV_IOMMU_FQ_CAUSE_MSI_INVALID = 262,
RISCV_IOMMU_FQ_CAUSE_MSI_MISCONFIGURED = 263,
RISCV_IOMMU_FQ_CAUSE_MRIF_FAULT = 264,
RISCV_IOMMU_FQ_CAUSE_PDT_LOAD_FAULT = 265,
RISCV_IOMMU_FQ_CAUSE_PDT_INVALID = 266,
RISCV_IOMMU_FQ_CAUSE_PDT_MISCONFIGURED = 267,
RISCV_IOMMU_FQ_CAUSE_DDT_CORRUPTED = 268,
RISCV_IOMMU_FQ_CAUSE_PDT_CORRUPTED = 269,
RISCV_IOMMU_FQ_CAUSE_MSI_PT_CORRUPTED = 270,
RISCV_IOMMU_FQ_CAUSE_MRIF_CORRUIPTED = 271,
RISCV_IOMMU_FQ_CAUSE_INTERNAL_DP_ERROR = 272,
RISCV_IOMMU_FQ_CAUSE_MSI_WR_FAULT = 273,
RISCV_IOMMU_FQ_CAUSE_PT_CORRUPTED = 274
};
/**
* enum riscv_iommu_fq_ttypes: Fault/event transaction types
* @RISCV_IOMMU_FQ_TTYP_NONE: None. Fault not caused by an inbound transaction.
* @RISCV_IOMMU_FQ_TTYP_UADDR_INST_FETCH: Instruction fetch from untranslated address
* @RISCV_IOMMU_FQ_TTYP_UADDR_RD: Read from untranslated address
* @RISCV_IOMMU_FQ_TTYP_UADDR_WR: Write/AMO to untranslated address
* @RISCV_IOMMU_FQ_TTYP_TADDR_INST_FETCH: Instruction fetch from translated address
* @RISCV_IOMMU_FQ_TTYP_TADDR_RD: Read from translated address
* @RISCV_IOMMU_FQ_TTYP_TADDR_WR: Write/AMO to translated address
* @RISCV_IOMMU_FQ_TTYP_PCIE_ATS_REQ: PCIe ATS translation request
* @RISCV_IOMMU_FQ_TTYP_PCIE_MSG_REQ: PCIe message request
*
* Values are on table 12 of the spec, type 4 and 10 - 31 are reserved for standard use
* and 31 - 63 for custom use.
*/
enum riscv_iommu_fq_ttypes {
RISCV_IOMMU_FQ_TTYP_NONE = 0,
RISCV_IOMMU_FQ_TTYP_UADDR_INST_FETCH = 1,
RISCV_IOMMU_FQ_TTYP_UADDR_RD = 2,
RISCV_IOMMU_FQ_TTYP_UADDR_WR = 3,
RISCV_IOMMU_FQ_TTYP_TADDR_INST_FETCH = 5,
RISCV_IOMMU_FQ_TTYP_TADDR_RD = 6,
RISCV_IOMMU_FQ_TTYP_TADDR_WR = 7,
RISCV_IOMMU_FQ_TTYP_PCIE_ATS_REQ = 8,
RISCV_IOMMU_FQ_TTYP_PCIE_MSG_REQ = 9,
};
/**
* struct riscv_iommu_pq_record - PCIe Page Request record
* @hdr: Header, includes PID, DID etc
* @payload: Holds the page address, request group and permission bits
*
* For more infos on the PCIe Page Request queue see chapter 3.3.
*/
struct riscv_iommu_pq_record {
u64 hdr;
u64 payload;
};
/* Header fields */
#define RISCV_IOMMU_PQ_HDR_PID GENMASK_ULL(31, 12)
#define RISCV_IOMMU_PQ_HDR_PV BIT_ULL(32)
#define RISCV_IOMMU_PQ_HDR_PRIV BIT_ULL(33)
#define RISCV_IOMMU_PQ_HDR_EXEC BIT_ULL(34)
#define RISCV_IOMMU_PQ_HDR_DID GENMASK_ULL(63, 40)
/* Payload fields */
#define RISCV_IOMMU_PQ_PAYLOAD_R BIT_ULL(0)
#define RISCV_IOMMU_PQ_PAYLOAD_W BIT_ULL(1)
#define RISCV_IOMMU_PQ_PAYLOAD_L BIT_ULL(2)
#define RISCV_IOMMU_PQ_PAYLOAD_RWL_MASK GENMASK_ULL(2, 0)
#define RISCV_IOMMU_PQ_PAYLOAD_PRGI GENMASK_ULL(11, 3) /* Page Request Group Index */
#define RISCV_IOMMU_PQ_PAYLOAD_ADDR GENMASK_ULL(63, 12)
/**
* struct riscv_iommu_msipte - MSI Page Table Entry
* @pte: MSI PTE
* @mrif_info: Memory-resident interrupt file info
*
* The MSI Page Table is used for virtualizing MSIs, so that when
* a device sends an MSI to a guest, the IOMMU can reroute it
* by translating the MSI address, either to a guest interrupt file
* or a memory resident interrupt file (MRIF). Note that this page table
* is an array of MSI PTEs, not a multi-level pt, each entry
* is a leaf entry. For more infos check out the AIA spec, chapter 9.5.
*
