From b900c11e0655ca92215a59daffeee66b6f2b741b Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:23 -0700 Subject: [PATCH 01/31] iommu: Add new iommu op to create domains owned by userspace mainline inclusion from mainline-v6.7-rc1 commit 909f4abd1097769d024c3a9c2e59c2fbe5d2d0c0 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?909f4abd1097769d024c3a9c2e59c2fbe5d2d0c0 -------------------------------- Introduce a new iommu_domain op to create domains owned by userspace, e.g. through IOMMUFD. These domains have a few different properties compares to kernel owned domains: - They may be PAGING domains, but created with special parameters. For instance aperture size changes/number of levels, different IOPTE formats, or other things necessary to make a vIOMMU work - We have to track all the memory allocations with GFP_KERNEL_ACCOUNT to make the cgroup sandbox stronger - Device-specialty domains, such as NESTED domains can be created by IOMMUFD. The new op clearly says the domain is being created by IOMMUFD, that the domain is intended for userspace use, and it provides a way to pass user flags or a driver specific uAPI structure to customize the created domain to exactly what the vIOMMU userspace driver requires. iommu drivers that cannot support VFIO/IOMMUFD should not support this op. This includes any driver that cannot provide a fully functional PAGING domain. This new op for now is only supposed to be used by IOMMUFD, hence no wrapper for it. IOMMUFD would call the callback directly. As for domain free, IOMMUFD would use iommu_domain_free(). Intel-SIG: 909f4abd1097 iommu: Add new iommu op to create domains owned by userspace Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-2-yi.l.liu@intel.com Suggested-by: Jason Gunthorpe Signed-off-by: Lu Baolu Co-developed-by: Nicolin Chen Signed-off-by: Nicolin Chen Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- include/linux/iommu.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0225cf7445de..2c64d331fe8e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -234,7 +234,15 @@ struct iommu_iotlb_gather { * op is allocated in the iommu driver and freed by the caller after * use. The information type is one of enum iommu_hw_info_type defined * in include/uapi/linux/iommufd.h. - * @domain_alloc: allocate iommu domain + * @domain_alloc: allocate and return an iommu domain if success. Otherwise + * NULL is returned. The domain is not fully initialized until + * the caller iommu_domain_alloc() returns. + * @domain_alloc_user: Allocate an iommu domain corresponding to the input + * parameters as defined in include/uapi/linux/iommufd.h. + * Unlike @domain_alloc, it is called only by IOMMUFD and + * must fully initialize the new domain before return. + * Upon success, a domain is returned. Upon failure, + * ERR_PTR must be returned. * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -267,6 +275,7 @@ struct iommu_ops { /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); + struct iommu_domain *(*domain_alloc_user)(struct device *dev, u32 flags); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); -- Gitee From ce6c77424118a67c84f75e50fe7bba22587823ca Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:24 -0700 Subject: [PATCH 02/31] iommufd: Use the domain_alloc_user() op for domain allocation mainline inclusion from mainline-v6.7-rc1 commit 7975b722087fa23ff3ad1ff4998b8572a7e17e84 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?7975b722087fa23ff3ad1ff4998b8572a7e17e84 -------------------------------- Make IOMMUFD use iommu_domain_alloc_user() by default for iommu_domain creation. IOMMUFD needs to support iommu_domain allocation with parameters from userspace in nested support, and a driver is expected to implement everything under this op. If the iommu driver doesn't provide domain_alloc_user callback then IOMMUFD falls back to use iommu_domain_alloc() with an UNMANAGED type if possible. Intel-SIG: 7975b722087f iommufd: Use the domain_alloc_user() op for domain allocation Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-3-yi.l.liu@intel.com Suggested-by: Jason Gunthorpe Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Co-developed-by: Nicolin Chen Signed-off-by: Nicolin Chen Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index cf2c1504e20d..48874f896521 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -5,6 +5,7 @@ #include #include +#include "../iommu-priv.h" #include "iommufd_private.h" void iommufd_hw_pagetable_destroy(struct iommufd_object *obj) @@ -74,6 +75,7 @@ struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, bool immediate_attach) { + const struct iommu_ops *ops = dev_iommu_ops(idev->dev); struct iommufd_hw_pagetable *hwpt; int rc; @@ -88,10 +90,19 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, refcount_inc(&ioas->obj.users); hwpt->ioas = ioas; - hwpt->domain = iommu_domain_alloc(idev->dev->bus); - if (!hwpt->domain) { - rc = -ENOMEM; - goto out_abort; + if (ops->domain_alloc_user) { + hwpt->domain = ops->domain_alloc_user(idev->dev, 0); + if (IS_ERR(hwpt->domain)) { + rc = PTR_ERR(hwpt->domain); + hwpt->domain = NULL; + goto out_abort; + } + } else { + hwpt->domain = iommu_domain_alloc(idev->dev->bus); + if (!hwpt->domain) { + rc = -ENOMEM; + goto out_abort; + } } /* -- Gitee From c87b597345bfa45b92415887e7b97f2022946559 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:25 -0700 Subject: [PATCH 03/31] iommufd: Flow user flags for domain allocation to domain_alloc_user() mainline inclusion from mainline-v6.7-rc1 commit 89d63875d80ea127280c60dd4cd101af1d9b6557 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?89d63875d80ea127280c60dd4cd101af1d9b6557 -------------------------------- Extends iommufd_hw_pagetable_alloc() to accept user flags, the uAPI will provide the flags. Intel-SIG: 89d63875d80e iommufd: Flow user flags for domain allocation to domain_alloc_user() Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-4-yi.l.liu@intel.com Reviewed-by: Kevin Tian Signed-off-by: Yi Liu Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/device.c | 2 +- drivers/iommu/iommufd/hw_pagetable.c | 9 ++++++--- drivers/iommu/iommufd/iommufd_private.h | 3 ++- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index ce78c3671539..e88fa73a45e6 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -540,7 +540,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev, } hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev, - immediate_attach); + 0, immediate_attach); if (IS_ERR(hwpt)) { destroy_hwpt = ERR_CAST(hwpt); goto out_unlock; diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 48874f896521..5be7a31cbd9c 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -61,6 +61,7 @@ int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt) * @ictx: iommufd context * @ioas: IOAS to associate the domain with * @idev: Device to get an iommu_domain for + * @flags: Flags from userspace * @immediate_attach: True if idev should be attached to the hwpt * * Allocate a new iommu_domain and return it as a hw_pagetable. The HWPT @@ -73,7 +74,8 @@ int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt) */ struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, - struct iommufd_device *idev, bool immediate_attach) + struct iommufd_device *idev, u32 flags, + bool immediate_attach) { const struct iommu_ops *ops = dev_iommu_ops(idev->dev); struct iommufd_hw_pagetable *hwpt; @@ -91,7 +93,7 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, hwpt->ioas = ioas; if (ops->domain_alloc_user) { - hwpt->domain = ops->domain_alloc_user(idev->dev, 0); + hwpt->domain = ops->domain_alloc_user(idev->dev, flags); if (IS_ERR(hwpt->domain)) { rc = PTR_ERR(hwpt->domain); hwpt->domain = NULL; @@ -166,7 +168,8 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) } mutex_lock(&ioas->mutex); - hwpt = iommufd_hw_pagetable_alloc(ucmd->ictx, ioas, idev, false); + hwpt = iommufd_hw_pagetable_alloc(ucmd->ictx, ioas, + idev, cmd->flags, false); if (IS_ERR(hwpt)) { rc = PTR_ERR(hwpt); goto out_unlock; diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 2c58670011fe..3064997a0181 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -242,7 +242,8 @@ struct iommufd_hw_pagetable { struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, - struct iommufd_device *idev, bool immediate_attach); + struct iommufd_device *idev, u32 flags, + bool immediate_attach); int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt); int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt, struct iommufd_device *idev); -- Gitee From 587f3e904db80aed51ad5f23f4ca9f05f5013133 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:26 -0700 Subject: [PATCH 04/31] iommufd: Support allocating nested parent domain mainline inclusion from mainline-v6.7-rc1 commit 4ff542163397073f86eda484318d61980ff1031d category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?4ff542163397073f86eda484318d61980ff1031d -------------------------------- Extend IOMMU_HWPT_ALLOC to allocate domains to be used as parent (stage-2) in nested translation. Add IOMMU_HWPT_ALLOC_NEST_PARENT to the uAPI. Intel-SIG: 4ff542163397 iommufd: Support allocating nested parent domain Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-5-yi.l.liu@intel.com Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 5 ++++- include/uapi/linux/iommufd.h | 12 +++++++++++- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 5be7a31cbd9c..8b3d2875d642 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -83,6 +83,9 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, lockdep_assert_held(&ioas->mutex); + if (flags && !ops->domain_alloc_user) + return ERR_PTR(-EOPNOTSUPP); + hwpt = iommufd_object_alloc(ictx, hwpt, IOMMUFD_OBJ_HW_PAGETABLE); if (IS_ERR(hwpt)) return hwpt; @@ -154,7 +157,7 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc; - if (cmd->flags || cmd->__reserved) + if ((cmd->flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) || cmd->__reserved) return -EOPNOTSUPP; idev = iommufd_get_device(ucmd, cmd->dev_id); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index b4ba0c0cbab6..4a7c5c8fdbb4 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -347,10 +347,20 @@ struct iommu_vfio_ioas { }; #define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) +/** + * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation + * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a domain which can serve + * as the parent domain in the nesting + * configuration. + */ +enum iommufd_hwpt_alloc_flags { + IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, +}; + /** * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) * @size: sizeof(struct iommu_hwpt_alloc) - * @flags: Must be 0 + * @flags: Combination of enum iommufd_hwpt_alloc_flags * @dev_id: The device to allocate this HWPT for * @pt_id: The IOAS to connect this HWPT to * @out_hwpt_id: The ID of the new HWPT -- Gitee From f7aa9d197ed373eee0bd4c4a14b38d6bdc4cddc6 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Mon, 18 Sep 2023 18:16:37 -0700 Subject: [PATCH 05/31] iommufd/selftest: Iterate idev_ids in mock_domain's alloc_hwpt test mainline inclusion from mainline-v6.7-rc1 commit bb812e0069ce5de9af2a7910951c8c95632cebe3 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?bb812e0069ce5de9af2a7910951c8c95632cebe3 -------------------------------- The point in iterating variant->mock_domains is to test the idev_ids[0] and idev_ids[1]. So use it instead of keeping testing idev_ids[0] only. Intel-SIG: bb812e0069ce iommufd/selftest: Iterate idev_ids in mock_domain's alloc_hwpt test Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230919011637.16483-1-nicolinc@nvidia.com Signed-off-by: Nicolin Chen Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- tools/testing/selftests/iommu/iommufd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 33d08600be13..9f705c1ea30f 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1407,7 +1407,7 @@ TEST_F(iommufd_mock_domain, alloc_hwpt) uint32_t stddev_id; uint32_t hwpt_id; - test_cmd_hwpt_alloc(self->idev_ids[0], self->ioas_id, &hwpt_id); + test_cmd_hwpt_alloc(self->idev_ids[i], self->ioas_id, &hwpt_id); test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); test_ioctl_destroy(stddev_id); test_ioctl_destroy(hwpt_id); -- Gitee From 57ecbd844748fe441a57486128e953608eb82cb9 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:27 -0700 Subject: [PATCH 06/31] iommufd/selftest: Add domain_alloc_user() support in iommu mock mainline inclusion from mainline-v6.7-rc1 commit 408663619fcfc89c087df65b362c91bf0a0be617 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?408663619fcfc89c087df65b362c91bf0a0be617 -------------------------------- Add mock_domain_alloc_user() and a new test case for IOMMU_HWPT_ALLOC_NEST_PARENT. Intel-SIG: 408663619fcf iommufd/selftest: Add domain_alloc_user() support in iommu mock Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-6-yi.l.liu@intel.com Co-developed-by: Nicolin Chen Signed-off-by: Nicolin Chen Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 19 +++++++++++++++ tools/testing/selftests/iommu/iommufd.c | 24 +++++++++++++++---- .../selftests/iommu/iommufd_fail_nth.c | 2 +- tools/testing/selftests/iommu/iommufd_utils.h | 11 ++++++--- 4 files changed, 48 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 56506d5753f1..fe7e3c7d933a 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -146,6 +146,8 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) return info; } +static const struct iommu_ops mock_ops; + static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type) { struct mock_iommu_domain *mock; @@ -162,10 +164,26 @@ static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type) mock->domain.geometry.aperture_start = MOCK_APERTURE_START; mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST; mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE; + mock->domain.ops = mock_ops.default_domain_ops; + mock->domain.type = iommu_domain_type; xa_init(&mock->pfns); return &mock->domain; } +static struct iommu_domain * +mock_domain_alloc_user(struct device *dev, u32 flags) +{ + struct iommu_domain *domain; + + if (flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) + return ERR_PTR(-EOPNOTSUPP); + + domain = mock_domain_alloc(IOMMU_DOMAIN_UNMANAGED); + if (!domain) + domain = ERR_PTR(-ENOMEM); + return domain; +} + static void mock_domain_free(struct iommu_domain *domain) { struct mock_iommu_domain *mock = @@ -307,6 +325,7 @@ static const struct iommu_ops mock_ops = { .pgsize_bitmap = MOCK_IO_PAGE_SIZE, .hw_info = mock_domain_hw_info, .domain_alloc = mock_domain_alloc, + .domain_alloc_user = mock_domain_alloc_user, .capable = mock_domain_capable, .set_platform_dma_ops = mock_domain_set_plaform_dma_ops, .device_group = generic_device_group, diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 9f705c1ea30f..9c129e63d7c7 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -114,6 +114,7 @@ TEST_F(iommufd, cmd_length) TEST_LENGTH(iommu_destroy, IOMMU_DESTROY); TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO); + TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC); TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC); TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES); TEST_LENGTH(iommu_ioas_allow_iovas, IOMMU_IOAS_ALLOW_IOVAS); @@ -1404,13 +1405,28 @@ TEST_F(iommufd_mock_domain, alloc_hwpt) int i; for (i = 0; i != variant->mock_domains; i++) { + uint32_t hwpt_id[2]; uint32_t stddev_id; - uint32_t hwpt_id; - test_cmd_hwpt_alloc(self->idev_ids[i], self->ioas_id, &hwpt_id); - test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + test_err_hwpt_alloc(EOPNOTSUPP, + self->idev_ids[i], self->ioas_id, + ~IOMMU_HWPT_ALLOC_NEST_PARENT, &hwpt_id[0]); + test_cmd_hwpt_alloc(self->idev_ids[i], self->ioas_id, + 0, &hwpt_id[0]); + test_cmd_hwpt_alloc(self->idev_ids[i], self->ioas_id, + IOMMU_HWPT_ALLOC_NEST_PARENT, &hwpt_id[1]); + + /* Do a hw_pagetable rotation test */ + test_cmd_mock_domain_replace(self->stdev_ids[i], hwpt_id[0]); + EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, hwpt_id[0])); + test_cmd_mock_domain_replace(self->stdev_ids[i], hwpt_id[1]); + EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, hwpt_id[1])); + test_cmd_mock_domain_replace(self->stdev_ids[i], self->ioas_id); + test_ioctl_destroy(hwpt_id[1]); + + test_cmd_mock_domain(hwpt_id[0], &stddev_id, NULL, NULL); test_ioctl_destroy(stddev_id); - test_ioctl_destroy(hwpt_id); + test_ioctl_destroy(hwpt_id[0]); } } diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index a220ca2a689d..3d7838506bfe 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -615,7 +615,7 @@ TEST_FAIL_NTH(basic_fail_nth, device) if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info))) return -1; - if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, &hwpt_id)) + if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, &hwpt_id)) return -1; if (_test_cmd_mock_domain_replace(self->fd, stdev_id, ioas_id2, NULL)) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index e0753d03ecaa..be4970a84977 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -103,10 +103,11 @@ static int _test_cmd_mock_domain_replace(int fd, __u32 stdev_id, __u32 pt_id, pt_id, NULL)) static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, - __u32 *hwpt_id) + __u32 flags, __u32 *hwpt_id) { struct iommu_hwpt_alloc cmd = { .size = sizeof(cmd), + .flags = flags, .dev_id = device_id, .pt_id = pt_id, }; @@ -120,8 +121,12 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, return 0; } -#define test_cmd_hwpt_alloc(device_id, pt_id, hwpt_id) \ - ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, hwpt_id)) +#define test_cmd_hwpt_alloc(device_id, pt_id, flags, hwpt_id) \ + ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, \ + pt_id, flags, hwpt_id)) +#define test_err_hwpt_alloc(_errno, device_id, pt_id, flags, hwpt_id) \ + EXPECT_ERRNO(_errno, _test_cmd_hwpt_alloc(self->fd, device_id, \ + pt_id, flags, hwpt_id)) static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, unsigned int ioas_id) -- Gitee From d7ed92ba92a12107600890ba9ec54feb7f8d5795 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Sep 2023 00:15:28 -0700 Subject: [PATCH 07/31] iommu/vt-d: Add domain_alloc_user op mainline inclusion from mainline-v6.7-rc1 commit c97d1b20d3835178bcd0e3a86c20ce4e36b6d80c category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?c97d1b20d3835178bcd0e3a86c20ce4e36b6d80c -------------------------------- Add the domain_alloc_user() op implementation. It supports allocating domains to be used as parent under nested translation. Unlike other drivers VT-D uses only a single page table format so it only needs to check if the HW can support nesting. Intel-SIG: c97d1b20d383 iommu/vt-d: Add domain_alloc_user op Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20230928071528.26258-7-yi.l.liu@intel.com Signed-off-by: Yi Liu Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/intel/iommu.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 4c3707384bd9..da2b79abfc13 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4059,6 +4059,33 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) return NULL; } +static struct iommu_domain * +intel_iommu_domain_alloc_user(struct device *dev, u32 flags) +{ + struct iommu_domain *domain; + struct intel_iommu *iommu; + + if (flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) + return ERR_PTR(-EOPNOTSUPP); + + iommu = device_to_iommu(dev, NULL, NULL); + if (!iommu) + return ERR_PTR(-ENODEV); + + if ((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) && !ecap_nest(iommu->ecap)) + return ERR_PTR(-EOPNOTSUPP); + + /* + * domain_alloc_user op needs to fully initialize a domain + * before return, so uses iommu_domain_alloc() here for + * simple. + */ + domain = iommu_domain_alloc(dev->bus); + if (!domain) + domain = ERR_PTR(-ENOMEM); + return domain; +} + static void intel_iommu_domain_free(struct iommu_domain *domain) { if (domain != &si_domain->domain && domain != &blocking_domain) @@ -4792,6 +4819,7 @@ const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .hw_info = intel_iommu_hw_info, .domain_alloc = intel_iommu_domain_alloc, + .domain_alloc_user = intel_iommu_domain_alloc_user, .probe_device = intel_iommu_probe_device, .probe_finalize = intel_iommu_probe_finalize, .release_device = intel_iommu_release_device, -- Gitee From 139c631d938cc9375bf5fe5a2e6e3886e97847c5 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Sun, 15 Oct 2023 00:46:48 -0700 Subject: [PATCH 08/31] iommufd/selftest: Rework TEST_LENGTH to test min_size explicitly mainline inclusion from mainline-v6.7-rc1 commit 266dcae34d8f44c3bbab00e227f8b14517682bb7 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?266dcae34d8f44c3bbab00e227f8b14517682bb7 -------------------------------- TEST_LENGTH passing ".size = sizeof(struct _struct) - 1" expects -EINVAL from "if (ucmd.user_size < op->min_size)" check in iommufd_fops_ioctl(). This has been working when min_size is exactly the size of the structure. However, if the size of the structure becomes larger than min_size, i.e. the passing size above is larger than min_size, that min_size sanity no longer works. Since the first test in TEST_LENGTH() was to test that min_size sanity routine, rework it to support a min_size calculation, rather than using the full size of the structure. Intel-SIG: 266dcae34d8f iommufd/selftest: Rework TEST_LENGTH to test min_size explicitly Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231015074648.24185-1-nicolinc@nvidia.com Signed-off-by: Nicolin Chen Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend-commit-log ] Signed-off-by: Jason Zeng --- tools/testing/selftests/iommu/iommufd.c | 29 ++++++++++++++----------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 9c129e63d7c7..7a29d68bd1d2 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -86,12 +86,13 @@ TEST_F(iommufd, cmd_fail) TEST_F(iommufd, cmd_length) { -#define TEST_LENGTH(_struct, _ioctl) \ +#define TEST_LENGTH(_struct, _ioctl, _last) \ { \ + size_t min_size = offsetofend(struct _struct, _last); \ struct { \ struct _struct cmd; \ uint8_t extra; \ - } cmd = { .cmd = { .size = sizeof(struct _struct) - 1 }, \ + } cmd = { .cmd = { .size = min_size - 1 }, \ .extra = UINT8_MAX }; \ int old_errno; \ int rc; \ @@ -112,17 +113,19 @@ TEST_F(iommufd, cmd_length) } \ } - TEST_LENGTH(iommu_destroy, IOMMU_DESTROY); - TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO); - TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC); - TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC); - TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES); - TEST_LENGTH(iommu_ioas_allow_iovas, IOMMU_IOAS_ALLOW_IOVAS); - TEST_LENGTH(iommu_ioas_map, IOMMU_IOAS_MAP); - TEST_LENGTH(iommu_ioas_copy, IOMMU_IOAS_COPY); - TEST_LENGTH(iommu_ioas_unmap, IOMMU_IOAS_UNMAP); - TEST_LENGTH(iommu_option, IOMMU_OPTION); - TEST_LENGTH(iommu_vfio_ioas, IOMMU_VFIO_IOAS); + TEST_LENGTH(iommu_destroy, IOMMU_DESTROY, id); + TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO, __reserved); + TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC, __reserved); + TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC, out_ioas_id); + TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES, + out_iova_alignment); + TEST_LENGTH(iommu_ioas_allow_iovas, IOMMU_IOAS_ALLOW_IOVAS, + allowed_iovas); + TEST_LENGTH(iommu_ioas_map, IOMMU_IOAS_MAP, iova); + TEST_LENGTH(iommu_ioas_copy, IOMMU_IOAS_COPY, src_iova); + TEST_LENGTH(iommu_ioas_unmap, IOMMU_IOAS_UNMAP, length); + TEST_LENGTH(iommu_option, IOMMU_OPTION, val64); + TEST_LENGTH(iommu_vfio_ioas, IOMMU_VFIO_IOAS, __reserved); #undef TEST_LENGTH } -- Gitee From 5d24db65a7d4dd141d5034847027bd3e729dbdb7 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:52 +0100 Subject: [PATCH 09/31] vfio/iova_bitmap: Export more API symbols mainline inclusion from mainline-v6.7-rc1 commit 53f0b020218fcc0a56a11df39630dbd379e4d9a6 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?53f0b020218fcc0a56a11df39630dbd379e4d9a6 -------------------------------- In preparation to move iova_bitmap into iommufd, export the rest of API symbols that will be used in what could be used by modules, namely: iova_bitmap_alloc iova_bitmap_free iova_bitmap_for_each Intel-SIG: 53f0b020218f vfio/iova_bitmap: Export more API symbols Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-2-joao.m.martins@oracle.com Suggested-by: Alex Williamson Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/vfio/iova_bitmap.