To allow IOMMU drivers to allocate own vDEVICE structures, move the struct iommufd_vdevice to the public header and provide a pair of viommu ops.

The iommufd_vdevice_alloc_ioctl will prioritize the callback function from the viommu ops, i.e. a driver-allocated vDEVICE.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 8 ------ include/linux/iommufd.h | 38 +++++++++++++++++++++++++ drivers/iommu/iommufd/viommu.c | 9 +++++- 3 files changed, 46 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 80e8c76d25f2..5c69ac05c029 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -607,14 +607,6 @@ void iommufd_viommu_destroy(struct iommufd_object *obj); int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_vdevice_destroy(struct iommufd_object *obj);

-struct iommufd_vdevice { - struct iommufd_object obj; - struct iommufd_ctx *ictx; - struct iommufd_viommu *viommu; - struct device *dev; - u64 id; /* per-vIOMMU virtual ID */ -}; - #ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); void iommufd_selftest_destroy(struct iommufd_object *obj); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 34b6e6ca4bfa..422eda95d19e 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -104,6 +104,14 @@ struct iommufd_viommu { unsigned int type; };

+struct iommufd_vdevice { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommufd_viommu *viommu; + struct device *dev; + u64 id; /* per-vIOMMU virtual ID */ +}; + /** * struct iommufd_viommu_ops - vIOMMU specific operations * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory @@ -120,6 +128,15 @@ struct iommufd_viommu { * array->entry_num to report the number of handled requests. * The data structure of the array entry must be defined in * include/uapi/linux/iommufd.h + * @vdevice_alloc: Allocate a vDEVICE object and init its driver-level structure + * or HW procedure. Note that the core-level structure is filled + * by the iommufd core after calling this op. @virt_id carries a + * per-vIOMMU virtual ID (refer to struct iommu_vdevice_alloc in + * include/uapi/linux/iommufd.h) for the driver to initialize HW + * for an attached physical device. + * @vdevice_destroy: Clean up all driver-specific parts of an iommufd_vdevice. + * The memory of the vDEVICE will be free-ed by iommufd core + * after calling this op */ struct iommufd_viommu_ops { void (*destroy)(struct iommufd_viommu *viommu); @@ -128,6 +145,10 @@ struct iommufd_viommu_ops { const struct iommu_user_data *user_data); int (*cache_invalidate)(struct iommufd_viommu *viommu, struct iommu_user_data_array *array); + struct iommufd_vdevice *(*vdevice_alloc)(struct iommufd_viommu *viommu, + struct device *dev, + u64 virt_id); + void (*vdevice_destroy)(struct iommufd_vdevice *vdev); };

#if IS_ENABLED(CONFIG_IOMMUFD) @@ -245,4 +266,21 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, ret->member.ops = viommu_ops; \ ret; \ }) + +#define iommufd_vdevice_alloc(viommu, drv_struct, member) \ + ({ \ + drv_struct *ret; \ + \ + static_assert(__same_type(struct iommufd_viommu, *viommu)); \ + static_assert(__same_type(struct iommufd_vdevice, \ + ((drv_struct *)NULL)->member)); \ + static_assert(offsetof(drv_struct, member.obj) == 0); \ + ret = (drv_struct *)_iommufd_object_alloc( \ + viommu->ictx, sizeof(drv_struct), IOMMUFD_OBJ_VDEVICE);\ + if (!IS_ERR(ret)) { \ + ret->member.viommu = viommu; \ + ret->member.ictx = viommu->ictx; \ + } \ + ret; \ + }) #endif diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 01df2b985f02..d4c7c5072e42 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -90,6 +90,9 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj) container_of(obj, struct iommufd_vdevice, obj); struct iommufd_viommu *viommu = vdev->viommu;

+ if (viommu->ops && viommu->ops->vdevice_destroy) + viommu->ops->vdevice_destroy(vdev); + /* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */ xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL); refcount_dec(&viommu->obj.users); @@ -124,7 +127,11 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) goto out_put_idev; }

- vdev = iommufd_object_alloc(ucmd->ictx, vdev, IOMMUFD_OBJ_VDEVICE); + if (viommu->ops && viommu->ops->vdevice_alloc) + vdev = viommu->ops->vdevice_alloc(viommu, idev->dev, virt_id); + else + vdev = iommufd_object_alloc(ucmd->ictx, vdev, + IOMMUFD_OBJ_VDEVICE); if (IS_ERR(vdev)) { rc = PTR_ERR(vdev); goto out_put_idev;

Similar to the iommu_copy_struct_from_user helper receiving data from the user space, add an iommu_copy_struct_to_user helper to report output data back to the user space data pointer.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommu.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ba7add27e9a0..02e9d5904836 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -562,6 +562,46 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, return 0; }

+/** + * __iommu_copy_struct_to_user - Report iommu driver specific user space data + * @dst_data: Pointer to a struct iommu_user_data for user space data location + * @src_data: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @data_type: The data type of the @src_data. Must match with @dst_data.type + * @data_len: Length of current user data structure, i.e. sizeof(struct _src) + * @min_len: Initial length of user data structure for backward compatibility. + * This should be offsetofend using the last member in the user data + * struct that was initially added to include/uapi/linux/iommufd.h + */ +static inline int +__iommu_copy_struct_to_user(const struct iommu_user_data *dst_data, + void *src_data, unsigned int data_type, + size_t data_len, size_t min_len) +{ + if (WARN_ON(!dst_data || !src_data)) + return -EINVAL; + if (dst_data->type != data_type) + return -EINVAL; + if (dst_data->len < min_len || data_len < dst_data->len) + return -EINVAL; + return copy_struct_to_user(dst_data->uptr, dst_data->len, src_data, + data_len, NULL); +} + +/** + * iommu_copy_struct_to_user - Report iommu driver specific user space data + * @user_data: Pointer to a struct iommu_user_data for user space data location + * @ksrc: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @data_type: The data type of the @ksrc. Must match with @user_data->type + * @min_last: The last member of the data structure @ksrc points in the initial + * version. + * Return 0 for success, otherwise -error. + */ +#define iommu_copy_struct_to_user(user_data, ksrc, data_type, min_last) \ + __iommu_copy_struct_to_user(user_data, ksrc, data_type, sizeof(*ksrc), \ + offsetofend(typeof(*ksrc), min_last)) + /** * struct iommu_ops - iommu ops and capabilities * @capable: check capability

When an IOMMU driver calls iommufd_viommu_alloc(), it must pass in an ictx pointer as the underlying _iommufd_object_alloc() helper function requires that to allocate a new object. However, neither the iommufd_viommu_alloc() nor its underlying _iommufd_object_alloc() saves the ictx in the allocated viommu object, although viommu could hold an ictx pointer.

When the IOMMU driver wants to use another iommufd function passing in the allocated viommu, it could have avoided passing in the ictx pointer again, if viommu->ictx is valid.

Save ictx to viommu->ictx in the iommufd_viommu_alloc(), in order to ease a new vIOMMU-based helper that would then get the ictx from viommu->ictx.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommufd.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 422eda95d19e..dc6535e848df 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -262,8 +262,10 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, static_assert(offsetof(drv_struct, member.obj) == 0); \ ret = (drv_struct *)_iommufd_object_alloc( \ ictx, sizeof(drv_struct), IOMMUFD_OBJ_VIOMMU); \ - if (!IS_ERR(ret)) \ + if (!IS_ERR(ret)) { \ ret->member.ops = viommu_ops; \ + ret->member.ictx = ictx; \ + } \ ret; \ })

Add a simple user_data for an input-to-output loopback test.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 13 +++++++++++++ drivers/iommu/iommufd/selftest.c | 19 +++++++++++++++++++ 2 files changed, 32 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 1cd7e8394129..fbf9ecb35a13 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -227,6 +227,19 @@ struct iommu_hwpt_invalidate_selftest {

#define IOMMU_VIOMMU_TYPE_SELFTEST 0xdeadbeef

+/** + * struct iommu_viommu_selftest - vIOMMU data for Mock driver + * (IOMMU_VIOMMU_TYPE_SELFTEST) + * @in_data: Input random data from user space + * @out_data: Output data (matching @in_data) to user space + * + * Simply set @out_data=@in_data for a loopback test + */ +struct iommu_viommu_selftest { + __u32 in_data; + __u32 out_data; +}; + /* Should not be equal to any defined value in enum iommu_viommu_invalidate_data_type */ #define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST 0xdeadbeef #define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 8b8ba4fb91cd..033345f81df9 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -740,16 +740,35 @@ mock_viommu_alloc(struct device *dev, struct iommu_domain *domain, { struct mock_iommu_device *mock_iommu = iommu_get_iommu_dev(dev, struct mock_iommu_device, iommu_dev); + struct iommu_viommu_selftest data; struct mock_viommu *mock_viommu; + int rc;

if (viommu_type != IOMMU_VIOMMU_TYPE_SELFTEST) return ERR_PTR(-EOPNOTSUPP);

+ if (user_data) { + rc = iommu_copy_struct_from_user( + &data, user_data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); + if (rc) + return ERR_PTR(rc); + } + mock_viommu = iommufd_viommu_alloc(ictx, struct mock_viommu, core, &mock_viommu_ops); if (IS_ERR(mock_viommu)) return ERR_CAST(mock_viommu);

+ if (user_data) { + data.out_data = data.in_data; + rc = iommu_copy_struct_to_user( + user_data, &data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); + if (rc) { + iommufd_struct_destroy(mock_viommu, core); + return ERR_PTR(rc); + } + } + refcount_inc(&mock_iommu->users); return &mock_viommu->core; }

Extend the existing test_cmd/err_viommu_alloc helpers to accept optional user data. And add a TEST_F for a loopback test.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- tools/testing/selftests/iommu/iommufd_utils.h | 21 ++++++++----- tools/testing/selftests/iommu/iommufd.c | 30 ++++++++++++++----- .../selftests/iommu/iommufd_fail_nth.c | 5 ++-- 3 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 72f6636e5d90..a5d4cbd089ba 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -897,7 +897,8 @@ static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 pasid, pasid, fault_fd))

static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, - __u32 type, __u32 flags, __u32 *viommu_id) + __u32 flags, __u32 type, void *data, + __u32 data_len, __u32 *viommu_id) { struct iommu_viommu_alloc cmd = { .size = sizeof(cmd), @@ -905,6 +906,8 @@ static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, .type = type, .dev_id = device_id, .hwpt_id = hwpt_id, + .data_uptr = (uint64_t)data, + .data_len = data_len, }; int ret;

@@ -916,13 +919,15 @@ static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, return 0; }

-#define test_cmd_viommu_alloc(device_id, hwpt_id, type, viommu_id) \ - ASSERT_EQ(0, _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ - type, 0, viommu_id)) -#define test_err_viommu_alloc(_errno, device_id, hwpt_id, type, viommu_id) \ - EXPECT_ERRNO(_errno, \ - _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ - type, 0, viommu_id)) +#define test_cmd_viommu_alloc(device_id, hwpt_id, type, data, data_len, \ + viommu_id) \ + ASSERT_EQ(0, _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, 0, \ + type, data, data_len, viommu_id)) +#define test_err_viommu_alloc(_errno, device_id, hwpt_id, type, data, \ + data_len, viommu_id) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, 0, \ + type, data, data_len, viommu_id))

static int _test_cmd_vdevice_alloc(int fd, __u32 viommu_id, __u32 idev_id, __u64 virt_id, __u32 *vdev_id) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 1a8e85afe9aa..666a91d53195 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2688,7 +2688,7 @@ FIXTURE_SETUP(iommufd_viommu)