* Also in basic mode the mrif_info field is ignored by the IOMMU and can
* be used by software, any other reserved fields on pte must be zeroed-out
* by software.
*/
struct riscv_iommu_msipte {
u64 pte;
u64 mrif_info;
};
/* Fields on pte */
#define RISCV_IOMMU_MSIPTE_V BIT_ULL(0)
#define RISCV_IOMMU_MSIPTE_M GENMASK_ULL(2, 1)
#define RISCV_IOMMU_MSIPTE_MRIF_ADDR GENMASK_ULL(53, 7) /* When M == 1 (MRIF mode) */
#define RISCV_IOMMU_MSIPTE_PPN RISCV_IOMMU_PPN_FIELD /* When M == 3 (basic mode) */
#define RISCV_IOMMU_MSIPTE_C BIT_ULL(63)
/* Fields on mrif_info */
#define RISCV_IOMMU_MSIPTE_MRIF_NID GENMASK_ULL(9, 0)
#define RISCV_IOMMU_MSIPTE_MRIF_NPPN RISCV_IOMMU_PPN_FIELD
#define RISCV_IOMMU_MSIPTE_MRIF_NID_MSB BIT_ULL(60)
/* Helper functions: command structure builders. */
static inline void riscv_iommu_cmd_inval_vma(struct riscv_iommu_command *cmd)
{
cmd->dword0 = FIELD_PREP(RISCV_IOMMU_CMD_OPCODE, RISCV_IOMMU_CMD_IOTINVAL_OPCODE) |
FIELD_PREP(RISCV_IOMMU_CMD_FUNC, RISCV_IOMMU_CMD_IOTINVAL_FUNC_VMA);
cmd->dword1 = 0;
}
static inline void riscv_iommu_cmd_inval_set_addr(struct riscv_iommu_command *cmd,
u64 addr)
{
cmd->dword1 = FIELD_PREP(RISCV_IOMMU_CMD_IOTINVAL_ADDR, phys_to_pfn(addr));
cmd->dword0 |= RISCV_IOMMU_CMD_IOTINVAL_AV;
}
static inline void riscv_iommu_cmd_inval_set_pscid(struct riscv_iommu_command *cmd,
int pscid)
{
cmd->dword0 |= FIELD_PREP(RISCV_IOMMU_CMD_IOTINVAL_PSCID, pscid) |
RISCV_IOMMU_CMD_IOTINVAL_PSCV;
}
static inline void riscv_iommu_cmd_inval_set_gscid(struct riscv_iommu_command *cmd,
int gscid)
{
cmd->dword0 |= FIELD_PREP(RISCV_IOMMU_CMD_IOTINVAL_GSCID, gscid) |
RISCV_IOMMU_CMD_IOTINVAL_GV;
}
static inline void riscv_iommu_cmd_iofence(struct riscv_iommu_command *cmd)
{
cmd->dword0 = FIELD_PREP(RISCV_IOMMU_CMD_OPCODE, RISCV_IOMMU_CMD_IOFENCE_OPCODE) |
FIELD_PREP(RISCV_IOMMU_CMD_FUNC, RISCV_IOMMU_CMD_IOFENCE_FUNC_C) |
RISCV_IOMMU_CMD_IOFENCE_PR | RISCV_IOMMU_CMD_IOFENCE_PW;
cmd->dword1 = 0;
}
static inline void riscv_iommu_cmd_iofence_set_av(struct riscv_iommu_command *cmd,
u64 addr, u32 data)
{
cmd->dword0 = FIELD_PREP(RISCV_IOMMU_CMD_OPCODE, RISCV_IOMMU_CMD_IOFENCE_OPCODE) |
FIELD_PREP(RISCV_IOMMU_CMD_FUNC, RISCV_IOMMU_CMD_IOFENCE_FUNC_C) |
FIELD_PREP(RISCV_IOMMU_CMD_IOFENCE_DATA, data) |
RISCV_IOMMU_CMD_IOFENCE_AV;
cmd->dword1 = addr >> 2;
}
static inline void riscv_iommu_cmd_iodir_inval_ddt(struct riscv_iommu_command *cmd)
{
cmd->dword0 = FIELD_PREP(RISCV_IOMMU_CMD_OPCODE, RISCV_IOMMU_CMD_IODIR_OPCODE) |
FIELD_PREP(RISCV_IOMMU_CMD_FUNC, RISCV_IOMMU_CMD_IODIR_FUNC_INVAL_DDT);
cmd->dword1 = 0;
}
static inline void riscv_iommu_cmd_iodir_inval_pdt(struct riscv_iommu_command *cmd)
{
cmd->dword0 = FIELD_PREP(RISCV_IOMMU_CMD_OPCODE, RISCV_IOMMU_CMD_IODIR_OPCODE) |
FIELD_PREP(RISCV_IOMMU_CMD_FUNC, RISCV_IOMMU_CMD_IODIR_FUNC_INVAL_PDT);
cmd->dword1 = 0;
}
static inline void riscv_iommu_cmd_iodir_set_did(struct riscv_iommu_command *cmd,
unsigned int devid)
{
cmd->dword0 |= FIELD_PREP(RISCV_IOMMU_CMD_IODIR_DID, devid) |
RISCV_IOMMU_CMD_IODIR_DV;
}
static inline void riscv_iommu_cmd_iodir_set_pid(struct riscv_iommu_command *cmd,
unsigned int pasid)
{
cmd->dword0 |= FIELD_PREP(RISCV_IOMMU_CMD_IODIR_PID, pasid);
}
#endif /* _RISCV_IOMMU_BITS_H_ */

