This per-vIOMMU cache_invalidate op is like the cache_invalidate_user op in struct iommu_domain_ops, but wider, supporting device cache (e.g. PCI ATC invaldiations).

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommufd.h | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index e6cd288e8b83..0287a6d00192 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -15,6 +15,7 @@ struct device; struct file; struct iommu_group; struct iommu_user_data; +struct iommu_user_data_array; struct iommufd_access; struct iommufd_ctx; struct iommufd_device; @@ -104,12 +105,21 @@ struct iommufd_viommu { * must be defined in include/uapi/linux/iommufd.h. * It must fully initialize the new iommu_domain before * returning. Upon failure, ERR_PTR must be returned. + * @cache_invalidate: Flush hardware cache used by a vIOMMU. It can be used for + * any IOMMU hardware specific cache: TLB and device cache. + * The @array passes in the cache invalidation requests, in + * form of a driver data structure. A driver must update the + * 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 */ struct iommufd_viommu_ops { void (*free)(struct iommufd_viommu *viommu); struct iommu_domain *(*alloc_domain_nested)( struct iommufd_viommu *viommu, const struct iommu_user_data *user_data); + int (*cache_invalidate)(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array); };

#if IS_ENABLED(CONFIG_IOMMUFD)

A vIOMMU-based hwpt_nested requires a cache invalidation op too, either using the one in iommu_domain_ops or the one in viommu_ops. Enforce that upon the allocated hwpt_nested.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/hw_pagetable.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 1df5d40c93df..fd260a67b82c 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -302,7 +302,9 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags, } hwpt->domain->owner = viommu->iommu_dev->ops;

- if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { + if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED || + (!viommu->ops->cache_invalidate && + !hwpt->domain->ops->cache_invalidate_user))) { rc = -EINVAL; goto out_abort; }

This avoids a bigger trouble of exposing struct iommufd_device and struct iommufd_vdevice in the public header.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- include/linux/iommufd.h | 8 ++++++++ drivers/iommu/iommufd/driver.c | 13 +++++++++++++ 2 files changed, 21 insertions(+)

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 0287a6d00192..dc174d02132b 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -184,6 +184,8 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, enum iommufd_object_type type); +struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, + unsigned long vdev_id); #else /* !CONFIG_IOMMUFD_DRIVER */ static inline struct iommufd_object * _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, @@ -191,6 +193,12 @@ _iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct device * +iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) +{ + return NULL; +} #endif /* CONFIG_IOMMUFD_DRIVER */

/* diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index c0876d3f91c7..3604443f82a1 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -36,3 +36,16 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, return ERR_PTR(rc); } EXPORT_SYMBOL_NS_GPL(_iommufd_object_alloc, 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) +{ + struct iommufd_vdevice *vdev; + + lockdep_is_held(&viommu->vdevs.xa_lock); + + vdev = xa_load(&viommu->vdevs, vdev_id); + return vdev ? vdev->idev->dev : NULL; +} +EXPORT_SYMBOL_NS_GPL(iommufd_viommu_find_dev, IOMMUFD);

Similar to the coverage of cache_invalidate_user for iotlb invalidation, add a device cache and a viommu_cache_invalidate function to test it out.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 25 +++++++++ drivers/iommu/iommufd/selftest.c | 76 +++++++++++++++++++++++++++- 2 files changed, 100 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index edced4ac7cd3..46558f83e734 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -54,6 +54,11 @@ enum { MOCK_NESTED_DOMAIN_IOTLB_NUM = 4, };

+enum { + MOCK_DEV_CACHE_ID_MAX = 3, + MOCK_DEV_CACHE_NUM = 4, +}; + struct iommu_test_cmd { __u32 size; __u32 op; @@ -152,6 +157,7 @@ struct iommu_test_hw_info { /* Should not be equal to any defined value in enum iommu_hwpt_data_type */ #define IOMMU_HWPT_DATA_SELFTEST 0xdead #define IOMMU_TEST_IOTLB_DEFAULT 0xbadbeef +#define IOMMU_TEST_DEV_CACHE_DEFAULT 0xbaddad

/** * struct iommu_hwpt_selftest @@ -182,4 +188,23 @@ struct iommu_hwpt_invalidate_selftest {