/* Allocate a vIOMMU taking refcount of the parent hwpt */ test_cmd_viommu_alloc(self->device_id, self->hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, &self->viommu_id);

/* Allocate a regular nested hwpt */ @@ -2727,24 +2727,27 @@ TEST_F(iommufd_viommu, viommu_negative_tests) if (self->device_id) { /* Negative test -- invalid hwpt (hwpt_id=0) */ test_err_viommu_alloc(ENOENT, device_id, 0, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL);

/* Negative test -- not a nesting parent hwpt */ test_cmd_hwpt_alloc(device_id, ioas_id, 0, &hwpt_id); test_err_viommu_alloc(EINVAL, device_id, hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL); test_ioctl_destroy(hwpt_id);

/* Negative test -- unsupported viommu type */ test_err_viommu_alloc(EOPNOTSUPP, device_id, self->hwpt_id, - 0xdead, NULL); + 0xdead, NULL, 0, NULL); EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, self->hwpt_id)); EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, self->viommu_id)); } else { test_err_viommu_alloc(ENOENT, self->device_id, self->hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + NULL); } }

@@ -2791,6 +2794,20 @@ TEST_F(iommufd_viommu, viommu_alloc_nested_iopf) } }

+TEST_F(iommufd_viommu, viommu_alloc_with_data) +{ + struct iommu_viommu_selftest data = { + .in_data = 0xbeef, + }; + + if (self->device_id) { + test_cmd_viommu_alloc(self->device_id, self->hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, &data, + sizeof(data), &self->viommu_id); + assert(data.out_data == data.in_data); + } +} + TEST_F(iommufd_viommu, vdevice_alloc) { uint32_t viommu_id = self->viommu_id; @@ -3105,8 +3122,7 @@ TEST_F(iommufd_device_pasid, pasid_attach)

/* Allocate a regular nested hwpt based on viommu */ test_cmd_viommu_alloc(self->device_id, parent_hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, - &viommu_id); + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, &viommu_id); test_cmd_hwpt_alloc_nested(self->device_id, viommu_id, IOMMU_HWPT_ALLOC_PASID, &nested_hwpt_id[2], diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index e11ec4b121fc..f7ccf1822108 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -688,8 +688,9 @@ TEST_FAIL_NTH(basic_fail_nth, device) IOMMU_HWPT_DATA_NONE, 0, 0)) return -1;

- if (_test_cmd_viommu_alloc(self->fd, idev_id, hwpt_id, - IOMMU_VIOMMU_TYPE_SELFTEST, 0, &viommu_id)) + if (_test_cmd_viommu_alloc(self->fd, idev_id, hwpt_id, 0, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL, 0, + &viommu_id)) return -1;

if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id))

The new HW QUEUE object will be added for HW to access the guest queue for HW-accelerated virtualization feature. It needs to ensure the guest memory pages are pinned when HW accesses them and they are contiguous in physical address space.

This is very like the existing iommufd_access_pin_pages() that outputs the pinned page list for the caller to test its contiguity.

Move those code from iommufd_access_pin/unpin_pages() and related function for a pair of iopt helpers that can be shared with the HW QUEUE allocator.

Rename check_area_prot() to align with the existing iopt_area helpers, and inline it to the header since iommufd_access_rw() still uses it.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/io_pagetable.h | 8 ++ drivers/iommu/iommufd/iommufd_private.h | 6 ++ drivers/iommu/iommufd/device.c | 117 ++---------------------- drivers/iommu/iommufd/io_pagetable.c | 95 +++++++++++++++++++ 4 files changed, 117 insertions(+), 109 deletions(-)

diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index 10c928a9a463..4288a2b1a90f 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -114,6 +114,14 @@ static inline unsigned long iopt_area_iova_to_index(struct iopt_area *area, return iopt_area_start_byte(area, iova) / PAGE_SIZE; }

+static inline bool iopt_area_check_prot(struct iopt_area *area, + unsigned int flags) +{ + if (flags & IOMMUFD_ACCESS_RW_WRITE) + return area->iommu_prot & IOMMU_WRITE; + return area->iommu_prot & IOMMU_READ; +} + #define __make_iopt_iter(name) \ static inline struct iopt_##name *iopt_##name##_iter_first( \ struct io_pagetable *iopt, unsigned long start, \ diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 8d96aa514033..79160b039bc7 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -130,6 +130,12 @@ int iopt_cut_iova(struct io_pagetable *iopt, unsigned long *iovas, void iopt_enable_large_pages(struct io_pagetable *iopt); int iopt_disable_large_pages(struct io_pagetable *iopt);

+int iopt_pin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct page **out_pages, + unsigned int flags); +void iopt_unpin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length); + struct iommufd_ucmd { struct iommufd_ctx *ictx; void __user *ubuffer; diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 2111bad72c72..a5c6be164254 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1240,58 +1240,17 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova, void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length) { - struct iopt_area_contig_iter iter; - struct io_pagetable *iopt; - unsigned long last_iova; - struct iopt_area *area; - - if (WARN_ON(!length) || - WARN_ON(check_add_overflow(iova, length - 1, &last_iova))) - return; - - mutex_lock(&access->ioas_lock); + guard(mutex)(&access->ioas_lock); /* * The driver must be doing something wrong if it calls this before an * iommufd_access_attach() or after an iommufd_access_detach(). */ - if (WARN_ON(!access->ioas_unpin)) { - mutex_unlock(&access->ioas_lock); + if (WARN_ON(!access->ioas_unpin)) return; - } - iopt = &access->ioas_unpin->iopt; - - down_read(&iopt->iova_rwsem); - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) - iopt_area_remove_access( - area, iopt_area_iova_to_index(area, iter.cur_iova), - iopt_area_iova_to_index( - area, - min(last_iova, iopt_area_last_iova(area)))); - WARN_ON(!iopt_area_contig_done(&iter)); - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); + iopt_unpin_pages(&access->ioas_unpin->iopt, iova, length); } EXPORT_SYMBOL_NS_GPL(iommufd_access_unpin_pages, "IOMMUFD");

-static bool iopt_area_contig_is_aligned(struct iopt_area_contig_iter *iter) -{ - if (iopt_area_start_byte(iter->area, iter->cur_iova) % PAGE_SIZE) - return false; - - if (!iopt_area_contig_done(iter) && - (iopt_area_start_byte(iter->area, iopt_area_last_iova(iter->area)) % - PAGE_SIZE) != (PAGE_SIZE - 1)) - return false; - return true; -} - -static bool check_area_prot(struct iopt_area *area, unsigned int flags) -{ - if (flags & IOMMUFD_ACCESS_RW_WRITE) - return area->iommu_prot & IOMMU_WRITE; - return area->iommu_prot & IOMMU_READ; -} - /** * iommufd_access_pin_pages() - Return a list of pages under the iova * @access: IOAS access to act on @@ -1315,76 +1274,16 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length, struct page **out_pages, unsigned int flags) { - struct iopt_area_contig_iter iter; - struct io_pagetable *iopt; - unsigned long last_iova; - struct iopt_area *area; - int rc; - /* Driver's ops don't support pin_pages */ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && WARN_ON(access->iova_alignment != PAGE_SIZE || !access->ops->unmap)) return -EINVAL;

- if (!length) - return -EINVAL; - if (check_add_overflow(iova, length - 1, &last_iova)) - return -EOVERFLOW; - - mutex_lock(&access->ioas_lock); - if (!access->ioas) { - mutex_unlock(&access->ioas_lock); + guard(mutex)(&access->ioas_lock); + if (!access->ioas) return -ENOENT; - } - iopt = &access->ioas->iopt; - - down_read(&iopt->iova_rwsem); - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) { - unsigned long last = min(last_iova, iopt_area_last_iova(area)); - unsigned long last_index = iopt_area_iova_to_index(area, last); - unsigned long index = - iopt_area_iova_to_index(area, iter.cur_iova); - - if (area->prevent_access || - !iopt_area_contig_is_aligned(&iter)) { - rc = -EINVAL; - goto err_remove; - } - - if (!check_area_prot(area, flags)) { - rc = -EPERM; - goto err_remove; - } - - rc = iopt_area_add_access(area, index, last_index, out_pages, - flags); - if (rc) - goto err_remove; - out_pages += last_index - index + 1; - } - if (!iopt_area_contig_done(&iter)) { - rc = -ENOENT; - goto err_remove; - } - - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); - return 0; - -err_remove: - if (iova < iter.cur_iova) { - last_iova = iter.cur_iova - 1; - iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) - iopt_area_remove_access( - area, - iopt_area_iova_to_index(area, iter.cur_iova), - iopt_area_iova_to_index( - area, min(last_iova, - iopt_area_last_iova(area)))); - } - up_read(&iopt->iova_rwsem); - mutex_unlock(&access->ioas_lock); - return rc; + return iopt_pin_pages(&access->ioas->iopt, iova, length, out_pages, + flags); } EXPORT_SYMBOL_NS_GPL(iommufd_access_pin_pages, "IOMMUFD");

@@ -1431,7 +1330,7 @@ int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, goto err_out; }

- if (!check_area_prot(area, flags)) { + if (!iopt_area_check_prot(area, flags)) { rc = -EPERM; goto err_out; } diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 8a790e597e12..4dfe14dcbb51 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1472,3 +1472,98 @@ int iopt_table_enforce_dev_resv_regions(struct io_pagetable *iopt, up_write(&iopt->iova_rwsem); return rc; } + +static bool iopt_area_contig_is_aligned(struct iopt_area_contig_iter *iter) +{ + if (iopt_area_start_byte(iter->area, iter->cur_iova) % PAGE_SIZE) + return false; + + if (!iopt_area_contig_done(iter) && + (iopt_area_start_byte(iter->area, iopt_area_last_iova(iter->area)) % + PAGE_SIZE) != (PAGE_SIZE - 1)) + return false; + return true; +} + +int iopt_pin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct page **out_pages, + unsigned int flags) +{ + struct iopt_area_contig_iter iter; + unsigned long last_iova; + struct iopt_area *area; + int rc; + + if (!length) + return -EINVAL; + if (check_add_overflow(iova, length - 1, &last_iova)) + return -EOVERFLOW; + + down_read(&iopt->iova_rwsem); + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) { + unsigned long last = min(last_iova, iopt_area_last_iova(area)); + unsigned long last_index = iopt_area_iova_to_index(area, last); + unsigned long index = + iopt_area_iova_to_index(area, iter.cur_iova); + + if (area->prevent_access || + !iopt_area_contig_is_aligned(&iter)) { + rc = -EINVAL; + goto err_remove; + } + + if (!iopt_area_check_prot(area, flags)) { + rc = -EPERM; + goto err_remove; + } + + rc = iopt_area_add_access(area, index, last_index, out_pages, + flags); + if (rc) + goto err_remove; + out_pages += last_index - index + 1; + } + if (!iopt_area_contig_done(&iter)) { + rc = -ENOENT; + goto err_remove; + } + + up_read(&iopt->iova_rwsem); + return 0; + +err_remove: + if (iova < iter.cur_iova) { + last_iova = iter.cur_iova - 1; + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) + iopt_area_remove_access( + area, + iopt_area_iova_to_index(area, iter.cur_iova), + iopt_area_iova_to_index( + area, min(last_iova, + iopt_area_last_iova(area)))); + } + up_read(&iopt->iova_rwsem); + return rc; +} + +void iopt_unpin_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length) +{ + struct iopt_area_contig_iter iter; + unsigned long last_iova; + struct iopt_area *area; + + if (WARN_ON(!length) || + WARN_ON(check_add_overflow(iova, length - 1, &last_iova))) + return; + + down_read(&iopt->iova_rwsem); + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) + iopt_area_remove_access( + area, iopt_area_iova_to_index(area, iter.cur_iova), + iopt_area_iova_to_index( + area, + min(last_iova, iopt_area_last_iova(area)))); + WARN_ON(!iopt_area_contig_done(&iter)); + up_read(&iopt->iova_rwsem); +}