120
drivers/iommu/riscv/iommu-pci.c Normal file
View File

@ -0,0 +1,120 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright © 2022-2024 Rivos Inc.
* Copyright © 2023 FORTH-ICS/CARV
*
* RISCV IOMMU as a PCIe device
*
* Authors
* Tomasz Jeznach <tjeznach@rivosinc.com>
* Nick Kossifidis <mick@ics.forth.gr>
*/
#include <linux/compiler.h>
#include <linux/init.h>
#include <linux/iommu.h>
#include <linux/kernel.h>
#include <linux/pci.h>
#include "iommu-bits.h"
#include "iommu.h"
/* QEMU RISC-V IOMMU implementation */
#define PCI_DEVICE_ID_REDHAT_RISCV_IOMMU 0x0014
/* Rivos Inc. assigned PCI Vendor and Device IDs */
#ifndef PCI_VENDOR_ID_RIVOS
#define PCI_VENDOR_ID_RIVOS 0x1efd
#endif
#define PCI_DEVICE_ID_RIVOS_RISCV_IOMMU_GA 0x0008
static int riscv_iommu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct device *dev = &pdev->dev;
struct riscv_iommu_device *iommu;
int rc, vec;
rc = pcim_enable_device(pdev);
if (rc)
return rc;
if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM))
return -ENODEV;
if (pci_resource_len(pdev, 0) < RISCV_IOMMU_REG_SIZE)
return -ENODEV;
rc = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
if (rc)
return dev_err_probe(dev, rc, "pcim_iomap_regions failed\n");
iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
if (!iommu)
return -ENOMEM;
iommu->dev = dev;
iommu->reg = pcim_iomap_table(pdev)[0];
pci_set_master(pdev);
dev_set_drvdata(dev, iommu);
/* Check device reported capabilities / features. */
iommu->caps = riscv_iommu_readq(iommu, RISCV_IOMMU_REG_CAPABILITIES);
iommu->fctl = riscv_iommu_readl(iommu, RISCV_IOMMU_REG_FCTL);
/* The PCI driver only uses MSIs, make sure the IOMMU supports this */
switch (FIELD_GET(RISCV_IOMMU_CAPABILITIES_IGS, iommu->caps)) {
case RISCV_IOMMU_CAPABILITIES_IGS_MSI:
case RISCV_IOMMU_CAPABILITIES_IGS_BOTH:
break;
default:
return dev_err_probe(dev, -ENODEV,
"unable to use message-signaled interrupts\n");
}
/* Allocate and assign IRQ vectors for the various events */
rc = pci_alloc_irq_vectors(pdev, 1, RISCV_IOMMU_INTR_COUNT,
PCI_IRQ_MSIX | PCI_IRQ_MSI);
if (rc <= 0)
return dev_err_probe(dev, -ENODEV,
"unable to allocate irq vectors\n");
iommu->irqs_count = rc;
for (vec = 0; vec < iommu->irqs_count; vec++)
iommu->irqs[vec] = msi_get_virq(dev, vec);
/* Enable message-signaled interrupts, fctl.WSI */
if (iommu->fctl & RISCV_IOMMU_FCTL_WSI) {
iommu->fctl ^= RISCV_IOMMU_FCTL_WSI;
riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FCTL, iommu->fctl);
}
return riscv_iommu_init(iommu);
}
static void riscv_iommu_pci_remove(struct pci_dev *pdev)
{
struct riscv_iommu_device *iommu = dev_get_drvdata(&pdev->dev);
riscv_iommu_remove(iommu);
}
static const struct pci_device_id riscv_iommu_pci_tbl[] = {
{PCI_VDEVICE(REDHAT, PCI_DEVICE_ID_REDHAT_RISCV_IOMMU), 0},