#define IOMMU_VIOMMU_TYPE_SELFTEST 0xdeadbeef

+/* 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 + +/** + * struct iommu_viommu_invalidate_selftest - Invalidation data for Mock VIOMMU + * (IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST) + * @flags: Invalidate flags + * @cache_id: Invalidate cache entry index + * + * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @cache_id will be ignored + */ +struct iommu_viommu_invalidate_selftest { +#define IOMMU_TEST_INVALIDATE_FLAG_ALL (1 << 0) + __u32 flags; + __u32 vdev_id; + __u32 cache_id; +}; + #endif diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 33a0fcc0eff7..01556854f2f2 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -163,6 +163,7 @@ struct mock_dev { struct device dev; unsigned long flags; int id; + u32 cache[MOCK_DEV_CACHE_NUM]; };

static inline struct mock_dev *to_mock_dev(struct device *dev) @@ -606,9 +607,80 @@ mock_viommu_alloc_domain_nested(struct iommufd_viommu *viommu, return &mock_nested->domain; }

+static int mock_viommu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array) +{ + struct iommu_viommu_invalidate_selftest *cmds; + struct iommu_viommu_invalidate_selftest *cur; + struct iommu_viommu_invalidate_selftest *end; + int rc; + + /* A zero-length array is allowed to validate the array type */ + if (array->entry_num == 0 && + array->type == IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST) { + array->entry_num = 0; + return 0; + } + + cmds = kcalloc(array->entry_num, sizeof(*cmds), GFP_KERNEL); + if (!cmds) + return -ENOMEM; + cur = cmds; + end = cmds + array->entry_num; + + static_assert(sizeof(*cmds) == 3 * sizeof(u32)); + rc = iommu_copy_struct_from_full_user_array( + cmds, sizeof(*cmds), array, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST); + if (rc) + goto out; + + while (cur != end) { + struct mock_dev *mdev; + struct device *dev; + int i; + + if (cur->flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) { + rc = -EOPNOTSUPP; + goto out; + } + + if (cur->cache_id > MOCK_DEV_CACHE_ID_MAX) { + rc = -EINVAL; + goto out; + } + + xa_lock(&viommu->vdevs); + dev = iommufd_viommu_find_dev(viommu, + (unsigned long)cur->vdev_id); + if (!dev) { + xa_unlock(&viommu->vdevs); + rc = -EINVAL; + goto out; + } + mdev = container_of(dev, struct mock_dev, dev); + + if (cur->flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) { + /* Invalidate all cache entries and ignore cache_id */ + for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) + mdev->cache[i] = 0; + } else { + mdev->cache[cur->cache_id] = 0; + } + xa_unlock(&viommu->vdevs); + + cur++; + } +out: + array->entry_num = cur - cmds; + kfree(cmds); + return rc; +} + static struct iommufd_viommu_ops mock_viommu_ops = { .free = mock_viommu_free, .alloc_domain_nested = mock_viommu_alloc_domain_nested, + .cache_invalidate = mock_viommu_cache_invalidate, };

static struct iommufd_viommu *mock_viommu_alloc(struct device *dev, @@ -779,7 +851,7 @@ static void mock_dev_release(struct device *dev) static struct mock_dev *mock_dev_create(unsigned long dev_flags) { struct mock_dev *mdev; - int rc; + int rc, i;

if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA)) @@ -793,6 +865,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) mdev->flags = dev_flags; mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; + for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) + mdev->cache[i] = IOMMU_TEST_DEV_CACHE_DEFAULT;

rc = ida_alloc(&mock_dev_ida, GFP_KERNEL); if (rc < 0)

Similar to IOMMU_TEST_OP_MD_CHECK_IOTLB verifying a mock_domain's iotlb, IOMMU_TEST_OP_DEV_CHECK_CACHE will be used to verify a mock_dev's cache.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/iommufd_test.h | 5 ++++ tools/testing/selftests/iommu/iommufd_utils.h | 24 +++++++++++++++++++ drivers/iommu/iommufd/selftest.c | 22 +++++++++++++++++ tools/testing/selftests/iommu/iommufd.c | 7 +++++- 4 files changed, 57 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 46558f83e734..a6b7a163f636 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -23,6 +23,7 @@ enum { IOMMU_TEST_OP_DIRTY, IOMMU_TEST_OP_MD_CHECK_IOTLB, IOMMU_TEST_OP_TRIGGER_IOPF, + IOMMU_TEST_OP_DEV_CHECK_CACHE, };

enum { @@ -140,6 +141,10 @@ struct iommu_test_cmd { __u32 perm; __u64 addr; } trigger_iopf; + struct { + __u32 id; + __u32 cache; + } check_dev_cache; }; __u32 last; }; diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 5b17d7b2ac5c..3ae6cb5eed7d 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -234,6 +234,30 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, __u32 ft_i test_cmd_hwpt_check_iotlb(hwpt_id, i, expected); \ })