Introduce a new IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl for user space to allocate a HW QUEUE object for a vIOMMU specific HW-accelerated queue, e.g.: - NVIDIA's Virtual Command Queue - AMD vIOMMU's Command Buffer, Event Log Buffer, and PPR Log Buffer

This is a vIOMMU based ioctl. Simply increase the refcount of the vIOMMU.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 2 + include/uapi/linux/iommufd.h | 42 ++++++++++ drivers/iommu/iommufd/main.c | 6 ++ drivers/iommu/iommufd/viommu.c | 104 ++++++++++++++++++++++++ 4 files changed, 154 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 79160b039bc7..36a4e060982f 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -611,6 +611,8 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_viommu_destroy(struct iommufd_object *obj); int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd); void iommufd_vdevice_destroy(struct iommufd_object *obj); +int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_hw_queue_destroy(struct iommufd_object *obj);

#ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index cc90299a08d9..001e2deb5a2d 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -56,6 +56,7 @@ enum { IOMMUFD_CMD_VDEVICE_ALLOC = 0x91, IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92, IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93, + IOMMUFD_CMD_HW_QUEUE_ALLOC = 0x94, };

/** @@ -1147,4 +1148,45 @@ struct iommu_veventq_alloc { __u32 __reserved; }; #define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC) + +/** + * enum iommu_hw_queue_type - HW Queue Type + * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use + */ +enum iommu_hw_queue_type { + IOMMU_HW_QUEUE_TYPE_DEFAULT = 0, +}; + +/** + * struct iommu_hw_queue_alloc - ioctl(IOMMU_HW_QUEUE_ALLOC) + * @size: sizeof(struct iommu_hw_queue_alloc) + * @flags: Must be 0 + * @viommu_id: Virtual IOMMU ID to associate the HW queue with + * @type: One of enum iommu_hw_queue_type + * @index: The logical index to the HW queue per virtual IOMMU for a multi-queue + * model + * @out_hw_queue_id: The ID of the new HW queue + * @base_addr: Base address of the queue memory in guest physical address space + * @length: Length of the queue memory in the guest physical address space + * + * Allocate a HW queue object for a vIOMMU-specific HW-accelerated queue, which + * allows HW to access a guest queue memory described by @base_addr and @length. + * Upon success, the underlying physical pages of the guest queue memory will be + * pinned to prevent VMM from unmapping them in the IOAS until the HW queue gets + * destroyed. + * + * A vIOMMU can allocate multiple queues, but it must use a different @index to + * separate each allocation, e.g. HW queue0, HW queue1, ... + */ +struct iommu_hw_queue_alloc { + __u32 size; + __u32 flags; + __u32 viommu_id; + __u32 type; + __u32 index; + __u32 out_hw_queue_id; + __aligned_u64 base_addr; + __aligned_u64 length; +}; +#define IOMMU_HW_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HW_QUEUE_ALLOC) #endif diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 2b9ee9b4a424..10410e2f710a 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -292,6 +292,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_fault_alloc fault; struct iommu_hw_info info; + struct iommu_hw_queue_alloc hw_queue; struct iommu_hwpt_alloc hwpt; struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; struct iommu_hwpt_invalidate cache; @@ -334,6 +335,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { struct iommu_fault_alloc, out_fault_fd), IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info, __reserved), + IOCTL_OP(IOMMU_HW_QUEUE_ALLOC, iommufd_hw_queue_alloc_ioctl, + struct iommu_hw_queue_alloc, length), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, __reserved), IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap, @@ -490,6 +493,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_FAULT] = { .destroy = iommufd_fault_destroy, }, + [IOMMUFD_OBJ_HW_QUEUE] = { + .destroy = iommufd_hw_queue_destroy, + }, [IOMMUFD_OBJ_HWPT_PAGING] = { .destroy = iommufd_hwpt_paging_destroy, .abort = iommufd_hwpt_paging_abort, diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index a65153458a26..ef41aec0b5bf 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -170,3 +170,107 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) iommufd_put_object(ucmd->ictx, &viommu->obj); return rc; } + +void iommufd_hw_queue_destroy(struct iommufd_object *obj) +{ + struct iommufd_hw_queue *hw_queue = + container_of(obj, struct iommufd_hw_queue, obj); + struct iommufd_viommu *viommu = hw_queue->viommu; + + if (viommu->ops->hw_queue_destroy) + viommu->ops->hw_queue_destroy(hw_queue); + iopt_unpin_pages(&viommu->hwpt->ioas->iopt, hw_queue->base_addr, + hw_queue->length); + refcount_dec(&viommu->obj.users); +} + +int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_hw_queue_alloc *cmd = ucmd->cmd; + struct iommufd_hw_queue *hw_queue; + struct iommufd_hwpt_paging *hwpt; + struct iommufd_viommu *viommu; + struct page **pages; + int max_npages, i; + u64 end; + int rc; + + if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT) + return -EOPNOTSUPP; + if (!cmd->base_addr || !cmd->length) + return -EINVAL; + if (check_add_overflow(cmd->base_addr, cmd->length - 1, &end)) + return -EOVERFLOW; + + max_npages = DIV_ROUND_UP(cmd->length, PAGE_SIZE); + pages = kcalloc(max_npages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + viommu = iommufd_get_viommu(ucmd, cmd->viommu_id); + if (IS_ERR(viommu)) { + rc = PTR_ERR(viommu); + goto out_free; + } + hwpt = viommu->hwpt; + + if (!viommu->ops || !viommu->ops->hw_queue_alloc) { + rc = -EOPNOTSUPP; + goto out_put_viommu; + } + + /* Quick test on the base address */ + if (!iommu_iova_to_phys(hwpt->common.domain, cmd->base_addr)) { + rc = -ENXIO; + goto out_put_viommu; + } + + /* + * The underlying physical pages must be pinned to prevent them from + * being unmapped (via IOMMUFD_CMD_IOAS_UNMAP) during the life cycle + * of the HW QUEUE object. + */ + rc = iopt_pin_pages(&hwpt->ioas->iopt, cmd->base_addr, cmd->length, + pages, 0); + if (rc) + goto out_put_viommu; + + if (viommu->ops->flags & IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA) { + /* Validate if the underlying physical pages are contiguous */ + for (i = 1; i < max_npages && pages[i]; i++) { + if (page_to_pfn(pages[i]) == + page_to_pfn(pages[i - 1]) + 1) + continue; + rc = -EFAULT; + goto out_unpin; + } + } + + hw_queue = viommu->ops->hw_queue_alloc(viommu, cmd->type, cmd->index, + cmd->base_addr, cmd->length); + if (IS_ERR(hw_queue)) { + rc = PTR_ERR(hw_queue); + goto out_unpin; + } + + hw_queue->viommu = viommu; + refcount_inc(&viommu->obj.users); + hw_queue->ictx = ucmd->ictx; + hw_queue->length = cmd->length; + hw_queue->base_addr = cmd->base_addr; + cmd->out_hw_queue_id = hw_queue->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + iommufd_object_abort_and_destroy(ucmd->ictx, &hw_queue->obj); + else + iommufd_object_finalize(ucmd->ictx, &hw_queue->obj); + goto out_put_viommu; + +out_unpin: + iopt_unpin_pages(&hwpt->ioas->iopt, cmd->base_addr, cmd->length); +out_put_viommu: + iommufd_put_object(ucmd->ictx, &viommu->obj); +out_free: + kfree(pages); + return rc; +}

NVIDIA Virtual Command Queue is one of the iommufd users exposing vIOMMU features to user space VMs. Its hardware has a strict rule when mapping and unmapping multiple global CMDQVs to/from a VM-owned VINTF, requiring mappings in ascending order and unmappings in descending order.

The tegra241-cmdqv driver can apply the rule for a mapping in the LVCMDQ allocation handler. However, it can't do the same for an unmapping since user space could start random destroy calls breaking the rule, while the destroy op in the driver level can't reject a destroy call as it returns void.

Add iommufd_hw_queue_depend/undepend for-driver helpers, allowing LVCMDQ allocator to refcount_inc() a sibling LVCMDQ object and LVCMDQ destroyer to refcount_dec(), so that iommufd core will help block a random destroy call that breaks the rule.

This is a bit of compromise, because a driver might end up with abusing the API that deadlocks the objects. So restrict the API to a dependency between two driver-allocated objects of the same type, as iommufd would unlikely build any core-level dependency in this case. And encourage to use the macro version that currently supports the HW QUEUE objects only.