{PCI_VDEVICE(RIVOS, PCI_DEVICE_ID_RIVOS_RISCV_IOMMU_GA), 0},
{0,}
};
static struct pci_driver riscv_iommu_pci_driver = {
.name = KBUILD_MODNAME,
.id_table = riscv_iommu_pci_tbl,
.probe = riscv_iommu_pci_probe,
.remove = riscv_iommu_pci_remove,
.driver = {
.suppress_bind_attrs = true,
},
};
builtin_pci_driver(riscv_iommu_pci_driver);

92
drivers/iommu/riscv/iommu-platform.c Normal file
View File

@ -0,0 +1,92 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* RISC-V IOMMU as a platform device
*
* Copyright © 2023 FORTH-ICS/CARV
* Copyright © 2023-2024 Rivos Inc.
*
* Authors
* Nick Kossifidis <mick@ics.forth.gr>
* Tomasz Jeznach <tjeznach@rivosinc.com>
*/
#include <linux/kernel.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include "iommu-bits.h"
#include "iommu.h"
static int riscv_iommu_platform_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct riscv_iommu_device *iommu = NULL;
struct resource *res = NULL;
int vec;
iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
if (!iommu)
return -ENOMEM;
iommu->dev = dev;
iommu->reg = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
if (IS_ERR(iommu->reg))
return dev_err_probe(dev, PTR_ERR(iommu->reg),
"could not map register region\n");
dev_set_drvdata(dev, iommu);
/* Check device reported capabilities / features. */
iommu->caps = riscv_iommu_readq(iommu, RISCV_IOMMU_REG_CAPABILITIES);
iommu->fctl = riscv_iommu_readl(iommu, RISCV_IOMMU_REG_FCTL);
/* For now we only support WSI */
switch (FIELD_GET(RISCV_IOMMU_CAPABILITIES_IGS, iommu->caps)) {
case RISCV_IOMMU_CAPABILITIES_IGS_WSI:
case RISCV_IOMMU_CAPABILITIES_IGS_BOTH:
break;
default:
return dev_err_probe(dev, -ENODEV,
"unable to use wire-signaled interrupts\n");
}
iommu->irqs_count = platform_irq_count(pdev);
if (iommu->irqs_count <= 0)
return dev_err_probe(dev, -ENODEV,
"no IRQ resources provided\n");
if (iommu->irqs_count > RISCV_IOMMU_INTR_COUNT)
iommu->irqs_count = RISCV_IOMMU_INTR_COUNT;
for (vec = 0; vec < iommu->irqs_count; vec++)
iommu->irqs[vec] = platform_get_irq(pdev, vec);
/* Enable wire-signaled interrupts, fctl.WSI */
if (!(iommu->fctl & RISCV_IOMMU_FCTL_WSI)) {
iommu->fctl |= RISCV_IOMMU_FCTL_WSI;
riscv_iommu_writel(iommu, RISCV_IOMMU_REG_FCTL, iommu->fctl);
}
return riscv_iommu_init(iommu);
};
static void riscv_iommu_platform_remove(struct platform_device *pdev)
{
riscv_iommu_remove(dev_get_drvdata(&pdev->dev));
};
static const struct of_device_id riscv_iommu_of_match[] = {
{.compatible = "riscv,iommu",},
{},
};
static struct platform_driver riscv_iommu_platform_driver = {
.probe = riscv_iommu_platform_probe,
.remove_new = riscv_iommu_platform_remove,
.driver = {
.name = "riscv,iommu",
.of_match_table = riscv_iommu_of_match,
.suppress_bind_attrs = true,
},
};
builtin_platform_driver(riscv_iommu_platform_driver);