+#define test_cmd_dev_check_cache(device_id, cache_id, expected) \ + ({ \ + struct iommu_test_cmd test_cmd = { \ + .size = sizeof(test_cmd), \ + .op = IOMMU_TEST_OP_DEV_CHECK_CACHE, \ + .id = device_id, \ + .check_dev_cache = { \ + .id = cache_id, \ + .cache = expected, \ + }, \ + }; \ + ASSERT_EQ(0, ioctl(self->fd, \ + _IOMMU_TEST_CMD( \ + IOMMU_TEST_OP_DEV_CHECK_CACHE), \ + &test_cmd)); \ + }) + +#define test_cmd_dev_check_cache_all(device_id, expected) \ + ({ \ + int c; \ + for (c = 0; c < MOCK_DEV_CACHE_NUM; c++) \ + test_cmd_dev_check_cache(device_id, c, expected); \ + }) + static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, uint32_t data_type, uint32_t lreq, uint32_t *nreqs) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 01556854f2f2..7bb47b4a6d63 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -1122,6 +1122,24 @@ static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, return rc; }

+static int iommufd_test_dev_check_cache(struct iommufd_ucmd *ucmd, u32 idev_id, + unsigned int cache_id, u32 cache) +{ + struct iommufd_device *idev; + struct mock_dev *mdev; + int rc = 0; + + idev = iommufd_get_device(ucmd, idev_id); + if (IS_ERR(idev)) + return PTR_ERR(idev); + mdev = container_of(idev->dev, struct mock_dev, dev); + + if (cache_id > MOCK_DEV_CACHE_ID_MAX || mdev->cache[cache_id] != cache) + rc = -EINVAL; + iommufd_put_object(ucmd->ictx, &idev->obj); + return rc; +} + struct selftest_access { struct iommufd_access *access; struct file *file; @@ -1631,6 +1649,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd) return iommufd_test_md_check_iotlb(ucmd, cmd->id, cmd->check_iotlb.id, cmd->check_iotlb.iotlb); + case IOMMU_TEST_OP_DEV_CHECK_CACHE: + return iommufd_test_dev_check_cache(ucmd, cmd->id, + cmd->check_dev_cache.id, + cmd->check_dev_cache.cache); case IOMMU_TEST_OP_CREATE_ACCESS: return iommufd_test_create_access(ucmd, cmd->id, cmd->create_access.flags); diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 44fbc7e5aa2e..ff0181e5db48 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -222,6 +222,8 @@ FIXTURE_SETUP(iommufd_ioas) for (i = 0; i != variant->mock_domains; i++) { test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id, &self->device_id); + test_cmd_dev_check_cache_all(self->device_id, + IOMMU_TEST_DEV_CACHE_DEFAULT); self->base_iova = MOCK_APERTURE_START; } } @@ -1386,9 +1388,12 @@ FIXTURE_SETUP(iommufd_mock_domain)

ASSERT_GE(ARRAY_SIZE(self->hwpt_ids), variant->mock_domains);

- for (i = 0; i != variant->mock_domains; i++) + for (i = 0; i != variant->mock_domains; i++) { test_cmd_mock_domain(self->ioas_id, &self->stdev_ids[i], &self->hwpt_ids[i], &self->idev_ids[i]); + test_cmd_dev_check_cache_all(self->idev_ids[0], + IOMMU_TEST_DEV_CACHE_DEFAULT); + } self->hwpt_id = self->hwpt_ids[0];

self->mmap_flags = MAP_SHARED | MAP_ANONYMOUS;

Add a viommu_cache test function to cover vIOMMU invalidations using the updated IOMMU_HWPT_INVALIDATE ioctl, which now allows passing in a vIOMMU via its hwpt_id field.

Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- tools/testing/selftests/iommu/iommufd_utils.h | 32 ++++ tools/testing/selftests/iommu/iommufd.c | 173 ++++++++++++++++++ 2 files changed, 205 insertions(+)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 3ae6cb5eed7d..aa458c80ad30 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -289,6 +289,38 @@ static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, data_type, lreq, nreqs)); \ })

+static int _test_cmd_viommu_invalidate(int fd, __u32 viommu_id, void *reqs, + uint32_t data_type, uint32_t lreq, + uint32_t *nreqs) +{ + struct iommu_hwpt_invalidate cmd = { + .size = sizeof(cmd), + .hwpt_id = viommu_id, + .data_type = data_type, + .data_uptr = (uint64_t)reqs, + .entry_len = lreq, + .entry_num = *nreqs, + }; + int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd); + *nreqs = cmd.entry_num; + return rc; +} + +#define test_cmd_viommu_invalidate(viommu, reqs, lreq, nreqs) \ + ({ \ + ASSERT_EQ(0, \ + _test_cmd_viommu_invalidate(self->fd, viommu, reqs, \ + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, \ + lreq, nreqs)); \ + }) +#define test_err_viommu_invalidate(_errno, viommu_id, reqs, data_type, lreq, \ + nreqs) \ + ({ \ + EXPECT_ERRNO(_errno, _test_cmd_viommu_invalidate( \ + self->fd, viommu_id, reqs, \ + data_type, lreq, nreqs)); \ + }) + static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, unsigned int ioas_id) { diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index ff0181e5db48..9a7d4b9c44f6 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -2498,4 +2498,177 @@ TEST_F(iommufd_viommu, vdevice_alloc) } }