Reviewed-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommufd.h | 44 ++++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/driver.c | 28 ++++++++++++++++++++++ 2 files changed, 72 insertions(+)

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 0b5bea7286b8..ddca0d2835df 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -241,6 +241,10 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, enum iommufd_object_type type); void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj); +int _iommufd_object_depend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended); +void _iommufd_object_undepend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended); struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id); int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, @@ -261,6 +265,18 @@ static inline void iommufd_object_abort(struct iommufd_ctx *ictx, { }

+static inline int _iommufd_object_depend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended) +{ + return -EOPNOTSUPP; +} + +static inline void +_iommufd_object_undepend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended) +{ +} + static inline struct device * iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) { @@ -346,4 +362,32 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, iommufd_object_abort(drv_struct->member.ictx, \ &drv_struct->member.obj); \ }) + +/* + * Helpers for IOMMU driver to build/destroy a dependency between two sibling + * structures created by one of the allocators above + */ +#define iommufd_hw_queue_depend(dependent, depended, member) \ + ({ \ + static_assert(__same_type(struct iommufd_hw_queue, \ + dependent->member)); \ + static_assert(offsetof(typeof(*dependent), member.obj) == 0); \ + static_assert(__same_type(struct iommufd_hw_queue, \ + depended->member)); \ + static_assert(offsetof(typeof(*depended), member.obj) == 0); \ + _iommufd_object_depend(&dependent->member.obj, \ + &depended->member.obj); \ + }) + +#define iommufd_hw_queue_undepend(dependent, depended, member) \ + ({ \ + static_assert(__same_type(struct iommufd_hw_queue, \ + dependent->member)); \ + static_assert(offsetof(typeof(*dependent), member.obj) == 0); \ + static_assert(__same_type(struct iommufd_hw_queue, \ + depended->member)); \ + static_assert(offsetof(typeof(*depended), member.obj) == 0); \ + _iommufd_object_undepend(&dependent->member.obj, \ + &depended->member.obj); \ + }) #endif diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 7980a09761c2..0bcf0438d255 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -50,6 +50,34 @@ void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj) } EXPORT_SYMBOL_NS_GPL(iommufd_object_abort, "IOMMUFD");

+/* Driver should use a per-structure helper in include/linux/iommufd.h */ +int _iommufd_object_depend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended) +{ + /* Reject self dependency that dead locks */ + if (obj_dependent == obj_depended) + return -EINVAL; + /* Only support dependency between two objects of the same type */ + if (obj_dependent->type != obj_depended->type) + return -EINVAL; + + refcount_inc(&obj_depended->users); + return 0; +} +EXPORT_SYMBOL_NS_GPL(_iommufd_object_depend, "IOMMUFD"); + +/* Driver should use a per-structure helper in include/linux/iommufd.h */ +void _iommufd_object_undepend(struct iommufd_object *obj_dependent, + struct iommufd_object *obj_depended) +{ + if (WARN_ON_ONCE(obj_dependent == obj_depended || + obj_dependent->type != obj_depended->type)) + return; + + refcount_dec(&obj_depended->users); +} +EXPORT_SYMBOL_NS_GPL(_iommufd_object_undepend, "IOMMUFD"); + /* Caller should xa_lock(&viommu->vdevs) to protect the return value */ struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)

For vIOMMU passing through HW resources to user space (VMs), allowing a VM to control the passed through HW directly by accessing hardware registers, add an mmap infrastructure to map the physical MMIO pages to user space.

Maintain an maple tree per ictx as a translation table managing mmappable regions, from an allocated for-user mmap offset to an iommufd_mmap struct, where it stores the real PFN range for a remap_pfn_range call.

To allow an IOMMU driver to add and delete mmappable regions onto/from the maple tree, add iommufd_viommu_alloc/destroy_mmap helpers.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_private.h | 11 +++++ include/linux/iommufd.h | 39 ++++++++++++++++ drivers/iommu/iommufd/driver.c | 52 +++++++++++++++++++++ drivers/iommu/iommufd/main.c | 61 +++++++++++++++++++++++++ 4 files changed, 163 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 36a4e060982f..c87326d7ecfc 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -7,6 +7,7 @@ #include <linux/iommu.h> #include <linux/iommufd.h> #include <linux/iova_bitmap.h> +#include <linux/maple_tree.h> #include <linux/rwsem.h> #include <linux/uaccess.h> #include <linux/xarray.h> @@ -44,6 +45,7 @@ struct iommufd_ctx { struct xarray groups; wait_queue_head_t destroy_wait; struct rw_semaphore ioas_creation_lock; + struct maple_tree mt_mmap;

struct mutex sw_msi_lock; struct list_head sw_msi_list; @@ -55,6 +57,15 @@ struct iommufd_ctx { struct iommufd_ioas *vfio_ioas; };

+/* Entry for iommufd_ctx::mt_mmap */ +struct iommufd_mmap { + struct iommufd_object *owner; + + /* Physical range for remap_pfn_range() */ + unsigned long base_pfn; + unsigned long num_pfns; +}; + /* * The IOVA to PFN map. The map automatically copies the PFNs into multiple * domains and permits sharing of PFNs between io_pagetable instances. This diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index ddca0d2835df..47af130f4212 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -245,6 +245,10 @@ int _iommufd_object_depend(struct iommufd_object *obj_dependent, struct iommufd_object *obj_depended); void _iommufd_object_undepend(struct iommufd_object *obj_dependent, struct iommufd_object *obj_depended); +int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner, + phys_addr_t base, size_t length, unsigned long *offset); +void _iommufd_destroy_mmap(struct iommufd_ctx *ictx, + struct iommufd_object *owner, unsigned long offset); struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id); int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu, @@ -277,6 +281,20 @@ _iommufd_object_undepend(struct iommufd_object *obj_dependent, { }

+static inline int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, + struct iommufd_object *owner, + phys_addr_t base, size_t length, + unsigned long *offset) +{ + return -EOPNOTSUPP; +} + +static inline void _iommufd_destroy_mmap(struct iommufd_ctx *ictx, + struct iommufd_object *owner, + unsigned long offset) +{ +} + static inline struct device * iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) { @@ -390,4 +408,25 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu, _iommufd_object_undepend(&dependent->member.obj, \ &depended->member.obj); \ }) + +/* + * Helpers for IOMMU driver to alloc/destroy an mmapable area for a structure. + * Driver should report the @out_offset and @length to user space for an mmap() + */ +#define iommufd_viommu_alloc_mmap(viommu, member, base, length, out_offset) \ + ({ \ + static_assert(__same_type(struct iommufd_viommu, \ + viommu->member)); \ + static_assert(offsetof(typeof(*viommu), member.obj) == 0); \ + _iommufd_alloc_mmap(viommu->member.ictx, &viommu->member.obj, \ + base, length, out_offset); \ + }) +#define iommufd_viommu_destroy_mmap(viommu, member, offset) \ + ({ \ + static_assert(__same_type(struct iommufd_viommu, \ + viommu->member)); \ + static_assert(offsetof(typeof(*viommu), member.obj) == 0); \ + _iommufd_destroy_mmap(viommu->member.ictx, \ + &viommu->member.obj, offset); \ + }) #endif diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 0bcf0438d255..2d2695e2562d 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -78,6 +78,58 @@ void _iommufd_object_undepend(struct iommufd_object *obj_dependent, } EXPORT_SYMBOL_NS_GPL(_iommufd_object_undepend, "IOMMUFD");

+/* + * Allocate an @offset to return to user space to use for an mmap() syscall + * + * Driver should use a per-structure helper in include/linux/iommufd.h + */ +int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner, + phys_addr_t base, size_t length, unsigned long *offset) +{ + struct iommufd_mmap *immap; + unsigned long startp; + int num_pfns, rc; + + if (WARN_ON_ONCE(!offset)) + return -EINVAL; + if (!PAGE_ALIGNED(base)) + return -EINVAL; + if (!length || !PAGE_ALIGNED(length)) + return -EINVAL; + num_pfns = length >> PAGE_SHIFT; + + immap = kzalloc(sizeof(*immap), GFP_KERNEL); + if (!immap) + return -ENOMEM; + immap->owner = owner; + immap->base_pfn = base >> PAGE_SHIFT; + immap->num_pfns = length >> PAGE_SHIFT; + + rc = mtree_alloc_range(&ictx->mt_mmap, &startp, immap, immap->num_pfns, + 0, U32_MAX >> PAGE_SHIFT, GFP_KERNEL); + if (rc < 0) { + kfree(immap); + return rc; + } + + /* mmap() syscall will right-shift the offset in vma->vm_pgoff */ + *offset = startp << PAGE_SHIFT; + return 0; +} +EXPORT_SYMBOL_NS_GPL(_iommufd_alloc_mmap, "IOMMUFD"); + +/* Driver should use a per-structure helper in include/linux/iommufd.h */ +void _iommufd_destroy_mmap(struct iommufd_ctx *ictx, + struct iommufd_object *owner, unsigned long offset) +{ + struct iommufd_mmap *immap; + + immap = mtree_erase(&ictx->mt_mmap, offset >> PAGE_SHIFT); + WARN_ON_ONCE(!immap || immap->owner != owner); + kfree(immap); +} +EXPORT_SYMBOL_NS_GPL(_iommufd_destroy_mmap, "IOMMUFD"); + /* Caller should xa_lock(&viommu->vdevs) to protect the return value */ struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 10410e2f710a..1d7f3584aea0 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -213,6 +213,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp) xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT); xa_init(&ictx->groups); ictx->file = filp; + mt_init_flags(&ictx->mt_mmap, MT_FLAGS_ALLOC_RANGE); init_waitqueue_head(&ictx->destroy_wait); mutex_init(&ictx->sw_msi_lock); INIT_LIST_HEAD(&ictx->sw_msi_list); @@ -410,11 +411,71 @@ static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, return ret; }

+static void iommufd_fops_vma_open(struct vm_area_struct *vma) +{ + struct iommufd_mmap *immap = vma->vm_private_data; + + refcount_inc(&immap->owner->users); +} + +static void iommufd_fops_vma_close(struct vm_area_struct *vma) +{ + struct iommufd_mmap *immap = vma->vm_private_data; + + refcount_dec(&immap->owner->users); +} + +static const struct vm_operations_struct iommufd_vma_ops = { + .open = iommufd_fops_vma_open, + .close = iommufd_fops_vma_close, +}; + +/* + * Kernel driver must first use the for-driver helpers to register an mmappable + * MMIO region to the iommufd core to allocate an offset. Then, it should report + * to user space this offset and the length of the MMIO region for mmap syscall, + * via a prior IOMMU_VIOMMU_ALLOC ioctl. + */ +static int iommufd_fops_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct iommufd_ctx *ictx = filp->private_data; + size_t length = vma->vm_end - vma->vm_start; + struct iommufd_mmap *immap; + int rc; + + if (!PAGE_ALIGNED(length)) + return -EINVAL; + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + if (vma->vm_flags & VM_EXEC) + return -EPERM; + + /* vma->vm_pgoff carries an index to an mtree entry (immap) */ + immap = mtree_load(&ictx->mt_mmap, vma->vm_pgoff); + if (!immap) + return -ENXIO; + if (length >> PAGE_SHIFT != immap->num_pfns) + return -ENXIO; + + vma->vm_pgoff = 0; + vma->vm_private_data = immap; + vma->vm_ops = &iommufd_vma_ops; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO); + + rc = remap_pfn_range(vma, vma->vm_start, immap->base_pfn, length, + vma->vm_page_prot); + if (!rc) /* vm_ops.open won't be called for mmap itself. */ + refcount_inc(&immap->owner->users); + return rc; +} + static const struct file_operations iommufd_fops = { .owner = THIS_MODULE, .open = iommufd_fops_open, .release = iommufd_fops_release, .unlocked_ioctl = iommufd_fops_ioctl, + .mmap = iommufd_fops_mmap, };

/**

Extend the loopback test to a new mmap page.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 4 +++ drivers/iommu/iommufd/selftest.c | 41 ++++++++++++++++++++++--- tools/testing/selftests/iommu/iommufd.c | 7 +++++ 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 51cd744a354f..8fc618b2bcf9 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -232,12 +232,16 @@ struct iommu_hwpt_invalidate_selftest { * (IOMMU_VIOMMU_TYPE_SELFTEST) * @in_data: Input random data from user space * @out_data: Output data (matching @in_data) to user space + * @out_mmap_offset: The offset argument for mmap syscall + * @out_mmap_length: The length argument for mmap syscall * * Simply set @out_data=@in_data for a loopback test */ struct iommu_viommu_selftest { __u32 in_data; __u32 out_data; + __aligned_u64 out_mmap_offset; + __aligned_u64 out_mmap_length; };