1661
drivers/iommu/riscv/iommu.c Normal file
View File

File diff suppressed because it is too large Load Diff

88
drivers/iommu/riscv/iommu.h Normal file
View File

@ -0,0 +1,88 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright © 2022-2024 Rivos Inc.
* Copyright © 2023 FORTH-ICS/CARV
*
* Authors
* Tomasz Jeznach <tjeznach@rivosinc.com>
* Nick Kossifidis <mick@ics.forth.gr>
*/
#ifndef _RISCV_IOMMU_H_
#define _RISCV_IOMMU_H_
#include <linux/iommu.h>
#include <linux/types.h>
#include <linux/iopoll.h>
#include "iommu-bits.h"
struct riscv_iommu_device;
struct riscv_iommu_queue {
atomic_t prod; /* unbounded producer allocation index */
atomic_t head; /* unbounded shadow ring buffer consumer index */
atomic_t tail; /* unbounded shadow ring buffer producer index */
unsigned int mask; /* index mask, queue length - 1 */
unsigned int irq; /* allocated interrupt number */
struct riscv_iommu_device *iommu; /* iommu device handling the queue when active */
void *base; /* ring buffer kernel pointer */
dma_addr_t phys; /* ring buffer physical address */
u16 qbr; /* base register offset, head and tail reference */
u16 qcr; /* control and status register offset */
u8 qid; /* queue identifier, same as RISCV_IOMMU_INTR_XX */
};
struct riscv_iommu_device {
/* iommu core interface */
struct iommu_device iommu;
/* iommu hardware */
struct device *dev;
/* hardware control register space */
void __iomem *reg;
/* supported and enabled hardware capabilities */
u64 caps;
u32 fctl;
/* available interrupt numbers, MSI or WSI */
unsigned int irqs[RISCV_IOMMU_INTR_COUNT];
unsigned int irqs_count;
unsigned int icvec;
/* hardware queues */
struct riscv_iommu_queue cmdq;
struct riscv_iommu_queue fltq;
/* device directory */
unsigned int ddt_mode;
dma_addr_t ddt_phys;
u64 *ddt_root;
};
int riscv_iommu_init(struct riscv_iommu_device *iommu);
void riscv_iommu_remove(struct riscv_iommu_device *iommu);
#define riscv_iommu_readl(iommu, addr) \
readl_relaxed((iommu)->reg + (addr))
#define riscv_iommu_readq(iommu, addr) \
readq_relaxed((iommu)->reg + (addr))
#define riscv_iommu_writel(iommu, addr, val) \
writel_relaxed((val), (iommu)->reg + (addr))
#define riscv_iommu_writeq(iommu, addr, val) \
writeq_relaxed((val), (iommu)->reg + (addr))
#define riscv_iommu_readq_timeout(iommu, addr, val, cond, delay_us, timeout_us) \
readx_poll_timeout(readq_relaxed, (iommu)->reg + (addr), val, cond, \
delay_us, timeout_us)
#define riscv_iommu_readl_timeout(iommu, addr, val, cond, delay_us, timeout_us) \
readx_poll_timeout(readl_relaxed, (iommu)->reg + (addr), val, cond, \
delay_us, timeout_us)
#endif