+TEST_F(iommufd_viommu, vdevice_cache) +{ + struct iommu_viommu_invalidate_selftest inv_reqs[2] = {}; + uint32_t viommu_id = self->viommu_id; + uint32_t dev_id = self->device_id; + uint32_t vdev_id = 0; + uint32_t num_inv; + + if (dev_id) { + test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id); + + test_cmd_dev_check_cache_all(dev_id, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Check data_type by passing zero-length array */ + num_inv = 0; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: Invalid data_type */ + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST_INVALID, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: structure size sanity */ + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs) + 1, &num_inv); + assert(!num_inv); + + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + 1, &num_inv); + assert(!num_inv); + + /* Negative test: invalid flag is passed */ + num_inv = 1; + inv_reqs[0].flags = 0xffffffff; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EOPNOTSUPP, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid data_uptr when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EINVAL, viommu_id, NULL, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid entry_len when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + 0, &num_inv); + assert(!num_inv); + + /* Negative test: invalid cache_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = MOCK_DEV_CACHE_ID_MAX + 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid vdev_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x9; + inv_reqs[0].cache_id = 0; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* + * Invalidate the 1st cache entry but fail the 2nd request + * due to invalid flags configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 0; + inv_reqs[1].flags = 0xffffffff; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = 1; + test_err_viommu_invalidate(EOPNOTSUPP, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* + * Invalidate the 1st cache entry but fail the 2nd request + * due to invalid cache_id configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 0; + inv_reqs[1].flags = 0; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = MOCK_DEV_CACHE_ID_MAX + 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Invalidate the 2nd cache entry and verify */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 1; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, 0); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Invalidate the 3rd and 4th cache entries and verify */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 2; + inv_reqs[1].flags = 0; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = 3; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 2); + test_cmd_dev_check_cache_all(dev_id, 0); + + /* Invalidate all cache entries for nested_dev_id[1] and verify */ + num_inv = 1; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache_all(dev_id, 0); + test_ioctl_destroy(vdev_id); + } +} + TEST_HARNESS_MAIN

With the introduction of the new object and its infrastructure, update the doc and the vIOMMU graph to reflect that.

Reviewed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- Documentation/userspace-api/iommufd.rst | 41 +++++++++++++++++++------ 1 file changed, 32 insertions(+), 9 deletions(-)

diff --git a/Documentation/userspace-api/iommufd.rst b/Documentation/userspace-api/iommufd.rst index 92d16efad5b0..3c27cc92c2cb 100644 --- a/Documentation/userspace-api/iommufd.rst +++ b/Documentation/userspace-api/iommufd.rst @@ -94,6 +94,19 @@ Following IOMMUFD objects are exposed to userspace: backed by corresponding vIOMMU objects, in which case a guest OS would do the "dispatch" naturally instead of VMM trappings.

+ - IOMMUFD_OBJ_VDEVICE, representing a virtual device for an IOMMUFD_OBJ_DEVICE + against an IOMMUFD_OBJ_VIOMMU. This virtual device holds the device's virtual + information or attributes (related to the vIOMMU) in a VM. An immediate vDATA + example can be the virtual ID of the device on a vIOMMU, which is a unique ID + that VMM assigns to the device for a translation channel/port of the vIOMMU, + e.g. vSID of ARM SMMUv3, vDeviceID of AMD IOMMU, and vID of Intel VT-d to a + Context Table. Potential use cases of some advanced security information can + be forwarded via this object too, such as security level or realm information + in a Confidential Compute Architecture. A VMM should create a vDEVICE object + to forward all the device information in a VM, when it connects a device to a + vIOMMU, which is a separate ioctl call from attaching the same device to an + HWPT_PAGING that the vIOMMU holds. + All user-visible objects are destroyed via the IOMMU_DESTROY uAPI.