/* Should not be equal to any defined value in enum iommu_viommu_invalidate_data_type */ diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 692c29ccdc46..36e7fc0059dc 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -149,6 +149,9 @@ struct mock_viommu { struct iommufd_viommu core; struct mock_iommu_domain *s2_parent; struct mock_hw_queue *hw_queue[IOMMU_TEST_HW_QUEUE_MAX]; + + unsigned long mmap_offset; + u32 *page; /* Mmap page to test u32 type of in_data */ };

static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) @@ -647,9 +650,14 @@ static void mock_viommu_destroy(struct iommufd_viommu *viommu) { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); + struct mock_viommu *mock_viommu = to_mock_viommu(viommu);

if (refcount_dec_and_test(&mock_iommu->users)) complete(&mock_iommu->complete); + if (mock_viommu->mmap_offset) + iommufd_viommu_destroy_mmap(mock_viommu, core, + mock_viommu->mmap_offset); + free_page((unsigned long)mock_viommu->page);

/* iommufd core frees mock_viommu and viommu */ } @@ -831,17 +839,42 @@ mock_viommu_alloc(struct device *dev, struct iommu_domain *domain, return ERR_CAST(mock_viommu);

if (user_data) { + mock_viommu->page = + (u32 *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!mock_viommu->page) { + rc = -ENOMEM; + goto err_destroy_struct; + } + + rc = iommufd_viommu_alloc_mmap(mock_viommu, core, + __pa(mock_viommu->page), + PAGE_SIZE, + &mock_viommu->mmap_offset); + if (rc) + goto err_free_page; + + /* For loopback tests on both the page and out_data */ + *mock_viommu->page = data.in_data; data.out_data = data.in_data; + data.out_mmap_length = PAGE_SIZE; + data.out_mmap_offset = mock_viommu->mmap_offset; rc = iommu_copy_struct_to_user( user_data, &data, IOMMU_VIOMMU_TYPE_SELFTEST, out_data); - if (rc) { - iommufd_struct_destroy(mock_viommu, core); - return ERR_PTR(rc); - } + if (rc) + goto err_destroy_mmap; }

refcount_inc(&mock_iommu->users); return &mock_viommu->core; + +err_destroy_mmap: + iommufd_viommu_destroy_mmap(mock_viommu, core, + mock_viommu->mmap_offset); +err_free_page: + free_page((unsigned long)mock_viommu->page); +err_destroy_struct: + iommufd_struct_destroy(mock_viommu, core); + return ERR_PTR(rc); }

static const struct iommu_ops mock_ops = { diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index bfdb3a3f1d23..38ad71efb338 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2799,12 +2799,19 @@ TEST_F(iommufd_viommu, viommu_alloc_with_data) struct iommu_viommu_selftest data = { .in_data = 0xbeef, }; + uint32_t *test;

if (self->device_id) { test_cmd_viommu_alloc(self->device_id, self->hwpt_id, IOMMU_VIOMMU_TYPE_SELFTEST, &data, sizeof(data), &self->viommu_id); assert(data.out_data == data.in_data); + test = mmap(NULL, data.out_mmap_length, PROT_READ | PROT_WRITE, + MAP_SHARED, self->fd, data.out_mmap_offset); + assert(test && *test == data.in_data); + EXPECT_ERRNO(EBUSY, + _test_ioctl_destroy(self->fd, self->viommu_id)); + munmap(test, data.out_mmap_length); } }

An impl driver might want to allocate its own type of vIOMMU object or the standard IOMMU_VIOMMU_TYPE_ARM_SMMUV3 by setting up its own SW/HW bits, as the tegra241-cmdqv driver will add IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV.

Add a vsmmu_alloc op and prioritize it in arm_vsmmu_alloc().

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 6 ++++++ .../iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 17 +++++++++++------ 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 6b8f0d20dac3..a5835af72417 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -16,6 +16,7 @@ #include <linux/sizes.h>

struct arm_smmu_device; +struct arm_smmu_domain;

/* MMIO registers */ #define ARM_SMMU_IDR0 0x0 @@ -720,6 +721,11 @@ struct arm_smmu_impl_ops { int (*init_structures)(struct arm_smmu_device *smmu); struct arm_smmu_cmdq *(*get_secondary_cmdq)( struct arm_smmu_device *smmu, struct arm_smmu_cmdq_ent *ent); + struct arm_vsmmu *(*vsmmu_alloc)( + struct arm_smmu_device *smmu, + struct arm_smmu_domain *smmu_domain, struct iommufd_ctx *ictx, + unsigned int viommu_type, + const struct iommu_user_data *user_data); };

/* An SMMUv3 instance */ diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 66855cae775e..b316d1df043f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -392,10 +392,7 @@ struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, iommu_get_iommu_dev(dev, struct arm_smmu_device, iommu); struct arm_smmu_master *master = dev_iommu_priv_get(dev); struct arm_smmu_domain *s2_parent = to_smmu_domain(parent); - struct arm_vsmmu *vsmmu; - - if (viommu_type != IOMMU_VIOMMU_TYPE_ARM_SMMUV3) - return ERR_PTR(-EOPNOTSUPP); + struct arm_vsmmu *vsmmu = ERR_PTR(-EOPNOTSUPP);

if (!(smmu->features & ARM_SMMU_FEAT_NESTING)) return ERR_PTR(-EOPNOTSUPP); @@ -423,8 +420,16 @@ struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, !(smmu->features & ARM_SMMU_FEAT_S2FWB)) return ERR_PTR(-EOPNOTSUPP);

- vsmmu = iommufd_viommu_alloc(ictx, struct arm_vsmmu, core, - &arm_vsmmu_ops); + /* Prioritize the impl that may support IOMMU_VIOMMU_TYPE_ARM_SMMUV3 */ + if (master->smmu->impl_ops && master->smmu->impl_ops->vsmmu_alloc) + vsmmu = master->smmu->impl_ops->vsmmu_alloc( + master->smmu, s2_parent, ictx, viommu_type, user_data); + if (PTR_ERR(vsmmu) == -EOPNOTSUPP) { + /* Otherwise, allocate an IOMMU_VIOMMU_TYPE_ARM_SMMUV3 here */ + if (viommu_type == IOMMU_VIOMMU_TYPE_ARM_SMMUV3) + vsmmu = iommufd_viommu_alloc(ictx, struct arm_vsmmu, + core, &arm_vsmmu_ops); + } if (IS_ERR(vsmmu)) return ERR_CAST(vsmmu);

Repurpose the @__reserved field in the struct iommu_hw_info_arm_smmuv3, to an HW implementation-defined field @impl.

This will be used by Tegra241 CMDQV implementation on top of a standard ARM SMMUv3 IOMMU. The @impl will be only valid if @flags is set with an implementation-defined flag.

Thus in the driver-level, add an hw_info impl op that will return such a flag and fill the impl field.

Reviewed-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 1 + include/uapi/linux/iommufd.h | 4 ++-- .../iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 17 ++++++++++++++--- 3 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index a5835af72417..bab7a9ce1283 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -726,6 +726,7 @@ struct arm_smmu_impl_ops { struct arm_smmu_domain *smmu_domain, struct iommufd_ctx *ictx, unsigned int viommu_type, const struct iommu_user_data *user_data); + u32 (*hw_info)(struct arm_smmu_device *smmu, u32 *impl); };

/* An SMMUv3 instance */ diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 001e2deb5a2d..28ab42a85268 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -554,7 +554,7 @@ struct iommu_hw_info_vtd { * (IOMMU_HW_INFO_TYPE_ARM_SMMUV3) * * @flags: Must be set to 0 - * @__reserved: Must be 0 + * @impl: Must be 0 * @idr: Implemented features for ARM SMMU Non-secure programming interface * @iidr: Information about the implementation and implementer of ARM SMMU, * and architecture version supported @@ -585,7 +585,7 @@ struct iommu_hw_info_vtd { */ struct iommu_hw_info_arm_smmuv3 { __u32 flags; - __u32 __reserved; + __u32 impl; __u32 idr[6]; __u32 iidr; __u32 aidr; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index b316d1df043f..8ea9a022e444 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -10,6 +10,7 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct arm_smmu_device *smmu = master->smmu; struct iommu_hw_info_arm_smmuv3 *info; u32 __iomem *base_idr; unsigned int i; @@ -18,15 +19,25 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type) if (!info) return ERR_PTR(-ENOMEM);

- base_idr = master->smmu->base + ARM_SMMU_IDR0; + base_idr = smmu->base + ARM_SMMU_IDR0; for (i = 0; i <= 5; i++) info->idr[i] = readl_relaxed(base_idr + i); - info->iidr = readl_relaxed(master->smmu->base + ARM_SMMU_IIDR); - info->aidr = readl_relaxed(master->smmu->base + ARM_SMMU_AIDR); + info->iidr = readl_relaxed(smmu->base + ARM_SMMU_IIDR); + info->aidr = readl_relaxed(smmu->base + ARM_SMMU_AIDR);

*length = sizeof(*info); *type = IOMMU_HW_INFO_TYPE_ARM_SMMUV3;

+ if (smmu->impl_ops && smmu->impl_ops->hw_info) { + u32 flags, impl; + + flags = smmu->impl_ops->hw_info(smmu, &impl); + if (flags) { + info->impl = impl; + info->flags |= flags; + } + } + return info; }

The current flow of tegra241_cmdqv_remove_vintf() is: 1. For each LVCMDQ, tegra241_vintf_remove_lvcmdq(): a. Disable the LVCMDQ HW b. Release the LVCMDQ SW resource 2. For current VINTF, tegra241_vintf_hw_deinit(): c. Disable all LVCMDQ HWs d. Disable VINTF HW

Obviously, the step 1.a and the step 2.c are redundant.

Since tegra241_vintf_hw_deinit() disables all of its LVCMDQ HWs, it could simplify the flow in tegra241_cmdqv_remove_vintf() by calling that first: 1. For current VINTF, tegra241_vintf_hw_deinit(): a. Disable all LVCMDQ HWs b. Disable VINTF HW 2. Release all LVCMDQ SW resources

Drop tegra241_vintf_remove_lvcmdq(), and move tegra241_vintf_free_lvcmdq() as the new step 2.