75
drivers/iommu/s390-iommu.c
View File

@ -33,6 +33,8 @@ struct s390_domain {
struct rcu_head rcu;
};
static struct iommu_domain blocking_domain;
static inline unsigned int calc_rtx(dma_addr_t ptr)
{
return ((unsigned long)ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
@ -369,20 +371,36 @@ static void s390_domain_free(struct iommu_domain *domain)
call_rcu(&s390_domain->rcu, s390_iommu_rcu_free_domain);
}
static void s390_iommu_detach_device(struct iommu_domain *domain,
struct device *dev)
static void zdev_s390_domain_update(struct zpci_dev *zdev,
struct iommu_domain *domain)
{
struct s390_domain *s390_domain = to_s390_domain(domain);
struct zpci_dev *zdev = to_zpci_dev(dev);
unsigned long flags;
spin_lock_irqsave(&zdev->dom_lock, flags);
zdev->s390_domain = domain;
spin_unlock_irqrestore(&zdev->dom_lock, flags);
}
static int blocking_domain_attach_device(struct iommu_domain *domain,
struct device *dev)
{
struct zpci_dev *zdev = to_zpci_dev(dev);
struct s390_domain *s390_domain;
unsigned long flags;
if (zdev->s390_domain->type == IOMMU_DOMAIN_BLOCKED)
return 0;
s390_domain = to_s390_domain(zdev->s390_domain);
spin_lock_irqsave(&s390_domain->list_lock, flags);
list_del_rcu(&zdev->iommu_list);
spin_unlock_irqrestore(&s390_domain->list_lock, flags);
zpci_unregister_ioat(zdev, 0);
zdev->s390_domain = NULL;
zdev->dma_table = NULL;
zdev_s390_domain_update(zdev, domain);
return 0;
}
static int s390_iommu_attach_device(struct iommu_domain *domain,
@ -401,20 +419,15 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
domain->geometry.aperture_end < zdev->start_dma))
return -EINVAL;
if (zdev->s390_domain)
s390_iommu_detach_device(&zdev->s390_domain->domain, dev);
blocking_domain_attach_device(&blocking_domain, dev);
/* If we fail now DMA remains blocked via blocking domain */
cc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
virt_to_phys(s390_domain->dma_table), &status);
/*
* If the device is undergoing error recovery the reset code
* will re-establish the new domain.
*/
if (cc && status != ZPCI_PCI_ST_FUNC_NOT_AVAIL)
return -EIO;
zdev->dma_table = s390_domain->dma_table;
zdev->s390_domain = s390_domain;
zdev_s390_domain_update(zdev, domain);
spin_lock_irqsave(&s390_domain->list_lock, flags);
list_add_rcu(&zdev->iommu_list, &s390_domain->devices);
@ -466,21 +479,13 @@ static struct iommu_device *s390_iommu_probe_device(struct device *dev)
if (zdev->tlb_refresh)
dev->iommu->shadow_on_flush = 1;
/* Start with DMA blocked */
spin_lock_init(&zdev->dom_lock);
zdev_s390_domain_update(zdev, &blocking_domain);
return &zdev->iommu_dev;
}
static void s390_iommu_release_device(struct device *dev)
{
struct zpci_dev *zdev = to_zpci_dev(dev);
/*
* release_device is expected to detach any domain currently attached
* to the device, but keep it attached to other devices in the group.
*/
if (zdev)
s390_iommu_detach_device(&zdev->s390_domain->domain, dev);
}
static int zpci_refresh_all(struct zpci_dev *zdev)
{
return zpci_refresh_trans((u64)zdev->fh << 32, zdev->start_dma,
@ -697,9 +702,15 @@ static size_t s390_iommu_unmap_pages(struct iommu_domain *domain,
struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev)
{
if (!zdev || !zdev->s390_domain)
struct s390_domain *s390_domain;
lockdep_assert_held(&zdev->dom_lock);
if (zdev->s390_domain->type == IOMMU_DOMAIN_BLOCKED)
return NULL;
return &zdev->s390_domain->ctrs;
s390_domain = to_s390_domain(zdev->s390_domain);
return &s390_domain->ctrs;
}
int zpci_init_iommu(struct zpci_dev *zdev)
@ -776,11 +787,19 @@ static int __init s390_iommu_init(void)
}
subsys_initcall(s390_iommu_init);
static struct iommu_domain blocking_domain = {
.type = IOMMU_DOMAIN_BLOCKED,
.ops = &(const struct iommu_domain_ops) {
.attach_dev = blocking_domain_attach_device,
}
};
static const struct iommu_ops s390_iommu_ops = {
.blocked_domain = &blocking_domain,
.release_domain = &blocking_domain,
.capable = s390_iommu_capable,
.domain_alloc_paging = s390_domain_alloc_paging,
.probe_device = s390_iommu_probe_device,
.release_device = s390_iommu_release_device,
.device_group = generic_device_group,
.pgsize_bitmap = SZ_4K,
.get_resv_regions = s390_iommu_get_resv_regions,