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/vfio/iova_bitmap.c b/drivers/vfio/iova_bitmap.c index 0848f920efb7..f54b56388e00 100644 --- a/drivers/vfio/iova_bitmap.c +++ b/drivers/vfio/iova_bitmap.c @@ -268,6 +268,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, iova_bitmap_free(bitmap); return ERR_PTR(rc); } +EXPORT_SYMBOL_GPL(iova_bitmap_alloc); /** * iova_bitmap_free() - Frees an IOVA bitmap object @@ -289,6 +290,7 @@ void iova_bitmap_free(struct iova_bitmap *bitmap) kfree(bitmap); } +EXPORT_SYMBOL_GPL(iova_bitmap_free); /* * Returns the remaining bitmap indexes from mapped_total_index to process for @@ -387,6 +389,7 @@ int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, return ret; } +EXPORT_SYMBOL_GPL(iova_bitmap_for_each); /** * iova_bitmap_set() - Records an IOVA range in bitmap -- Gitee From 8b4907940f730d659fec5c0540cf8d3fd2f11548 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:53 +0100 Subject: [PATCH 10/31] vfio: Move iova_bitmap into iommufd mainline inclusion from mainline-v6.7-rc1 commit 8c9c727b6142325ed5697240fceb99cbeb4ac2ec category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?8c9c727b6142325ed5697240fceb99cbeb4ac2ec -------------------------------- Both VFIO and IOMMUFD will need iova bitmap for storing dirties and walking the user bitmaps, so move to the common dependency into IOMMUFD. In doing so, create the symbol IOMMUFD_DRIVER which designates the builtin code that will be used by drivers when selected. Today this means MLX5_VFIO_PCI and PDS_VFIO_PCI. IOMMU drivers will do the same (in future patches) when supporting dirty tracking and select IOMMUFD_DRIVER accordingly. Given that the symbol maybe be disabled, add header definitions in iova_bitmap.h for when IOMMUFD_DRIVER=n Intel-SIG: 8c9c727b6142 vfio: Move iova_bitmap into iommufd Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-3-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Brett Creeley Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/Kconfig | 4 +++ drivers/iommu/iommufd/Makefile | 1 + drivers/{vfio => iommu/iommufd}/iova_bitmap.c | 0 drivers/vfio/Makefile | 3 +-- drivers/vfio/pci/mlx5/Kconfig | 1 + drivers/vfio/pci/pds/Kconfig | 1 + include/linux/iova_bitmap.h | 26 +++++++++++++++++++ 7 files changed, 34 insertions(+), 2 deletions(-) rename drivers/{vfio => iommu/iommufd}/iova_bitmap.c (100%) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 802c8d915229..3fd0a3888d22 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -7,6 +7,10 @@ config IOMMU_IOVA config IOMMU_API bool +config IOMMUFD_DRIVER + bool + default n + menuconfig IOMMU_SUPPORT bool "IOMMU Hardware Support" depends on MMU diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index 8aeba81800c5..34b446146961 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -11,3 +11,4 @@ iommufd-y := \ iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o obj-$(CONFIG_IOMMUFD) += iommufd.o +obj-$(CONFIG_IOMMUFD_DRIVER) += iova_bitmap.o diff --git a/drivers/vfio/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c similarity index 100% rename from drivers/vfio/iova_bitmap.c rename to drivers/iommu/iommufd/iova_bitmap.c diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index c82ea032d352..68c05705200f 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -1,8 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_VFIO) += vfio.o -vfio-y += vfio_main.o \ - iova_bitmap.o +vfio-y += vfio_main.o vfio-$(CONFIG_VFIO_DEVICE_CDEV) += device_cdev.o vfio-$(CONFIG_VFIO_GROUP) += group.o vfio-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/vfio/pci/mlx5/Kconfig b/drivers/vfio/pci/mlx5/Kconfig index 7088edc4fb28..c3ced56b7787 100644 --- a/drivers/vfio/pci/mlx5/Kconfig +++ b/drivers/vfio/pci/mlx5/Kconfig @@ -3,6 +3,7 @@ config MLX5_VFIO_PCI tristate "VFIO support for MLX5 PCI devices" depends on MLX5_CORE select VFIO_PCI_CORE + select IOMMUFD_DRIVER help This provides migration support for MLX5 devices using the VFIO framework. diff --git a/drivers/vfio/pci/pds/Kconfig b/drivers/vfio/pci/pds/Kconfig index 6eceef7b028a..fec9b167c7b9 100644 --- a/drivers/vfio/pci/pds/Kconfig +++ b/drivers/vfio/pci/pds/Kconfig @@ -5,6 +5,7 @@ config PDS_VFIO_PCI tristate "VFIO support for PDS PCI devices" depends on PDS_CORE && PCI_IOV select VFIO_PCI_CORE + select IOMMUFD_DRIVER help This provides generic PCI support for PDS devices using the VFIO framework. diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h index c006cf0a25f3..1c338f5e5b7a 100644 --- a/include/linux/iova_bitmap.h +++ b/include/linux/iova_bitmap.h @@ -7,6 +7,7 @@ #define _IOVA_BITMAP_H_ #include +#include struct iova_bitmap; @@ -14,6 +15,7 @@ typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap, unsigned long iova, size_t length, void *opaque); +#if IS_ENABLED(CONFIG_IOMMUFD_DRIVER) struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, unsigned long page_size, u64 __user *data); @@ -22,5 +24,29 @@ int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, iova_bitmap_fn_t fn); void iova_bitmap_set(struct iova_bitmap *bitmap, unsigned long iova, size_t length); +#else +static inline struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, + size_t length, + unsigned long page_size, + u64 __user *data) +{ + return NULL; +} + +static inline void iova_bitmap_free(struct iova_bitmap *bitmap) +{ +} + +static inline int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, + iova_bitmap_fn_t fn) +{ + return -EOPNOTSUPP; +} + +static inline void iova_bitmap_set(struct iova_bitmap *bitmap, + unsigned long iova, size_t length) +{ +} +#endif #endif -- Gitee From 5547fc2e2ff71f4342b0b7f9294ecbcfd59aa02e Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:54 +0100 Subject: [PATCH 11/31] iommufd/iova_bitmap: Move symbols to IOMMUFD namespace mainline inclusion from mainline-v6.7-rc1 commit 13578d4ebe8be1c16146f37c0c91f2579611cff2 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?13578d4ebe8be1c16146f37c0c91f2579611cff2 -------------------------------- Have the IOVA bitmap exported symbols adhere to the IOMMUFD symbol export convention i.e. using the IOMMUFD namespace. In doing so, import the namespace in the current users. This means VFIO and the vfio-pci drivers that use iova_bitmap_set(). Intel-SIG: 13578d4ebe8b iommufd/iova_bitmap: Move symbols to IOMMUFD namespace Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-4-joao.m.martins@oracle.com Suggested-by: Jason Gunthorpe Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Brett Creeley Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/iova_bitmap.c | 8 ++++---- drivers/vfio/pci/mlx5/main.c | 1 + drivers/vfio/pci/pds/pci_drv.c | 1 + drivers/vfio/vfio_main.c | 1 + 4 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c index f54b56388e00..0a92c9eeaf7f 100644 --- a/drivers/iommu/iommufd/iova_bitmap.c +++ b/drivers/iommu/iommufd/iova_bitmap.c @@ -268,7 +268,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, iova_bitmap_free(bitmap); return ERR_PTR(rc); } -EXPORT_SYMBOL_GPL(iova_bitmap_alloc); +EXPORT_SYMBOL_NS_GPL(iova_bitmap_alloc, IOMMUFD); /** * iova_bitmap_free() - Frees an IOVA bitmap object @@ -290,7 +290,7 @@ void iova_bitmap_free(struct iova_bitmap *bitmap) kfree(bitmap); } -EXPORT_SYMBOL_GPL(iova_bitmap_free); +EXPORT_SYMBOL_NS_GPL(iova_bitmap_free, IOMMUFD); /* * Returns the remaining bitmap indexes from mapped_total_index to process for @@ -389,7 +389,7 @@ int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque, return ret; } -EXPORT_SYMBOL_GPL(iova_bitmap_for_each); +EXPORT_SYMBOL_NS_GPL(iova_bitmap_for_each, IOMMUFD); /** * iova_bitmap_set() - Records an IOVA range in bitmap @@ -423,4 +423,4 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, cur_bit += nbits; } while (cur_bit <= last_bit); } -EXPORT_SYMBOL_GPL(iova_bitmap_set); +EXPORT_SYMBOL_NS_GPL(iova_bitmap_set, IOMMUFD); diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 42ec574a8622..5cf2b491d15a 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -1376,6 +1376,7 @@ static struct pci_driver mlx5vf_pci_driver = { module_pci_driver(mlx5vf_pci_driver); +MODULE_IMPORT_NS(IOMMUFD); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Max Gurtovoy "); MODULE_AUTHOR("Yishai Hadas "); diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c index caffa1a2cf59..a34dda516629 100644 --- a/drivers/vfio/pci/pds/pci_drv.c +++ b/drivers/vfio/pci/pds/pci_drv.c @@ -204,6 +204,7 @@ static struct pci_driver pds_vfio_pci_driver = { module_pci_driver(pds_vfio_pci_driver); +MODULE_IMPORT_NS(IOMMUFD); MODULE_DESCRIPTION(PDS_VFIO_DRV_DESCRIPTION); MODULE_AUTHOR("Brett Creeley "); MODULE_LICENSE("GPL"); diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 40732e8ed4c6..a96d97da367d 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1693,6 +1693,7 @@ static void __exit vfio_cleanup(void) module_init(vfio_init); module_exit(vfio_cleanup); +MODULE_IMPORT_NS(IOMMUFD); MODULE_VERSION(DRIVER_VERSION); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR(DRIVER_AUTHOR); -- Gitee From aeff369a2057ff0ca47c3b66532ac9f08bebae3b Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:55 +0100 Subject: [PATCH 12/31] iommu: Add iommu_domain ops for dirty tracking mainline inclusion from mainline-v6.7-rc1 commit 750e2e902b7180cb82d2f9b1e372e32087bb8b1b category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?750e2e902b7180cb82d2f9b1e372e32087bb8b1b -------------------------------- Add to iommu domain operations a set of callbacks to perform dirty tracking, particulary to start and stop tracking and to read and clear the dirty data. Drivers are generally expected to dynamically change its translation structures to toggle the tracking and flush some form of control state structure that stands in the IOVA translation path. Though it's not mandatory, as drivers can also enable dirty tracking at boot, and just clear the dirty bits before setting dirty tracking. For each of the newly added IOMMU core APIs: iommu_cap::IOMMU_CAP_DIRTY_TRACKING: new device iommu_capable value when probing for capabilities of the device. .set_dirty_tracking(): an iommu driver is expected to change its translation structures and enable dirty tracking for the devices in the iommu_domain. For drivers making dirty tracking always-enabled, it should just return 0. .read_and_clear_dirty(): an iommu driver is expected to walk the pagetables for the iova range passed in and use iommu_dirty_bitmap_record() to record dirty info per IOVA. When detecting that a given IOVA is dirty it should also clear its dirty state from the PTE, *unless* the flag IOMMU_DIRTY_NO_CLEAR is passed in -- flushing is steered from the caller of the domain_op via iotlb_gather. The iommu core APIs use the same data structure in use for dirty tracking for VFIO device dirty (struct iova_bitmap) abstracted by iommu_dirty_bitmap_record() helper function. domain::dirty_ops: IOMMU domains will store the dirty ops depending on whether the iommu device supports dirty tracking or not. iommu drivers can then use this field to figure if the dirty tracking is supported+enforced on attach. The enforcement is enable via domain_alloc_user() which is done via IOMMUFD hwpt flag introduced later. Intel-SIG: 750e2e902b71 iommu: Add iommu_domain ops for dirty tracking Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- include/linux/io-pgtable.h | 4 +++ include/linux/iommu.h | 70 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 1b7a44b35616..25142a0e2fc2 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -166,6 +166,10 @@ struct io_pgtable_ops { struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); + int (*read_and_clear_dirty)(struct io_pgtable_ops *ops, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty); }; /** diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2c64d331fe8e..5398c399fe9d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #define IOMMU_READ (1 << 0) @@ -37,6 +38,7 @@ struct bus_type; struct device; struct iommu_domain; struct iommu_domain_ops; +struct iommu_dirty_ops; struct notifier_block; struct iommu_sva; struct iommu_fault_event; @@ -95,6 +97,8 @@ struct iommu_domain_geometry { struct iommu_domain { unsigned type; const struct iommu_domain_ops *ops; + const struct iommu_dirty_ops *dirty_ops; + unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; @@ -133,6 +137,7 @@ enum iommu_cap { * usefully support the non-strict DMA flush queue. */ IOMMU_CAP_DEFERRED_FLUSH, + IOMMU_CAP_DIRTY_TRACKING, /* IOMMU supports dirty tracking */ }; /* These are the possible reserved region types */ @@ -227,6 +232,35 @@ struct iommu_iotlb_gather { bool queued; }; +/** + * struct iommu_dirty_bitmap - Dirty IOVA bitmap state + * @bitmap: IOVA bitmap + * @gather: Range information for a pending IOTLB flush + */ +struct iommu_dirty_bitmap { + struct iova_bitmap *bitmap; + struct iommu_iotlb_gather *gather; +}; + +/* Read but do not clear any dirty bits */ +#define IOMMU_DIRTY_NO_CLEAR (1 << 0) + +/** + * struct iommu_dirty_ops - domain specific dirty tracking operations + * @set_dirty_tracking: Enable or Disable dirty tracking on the iommu domain + * @read_and_clear_dirty: Walk IOMMU page tables for dirtied PTEs marshalled + * into a bitmap, with a bit represented as a page. + * Reads the dirty PTE bits and clears it from IO + * pagetables. + */ +struct iommu_dirty_ops { + int (*set_dirty_tracking)(struct iommu_domain *domain, bool enabled); + int (*read_and_clear_dirty)(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty); +}; + /** * struct iommu_ops - iommu ops and capabilities * @capable: check capability @@ -641,6 +675,28 @@ static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather) return gather && gather->queued; } +static inline void iommu_dirty_bitmap_init(struct iommu_dirty_bitmap *dirty, + struct iova_bitmap *bitmap, + struct iommu_iotlb_gather *gather) +{ + if (gather) + iommu_iotlb_gather_init(gather); + + dirty->bitmap = bitmap; + dirty->gather = gather; +} + +static inline void iommu_dirty_bitmap_record(struct iommu_dirty_bitmap *dirty, + unsigned long iova, + unsigned long length) +{ + if (dirty->bitmap) + iova_bitmap_set(dirty->bitmap, iova, length); + + if (dirty->gather) + iommu_iotlb_gather_add_range(dirty->gather, iova, length); +} + /* PCI device grouping function */ extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ @@ -747,6 +803,8 @@ struct iommu_fwspec {}; struct iommu_device {}; struct iommu_fault_param {}; struct iommu_iotlb_gather {}; +struct iommu_dirty_bitmap {}; +struct iommu_dirty_ops {}; static inline bool iommu_present(const struct bus_type *bus) { @@ -979,6 +1037,18 @@ static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather) return false; } +static inline void iommu_dirty_bitmap_init(struct iommu_dirty_bitmap *dirty, + struct iova_bitmap *bitmap, + struct iommu_iotlb_gather *gather) +{ +} + +static inline void iommu_dirty_bitmap_record(struct iommu_dirty_bitmap *dirty, + unsigned long iova, + unsigned long length) +{ +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } -- Gitee From 13d698ca6fcdfbb967fc49634fe225e0381bc78e Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 17 Oct 2023 11:15:52 -0700 Subject: [PATCH 13/31] iommufd: Correct IOMMU_HWPT_ALLOC_NEST_PARENT description mainline inclusion from mainline-v6.7-rc1 commit b5f9e63278d6f32789478acf1ed41d21d92b36cf category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?b5f9e63278d6f32789478acf1ed41d21d92b36cf -------------------------------- The IOMMU_HWPT_ALLOC_NEST_PARENT flag is used to allocate a HWPT. Though a HWPT holds a domain in the core structure, it is still quite confusing to describe it using "domain" in the uAPI kdoc. Correct it to "HWPT". Intel-SIG: b5f9e63278d6 iommufd: Correct IOMMU_HWPT_ALLOC_NEST_PARENT description Backport IOMMUFD Dirty Tracking Fixes: 4ff542163397 ("iommufd: Support allocating nested parent domain") Link: https://lore.kernel.org/r/20231017181552.12667-1-nicolinc@nvidia.com Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- include/uapi/linux/iommufd.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 4a7c5c8fdbb4..be7a95042677 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -349,9 +349,8 @@ struct iommu_vfio_ioas { /** * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation - * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a domain which can serve - * as the parent domain in the nesting - * configuration. + * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a HWPT that can serve as + * the parent HWPT in a nesting configuration. */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, -- Gitee From a1cd490f405a26a343cd6f17333d88f449158d13 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:56 +0100 Subject: [PATCH 14/31] iommufd: Add a flag to enforce dirty tracking on attach mainline inclusion from mainline-v6.7-rc1 commit 5f9bdbf4c65860cc8b9c544d92bfd76fbea8d9c5 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?5f9bdbf4c65860cc8b9c544d92bfd76fbea8d9c5 -------------------------------- Throughout IOMMU domain lifetime that wants to use dirty tracking, some guarantees are needed such that any device attached to the iommu_domain supports dirty tracking. The idea is to handle a case where IOMMU in the system are assymetric feature-wise and thus the capability may not be supported for all devices. The enforcement is done by adding a flag into HWPT_ALLOC namely: IOMMU_HWPT_ALLOC_DIRTY_TRACKING .. Passed in HWPT_ALLOC ioctl() flags. The enforcement is done by creating a iommu_domain via domain_alloc_user() and validating the requested flags with what the device IOMMU supports (and failing accordingly) advertised). Advertising the new IOMMU domain feature flag requires that the individual iommu driver capability is supported when a future device attachment happens. Intel-SIG: 5f9bdbf4c658 iommufd: Add a flag to enforce dirty tracking on attach Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-6-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 4 +++- include/uapi/linux/iommufd.h | 3 +++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 8b3d2875d642..dd50ca9e2c09 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -157,7 +157,9 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc; - if ((cmd->flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) || cmd->__reserved) + if ((cmd->flags & ~(IOMMU_HWPT_ALLOC_NEST_PARENT | + IOMMU_HWPT_ALLOC_DIRTY_TRACKING)) || + cmd->__reserved) return -EOPNOTSUPP; idev = iommufd_get_device(ucmd, cmd->dev_id); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index be7a95042677..c76248410120 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -351,9 +351,12 @@ struct iommu_vfio_ioas { * enum iommufd_hwpt_alloc_flags - Flags for HWPT allocation * @IOMMU_HWPT_ALLOC_NEST_PARENT: If set, allocate a HWPT that can serve as * the parent HWPT in a nesting configuration. + * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is + * enforced on device attachment */ enum iommufd_hwpt_alloc_flags { IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1, }; /** -- Gitee From d68515e3b9349e5b1d4794749b6f9da0eaaef099 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:57 +0100 Subject: [PATCH 15/31] iommufd: Add IOMMU_HWPT_SET_DIRTY_TRACKING mainline inclusion from mainline-v6.7-rc1 commit e2a4b294784957fc28ecb1fed8a7e69da18eb18d category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?e2a4b294784957fc28ecb1fed8a7e69da18eb18d -------------------------------- Every IOMMU driver should be able to implement the needed iommu domain ops to control dirty tracking. Connect a hw_pagetable to the IOMMU core dirty tracking ops, specifically the ability to enable/disable dirty tracking on an IOMMU domain (hw_pagetable id). To that end add an io_pagetable kernel API to toggle dirty tracking: * iopt_set_dirty_tracking(iopt, [domain], state) The intended caller of this is via the hw_pagetable object that is created. Internally it will ensure the leftover dirty state is cleared /right before/ dirty tracking starts. This is also useful for iommu drivers which may decide that dirty tracking is always-enabled at boot without wanting to toggle dynamically via corresponding iommu domain op. Intel-SIG: e2a4b2947849 iommufd: Add IOMMU_HWPT_SET_DIRTY_TRACKING Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-7-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 24 +++++++++++ drivers/iommu/iommufd/io_pagetable.c | 54 +++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 12 ++++++ drivers/iommu/iommufd/main.c | 3 ++ include/uapi/linux/iommufd.h | 28 +++++++++++++ 5 files changed, 121 insertions(+) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index dd50ca9e2c09..c3b7bd9bfcbb 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -196,3 +196,27 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) iommufd_put_object(&idev->obj); return rc; } + +int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_set_dirty_tracking *cmd = ucmd->cmd; + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = -EOPNOTSUPP; + bool enable; + + if (cmd->flags & ~IOMMU_HWPT_DIRTY_TRACKING_ENABLE) + return rc; + + hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + ioas = hwpt->ioas; + enable = cmd->flags & IOMMU_HWPT_DIRTY_TRACKING_ENABLE; + + rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt->domain, enable); + + iommufd_put_object(&hwpt->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 117a39ae2e4a..49460d84473d 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -424,6 +424,60 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, return 0; } +static int iopt_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + struct iommu_iotlb_gather gather; + struct iommu_dirty_bitmap dirty; + struct iopt_area *area; + int ret = 0; + + lockdep_assert_held_read(&iopt->iova_rwsem); + + iommu_dirty_bitmap_init(&dirty, NULL, &gather); + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + if (!area->pages) + continue; + + ret = ops->read_and_clear_dirty(domain, iopt_area_iova(area), + iopt_area_length(area), 0, + &dirty); + if (ret) + break; + } + + iommu_iotlb_sync(domain, &gather); + return ret; +} + +int iopt_set_dirty_tracking(struct io_pagetable *iopt, + struct iommu_domain *domain, bool enable) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + int ret = 0; + + if (!ops) + return -EOPNOTSUPP; + + down_read(&iopt->iova_rwsem); + + /* Clear dirty bits from PTEs to ensure a clean snapshot */ + if (enable) { + ret = iopt_clear_dirty_data(iopt, domain); + if (ret) + goto out_unlock; + } + + ret = ops->set_dirty_tracking(domain, enable); + +out_unlock: + up_read(&iopt->iova_rwsem); + return ret; +} + int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova, unsigned long length, struct list_head *pages_list) { diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 3064997a0181..b09750848da6 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -8,6 +8,7 @@ #include #include #include +#include struct iommu_domain; struct iommu_group; @@ -70,6 +71,9 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, unsigned long length, unsigned long *unmapped); int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped); +int iopt_set_dirty_tracking(struct io_pagetable *iopt, + struct iommu_domain *domain, bool enable); + void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova, unsigned long length); int iopt_table_add_domain(struct io_pagetable *iopt, @@ -240,6 +244,14 @@ struct iommufd_hw_pagetable { struct list_head hwpt_item; }; +static inline struct iommufd_hw_pagetable * +iommufd_get_hwpt(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_HW_PAGETABLE), + struct iommufd_hw_pagetable, obj); +} +int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index e71523cbd0de..46fedd779714 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -307,6 +307,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; + struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; struct iommu_ioas_copy ioas_copy; @@ -342,6 +343,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc, __reserved), + IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, + struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, struct iommu_ioas_alloc, out_ioas_id), IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas, diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index c76248410120..5c82b68c88f3 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -47,6 +47,7 @@ enum { IOMMUFD_CMD_VFIO_IOAS, IOMMUFD_CMD_HWPT_ALLOC, IOMMUFD_CMD_GET_HW_INFO, + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, }; /** @@ -453,4 +454,31 @@ struct iommu_hw_info { __u32 __reserved; }; #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) + +/* + * enum iommufd_hwpt_set_dirty_tracking_flags - Flags for steering dirty + * tracking + * @IOMMU_HWPT_DIRTY_TRACKING_ENABLE: Enable dirty tracking + */ +enum iommufd_hwpt_set_dirty_tracking_flags { + IOMMU_HWPT_DIRTY_TRACKING_ENABLE = 1, +}; + +/** + * struct iommu_hwpt_set_dirty_tracking - ioctl(IOMMU_HWPT_SET_DIRTY_TRACKING) + * @size: sizeof(struct iommu_hwpt_set_dirty_tracking) + * @flags: Combination of enum iommufd_hwpt_set_dirty_tracking_flags + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @__reserved: Must be 0 + * + * Toggle dirty tracking on an HW pagetable. + */ +struct iommu_hwpt_set_dirty_tracking { + __u32 size; + __u32 flags; + __u32 hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) #endif -- Gitee From 2a12b41656fc34c14c8a6967ee9ede442aec7832 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:58 +0100 Subject: [PATCH 16/31] iommufd: Add IOMMU_HWPT_GET_DIRTY_BITMAP mainline inclusion from mainline-v6.7-rc1 commit b9a60d6f850e4470017b60f731220a58cda199aa category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?b9a60d6f850e4470017b60f731220a58cda199aa -------------------------------- Connect a hw_pagetable to the IOMMU core dirty tracking read_and_clear_dirty iommu domain op. It exposes all of the functionality for the UAPI that read the dirtied IOVAs while clearing the