Acked-by: Pranjal Shrivastava praan@google.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index ba029f7d24ce..8d418c131b1b 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -628,24 +628,17 @@ static int tegra241_cmdqv_init_vintf(struct tegra241_cmdqv *cmdqv, u16 max_idx,

/* Remove Helpers */

-static void tegra241_vintf_remove_lvcmdq(struct tegra241_vintf *vintf, u16 lidx) -{ - tegra241_vcmdq_hw_deinit(vintf->lvcmdqs[lidx]); - tegra241_vintf_free_lvcmdq(vintf, lidx); -} - static void tegra241_cmdqv_remove_vintf(struct tegra241_cmdqv *cmdqv, u16 idx) { struct tegra241_vintf *vintf = cmdqv->vintfs[idx]; u16 lidx;

+ tegra241_vintf_hw_deinit(vintf); + /* Remove LVCMDQ resources */ for (lidx = 0; lidx < vintf->cmdqv->num_lvcmdqs_per_vintf; lidx++) if (vintf->lvcmdqs[lidx]) - tegra241_vintf_remove_lvcmdq(vintf, lidx); - - /* Remove VINTF resources */ - tegra241_vintf_hw_deinit(vintf); + tegra241_vintf_free_lvcmdq(vintf, lidx);

dev_dbg(cmdqv->dev, "VINTF%u: deallocated\n", vintf->idx); tegra241_cmdqv_deinit_vintf(cmdqv, idx);

The CMDQV HW supports a user-space use for virtualization cases. It allows the VM to issue guest-level TLBI or ATC_INV commands directly to the queue and executes them without a VMEXIT, as HW will replace the VMID field in a TLBI command and the SID field in an ATC_INV command with the preset VMID and SID.

This is built upon the vIOMMU infrastructure by allowing VMM to allocate a VINTF (as a vIOMMU object) and assign VCMDQs (HW QUEUE objs) to the VINTF.

So firstly, replace the standard vSMMU model with the VINTF implementation but reuse the standard cache_invalidate op (for unsupported commands) and the standard alloc_domain_nested op (for standard nested STE).

Each VINTF has two 64KB MMIO pages (128B per logical VCMDQ): - Page0 (directly accessed by guest) has all the control and status bits. - Page1 (trapped by VMM) has guest-owned queue memory location/size info.

VMM should trap the emulated VINTF0's page1 of the guest VM for the guest- level VCMDQ location/size info and forward that to the kernel to translate to a physical memory location to program the VCMDQ HW during an allocation call. Then, it should mmap the assigned VINTF's page0 to the VINTF0 page0 of the guest VM. This allows the guest OS to read and write the guest-own VINTF's page0 for direct control of the VCMDQ HW.

For ATC invalidation commands that hold an SID, it requires all devices to register their virtual SIDs to the SID_MATCH registers and their physical SIDs to the pairing SID_REPLACE registers, so that HW can use those as a lookup table to replace those virtual SIDs with the correct physical SIDs. Thus, implement the driver-allocated vDEVICE op with a tegra241_vintf_sid structure to allocate SID_REPLACE and to program the SIDs accordingly.

This enables the HW accelerated feature for NVIDIA Grace CPU. Compared to the standard SMMUv3 operating in the nested translation mode trapping CMDQ for TLBI and ATC_INV commands, this gives a huge performance improvement: 70% to 90% reductions of invalidation time were measured by various DMA unmap tests running in a guest OS.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 15 + include/uapi/linux/iommufd.h | 51 ++- .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 6 +- .../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 413 +++++++++++++++++- 4 files changed, 476 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index bab7a9ce1283..d3f18a286447 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -1000,6 +1000,14 @@ int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, bool sync);

+static inline phys_addr_t +arm_smmu_domain_ipa_to_pa(struct arm_smmu_domain *smmu_domain, u64 ipa) +{ + if (WARN_ON_ONCE(smmu_domain->stage != ARM_SMMU_DOMAIN_S2)) + return 0; + return iommu_iova_to_phys(&smmu_domain->domain, ipa); +} + #ifdef CONFIG_ARM_SMMU_V3_SVA bool arm_smmu_sva_supported(struct arm_smmu_device *smmu); bool arm_smmu_master_sva_supported(struct arm_smmu_master *master); @@ -1076,9 +1084,16 @@ int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state, void arm_smmu_attach_commit_vmaster(struct arm_smmu_attach_state *state); void arm_smmu_master_clear_vmaster(struct arm_smmu_master *master); int arm_vmaster_report_event(struct arm_smmu_vmaster *vmaster, u64 *evt); +struct iommu_domain * +arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data); +int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array); #else #define arm_smmu_hw_info NULL #define arm_vsmmu_alloc NULL +#define arm_vsmmu_alloc_domain_nested NULL +#define arm_vsmmu_cache_invalidate NULL

static inline int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 28ab42a85268..a8a97f43ecc4 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -549,12 +549,26 @@ struct iommu_hw_info_vtd { __aligned_u64 ecap_reg; };

+/** + * enum iommu_hw_info_arm_smmuv3_flags - Flags for ARM SMMUv3 hw_info + * @IOMMU_HW_INFO_ARM_SMMUV3_HAS_TEGRA241_CMDQV: Tegra241 implementation with + * CMDQV support; @impl is valid + */ +enum iommu_hw_info_arm_smmuv3_flags { + IOMMU_HW_INFO_ARM_SMMUV3_HAS_TEGRA241_CMDQV = 1 << 0, +}; + /** * struct iommu_hw_info_arm_smmuv3 - ARM SMMUv3 hardware information * (IOMMU_HW_INFO_TYPE_ARM_SMMUV3) * - * @flags: Must be set to 0 - * @impl: Must be 0 + * @flags: Combination of enum iommu_hw_info_arm_smmuv3_flags + * @impl: Implementation-defined bits when the following flags are set: + * - IOMMU_HW_INFO_ARM_SMMUV3_HAS_TEGRA241_CMDQV + * Bits[15:12] - Log2 of the total number of SID replacements + * Bits[11:08] - Log2 of the total number of VINTFs per vIOMMU + * Bits[07:04] - Log2 of the total number of VCMDQs per vIOMMU + * Bits[03:00] - Version number for the CMDQ-V HW * @idr: Implemented features for ARM SMMU Non-secure programming interface * @iidr: Information about the implementation and implementer of ARM SMMU, * and architecture version supported @@ -952,10 +966,28 @@ struct iommu_fault_alloc { * enum iommu_viommu_type - Virtual IOMMU Type * @IOMMU_VIOMMU_TYPE_DEFAULT: Reserved for future use * @IOMMU_VIOMMU_TYPE_ARM_SMMUV3: ARM SMMUv3 driver specific type + * @IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV Extension for SMMUv3 */ enum iommu_viommu_type { IOMMU_VIOMMU_TYPE_DEFAULT = 0, IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV = 2, +}; + +/** + * struct iommu_viommu_tegra241_cmdqv - NVIDIA Tegra241 CMDQV Virtual Interface + * (IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV) + * @out_vintf_mmap_offset: mmap offset argument for VINTF's page0 + * @out_vintf_mmap_length: mmap length argument for VINTF's page0 + * + * Both @out_vintf_mmap_offset and @out_vintf_mmap_length are reported by kernel + * for user space to mmap the VINTF page0 from the host physical address space + * to the guest physical address space so that a guest kernel can directly R/W + * access to the VINTF page0 in order to control its virtual command queues. + */ +struct iommu_viommu_tegra241_cmdqv { + __aligned_u64 out_vintf_mmap_offset; + __aligned_u64 out_vintf_mmap_length; };

/** @@ -1152,9 +1184,24 @@ struct iommu_veventq_alloc { /** * enum iommu_hw_queue_type - HW Queue Type * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use + * @IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV: NVIDIA Tegra241 CMDQV Extension for + * ARM SMMUv3 */ enum iommu_hw_queue_type { IOMMU_HW_QUEUE_TYPE_DEFAULT = 0, + /* + * TEGRA241_CMDQV requirements (otherwise, allocation will fail) + * - alloc starts from the lowest @index=0 in ascending order + * - destroy starts from the last allocated @index in descending order + * - @base_addr must be aligned to @length in bytes and mapped in IOAS + * - @length must be a power of 2, with a minimum 32 bytes and a maximum + * 2 ^ idr[1].CMDQS * 16 bytes (use GET_HW_INFO call to read idr[1] + * from struct iommu_hw_info_arm_smmuv3) + * - suggest to back the queue memory with contiguous physical pages or + * a single huge page with alignment of the queue size, limit vSMMU's + * IDR1.CMDQS to the huge page size divided by 16 bytes + */ + IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV = 1, };

/** diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c index 8ea9a022e444..e88adf00ec40 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -227,7 +227,7 @@ static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg, return 0; }

-static struct iommu_domain * +struct iommu_domain * arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { @@ -338,8 +338,8 @@ static int arm_vsmmu_convert_user_cmd(struct arm_vsmmu *vsmmu, return 0; }

-static int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, - struct iommu_user_data_array *array) +int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array) { struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); struct arm_smmu_device *smmu = vsmmu->smmu; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index 869c90b660c1..4f3ecc265d6f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -8,7 +8,9 @@ #include <linux/dma-mapping.h> #include <linux/interrupt.h> #include <linux/iommu.h> +#include <linux/iommufd.h> #include <linux/iopoll.h> +#include <uapi/linux/iommufd.h>

#include <acpi/acpixf.h>

@@ -26,8 +28,10 @@ #define CMDQV_EN BIT(0)

#define TEGRA241_CMDQV_PARAM 0x0004 +#define CMDQV_NUM_SID_PER_VM_LOG2 GENMASK(15, 12) #define CMDQV_NUM_VINTF_LOG2 GENMASK(11, 8) #define CMDQV_NUM_VCMDQ_LOG2 GENMASK(7, 4) +#define CMDQV_VER GENMASK(3, 0)

#define TEGRA241_CMDQV_STATUS 0x0008 #define CMDQV_ENABLED BIT(0) @@ -53,6 +57,9 @@ #define VINTF_STATUS GENMASK(3, 1) #define VINTF_ENABLED BIT(0)

+#define TEGRA241_VINTF_SID_MATCH(s) (0x0040 + 0x4*(s)) +#define TEGRA241_VINTF_SID_REPLACE(s) (0x0080 + 0x4*(s)) + #define TEGRA241_VINTF_LVCMDQ_ERR_MAP_64(m) \ (0x00C0 + 0x8*(m)) #define LVCMDQ_ERR_MAP_NUM_64 2 @@ -114,16 +121,20 @@ MODULE_PARM_DESC(bypass_vcmdq,

/** * struct tegra241_vcmdq - Virtual Command Queue + * @core: Embedded iommufd_hw_queue structure * @idx: Global index in the CMDQV * @lidx: Local index in the VINTF * @enabled: Enable status * @cmdqv: Parent CMDQV pointer * @vintf: Parent VINTF pointer + * @prev: Previous LVCMDQ to depend on * @cmdq: Command Queue struct * @page0: MMIO Page0 base address * @page1: MMIO Page1 base address */ struct tegra241_vcmdq { + struct iommufd_hw_queue core; + u16 idx; u16 lidx;

@@ -131,22 +142,29 @@ struct tegra241_vcmdq {

struct tegra241_cmdqv *cmdqv; struct tegra241_vintf *vintf; + struct tegra241_vcmdq *prev; struct arm_smmu_cmdq cmdq;

void __iomem *page0; void __iomem *page1; }; +#define hw_queue_to_vcmdq(v) container_of(v, struct tegra241_vcmdq, core)