The diagrams below show relationships between user-visible objects and kernel @@ -133,16 +146,16 @@ creating the objects and links:: |____________| |____________| |______|

_______________________________________________________________________ - | iommufd (with vIOMMU) | + | iommufd (with vIOMMU/vDEVICE) | | | - | [5] | - | _____________ | - | | | | - | |----------------| vIOMMU | | - | | | | | - | | | | | - | | [1] | | [4] [2] | - | | ______ | | _____________ ________ | + | [5] [6] | + | _____________ _____________ | + | | | | | | + | |----------------| vIOMMU |<---| vDEVICE |<----| | + | | | | |_____________| | | + | | | | | | + | | [1] | | [4] | [2] | + | | ______ | | _____________ _|______ | | | | | | [3] | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | @@ -215,6 +228,15 @@ creating the objects and links:: the vIOMMU object and the HWPT_PAGING, then this vIOMMU object can be used as a nesting parent object to allocate an HWPT_NESTED object described above.

+6. IOMMUFD_OBJ_VDEVICE can be only manually created via the IOMMU_VDEVICE_ALLOC + uAPI, provided a viommu_id for an iommufd_viommu object and a dev_id for an + iommufd_device object. The vDEVICE object will be the binding between these + two parent objects. Another @virt_id will be also set via the uAPI providing + the iommufd core an index to store the vDEVICE object to a vDEVICE array per + vIOMMU. If necessary, the IOMMU driver may choose to implement a vdevce_alloc + op to init its HW for virtualization feature related to a vDEVICE. Successful + completion of this operation sets up the linkages between vIOMMU and device. + A device can only bind to an iommufd due to DMA ownership claim and attach to at most one IOAS object (no support of PASID yet).

@@ -228,6 +250,7 @@ User visible objects are backed by following datastructures: - iommufd_hwpt_paging for IOMMUFD_OBJ_HWPT_PAGING. - iommufd_hwpt_nested for IOMMUFD_OBJ_HWPT_NESTED. - iommufd_viommu for IOMMUFD_OBJ_VIOMMU. +- iommufd_vdevice for IOMMUFD_OBJ_VDEVICE

Several terminologies when looking at these datastructures:

Implement the vIOMMU's cache_invalidate op for user space to invalidate the IOTLB entries, Device ATS and CD entries that are still cached by hardware.

Add struct iommu_viommu_arm_smmuv3_invalidate defining invalidation entries that are simply in the native format of a 128-bit TLBI command. Scan those commands against the permitted command list and fix their VMID/SID fields.

Co-developed-by: Eric Auger eric.auger@redhat.com Signed-off-by: Eric Auger eric.auger@redhat.com Co-developed-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 5 + include/uapi/linux/iommufd.h | 24 ++++ .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 130 ++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 +- 4 files changed, 162 insertions(+), 3 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 5a025d310dbe..8bd740f537ee 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -529,6 +529,7 @@ struct arm_smmu_cmdq_ent { #define CMDQ_OP_TLBI_NH_ALL 0x10 #define CMDQ_OP_TLBI_NH_ASID 0x11 #define CMDQ_OP_TLBI_NH_VA 0x12 + #define CMDQ_OP_TLBI_NH_VAA 0x13 #define CMDQ_OP_TLBI_EL2_ALL 0x20 #define CMDQ_OP_TLBI_EL2_ASID 0x21 #define CMDQ_OP_TLBI_EL2_VA 0x22 @@ -949,6 +950,10 @@ void arm_smmu_attach_commit(struct arm_smmu_attach_state *state); void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master, const struct arm_smmu_ste *target);

+int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, + bool sync); + #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); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c2c5f49fdf17..8e66e2fde1dd 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -686,9 +686,11 @@ struct iommu_hwpt_get_dirty_bitmap { * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation * Data Type * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 + * @IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3: Invalidation data for ARM SMMUv3 */ enum iommu_hwpt_invalidate_data_type { IOMMU_HWPT_INVALIDATE_DATA_VTD_S1 = 0, + IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3 = 1, };

/** @@ -727,6 +729,28 @@ struct iommu_hwpt_vtd_s1_invalidate { __u32 __reserved; };

+/** + * struct iommu_viommu_arm_smmuv3_invalidate - ARM SMMUv3 cahce invalidation + * (IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3) + * @cmd: 128-bit cache invalidation command that runs in SMMU CMDQ. + * Must be little-endian. + * + * Supported command list only when passing in a vIOMMU via @hwpt_id: + * CMDQ_OP_TLBI_NSNH_ALL + * CMDQ_OP_TLBI_NH_VA + * CMDQ_OP_TLBI_NH_VAA + * CMDQ_OP_TLBI_NH_ALL + * CMDQ_OP_TLBI_NH_ASID + * CMDQ_OP_ATC_INV + * CMDQ_OP_CFGI_CD + * CMDQ_OP_CFGI_CD_ALL + * + * -EIO will be returned if the command is not supported. + */ +struct iommu_viommu_arm_smmuv3_invalidate { + __aligned_le64 cmd[2]; +}; + /** * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE) * @size: sizeof(struct iommu_hwpt_invalidate) 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 abb6d2868376..2479074db820 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 @@ -184,9 +184,131 @@ arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, return &nested_domain->domain; }