Dirty bits from the PTEs. In doing so, add an IO pagetable API iopt_read_and_clear_dirty_data() that performs the reading of dirty IOPTEs for a given IOVA range and then copying back to userspace bitmap. Underneath it uses the IOMMU domain kernel API which will read the dirty bits, as well as atomically clearing the IOPTE dirty bit and flushing the IOTLB at the end. The IOVA bitmaps usage takes care of the iteration of the bitmaps user pages efficiently and without copies. Within the iterator function we iterate over io-pagetable contigous areas that have been mapped. Contrary to past incantation of a similar interface in VFIO the IOVA range to be scanned is tied in to the bitmap size, thus the application needs to pass a appropriately sized bitmap address taking into account the iova range being passed *and* page size ... as opposed to allowing bitmap-iova != iova. Intel-SIG: b9a60d6f850e iommufd: Add IOMMU_HWPT_GET_DIRTY_BITMAP Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-8-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 22 +++++ drivers/iommu/iommufd/io_pagetable.c | 113 ++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 10 +++ drivers/iommu/iommufd/main.c | 4 + include/uapi/linux/iommufd.h | 35 ++++++++ 5 files changed, 184 insertions(+) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index c3b7bd9bfcbb..7316f69110ef 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -220,3 +220,25 @@ int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd) iommufd_put_object(&hwpt->obj); return rc; } + +int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) +{ + struct iommu_hwpt_get_dirty_bitmap *cmd = ucmd->cmd; + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = -EOPNOTSUPP; + + if ((cmd->flags || cmd->__reserved)) + return -EOPNOTSUPP; + + hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + ioas = hwpt->ioas; + rc = iopt_read_and_clear_dirty_data(&ioas->iopt, hwpt->domain, + cmd->flags, cmd); + + iommufd_put_object(&hwpt->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 49460d84473d..0989c9132fa4 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "io_pagetable.h" #include "double_span.h" @@ -424,6 +425,118 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, return 0; } +struct iova_bitmap_fn_arg { + struct io_pagetable *iopt; + struct iommu_domain *domain; + struct iommu_dirty_bitmap *dirty; +}; + +static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap, + unsigned long iova, size_t length, + void *opaque) +{ + struct iopt_area *area; + struct iopt_area_contig_iter iter; + struct iova_bitmap_fn_arg *arg = opaque; + struct iommu_domain *domain = arg->domain; + struct iommu_dirty_bitmap *dirty = arg->dirty; + const struct iommu_dirty_ops *ops = domain->dirty_ops; + unsigned long last_iova = iova + length - 1; + int ret; + + iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) { + unsigned long last = min(last_iova, iopt_area_last_iova(area)); + + ret = ops->read_and_clear_dirty(domain, iter.cur_iova, + last - iter.cur_iova + 1, 0, + dirty); + if (ret) + return ret; + } + + if (!iopt_area_contig_done(&iter)) + return -EINVAL; + return 0; +} + +static int +iommu_read_and_clear_dirty(struct iommu_domain *domain, + struct io_pagetable *iopt, unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + const struct iommu_dirty_ops *ops = domain->dirty_ops; + struct iommu_iotlb_gather gather; + struct iommu_dirty_bitmap dirty; + struct iova_bitmap_fn_arg arg; + struct iova_bitmap *iter; + int ret = 0; + + if (!ops || !ops->read_and_clear_dirty) + return -EOPNOTSUPP; + + iter = iova_bitmap_alloc(bitmap->iova, bitmap->length, + bitmap->page_size, + u64_to_user_ptr(bitmap->data)); + if (IS_ERR(iter)) + return -ENOMEM; + + iommu_dirty_bitmap_init(&dirty, iter, &gather); + + arg.iopt = iopt; + arg.domain = domain; + arg.dirty = &dirty; + iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty); + + iommu_iotlb_sync(domain, &gather); + iova_bitmap_free(iter); + + return ret; +} + +int iommufd_check_iova_range(struct io_pagetable *iopt, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + size_t iommu_pgsize = iopt->iova_alignment; + u64 last_iova; + + if (check_add_overflow(bitmap->iova, bitmap->length - 1, &last_iova)) + return -EOVERFLOW; + + if (bitmap->iova > ULONG_MAX || last_iova > ULONG_MAX) + return -EOVERFLOW; + + if ((bitmap->iova & (iommu_pgsize - 1)) || + ((last_iova + 1) & (iommu_pgsize - 1))) + return -EINVAL; + + if (!bitmap->page_size) + return -EINVAL; + + if ((bitmap->iova & (bitmap->page_size - 1)) || + ((last_iova + 1) & (bitmap->page_size - 1))) + return -EINVAL; + + return 0; +} + +int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain, + unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap) +{ + int ret; + + ret = iommufd_check_iova_range(iopt, bitmap); + if (ret) + return ret; + + down_read(&iopt->iova_rwsem); + ret = iommu_read_and_clear_dirty(domain, iopt, flags, bitmap); + up_read(&iopt->iova_rwsem); + + return ret; +} + static int iopt_clear_dirty_data(struct io_pagetable *iopt, struct iommu_domain *domain) { diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index b09750848da6..034129130db3 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include struct iommu_domain; @@ -71,6 +73,10 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, unsigned long length, unsigned long *unmapped); int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped); +int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt, + struct iommu_domain *domain, + unsigned long flags, + struct iommu_hwpt_get_dirty_bitmap *bitmap); int iopt_set_dirty_tracking(struct io_pagetable *iopt, struct iommu_domain *domain, bool enable); @@ -226,6 +232,8 @@ int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx); int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); +int iommufd_check_iova_range(struct io_pagetable *iopt, + struct iommu_hwpt_get_dirty_bitmap *bitmap); /* * A HW pagetable is called an iommu_domain inside the kernel. This user object @@ -252,6 +260,8 @@ iommufd_get_hwpt(struct iommufd_ucmd *ucmd, u32 id) struct iommufd_hw_pagetable, obj); } int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd); +int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd); + struct iommufd_hw_pagetable * iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, struct iommufd_device *idev, u32 flags, diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 46fedd779714..d50f42a730aa 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -307,6 +307,7 @@ union ucmd_buffer { struct iommu_destroy destroy; struct iommu_hw_info info; struct iommu_hwpt_alloc hwpt; + struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap; struct iommu_hwpt_set_dirty_tracking set_dirty_tracking; struct iommu_ioas_alloc alloc; struct iommu_ioas_allow_iovas allow_iovas; @@ -343,6 +344,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { __reserved), 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, + struct iommu_hwpt_get_dirty_bitmap, data), IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking, struct iommu_hwpt_set_dirty_tracking, __reserved), IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, @@ -555,5 +558,6 @@ MODULE_ALIAS_MISCDEV(VFIO_MINOR); MODULE_ALIAS("devname:vfio/vfio"); #endif MODULE_IMPORT_NS(IOMMUFD_INTERNAL); +MODULE_IMPORT_NS(IOMMUFD); MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices"); MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 5c82b68c88f3..dce38e32ca84 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -48,6 +48,7 @@ enum { IOMMUFD_CMD_HWPT_ALLOC, IOMMUFD_CMD_GET_HW_INFO, IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING, + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP, }; /** @@ -481,4 +482,38 @@ struct iommu_hwpt_set_dirty_tracking { }; #define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) + +/** + * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP) + * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap) + * @hwpt_id: HW pagetable ID that represents the IOMMU domain + * @flags: Must be zero + * @__reserved: Must be 0 + * @iova: base IOVA of the bitmap first bit + * @length: IOVA range size + * @page_size: page size granularity of each bit in the bitmap + * @data: bitmap where to set the dirty bits. The bitmap bits each + * represent a page_size which you deviate from an arbitrary iova. + * + * Checking a given IOVA is dirty: + * + * data[(iova / page_size) / 64] & (1ULL << ((iova / page_size) % 64)) + * + * Walk the IOMMU pagetables for a given IOVA range to return a bitmap + * with the dirty IOVAs. In doing so it will also by default clear any + * dirty bit metadata set in the IOPTE. + */ +struct iommu_hwpt_get_dirty_bitmap { + __u32 size; + __u32 hwpt_id; + __u32 flags; + __u32 __reserved; + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 data; +}; +#define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \ + IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP) + #endif -- Gitee From 6259f56d98e304b950db8578fea3183cf3f76e4c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:50:59 +0100 Subject: [PATCH 17/31] iommufd: Add capabilities to IOMMU_GET_HW_INFO mainline inclusion from mainline-v6.7-rc1 commit 7623683857e52b75184d37862c70f1230aef2edd category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?7623683857e52b75184d37862c70f1230aef2edd -------------------------------- Extend IOMMUFD_CMD_GET_HW_INFO op to query generic iommu capabilities for a given device. Capabilities are IOMMU agnostic and use device_iommu_capable() API passing one of the IOMMU_CAP_*. Enumerate IOMMU_CAP_DIRTY_TRACKING for now in the out_capabilities field returned back to userspace. Intel-SIG: 7623683857e5 iommufd: Add capabilities to IOMMU_GET_HW_INFO Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-9-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/device.c | 4 ++++ include/uapi/linux/iommufd.h | 17 +++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index e88fa73a45e6..2a41fd2b6ef8 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -1185,6 +1185,10 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd) */ cmd->data_len = data_len; + cmd->out_capabilities = 0; + if (device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING)) + cmd->out_capabilities |= IOMMU_HW_CAP_DIRTY_TRACKING; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); out_free: kfree(data); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index dce38e32ca84..036ebc6c19cf 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -418,6 +418,20 @@ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_INTEL_VTD, }; +/** + * enum iommufd_hw_capabilities + * @IOMMU_HW_CAP_DIRTY_TRACKING: IOMMU hardware support for dirty tracking + * If available, it means the following APIs + * are supported: + * + * IOMMU_HWPT_GET_DIRTY_BITMAP + * IOMMU_HWPT_SET_DIRTY_TRACKING + * + */ +enum iommufd_hw_capabilities { + IOMMU_HW_CAP_DIRTY_TRACKING = 1 << 0, +}; + /** * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) * @size: sizeof(struct iommu_hw_info) @@ -429,6 +443,8 @@ enum iommu_hw_info_type { * the iommu type specific hardware information data * @out_data_type: Output the iommu hardware info type as defined in the enum * iommu_hw_info_type. + * @out_capabilities: Output the generic iommu capability info type as defined + * in the enum iommu_hw_capabilities. * @__reserved: Must be 0 * * Query an iommu type specific hardware information data from an iommu behind @@ -453,6 +469,7 @@ struct iommu_hw_info { __aligned_u64 data_uptr; __u32 out_data_type; __u32 __reserved; + __aligned_u64 out_capabilities; }; #define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) -- Gitee From 80b28fdfcc91bc32ccf6944f72aa4cc06637f4fc Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:00 +0100 Subject: [PATCH 18/31] iommufd: Add a flag to skip clearing of IOPTE dirty mainline inclusion from mainline-v6.7-rc1 commit 609848132c71316df3260d1ec066539c21bba585 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?609848132c71316df3260d1ec066539c21bba585 -------------------------------- VFIO has an operation where it unmaps an IOVA while returning a bitmap with the dirty data. In reality the operation doesn't quite query the IO pagetables that the PTE was dirty or not. Instead it marks as dirty on anything that was mapped, and doing so in one syscall. In IOMMUFD the equivalent is done in two operations by querying with GET_DIRTY_IOVA followed by UNMAP_IOVA. However, this would incur two TLB flushes given that after clearing dirty bits IOMMU implementations require invalidating their IOTLB, plus another invalidation needed for