/** * struct tegra241_vintf - Virtual Interface + * @vsmmu: Embedded arm_vsmmu structure * @idx: Global index in the CMDQV * @enabled: Enable status * @hyp_own: Owned by hypervisor (in-kernel) * @cmdqv: Parent CMDQV pointer * @lvcmdqs: List of logical VCMDQ pointers * @base: MMIO base address + * @mmap_offset: Offset argument for mmap() syscall + * @sids: Stream ID replacement resources */ struct tegra241_vintf { + struct arm_vsmmu vsmmu; + u16 idx;

bool enabled; @@ -156,6 +174,24 @@ struct tegra241_vintf { struct tegra241_vcmdq **lvcmdqs;

void __iomem *base; + unsigned long mmap_offset; + + struct ida sids; +}; +#define viommu_to_vintf(v) container_of(v, struct tegra241_vintf, vsmmu.core) + +/** + * struct tegra241_vintf_sid - Virtual Interface Stream ID Replacement + * @core: Embedded iommufd_vdevice structure, holding virtual Stream ID + * @vintf: Parent VINTF pointer + * @sid: Physical Stream ID + * @idx: Replacement index in the VINTF + */ +struct tegra241_vintf_sid { + struct iommufd_vdevice core; + struct tegra241_vintf *vintf; + u32 sid; + u8 idx; };

/** @@ -163,10 +199,12 @@ struct tegra241_vintf { * @smmu: SMMUv3 device * @dev: CMDQV device * @base: MMIO base address + * @base_phys: MMIO physical base address, for mmap * @irq: IRQ number * @num_vintfs: Total number of VINTFs * @num_vcmdqs: Total number of VCMDQs * @num_lvcmdqs_per_vintf: Number of logical VCMDQs per VINTF + * @num_sids_per_vintf: Total number of SID replacements per VINTF * @vintf_ids: VINTF id allocator * @vintfs: List of VINTFs */ @@ -175,12 +213,14 @@ struct tegra241_cmdqv { struct device *dev;

void __iomem *base; + phys_addr_t base_phys; int irq;

/* CMDQV Hardware Params */ u16 num_vintfs; u16 num_vcmdqs; u16 num_lvcmdqs_per_vintf; + u16 num_sids_per_vintf;

struct ida vintf_ids;

@@ -351,6 +391,29 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu,

/* HW Reset Functions */

+/* + * When a guest-owned VCMDQ is disabled, if the guest did not enqueue a CMD_SYNC + * following an ATC_INV command at the end of the guest queue while this ATC_INV + * is timed out, the TIMEOUT will not be reported until this VCMDQ gets assigned + * to the next VM, which will be a false alarm potentially causing some unwanted + * behavior in the new VM. Thus, a guest-owned VCMDQ must flush the TIMEOUT when + * it gets disabled. This can be done by just issuing a CMD_SYNC to SMMU CMDQ. + */ +static void tegra241_vcmdq_hw_flush_timeout(struct tegra241_vcmdq *vcmdq) +{ + struct arm_smmu_device *smmu = &vcmdq->cmdqv->smmu; + u64 cmd_sync[CMDQ_ENT_DWORDS] = {}; + + cmd_sync[0] = FIELD_PREP(CMDQ_0_OP, CMDQ_OP_CMD_SYNC) | + FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_NONE); + + /* + * It does not hurt to insert another CMD_SYNC, taking advantage of the + * arm_smmu_cmdq_issue_cmdlist() that waits for the CMD_SYNC completion. + */ + arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, cmd_sync, 1, true); +} + /* This function is for LVCMDQ, so @vcmdq must not be unmapped yet */ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) { @@ -364,6 +427,8 @@ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, GERROR)), readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, CONS))); } + tegra241_vcmdq_hw_flush_timeout(vcmdq); + writel_relaxed(0, REG_VCMDQ_PAGE0(vcmdq, PROD)); writel_relaxed(0, REG_VCMDQ_PAGE0(vcmdq, CONS)); writeq_relaxed(0, REG_VCMDQ_PAGE1(vcmdq, BASE)); @@ -380,6 +445,12 @@ static void tegra241_vcmdq_hw_deinit(struct tegra241_vcmdq *vcmdq) dev_dbg(vcmdq->cmdqv->dev, "%sdeinited\n", h); }

+/* This function is for LVCMDQ, so @vcmdq must be mapped prior */ +static void _tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) +{ + writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); +} + /* This function is for LVCMDQ, so @vcmdq must be mapped prior */ static int tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) { @@ -390,7 +461,7 @@ static int tegra241_vcmdq_hw_init(struct tegra241_vcmdq *vcmdq) tegra241_vcmdq_hw_deinit(vcmdq);

/* Configure and enable VCMDQ */ - writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE)); + _tegra241_vcmdq_hw_init(vcmdq);

ret = vcmdq_write_config(vcmdq, VCMDQ_EN); if (ret) { @@ -420,6 +491,7 @@ static void tegra241_vcmdq_unmap_lvcmdq(struct tegra241_vcmdq *vcmdq) static void tegra241_vintf_hw_deinit(struct tegra241_vintf *vintf) { u16 lidx = vintf->cmdqv->num_lvcmdqs_per_vintf; + int sidx;

/* HW requires to unmap LVCMDQs in descending order */ while (lidx--) { @@ -429,6 +501,10 @@ static void tegra241_vintf_hw_deinit(struct tegra241_vintf *vintf) } } vintf_write_config(vintf, 0); + for (sidx = 0; sidx < vintf->cmdqv->num_sids_per_vintf; sidx++) { + writel(0, REG_VINTF(vintf, SID_MATCH(sidx))); + writel(0, REG_VINTF(vintf, SID_REPLACE(sidx))); + } }

/* Map a global VCMDQ to the pre-assigned LVCMDQ */ @@ -457,7 +533,8 @@ static int tegra241_vintf_hw_init(struct tegra241_vintf *vintf, bool hyp_own) * whether enabling it here or not, as !HYP_OWN cmdq HWs only support a * restricted set of supported commands. */ - regval = FIELD_PREP(VINTF_HYP_OWN, hyp_own); + regval = FIELD_PREP(VINTF_HYP_OWN, hyp_own) | + FIELD_PREP(VINTF_VMID, vintf->vsmmu.vmid); writel(regval, REG_VINTF(vintf, CONFIG));

ret = vintf_write_config(vintf, regval | VINTF_EN); @@ -584,7 +661,9 @@ static void tegra241_vintf_free_lvcmdq(struct tegra241_vintf *vintf, u16 lidx)

dev_dbg(vintf->cmdqv->dev, "%sdeallocated\n", lvcmdq_error_header(vcmdq, header, 64)); - kfree(vcmdq); + /* Guest-owned VCMDQ is free-ed with hw_queue by iommufd core */ + if (vcmdq->vintf->hyp_own) + kfree(vcmdq); }

static struct tegra241_vcmdq * @@ -671,7 +750,11 @@ static void tegra241_cmdqv_remove_vintf(struct tegra241_cmdqv *cmdqv, u16 idx)

dev_dbg(cmdqv->dev, "VINTF%u: deallocated\n", vintf->idx); tegra241_cmdqv_deinit_vintf(cmdqv, idx); - kfree(vintf); + if (!vintf->hyp_own) + ida_destroy(&vintf->sids); + /* Guest-owned VINTF is free-ed with viommu by iommufd core */ + if (vintf->hyp_own) + kfree(vintf); }

static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) @@ -699,10 +782,34 @@ static void tegra241_cmdqv_remove(struct arm_smmu_device *smmu) put_device(cmdqv->dev); /* smmu->impl_dev */ }

+static struct arm_vsmmu * +tegra241_cmdqv_alloc_vintf_user(struct arm_smmu_device *smmu, + struct arm_smmu_domain *smmu_domain, + struct iommufd_ctx *ictx, unsigned int type, + const struct iommu_user_data *user_data); + +static u32 tegra241_cmdqv_hw_info(struct arm_smmu_device *smmu, u32 *impl) +{ + struct tegra241_cmdqv *cmdqv = + container_of(smmu, struct tegra241_cmdqv, smmu); + u32 regval = readl_relaxed(REG_CMDQV(cmdqv, PARAM)); + + *impl = FIELD_GET(CMDQV_VER, regval); + *impl |= FIELD_PREP(CMDQV_NUM_VCMDQ_LOG2, + ilog2(cmdqv->num_lvcmdqs_per_vintf)); + /* One VINTF per VM is enough */ + *impl |= FIELD_PREP(CMDQV_NUM_VINTF_LOG2, ilog2(1)); + *impl |= FIELD_PREP(CMDQV_NUM_SID_PER_VM_LOG2, + ilog2(cmdqv->num_sids_per_vintf)); + return IOMMU_HW_INFO_ARM_SMMUV3_HAS_TEGRA241_CMDQV; +} + static struct arm_smmu_impl_ops tegra241_cmdqv_impl_ops = { .get_secondary_cmdq = tegra241_cmdqv_get_cmdq, .device_reset = tegra241_cmdqv_hw_reset, .device_remove = tegra241_cmdqv_remove, + .vsmmu_alloc = tegra241_cmdqv_alloc_vintf_user, + .hw_info = tegra241_cmdqv_hw_info, };

/* Probe Functions */ @@ -844,6 +951,7 @@ __tegra241_cmdqv_probe(struct arm_smmu_device *smmu, struct resource *res, cmdqv->irq = irq; cmdqv->base = base; cmdqv->dev = smmu->impl_dev; + cmdqv->base_phys = res->start;

if (cmdqv->irq > 0) { ret = request_threaded_irq(irq, NULL, tegra241_cmdqv_isr, @@ -860,6 +968,8 @@ __tegra241_cmdqv_probe(struct arm_smmu_device *smmu, struct resource *res, cmdqv->num_vintfs = 1 << FIELD_GET(CMDQV_NUM_VINTF_LOG2, regval); cmdqv->num_vcmdqs = 1 << FIELD_GET(CMDQV_NUM_VCMDQ_LOG2, regval); cmdqv->num_lvcmdqs_per_vintf = cmdqv->num_vcmdqs / cmdqv->num_vintfs; + cmdqv->num_sids_per_vintf = + 1 << FIELD_GET(CMDQV_NUM_SID_PER_VM_LOG2, regval);