+static int arm_vsmmu_vsid_to_sid(struct arm_vsmmu *vsmmu, u32 vsid, u32 *sid) +{ + struct arm_smmu_master *master; + struct device *dev; + int ret = 0; + + xa_lock(&vsmmu->core.vdevs); + dev = iommufd_viommu_find_dev(&vsmmu->core, (unsigned long)vsid); + if (!dev) { + ret = -EIO; + goto unlock; + } + master = dev_iommu_priv_get(dev); + + /* At this moment, iommufd only supports PCI device that has one SID */ + if (sid) + *sid = master->streams[0].id; +unlock: + xa_unlock(&vsmmu->core.vdevs); + return ret; +} + +/* This is basically iommu_viommu_arm_smmuv3_invalidate in u64 for conversion */ +struct arm_vsmmu_invalidation_cmd { + u64 cmd[2]; +}; + +/* + * Convert, in place, the raw invalidation command into an internal format that + * can be passed to arm_smmu_cmdq_issue_cmdlist(). Internally commands are + * stored in CPU endian. + * + * Enforce the VMID or SID on the command. + */ +static int arm_vsmmu_convert_user_cmd(struct arm_vsmmu *vsmmu, + struct arm_vsmmu_invalidation_cmd *cmd) +{ + /* Commands are le64 stored in u64 */ + cmd->cmd[0] = le64_to_cpu((__force __le64)cmd->cmd[0]); + cmd->cmd[1] = le64_to_cpu((__force __le64)cmd->cmd[1]); + + switch (cmd->cmd[0] & CMDQ_0_OP) { + case CMDQ_OP_TLBI_NSNH_ALL: + /* Convert to NH_ALL */ + cmd->cmd[0] = CMDQ_OP_TLBI_NH_ALL | + FIELD_PREP(CMDQ_TLBI_0_VMID, vsmmu->vmid); + cmd->cmd[1] = 0; + break; + case CMDQ_OP_TLBI_NH_VA: + case CMDQ_OP_TLBI_NH_VAA: + case CMDQ_OP_TLBI_NH_ALL: + case CMDQ_OP_TLBI_NH_ASID: + cmd->cmd[0] &= ~CMDQ_TLBI_0_VMID; + cmd->cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, vsmmu->vmid); + break; + case CMDQ_OP_ATC_INV: + case CMDQ_OP_CFGI_CD: + case CMDQ_OP_CFGI_CD_ALL: { + u32 sid, vsid = FIELD_GET(CMDQ_CFGI_0_SID, cmd->cmd[0]); + + if (arm_vsmmu_vsid_to_sid(vsmmu, vsid, &sid)) + return -EIO; + cmd->cmd[0] &= ~CMDQ_CFGI_0_SID; + cmd->cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, sid); + break; + } + default: + return -EIO; + } + return 0; +} + +static 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; + struct arm_vsmmu_invalidation_cmd *last; + struct arm_vsmmu_invalidation_cmd *cmds; + struct arm_vsmmu_invalidation_cmd *cur; + struct arm_vsmmu_invalidation_cmd *end; + int ret; + + cmds = kcalloc(array->entry_num, sizeof(*cmds), GFP_KERNEL); + if (!cmds) + return -ENOMEM; + cur = cmds; + end = cmds + array->entry_num; + + static_assert(sizeof(*cmds) == 2 * sizeof(u64)); + ret = iommu_copy_struct_from_full_user_array( + cmds, sizeof(*cmds), array, + IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3); + if (ret) + goto out; + + last = cmds; + while (cur != end) { + ret = arm_vsmmu_convert_user_cmd(vsmmu, cur); + if (ret) + goto out; + + /* FIXME work in blocks of CMDQ_BATCH_ENTRIES and copy each block? */ + cur++; + if (cur != end && (cur - last) != CMDQ_BATCH_ENTRIES - 1) + continue; + + /* FIXME always uses the main cmdq rather than trying to group by type */ + ret = arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, last->cmd, + cur - last, true); + if (ret) { + cur--; + goto out; + } + last = cur; + } +out: + array->entry_num = cur - cmds; + kfree(cmds); + return ret; +}

static const struct iommufd_viommu_ops arm_vsmmu_ops = { .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, + .cache_invalidate = arm_vsmmu_cache_invalidate, };

struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, @@ -206,6 +328,14 @@ struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, if (!(smmu->features & ARM_SMMU_FEAT_NESTING)) return ERR_PTR(-EOPNOTSUPP);