the UNMAP. To allow dirty bits to be queried faster, add a flag (IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR) that requests to not clear the dirty bits from the PTE (but just reading them), under the expectation that the next operation is the unmap. An alternative is to unmap and just perpectually mark as dirty as that's the same behaviour as today. So here equivalent functionally can be provided with unmap alone, and if real dirty info is required it will amortize the cost while querying. There's still a race against DMA where in theory the unmap of the IOVA (when the guest invalidates the IOTLB via emulated iommu) would race against the VF performing DMA on the same IOVA. As discussed in [0], we are accepting to resolve this race as throwing away the DMA and it doesn't matter if it hit physical DRAM or not, the VM can't tell if we threw it away because the DMA was blocked or because we failed to copy the DRAM. [0] https://lore.kernel.org/linux-iommu/20220502185239.GR8364@nvidia.com/ Intel-SIG: 609848132c71 iommufd: Add a flag to skip clearing of IOPTE dirty Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-10-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/hw_pagetable.c | 3 ++- drivers/iommu/iommufd/io_pagetable.c | 9 +++++++-- include/uapi/linux/iommufd.h | 15 ++++++++++++++- 3 files changed, 23 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 7316f69110ef..72a5269984b0 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -228,7 +228,8 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd) struct iommufd_ioas *ioas; int rc = -EOPNOTSUPP; - if ((cmd->flags || cmd->__reserved)) + if ((cmd->flags & ~(IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR)) || + cmd->__reserved) return -EOPNOTSUPP; hwpt = iommufd_get_hwpt(ucmd, cmd->hwpt_id); diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 0989c9132fa4..504ac1b01b2d 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -426,6 +426,7 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, } struct iova_bitmap_fn_arg { + unsigned long flags; struct io_pagetable *iopt; struct iommu_domain *domain; struct iommu_dirty_bitmap *dirty; @@ -442,13 +443,14 @@ static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap, struct iommu_dirty_bitmap *dirty = arg->dirty; const struct iommu_dirty_ops *ops = domain->dirty_ops; unsigned long last_iova = iova + length - 1; + unsigned long flags = arg->flags; int ret; iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) { unsigned long last = min(last_iova, iopt_area_last_iova(area)); ret = ops->read_and_clear_dirty(domain, iter.cur_iova, - last - iter.cur_iova + 1, 0, + last - iter.cur_iova + 1, flags, dirty); if (ret) return ret; @@ -482,12 +484,15 @@ iommu_read_and_clear_dirty(struct iommu_domain *domain, iommu_dirty_bitmap_init(&dirty, iter, &gather); + arg.flags = flags; arg.iopt = iopt; arg.domain = domain; arg.dirty = &dirty; iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty); - iommu_iotlb_sync(domain, &gather); + if (!(flags & IOMMU_DIRTY_NO_CLEAR)) + iommu_iotlb_sync(domain, &gather); + iova_bitmap_free(iter); return ret; diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 036ebc6c19cf..c44eecf5d318 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -500,11 +500,24 @@ struct iommu_hwpt_set_dirty_tracking { #define IOMMU_HWPT_SET_DIRTY_TRACKING _IO(IOMMUFD_TYPE, \ IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING) +/** + * enum iommufd_hwpt_get_dirty_bitmap_flags - Flags for getting dirty bits + * @IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR: Just read the PTEs without clearing + * any dirty bits metadata. This flag + * can be passed in the expectation + * where the next operation is an unmap + * of the same IOVA range. + * + */ +enum iommufd_hwpt_get_dirty_bitmap_flags { + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR = 1, +}; + /** * struct iommu_hwpt_get_dirty_bitmap - ioctl(IOMMU_HWPT_GET_DIRTY_BITMAP) * @size: sizeof(struct iommu_hwpt_get_dirty_bitmap) * @hwpt_id: HW pagetable ID that represents the IOMMU domain - * @flags: Must be zero + * @flags: Combination of enum iommufd_hwpt_get_dirty_bitmap_flags * @__reserved: Must be 0 * @iova: base IOVA of the bitmap first bit * @length: IOVA range size -- Gitee From 88cd90ee26aca2c7c237eb77c138684713fbc5c3 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:01 +0100 Subject: [PATCH 19/31] iommu/amd: Add domain_alloc_user based domain allocation mainline inclusion from mainline-v6.7-rc1 commit 134288158a415cd863b1c32c7dcddc0a1dc32aab category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?134288158a415cd863b1c32c7dcddc0a1dc32aab -------------------------------- Add the domain_alloc_user op implementation. To that end, refactor amd_iommu_domain_alloc() to receive a dev pointer and flags, while renaming it too, such that it becomes a common function shared with domain_alloc_user() implementation. The sole difference with domain_alloc_user() is that we initialize also other fields that iommu_domain_alloc() does. It lets it return the iommu domain correctly initialized in one function. This is in preparation to add dirty enforcement on AMD implementation of domain_alloc_user. Intel-SIG: 134288158a41 iommu/amd: Add domain_alloc_user based domain allocation Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-11-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Suravee Suthikulpanit Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/amd/iommu.c | 44 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 41 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 95bd7c25ba6f..667e23b0ab0d 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "amd_iommu.h" #include "../dma-iommu.h" @@ -2155,28 +2156,64 @@ static inline u64 dma_max_address(void) return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1); } -static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) +static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, + struct device *dev, u32 flags) { struct protection_domain *domain; + struct amd_iommu *iommu = NULL; + + if (dev) { + iommu = rlookup_amd_iommu(dev); + if (!iommu) + return ERR_PTR(-ENODEV); + } /* * Since DTE[Mode]=0 is prohibited on SNP-enabled system, * default to use IOMMU_DOMAIN_DMA[_FQ]. */ if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY)) - return NULL; + return ERR_PTR(-EINVAL); domain = protection_domain_alloc(type); if (!domain) - return NULL; + return ERR_PTR(-ENOMEM); domain->domain.geometry.aperture_start = 0; domain->domain.geometry.aperture_end = dma_max_address(); domain->domain.geometry.force_aperture = true; + if (iommu) { + domain->domain.type = type; + domain->domain.pgsize_bitmap = iommu->iommu.ops->pgsize_bitmap; + domain->domain.ops = iommu->iommu.ops->default_domain_ops; + } + return &domain->domain; } +static struct iommu_domain *amd_iommu_domain_alloc(unsigned int type) +{ + struct iommu_domain *domain; + + domain = do_iommu_domain_alloc(type, NULL, 0); + if (IS_ERR(domain)) + return NULL; + + return domain; +} + +static struct iommu_domain *amd_iommu_domain_alloc_user(struct device *dev, + u32 flags) +{ + unsigned int type = IOMMU_DOMAIN_UNMANAGED; + + if (flags) + return ERR_PTR(-EOPNOTSUPP); + + return do_iommu_domain_alloc(type, dev, flags); +} + static void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain; @@ -2464,6 +2501,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain) const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, + .domain_alloc_user = amd_iommu_domain_alloc_user, .probe_device = amd_iommu_probe_device, .release_device = amd_iommu_release_device, .probe_finalize = amd_iommu_probe_finalize, -- Gitee From ebb4f9309c67ec7e9a872dbd5e7cacaaf78f4bf2 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:02 +0100 Subject: [PATCH 20/31] iommu/amd: Access/Dirty bit support in IOPTEs mainline inclusion from mainline-v6.7-rc1 commit 421a511a293fe1c73b37f6147c6676c4ee6efa04 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?421a511a293fe1c73b37f6147c6676c4ee6efa04 -------------------------------- IOMMU advertises Access/Dirty bits if the extended feature register reports it. Relevant AMD IOMMU SDM ref[0] "1.3.8 Enhanced Support for Access and Dirty Bits" To enable it set the DTE flag in bits 7 and 8 to enable access, or access+dirty. With that, the IOMMU starts marking the D and A flags on every Memory Request or ATS translation request. It is on the VMM side to steer whether to enable dirty tracking or not, rather than wrongly doing in IOMMU. Relevant AMD IOMMU SDM ref [0], "Table 7. Device Table Entry (DTE) Field Definitions" particularly the entry "HAD". To actually toggle on and off it's relatively simple as it's setting 2 bits on DTE and flush the device DTE cache. To get what's dirtied use existing AMD io-pgtable support, by walking the pagetables over each IOVA, with fetch_pte(). The IOTLB flushing is left to the caller (much like unmap), and iommu_dirty_bitmap_record() is the one adding page-ranges to invalidate. This allows caller to batch the flush over a big span of IOVA space, without the iommu wondering about when to flush. Worthwhile sections from AMD IOMMU SDM: "2.2.3.1 Host Access Support" "2.2.3.2 Host Dirty Support" For details on how IOMMU hardware updates the dirty bit see, and expects from its consequent clearing by CPU: "2.2.7.4 Updating Accessed and Dirty Bits in the Guest Address Tables" "2.2.7.5 Clearing Accessed and Dirty Bits" Quoting the SDM: "The setting of accessed and dirty status bits in the page tables is visible to both the CPU and the peripheral when sharing guest page tables. The IOMMU interlocked operations to update A and D bits must be 64-bit operations and naturally aligned on a 64-bit boundary" .. and for the IOMMU update sequence to Dirty bit, essentially is states: 1. Decodes the read and write intent from the memory access. 2. If P=0 in the page descriptor, fail the access. 3. Compare the A & D bits in the descriptor with the read and write intent in the request. 4. If the A or D bits need to be updated in the descriptor: * Start atomic operation. * Read the descriptor as a 64-bit access. * If the descriptor no longer appears to require an update, release the atomic lock with no further action and continue to step 5. * Calculate the new A & D bits. * Write the descriptor as a 64-bit access. * End atomic operation. 5. Continue to the next stage of translation or to the memory access. Access/Dirty bits readout also need to consider the non-default page-sizes (aka replicated PTEs as mentined by manual), as AMD supports all powers of two (except 512G) page sizes. Select IOMMUFD_DRIVER only if IOMMUFD is enabled considering that IOMMU dirty tracking requires IOMMUFD. Intel-SIG: 421a511a293f iommu/amd: Access/Dirty bit support in IOPTEs Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-12-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Suravee Suthikulpanit Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/amd/Kconfig | 1 + drivers/iommu/amd/amd_iommu_types.h | 12 ++++ drivers/iommu/amd/io_pgtable.c | 68 +++++++++++++++++++ drivers/iommu/amd/iommu.c | 102 +++++++++++++++++++++++++++- 4 files changed, 182 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig index 9b5fc3356bf2..8bd4c3b183ec 100644 --- a/drivers/iommu/amd/Kconfig +++ b/drivers/iommu/amd/Kconfig @@ -10,6 +10,7 @@ config AMD_IOMMU select IOMMU_API select IOMMU_IOVA select IOMMU_IO_PGTABLE + select IOMMUFD_DRIVER if IOMMUFD depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE help With this option you can enable support for AMD IOMMU hardware in diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 7dc30c2b56b3..dec4e5c2b66b 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -97,7 +97,9 @@ #define FEATURE_GATS_MASK (3ULL) #define FEATURE_GAM_VAPIC BIT_ULL(21) #define FEATURE_GIOSUP BIT_ULL(48) +#define FEATURE_HASUP BIT_ULL(49) #define FEATURE_EPHSUP BIT_ULL(50) +#define FEATURE_HDSUP BIT_ULL(52) #define FEATURE_SNP BIT_ULL(63) #define FEATURE_PASID_SHIFT 32 @@ -212,6 +214,7 @@ /* macros and definitions for device table entries */ #define DEV_ENTRY_VALID 0x00 #define DEV_ENTRY_TRANSLATION 0x01 +#define DEV_ENTRY_HAD 0x07 #define DEV_ENTRY_PPR 0x34 #define DEV_ENTRY_IR 0x3d #define DEV_ENTRY_IW 0x3e @@ -370,10 +373,16 @@ #define PTE_LEVEL_PAGE_SIZE(level) \ (1ULL << (12 + (9 * (level)))) +/* + * The IOPTE dirty bit + */ +#define IOMMU_PTE_HD_BIT (6) + /* * Bit value definition for I/O PTE fields */ #define IOMMU_PTE_PR BIT_ULL(0) +#define IOMMU_PTE_HD BIT_ULL(IOMMU_PTE_HD_BIT) #define IOMMU_PTE_U BIT_ULL(59) #define IOMMU_PTE_FC BIT_ULL(60) #define IOMMU_PTE_IR