cmdqv->vintfs = kcalloc(cmdqv->num_vintfs, sizeof(*cmdqv->vintfs), GFP_KERNEL); @@ -913,3 +1023,298 @@ struct arm_smmu_device *tegra241_cmdqv_probe(struct arm_smmu_device *smmu) put_device(smmu->impl_dev); return ERR_PTR(-ENODEV); } + +/* User space VINTF and VCMDQ Functions */ + +static int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq) +{ + char header[64]; + + /* Configure the vcmdq only; User space does the enabling */ + _tegra241_vcmdq_hw_init(vcmdq); + + dev_dbg(vcmdq->cmdqv->dev, "%sinited at host PA 0x%llx size 0x%lx\n", + lvcmdq_error_header(vcmdq, header, 64), + vcmdq->cmdq.q.q_base & VCMDQ_ADDR, + 1UL << (vcmdq->cmdq.q.q_base & VCMDQ_LOG2SIZE)); + return 0; +} + +static struct iommufd_hw_queue * +tegra241_vintf_alloc_lvcmdq_user(struct iommufd_viommu *viommu, + unsigned int type, u32 lidx, u64 base_addr, + size_t length) +{ + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + struct tegra241_cmdqv *cmdqv = vintf->cmdqv; + struct arm_smmu_device *smmu = &cmdqv->smmu; + struct tegra241_vcmdq *vcmdq, *prev = NULL; + u32 log2size, max_n_shift; + phys_addr_t q_base; + char header[64]; + int ret; + + if (type != IOMMU_HW_QUEUE_TYPE_TEGRA241_CMDQV) + return ERR_PTR(-EOPNOTSUPP); + if (lidx >= cmdqv->num_lvcmdqs_per_vintf) + return ERR_PTR(-EINVAL); + if (vintf->lvcmdqs[lidx]) + return ERR_PTR(-EEXIST); + + /* + * HW requires to map LVCMDQs in ascending order, so reject if the + * previous lvcmdqs is not allocated yet. + */ + if (lidx) { + prev = vintf->lvcmdqs[lidx - 1]; + if (!prev) + return ERR_PTR(-EIO); + } + + /* + * @length must be a power of 2, in range of + * [ 32, 2 ^ (idr[1].CMDQS + CMDQ_ENT_SZ_SHIFT) ] + */ + max_n_shift = FIELD_GET(IDR1_CMDQS, + readl_relaxed(smmu->base + ARM_SMMU_IDR1)); + if (!is_power_of_2(length) || length < 32 || + length > (1 << (max_n_shift + CMDQ_ENT_SZ_SHIFT))) + return ERR_PTR(-EINVAL); + log2size = ilog2(length) - CMDQ_ENT_SZ_SHIFT; + + /* @base_addr must be aligned to @length */ + if (base_addr & ~VCMDQ_ADDR || base_addr & (length - 1)) + return ERR_PTR(-EINVAL); + + /* @base_addr must be mapped in the s2_parent domain */ + q_base = arm_smmu_domain_ipa_to_pa(vintf->vsmmu.s2_parent, base_addr); + if (!q_base) + return ERR_PTR(-ENXIO); + + vcmdq = iommufd_hw_queue_alloc(viommu, struct tegra241_vcmdq, core); + if (!vcmdq) + return ERR_PTR(-ENOMEM); + + /* + * HW requires to unmap LVCMDQs in descending order, so destroy() must + * follow this rule. Set a dependency on its previous LVCMDQ so iommufd + * core will help enforce it. + */ + if (prev) { + ret = iommufd_hw_queue_depend(vcmdq, prev, core); + if (ret) + goto free_vcmdq; + } + vcmdq->prev = prev; + + ret = tegra241_vintf_init_lvcmdq(vintf, lidx, vcmdq); + if (ret) + goto undepend_vcmdq; + + dev_dbg(cmdqv->dev, "%sallocated\n", + lvcmdq_error_header(vcmdq, header, 64)); + + tegra241_vcmdq_map_lvcmdq(vcmdq); + + vcmdq->cmdq.q.q_base = q_base & VCMDQ_ADDR; + vcmdq->cmdq.q.q_base |= log2size; + + ret = tegra241_vcmdq_hw_init_user(vcmdq); + if (ret) + goto unmap_lvcmdq; + vintf->lvcmdqs[lidx] = vcmdq; + + return &vcmdq->core; + +unmap_lvcmdq: + tegra241_vcmdq_unmap_lvcmdq(vcmdq); + tegra241_vintf_deinit_lvcmdq(vintf, lidx); +undepend_vcmdq: + if (vcmdq->prev) + iommufd_hw_queue_undepend(vcmdq, vcmdq->prev, core); +free_vcmdq: + iommufd_struct_destroy(vcmdq, core); + return ERR_PTR(ret); +} + +static void +tegra241_vintf_destroy_lvcmdq_user(struct iommufd_hw_queue *hw_queue) +{ + struct tegra241_vcmdq *vcmdq = hw_queue_to_vcmdq(hw_queue); + + tegra241_vcmdq_hw_deinit(vcmdq); + tegra241_vcmdq_unmap_lvcmdq(vcmdq); + tegra241_vintf_free_lvcmdq(vcmdq->vintf, vcmdq->lidx); + if (vcmdq->prev) + iommufd_hw_queue_undepend(vcmdq, vcmdq->prev, core); + + /* IOMMUFD core frees the memory of vcmdq and hw_queue */ +} + +static void tegra241_cmdqv_destroy_vintf_user(struct iommufd_viommu *viommu) +{ + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + + if (vintf->mmap_offset) + iommufd_viommu_destroy_mmap(vintf, vsmmu.core, + vintf->mmap_offset); + tegra241_cmdqv_remove_vintf(vintf->cmdqv, vintf->idx); + + /* IOMMUFD core frees the memory of vintf and viommu */ +} + +static struct iommufd_vdevice * +tegra241_vintf_alloc_vdevice(struct iommufd_viommu *viommu, struct device *dev, + u64 virt_sid) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct tegra241_vintf *vintf = viommu_to_vintf(viommu); + struct arm_smmu_stream *stream = &master->streams[0]; + struct tegra241_vintf_sid *vsid; + int sidx; + + if (virt_sid > UINT_MAX) + return ERR_PTR(-EINVAL); + + vsid = iommufd_vdevice_alloc(viommu, struct tegra241_vintf_sid, core); + if (!vsid) + return ERR_PTR(-ENOMEM); + + WARN_ON_ONCE(master->num_streams != 1); + + /* Find an empty pair of SID_REPLACE and SID_MATCH */ + sidx = ida_alloc_max(&vintf->sids, vintf->cmdqv->num_sids_per_vintf - 1, + GFP_KERNEL); + if (sidx < 0) { + iommufd_struct_destroy(vsid, core); + return ERR_PTR(sidx); + } + + writel(stream->id, REG_VINTF(vintf, SID_REPLACE(sidx))); + writel(virt_sid << 1 | 0x1, REG_VINTF(vintf, SID_MATCH(sidx))); + dev_dbg(vintf->cmdqv->dev, + "VINTF%u: allocated SID_REPLACE%d for pSID=%x, vSID=%x\n", + vintf->idx, sidx, stream->id, (u32)virt_sid); + + vsid->idx = sidx; + vsid->vintf = vintf; + vsid->sid = stream->id; + + return &vsid->core; +} + +static void tegra241_vintf_destroy_vdevice(struct iommufd_vdevice *vdev) +{ + struct tegra241_vintf_sid *vsid = + container_of(vdev, struct tegra241_vintf_sid, core); + struct tegra241_vintf *vintf = vsid->vintf; + + writel(0, REG_VINTF(vintf, SID_MATCH(vsid->idx))); + writel(0, REG_VINTF(vintf, SID_REPLACE(vsid->idx))); + ida_free(&vintf->sids, vsid->idx); + dev_dbg(vintf->cmdqv->dev, + "VINTF%u: deallocated SID_REPLACE%d for pSID=%x\n", vintf->idx, + vsid->idx, vsid->sid); + + /* IOMMUFD core frees the memory of vsid and vdev */ +} + +static struct iommufd_viommu_ops tegra241_cmdqv_viommu_ops = { + .destroy = tegra241_cmdqv_destroy_vintf_user, + .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, + .cache_invalidate = arm_vsmmu_cache_invalidate, + .vdevice_alloc = tegra241_vintf_alloc_vdevice, + .vdevice_destroy = tegra241_vintf_destroy_vdevice, + .hw_queue_alloc = tegra241_vintf_alloc_lvcmdq_user, + .hw_queue_destroy = tegra241_vintf_destroy_lvcmdq_user, +}; + +static struct arm_vsmmu * +tegra241_cmdqv_alloc_vintf_user(struct arm_smmu_device *smmu, + struct arm_smmu_domain *s2_parent, + struct iommufd_ctx *ictx, unsigned int type, + const struct iommu_user_data *user_data) +{ + struct tegra241_cmdqv *cmdqv = + container_of(smmu, struct tegra241_cmdqv, smmu); + struct iommu_viommu_tegra241_cmdqv data; + struct tegra241_vintf *vintf; + phys_addr_t page0_base; + int ret; + + if (type != IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV) + return ERR_PTR(-EOPNOTSUPP); + if (!user_data) + return ERR_PTR(-EINVAL); + + ret = iommu_copy_struct_from_user(&data, user_data, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + out_vintf_mmap_length); + if (ret) + return ERR_PTR(ret); + + vintf = iommufd_viommu_alloc(ictx, struct tegra241_vintf, vsmmu.core, + &tegra241_cmdqv_viommu_ops); + if (!vintf) + return ERR_PTR(-ENOMEM); + + ret = tegra241_cmdqv_init_vintf(cmdqv, cmdqv->num_vintfs - 1, vintf); + if (ret < 0) { + dev_err(cmdqv->dev, "no more available vintf\n"); + goto free_vintf; + } + + vintf->vsmmu.smmu = smmu; + vintf->vsmmu.s2_parent = s2_parent; + /* FIXME Move VMID allocation from the S2 domain allocation to here */ + vintf->vsmmu.vmid = s2_parent->s2_cfg.vmid; + + /* + * Initialize the user-owned VINTF without a LVCMDQ, because it has to + * wait for the allocation of a user-owned LVCMDQ, for security reason. + * It is different than the kernel-owned VINTF0, which had pre-assigned + * and pre-allocated global VCMDQs that would be mapped to the LVCMDQs + * by the tegra241_vintf_hw_init() call. + */ + ret = tegra241_vintf_hw_init(vintf, false); + if (ret) + goto deinit_vintf; + + vintf->lvcmdqs = kcalloc(cmdqv->num_lvcmdqs_per_vintf, + sizeof(*vintf->lvcmdqs), GFP_KERNEL); + if (!vintf->lvcmdqs) { + ret = -ENOMEM; + goto hw_deinit_vintf; + } + + page0_base = cmdqv->base_phys + TEGRA241_VINTFi_PAGE0(vintf->idx); + ret = iommufd_viommu_alloc_mmap(vintf, vsmmu.core, page0_base, SZ_64K, + &vintf->mmap_offset); + if (ret) + goto hw_deinit_vintf; + + data.out_vintf_mmap_length = SZ_64K; + data.out_vintf_mmap_offset = vintf->mmap_offset; + ret = iommu_copy_struct_to_user(user_data, &data, + IOMMU_VIOMMU_TYPE_TEGRA241_CMDQV, + out_vintf_mmap_length); + if (ret) + goto free_mmap; + + ida_init(&vintf->sids); + + dev_dbg(cmdqv->dev, "VINTF%u: allocated with vmid (%d)\n", vintf->idx, + vintf->vsmmu.vmid); + + return &vintf->vsmmu; + +free_mmap: + iommufd_viommu_destroy_mmap(vintf, vsmmu.core, vintf->mmap_offset); +hw_deinit_vintf: + tegra241_vintf_hw_deinit(vintf); +deinit_vintf: + tegra241_cmdqv_deinit_vintf(cmdqv, vintf->idx); +free_vintf: + iommufd_struct_destroy(vintf, vsmmu.core); + return ERR_PTR(ret); +}