+ /* + * FORCE_SYNC is not set with FEAT_NESTING. Some study of the exact HW + * defect is needed to determine if arm_vsmmu_cache_invalidate() needs + * any change to remove this. + */ + if (WARN_ON(smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) + return ERR_PTR(-EOPNOTSUPP); + /* * Must support some way to prevent the VM from bypassing the cache * because VFIO currently does not do any cache maintenance. diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 8215c49d3bac..d1abfb42d828 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -766,9 +766,9 @@ static void arm_smmu_cmdq_write_entries(struct arm_smmu_cmdq *cmdq, u64 *cmds, * insert their own list of commands then all of the commands from one * CPU will appear before any of the commands from the other CPU. */ -static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, - struct arm_smmu_cmdq *cmdq, - u64 *cmds, int n, bool sync) +int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, + bool sync) { u64 cmd_sync[CMDQ_ENT_DWORDS]; u32 prod;

From: Jason Gunthorpe jgg@nvidia.com

Now, ATC invalidation can be done with the vIOMMU invalidation op. A guest owned IOMMU_DOMAIN_NESTED can do an ATS too. Allow it to pass in the EATS field via the vSTE words.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 4 ++- include/uapi/linux/iommufd.h | 2 +- .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 31 ++++++++++++++++--- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 26 +++++++++++++--- 4 files changed, 53 insertions(+), 10 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 8bd740f537ee..af25f092303f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -305,7 +305,7 @@ static inline u32 arm_smmu_strtab_l2_idx(u32 sid) #define STRTAB_STE_1_NESTING_ALLOWED \ cpu_to_le64(STRTAB_STE_1_S1DSS | STRTAB_STE_1_S1CIR | \ STRTAB_STE_1_S1COR | STRTAB_STE_1_S1CSH | \ - STRTAB_STE_1_S1STALLD) + STRTAB_STE_1_S1STALLD | STRTAB_STE_1_EATS)

/* * Context descriptors. @@ -838,6 +838,7 @@ struct arm_smmu_domain { struct arm_smmu_nested_domain { struct iommu_domain domain; struct arm_vsmmu *vsmmu; + bool enable_ats : 1;

__le64 ste[2]; }; @@ -879,6 +880,7 @@ struct arm_smmu_master_domain { struct list_head devices_elm; struct arm_smmu_master *master; ioasid_t ssid; + bool nested_ats_flush : 1; };

static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 8e66e2fde1dd..056ba05a8022 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -404,7 +404,7 @@ struct iommu_hwpt_vtd_s1 { * a user stage-1 Context Descriptor Table. Must be little-endian. * Allowed fields: (Refer to "5.2 Stream Table Entry" in SMMUv3 HW Spec) * - word-0: V, Cfg, S1Fmt, S1ContextPtr, S1CDMax - * - word-1: S1DSS, S1CIR, S1COR, S1CSH, S1STALLD + * - word-1: EATS, S1DSS, S1CIR, S1COR, S1CSH, S1STALLD * * -EIO will be returned if @ste is not legal or contains any non-allowed field. * Cfg can be used to select a S1, Bypass or Abort configuration. A Bypass 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 2479074db820..c0c5cd807d34 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 @@ -96,8 +96,6 @@ static int arm_smmu_attach_dev_nested(struct iommu_domain *domain, .master = master, .old_domain = iommu_get_domain_for_dev(dev), .ssid = IOMMU_NO_PASID, - /* Currently invalidation of ATC is not supported */ - .disable_ats = true, }; struct arm_smmu_ste ste; int ret; @@ -108,6 +106,15 @@ static int arm_smmu_attach_dev_nested(struct iommu_domain *domain, return -EBUSY;

mutex_lock(&arm_smmu_asid_lock); + /* + * The VM has to control the actual ATS state at the PCI device because + * we forward the invalidations directly from the VM. If the VM doesn't + * think ATS is on it will not generate ATC flushes and the ATC will + * become incoherent. Since we can't access the actual virtual PCI ATS + * config bit here base this off the EATS value in the STE. If the EATS + * is set then the VM must generate ATC flushes. + */ + state.disable_ats = !nested_domain->enable_ats; ret = arm_smmu_attach_prepare(&state, domain); if (ret) { mutex_unlock(&arm_smmu_asid_lock); @@ -132,8 +139,10 @@ static const struct iommu_domain_ops arm_smmu_nested_ops = { .free = arm_smmu_domain_nested_free, };