7
drivers/media/platform/nvidia/tegra-vde/iommu.c
View File

@ -78,9 +78,10 @@ int tegra_vde_iommu_init(struct tegra_vde *vde)
arm_iommu_release_mapping(mapping);
}
#endif
vde->domain = iommu_domain_alloc(&platform_bus_type);
if (!vde->domain) {
err = -ENOMEM;
vde->domain = iommu_paging_domain_alloc(dev);
if (IS_ERR(vde->domain)) {
err = PTR_ERR(vde->domain);
vde->domain = NULL;
goto put_group;
}

6
drivers/remoteproc/remoteproc_core.c
View File

@ -109,10 +109,10 @@ static int rproc_enable_iommu(struct rproc *rproc)
return 0;
}
domain = iommu_domain_alloc(dev->bus);
if (!domain) {
domain = iommu_paging_domain_alloc(dev);
if (IS_ERR(domain)) {
dev_err(dev, "can't alloc iommu domain\n");
return -ENOMEM;
return PTR_ERR(domain);
}
iommu_set_fault_handler(domain, rproc_iommu_fault, rproc);

20
include/linux/iommu.h
View File

@ -511,8 +511,6 @@ static inline int __iommu_copy_struct_from_user_array(
* the caller iommu_domain_alloc() returns.
* @domain_alloc_user: Allocate an iommu domain corresponding to the input
* parameters as defined in include/uapi/linux/iommufd.h.
* Unlike @domain_alloc, it is called only by IOMMUFD and
* must fully initialize the new domain before return.
* Upon success, if the @user_data is valid and the @parent
* points to a kernel-managed domain, the new domain must be
* IOMMU_DOMAIN_NESTED type; otherwise, the @parent must be
@ -784,12 +782,14 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
};
}
extern int bus_iommu_probe(const struct bus_type *bus);
extern bool iommu_present(const struct bus_type *bus);
extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
extern bool iommu_group_has_isolated_msi(struct iommu_group *group);
extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus);
struct iommu_domain *iommu_paging_domain_alloc(struct device *dev);
struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags);
static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
{
return iommu_paging_domain_alloc_flags(dev, 0);
}
extern void iommu_domain_free(struct iommu_domain *domain);
extern int iommu_attach_device(struct iommu_domain *domain,
struct device *dev);
@ -1081,19 +1081,15 @@ struct iommu_iotlb_gather {};
struct iommu_dirty_bitmap {};
struct iommu_dirty_ops {};
static inline bool iommu_present(const struct bus_type *bus)
{
return false;
}
static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
{
return false;
}
static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
static inline struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev,
unsigned int flags)
{
return NULL;
return ERR_PTR(-ENODEV);
}
static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)

8
include/uapi/linux/iommufd.h
View File

@ -359,11 +359,19 @@ struct iommu_vfio_ioas {
* enforced on device attachment
* @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is
* valid.
* @IOMMU_HWPT_ALLOC_PASID: Requests a domain that can be used with PASID. The
* domain can be attached to any PASID on the device.
* Any domain attached to the non-PASID part of the
* device must also be flaged, otherwise attaching a
* PASID will blocked.
* If IOMMU does not support PASID it will return
* error (-EOPNOTSUPP).
*/
enum iommufd_hwpt_alloc_flags {
IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0,
IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1,
IOMMU_HWPT_FAULT_ID_VALID = 1 << 2,
IOMMU_HWPT_ALLOC_PASID = 1 << 3,
};
/**