-static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg) +static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg, + bool *enable_ats) { + unsigned int eats; unsigned int cfg;

if (!(arg->ste[0] & cpu_to_le64(STRTAB_STE_0_V))) { @@ -150,6 +159,18 @@ static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg) if (cfg != STRTAB_STE_0_CFG_ABORT && cfg != STRTAB_STE_0_CFG_BYPASS && cfg != STRTAB_STE_0_CFG_S1_TRANS) return -EIO; + + /* + * Only Full ATS or ATS UR is supported + * The EATS field will be set by arm_smmu_make_nested_domain_ste() + */ + eats = FIELD_GET(STRTAB_STE_1_EATS, le64_to_cpu(arg->ste[1])); + arg->ste[1] &= ~cpu_to_le64(STRTAB_STE_1_EATS); + if (eats != STRTAB_STE_1_EATS_ABT && eats != STRTAB_STE_1_EATS_TRANS) + return -EIO; + + if (cfg == STRTAB_STE_0_CFG_S1_TRANS) + *enable_ats = (eats == STRTAB_STE_1_EATS_TRANS); return 0; }

@@ -160,6 +181,7 @@ arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); struct arm_smmu_nested_domain *nested_domain; struct iommu_hwpt_arm_smmuv3 arg; + bool enable_ats = false; int ret;

ret = iommu_copy_struct_from_user(&arg, user_data, @@ -167,7 +189,7 @@ arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, if (ret) return ERR_PTR(ret);

- ret = arm_smmu_validate_vste(&arg); + ret = arm_smmu_validate_vste(&arg, &enable_ats); if (ret) return ERR_PTR(ret);

@@ -177,6 +199,7 @@ arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu,

nested_domain->domain.type = IOMMU_DOMAIN_NESTED; nested_domain->domain.ops = &arm_smmu_nested_ops; + nested_domain->enable_ats = enable_ats; nested_domain->vsmmu = vsmmu; nested_domain->ste[0] = arg.ste[0]; nested_domain->ste[1] = arg.ste[1] & ~cpu_to_le64(STRTAB_STE_1_EATS); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index d1abfb42d828..10b4dbc8d027 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2107,7 +2107,16 @@ int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, if (!master->ats_enabled) continue;

- arm_smmu_atc_inv_to_cmd(master_domain->ssid, iova, size, &cmd); + if (master_domain->nested_ats_flush) { + /* + * If a S2 used as a nesting parent is changed we have + * no option but to completely flush the ATC. + */ + arm_smmu_atc_inv_to_cmd(IOMMU_NO_PASID, 0, 0, &cmd); + } else { + arm_smmu_atc_inv_to_cmd(master_domain->ssid, iova, size, + &cmd); + }

for (i = 0; i < master->num_streams; i++) { cmd.atc.sid = master->streams[i].id; @@ -2631,7 +2640,7 @@ static void arm_smmu_disable_pasid(struct arm_smmu_master *master) static struct arm_smmu_master_domain * arm_smmu_find_master_domain(struct arm_smmu_domain *smmu_domain, struct arm_smmu_master *master, - ioasid_t ssid) + ioasid_t ssid, bool nested_ats_flush) { struct arm_smmu_master_domain *master_domain;

@@ -2640,7 +2649,8 @@ arm_smmu_find_master_domain(struct arm_smmu_domain *smmu_domain, list_for_each_entry(master_domain, &smmu_domain->devices, devices_elm) { if (master_domain->master == master && - master_domain->ssid == ssid) + master_domain->ssid == ssid && + master_domain->nested_ats_flush == nested_ats_flush) return master_domain; } return NULL; @@ -2671,13 +2681,18 @@ static void arm_smmu_remove_master_domain(struct arm_smmu_master *master, { struct arm_smmu_domain *smmu_domain = to_smmu_domain_devices(domain); struct arm_smmu_master_domain *master_domain; + bool nested_ats_flush = false; unsigned long flags;

if (!smmu_domain) return;

+ if (domain->type == IOMMU_DOMAIN_NESTED) + nested_ats_flush = to_smmu_nested_domain(domain)->enable_ats; + spin_lock_irqsave(&smmu_domain->devices_lock, flags); - master_domain = arm_smmu_find_master_domain(smmu_domain, master, ssid); + master_domain = arm_smmu_find_master_domain(smmu_domain, master, ssid, + nested_ats_flush); if (master_domain) { list_del(&master_domain->devices_elm); kfree(master_domain); @@ -2744,6 +2759,9 @@ int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, return -ENOMEM; master_domain->master = master; master_domain->ssid = state->ssid; + if (new_domain->type == IOMMU_DOMAIN_NESTED) + master_domain->nested_ats_flush = + to_smmu_nested_domain(new_domain)->enable_ats;

/* * During prepare we want the current smmu_domain and new