BIT_ULL(61) @@ -384,6 +393,7 @@ */ #define DTE_FLAG_V BIT_ULL(0) #define DTE_FLAG_TV BIT_ULL(1) +#define DTE_FLAG_HAD (3ULL << 7) #define DTE_FLAG_GIOV BIT_ULL(54) #define DTE_FLAG_GV BIT_ULL(55) #define DTE_GLX_SHIFT (56) @@ -413,6 +423,7 @@ #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_PR) +#define IOMMU_PTE_DIRTY(pte) ((pte) & IOMMU_PTE_HD) #define IOMMU_PTE_PAGE(pte) (iommu_phys_to_virt((pte) & IOMMU_PAGE_MASK)) #define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07) @@ -563,6 +574,7 @@ struct protection_domain { int nid; /* Node ID */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ + bool dirty_tracking; /* dirty tracking is enabled in the domain */ unsigned dev_cnt; /* devices assigned to this domain */ unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ }; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index 2892aa1b4dc1..6c0621f6f572 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -486,6 +486,73 @@ static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned lo return (__pte & ~offset_mask) | (iova & offset_mask); } +static bool pte_test_and_clear_dirty(u64 *ptep, unsigned long size, + unsigned long flags) +{ + bool test_only = flags & IOMMU_DIRTY_NO_CLEAR; + bool dirty = false; + int i, count; + + /* + * 2.2.3.2 Host Dirty Support + * When a non-default page size is used , software must OR the + * Dirty bits in all of the replicated host PTEs used to map + * the page. The IOMMU does not guarantee the Dirty bits are + * set in all of the replicated PTEs. Any portion of the page + * may have been written even if the Dirty bit is set in only + * one of the replicated PTEs. + */ + count = PAGE_SIZE_PTE_COUNT(size); + for (i = 0; i < count && test_only; i++) { + if (test_bit(IOMMU_PTE_HD_BIT, (unsigned long *)&ptep[i])) { + dirty = true; + break; + } + } + + for (i = 0; i < count && !test_only; i++) { + if (test_and_clear_bit(IOMMU_PTE_HD_BIT, + (unsigned long *)&ptep[i])) { + dirty = true; + } + } + + return dirty; +} + +static int iommu_v1_read_and_clear_dirty(struct io_pgtable_ops *ops, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty) +{ + struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops); + unsigned long end = iova + size - 1; + + do { + unsigned long pgsize = 0; + u64 *ptep, pte; + + ptep = fetch_pte(pgtable, iova, &pgsize); + if (ptep) + pte = READ_ONCE(*ptep); + if (!ptep || !IOMMU_PTE_PRESENT(pte)) { + pgsize = pgsize ?: PTE_LEVEL_PAGE_SIZE(0); + iova += pgsize; + continue; + } + + /* + * Mark the whole IOVA range as dirty even if only one of + * the replicated PTEs were marked dirty. + */ + if (pte_test_and_clear_dirty(ptep, pgsize, flags)) + iommu_dirty_bitmap_record(dirty, iova, pgsize); + iova += pgsize; + } while (iova < end); + + return 0; +} + /* * ---------------------------------------------------- */ @@ -527,6 +594,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo pgtable->iop.ops.map_pages = iommu_v1_map_pages; pgtable->iop.ops.unmap_pages = iommu_v1_unmap_pages; pgtable->iop.ops.iova_to_phys = iommu_v1_iova_to_phys; + pgtable->iop.ops.read_and_clear_dirty = iommu_v1_read_and_clear_dirty; return &pgtable->iop; } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 667e23b0ab0d..caad10f9cee3 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -66,6 +66,7 @@ LIST_HEAD(hpet_map); LIST_HEAD(acpihid_map); const struct iommu_ops amd_iommu_ops; +const struct iommu_dirty_ops amd_dirty_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); int amd_iommu_max_glx_val = -1; @@ -1611,6 +1612,9 @@ static void set_dte_entry(struct amd_iommu *iommu, u16 devid, pte_root |= 1ULL << DEV_ENTRY_PPR; } + if (domain->dirty_tracking) + pte_root |= DTE_FLAG_HAD; + if (domain->flags & PD_IOMMUV2_MASK) { u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl); u64 glx = domain->glx; @@ -2156,9 +2160,15 @@ static inline u64 dma_max_address(void) return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1); } +static bool amd_iommu_hd_support(struct amd_iommu *iommu) +{ + return iommu && (iommu->features & FEATURE_HDSUP); +} + static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, struct device *dev, u32 flags) { + bool dirty_tracking = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; struct protection_domain *domain; struct amd_iommu *iommu = NULL; @@ -2175,6 +2185,9 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, if (amd_iommu_snp_en && (type == IOMMU_DOMAIN_IDENTITY)) return ERR_PTR(-EINVAL); + if (dirty_tracking && !amd_iommu_hd_support(iommu)) + return ERR_PTR(-EOPNOTSUPP); + domain = protection_domain_alloc(type); if (!domain) return ERR_PTR(-ENOMEM); @@ -2187,6 +2200,9 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type, domain->domain.type = type; domain->domain.pgsize_bitmap = iommu->iommu.ops->pgsize_bitmap; domain->domain.ops = iommu->iommu.ops->default_domain_ops; + + if (dirty_tracking) + domain->domain.dirty_ops = &amd_dirty_ops; } return &domain->domain; @@ -2208,7 +2224,7 @@ static struct iommu_domain *amd_iommu_domain_alloc_user(struct device *dev, { unsigned int type = IOMMU_DOMAIN_UNMANAGED; - if (flags) + if (flags & ~IOMMU_HWPT_ALLOC_DIRTY_TRACKING) return ERR_PTR(-EOPNOTSUPP); return do_iommu_domain_alloc(type, dev, flags); @@ -2251,6 +2267,13 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, dev_data->defer_attach = false; + /* + * Restrict to devices with compatible IOMMU hardware support + * when enforcement of dirty tracking is enabled. + */ + if (dom->dirty_ops && !amd_iommu_hd_support(iommu)) + return -EINVAL; + if (dev_data->domain) detach_device(dev); @@ -2369,6 +2392,11 @@ static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap) return true; case IOMMU_CAP_DEFERRED_FLUSH: return true; + case IOMMU_CAP_DIRTY_TRACKING: { + struct amd_iommu *iommu = rlookup_amd_iommu(dev); + + return amd_iommu_hd_support(iommu); + } default: break; } @@ -2376,6 +2404,73 @@ static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } +static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain, + bool enable) +{ + struct protection_domain *pdomain = to_pdomain(domain); + struct dev_table_entry *dev_table; + struct iommu_dev_data *dev_data; + bool domain_flush = false; + struct amd_iommu *iommu; + unsigned long flags; + u64 pte_root; + + spin_lock_irqsave(&pdomain->lock, flags); + if (!(pdomain->dirty_tracking ^ enable)) { + spin_unlock_irqrestore(&pdomain->lock, flags); + return 0; + } + + list_for_each_entry(dev_data, &pdomain->dev_list, list) { + iommu = rlookup_amd_iommu(dev_data->dev); + if (!iommu) + continue; + + dev_table = get_dev_table(iommu); + pte_root = dev_table[dev_data->devid].data[0]; + + pte_root = (enable ? pte_root | DTE_FLAG_HAD : + pte_root & ~DTE_FLAG_HAD); + + /* Flush device DTE */ + dev_table[dev_data->devid].data[0] = pte_root; + device_flush_dte(dev_data); + domain_flush = true; + } + + /* Flush IOTLB to mark IOPTE dirty on the next translation(s) */ + if (domain_flush) { + amd_iommu_domain_flush_tlb_pde(pdomain); + amd_iommu_domain_flush_complete(pdomain); + } + pdomain->dirty_tracking = enable; + spin_unlock_irqrestore(&pdomain->lock, flags); + + return 0; +} + +static int amd_iommu_read_and_clear_dirty(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty) +{ + struct protection_domain *pdomain = to_pdomain(domain); + struct io_pgtable_ops *ops = &pdomain->iop.iop.ops; + unsigned long lflags; + + if (!ops || !ops->read_and_clear_dirty) + return -EOPNOTSUPP; + + spin_lock_irqsave(&pdomain->lock, lflags); + if (!pdomain->dirty_tracking && dirty->bitmap) { + spin_unlock_irqrestore(&pdomain->lock, lflags); + return -EINVAL; + } + spin_unlock_irqrestore(&pdomain->lock, lflags); + + return ops->read_and_clear_dirty(ops, iova, size, flags, dirty); +} + static void amd_iommu_get_resv_regions(struct device *dev, struct list_head *head) { @@ -2498,6 +2593,11 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain) return true; } +const struct iommu_dirty_ops amd_dirty_ops = { + .set_dirty_tracking = amd_iommu_set_dirty_tracking, + .read_and_clear_dirty = amd_iommu_read_and_clear_dirty, +}; + const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, -- Gitee From acf8e88b7f4290eab9db5a0e2f6c0ab67e201d99 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:03 +0100 Subject: [PATCH 21/31] iommu/vt-d: Access/Dirty bit support for SS domains mainline inclusion from mainline-v6.7-rc1 commit f35f22cc760eb2c7034bf53251399685d611e03f category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?f35f22cc760eb2c7034bf53251399685d611e03f -------------------------------- IOMMU advertises Access/Dirty bits for second-stage page table if the extended capability DMAR register reports it (ECAP, mnemonic ECAP.SSADS). The first stage table is compatible with CPU page table thus A/D bits are implicitly supported. Relevant Intel IOMMU SDM ref for first stage table "3.6.2 Accessed, Extended Accessed, and Dirty Flags" and second stage table "3.7.2 Accessed and Dirty Flags". First stage page table is enabled by default so it's allowed to set dirty tracking and no control bits needed, it just returns 0. To use SSADS, set bit 9 (SSADE) in the scalable-mode PASID table entry and flush the IOTLB via pasid_flush_caches() following the manual. Relevant SDM refs: "3.7.2 Accessed and Dirty Flags" "6.5.3.3 Guidance to Software for Invalidations, Table 23. Guidance to Software for Invalidations" PTE dirty bit is located in bit 9 and it's cached in the IOTLB so flush IOTLB to make sure IOMMU attempts to set the dirty bit again. Note that iommu_dirty_bitmap_record() will add the IOVA to iotlb_gather and thus the caller of the iommu op will flush the IOTLB. Relevant manuals over the hardware translation is chapter 6 with some special mention to: "6.2.3.1 Scalable-Mode PASID-Table Entry Programming Considerations" "6.2.4 IOTLB" Select IOMMUFD_DRIVER only if IOMMUFD is enabled, given that IOMMU dirty tracking requires IOMMUFD. Intel-SIG: f35f22cc760e iommu/vt-d: Access/Dirty bit support for SS domains Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-13-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/intel/Kconfig | 1 + drivers/iommu/intel/iommu.c | 103 +++++++++++++++++++++++++++++++++- drivers/iommu/intel/iommu.h | 16 ++++++ drivers/iommu/intel/pasid.c | 109 ++++++++++++++++++++++++++++++++++++ drivers/iommu/intel/pasid.h | 4 ++ 5 files changed, 232 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index 2e56bd79f589..f5348b80652b 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -15,6 +15,7 @@ config INTEL_IOMMU select DMA_OPS select IOMMU_API select IOMMU_IOVA + select IOMMUFD_DRIVER if IOMMUFD select NEED_DMA_MAP_STATE select DMAR_TABLE select SWIOTLB diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index da2b79abfc13..47f95833cf62 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -300,6 +300,7 @@ static int iommu_skip_te_disable; #define IDENTMAP_AZALIA 4 const struct iommu_ops intel_iommu_ops; +const struct iommu_dirty_ops intel_dirty_ops; static bool translation_pre_enabled(struct intel_iommu *iommu) { @@ -4064,8 +4065,10 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags) { struct iommu_domain *domain; struct intel_iommu *iommu; + bool dirty_tracking; - if (flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) + if (flags & + (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING))) return ERR_PTR(-EOPNOTSUPP); iommu = device_to_iommu(dev, NULL, NULL); @@ -4075,6 +4078,10 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags) if ((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) && !ecap_nest(iommu->ecap)) return ERR_PTR(-EOPNOTSUPP); + dirty_tracking = (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING); + if (dirty_tracking && !ssads_supported(iommu)) + return ERR_PTR(-EOPNOTSUPP); + /* * domain_alloc_user op needs to fully initialize a domain * before return, so uses iommu_domain_alloc() here for @@ -4083,6 +4090,15 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags) domain = iommu_domain_alloc(dev->bus); if (!domain) domain = ERR_PTR(-ENOMEM); + + if (!IS_ERR(domain) && dirty_tracking) { + if (to_dmar_domain(domain)->use_first_level) { + iommu_domain_free(domain); + return ERR_PTR(-EOPNOTSUPP); + } + domain->dirty_ops = &intel_dirty_ops; + } + return domain; } @@ -4106,6 +4122,9 @@ static int prepare_domain_attach_device(struct iommu_domain *domain, if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap)) return -EINVAL; + if (domain->dirty_ops && !ssads_supported(iommu)) + return -EINVAL; + /* check if this iommu agaw is sufficient for max mapped address */ addr_width = agaw_to_width(iommu->agaw); if (addr_width > cap_mgaw(iommu->cap)) @@ -4360,6 +4379,8 @@ static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap) return dmar_platform_optin(); case IOMMU_CAP_ENFORCE_CACHE_COHERENCY: return ecap_sc_support(info->iommu->ecap); + case IOMMU_CAP_DIRTY_TRACKING: + return ssads_supported(info->iommu); default: return false; } @@ -4757,6 +4778,9 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain, if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev)) return -EOPNOTSUPP; + if (domain->dirty_ops) + return -EINVAL; + if (context_copied(iommu, info->bus, info->devfn)) return -EBUSY; @@ -4815,6 +4839,83 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type) return vtd; } +static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain, + bool enable) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + struct device_domain_info *info; + int ret; + + spin_lock(&dmar_domain->lock); + if (dmar_domain->dirty_tracking == enable) + goto out_unlock; + + list_for_each_entry(info, &dmar_domain->devices, link) { + ret = intel_pasid_setup_dirty_tracking(info->iommu, + info->domain, info->dev, + IOMMU_NO_PASID, enable); + if (ret) + goto err_unwind; + } + + dmar_domain->dirty_tracking = enable; +out_unlock: + spin_unlock(&dmar_domain->lock); + + return 0; + +err_unwind: + list_for_each_entry(info, &dmar_domain->devices, link) + intel_pasid_setup_dirty_tracking(info->iommu, dmar_domain, + info->dev, IOMMU_NO_PASID, + dmar_domain->dirty_tracking); + spin_unlock(&dmar_domain->lock); + return ret; +} + +static int intel_iommu_read_and_clear_dirty(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + unsigned long end = iova + size - 1; + unsigned long pgsize; + + /* + * IOMMUFD core calls into a dirty tracking disabled domain without an + * IOVA bitmap set in order to clean dirty bits in all PTEs that might + * have occurred when we stopped dirty tracking. This ensures that we + * never inherit dirtied bits from a previous cycle. + */ + if (!dmar_domain->dirty_tracking && dirty->bitmap) + return -EINVAL; + + do { + struct dma_pte *pte; + int lvl = 0; + + pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &lvl, + GFP_ATOMIC); + pgsize = level_size(lvl) << VTD_PAGE_SHIFT; + if (!pte || !dma_pte_present(pte)) { + iova += pgsize; + continue; + } + + if (dma_sl_pte_test_and_clear_dirty(pte, flags)) + iommu_dirty_bitmap_record(dirty, iova, pgsize); + iova += pgsize; + } while (iova < end); + + return 0; +} + +const struct iommu_dirty_ops intel_dirty_ops = { + .set_dirty_tracking = intel_iommu_set_dirty_tracking, + .read_and_clear_dirty = intel_iommu_read_and_clear_dirty, +}; + const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .hw_info = intel_iommu_hw_info, diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 7dac94f62b4e..9f8de5df3cc3 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -48,6 +48,9 @@ #define DMA_FL_PTE_DIRTY BIT_ULL(6) #define DMA_FL_PTE_XD BIT_ULL(63) +#define DMA_SL_PTE_DIRTY_BIT 9 +#define DMA_SL_PTE_DIRTY BIT_ULL(DMA_SL_PTE_DIRTY_BIT) + #define ADDR_WIDTH_5LEVEL (57) #define ADDR_WIDTH_4LEVEL (48) @@ -539,6 +542,8 @@ enum { #define sm_supported(iommu) (intel_iommu_sm && ecap_smts((iommu)->ecap)) #define pasid_supported(iommu) (sm_supported(iommu) && \ ecap_pasid((iommu)->ecap)) +#define ssads_supported(iommu) (sm_supported(iommu) && \ + ecap_slads((iommu)->ecap)) struct pasid_entry; struct pasid_state_entry; @@ -592,6 +597,7 @@ struct dmar_domain { * otherwise, goes through the second * level. */ + u8 dirty_tracking:1; /* Dirty tracking is enabled */ spinlock_t lock; /* Protect device tracking lists */ struct list_head devices; /* all devices' list */ @@ -781,6 +787,16 @@ static inline bool dma_pte_present(struct dma_pte *pte) return (pte->val & 3) != 0; } +static inline bool dma_sl_pte_test_and_clear_dirty(struct dma_pte *pte, + unsigned long flags) +{ + if (flags & IOMMU_DIRTY_NO_CLEAR) + return (pte->val & DMA_SL_PTE_DIRTY) != 0; + + return test_and_clear_bit(DMA_SL_PTE_DIRTY_BIT, + (unsigned long *)&pte->val); +} + static inline bool dma_pte_superpage(struct dma_pte *pte) { return (pte->val & DMA_PTE_LARGE_PAGE); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 8f92b92f3d2a..b9264b9174e8 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -277,6 +277,11 @@ static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits) WRITE_ONCE(*ptr, (old & ~mask) | bits); } +static inline u64 pasid_get_bits(u64 *ptr) +{ + return READ_ONCE(*ptr); +} + /* * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode * PASID entry. @@ -335,6 +340,36 @@ static inline void pasid_set_fault_enable(struct pasid_entry *pe) pasid_set_bits(&pe->val[0], 1 << 1, 0); } +/* + * Enable second level A/D bits by setting the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry. + */ +static inline void pasid_set_ssade(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9); +} + +/* + * Disable second level A/D bits by clearing the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry. + */ +static inline void pasid_clear_ssade(struct pasid_entry *pe) +{ + pasid_set_bits(&pe->val[0], 1 << 9, 0); +} + +/* + * Checks if second level A/D bits specifically the SLADE (Second Level + * Access Dirty Enable) field (Bit 9) of a scalable mode PASID + * entry is set. + */ +static inline bool pasid_get_ssade(struct pasid_entry *pe) +{ + return pasid_get_bits(&pe->val[0]) & (1 << 9); +} + /* * Setup the WPE(Write Protect Enable) field (Bit 132) of a * scalable mode PASID entry. @@ -627,6 +662,8 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); + if (domain->dirty_tracking) + pasid_set_ssade(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -636,6 +673,78 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, return 0; } +/* + * Set up dirty tracking on a second only or nested translation type. + */ +int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu, + struct dmar_domain *domain, + struct device *dev, u32 pasid, + bool enabled) +{ + struct pasid_entry *pte; + u16 did, pgtt; + + spin_lock(&iommu->lock); + + pte = intel_pasid_get_entry(dev, pasid); + if (!pte) { + spin_unlock(&iommu->lock); + dev_err_ratelimited( + dev, "Failed to get pasid entry of PASID %d\n", pasid); + return -ENODEV; + } + + did = domain_id_iommu(domain, iommu); + pgtt = pasid_pte_get_pgtt(pte); + if (pgtt != PASID_ENTRY_PGTT_SL_ONLY && + pgtt != PASID_ENTRY_PGTT_NESTED) { + spin_unlock(&iommu->lock); + dev_err_ratelimited( + dev, + "Dirty tracking not supported on translation type %d\n", + pgtt); + return -EOPNOTSUPP; + } + + if (pasid_get_ssade(pte) == enabled) { + spin_unlock(&iommu->lock); + return 0; + } + + if (enabled) + pasid_set_ssade(pte); + else + pasid_clear_ssade(pte); + spin_unlock(&iommu->lock); + + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(pte, sizeof(*pte)); + + /* + * From VT-d spec table 25 "Guidance to Software for Invalidations": + * + * - PASID-selective-within-Domain PASID-cache invalidation + * If (PGTT=SS or Nested) + * - Domain-selective IOTLB invalidation + * Else + * - PASID-selective PASID-based IOTLB invalidation + * - If (pasid is RID_PASID) + * - Global Device-TLB invalidation to affected functions + * Else + * - PASID-based Device-TLB invalidation (with S=1 and + * Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions + */ + pasid_cache_invalidation_with_pasid(iommu, did, pasid); + + iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH); + + /* Device IOTLB doesn't need to be flushed in caching mode. */ + if (!cap_caching_mode(iommu->cap)) + devtlb_invalidation_with_pasid(iommu, dev, pasid); + + return 0; +} + /* * Set up the scalable mode pasid entry for passthrough translation type. */ diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 4e9e68c3c388..958050b093aa 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -106,6 +106,10 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, int intel_pasid_setup_second_level(struct intel_iommu *iommu, struct dmar_domain *domain, struct device *dev, u32 pasid); +int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu, + struct dmar_domain *domain, + struct device *dev, u32 pasid, + bool enabled); int intel_pasid_setup_pass_through(struct intel_iommu *iommu, struct dmar_domain *domain, struct device *dev, u32 pasid); -- Gitee From 3e1b61036ba77e370c68d67b059294e06af562fe Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:04 +0100 Subject: [PATCH 22/31] iommufd/selftest: Expand mock_domain with dev_flags mainline inclusion from mainline-v6.7-rc1 commit e04b23c8d4ed977dbab4a4159f9e4d9a878b5c65 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?e04b23c8d4ed977dbab4a4159f9e4d9a878b5c65 -------------------------------- Expand mock_domain test to be able to manipulate the device capabilities. This allows testing with mockdev without dirty tracking support advertised and thus make sure enforce_dirty test does the expected. To avoid breaking IOMMUFD_TEST UABI replicate the mock_domain struct and thus add an input dev_flags at the end. Intel-SIG: e04b23c8d4ed iommufd/selftest: Expand mock_domain with dev_flags Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-14-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/iommufd_test.h | 12 ++++++++ drivers/iommu/iommufd/selftest.c | 11 +++++-- tools/testing/selftests/iommu/iommufd_utils.h | 29 +++++++++++++++++++ 3 files changed, 50 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 3f3644375bf1..9817edcd8968 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -19,6 +19,7 @@ enum { IOMMU_TEST_OP_SET_TEMP_MEMORY_LIMIT, IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE, IOMMU_TEST_OP_ACCESS_REPLACE_IOAS, + IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS, }; enum { @@ -40,6 +41,10 @@ enum { MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES = 1 << 0, }; +enum { + MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0, +}; + struct iommu_test_cmd { __u32 size; __u32 op; @@ -56,6 +61,13 @@ struct iommu_test_cmd { /* out_idev_id is the standard iommufd_bind object */ __u32 out_idev_id; } mock_domain; + struct { + __u32 out_stdev_id; + __u32 out_hwpt_id; + __u32 out_idev_id; + /* Expand mock_domain to set mock device flags */ + __u32 dev_flags; + } mock_domain_flags; struct { __u32 pt_id; } mock_domain_replace; diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index fe7e3c7d933a..bd3704b28bfb 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -96,6 +96,7 @@ enum selftest_obj_type { struct mock_dev { struct device dev; + unsigned long flags; }; struct selftest_obj { @@ -381,7 +382,7 @@ static void mock_dev_release(struct device *dev) kfree(mdev); } -static struct mock_dev *mock_dev_create(void) +static struct mock_dev *mock_dev_create(unsigned long dev_flags) { struct mock_dev *mdev; int rc; @@ -391,6 +392,7 @@ static struct mock_dev *mock_dev_create(void) return ERR_PTR(-ENOMEM); device_initialize(&mdev->dev); + mdev->flags = dev_flags; mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; @@ -426,6 +428,7 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd, struct iommufd_device *idev; struct selftest_obj *sobj; u32 pt_id = cmd->id; + u32 dev_flags = 0; u32 idev_id; int rc; @@ -436,7 +439,10 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd, sobj->idev.ictx = ucmd->ictx; sobj->type = TYPE_IDEV; - sobj->idev.mock_dev = mock_dev_create(); + if (cmd->op == IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS) + dev_flags = cmd->mock_domain_flags.dev_flags; + + sobj->idev.mock_dev = mock_dev_create(dev_flags); if (IS_ERR(sobj->idev.mock_dev)) { rc = PTR_ERR(sobj->idev.mock_dev); goto out_sobj; @@ -1019,6 +1025,7 @@ int iommufd_test(struct iommufd_ucmd *ucmd) cmd->add_reserved.start, cmd->add_reserved.length); case IOMMU_TEST_OP_MOCK_DOMAIN: + case IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS: return iommufd_test_mock_domain(ucmd, cmd); case IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE: return iommufd_test_mock_domain_replace( diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index be4970a84977..1e0736adc991 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -74,6 +74,35 @@ static int _test_cmd_mock_domain(int fd, unsigned int ioas_id, __u32 *stdev_id, EXPECT_ERRNO(_errno, _test_cmd_mock_domain(self->fd, ioas_id, \ stdev_id, hwpt_id, NULL)) +static int _test_cmd_mock_domain_flags(int fd, unsigned int ioas_id, + __u32 stdev_flags, __u32 *stdev_id, + __u32 *hwpt_id, __u32 *idev_id) +{ + struct iommu_test_cmd cmd = { + .size = sizeof(cmd), + .op = IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS, + .id = ioas_id, + .mock_domain_flags = { .dev_flags = stdev_flags }, + }; + int ret; + + ret = ioctl(fd, IOMMU_TEST_CMD, &cmd); + if (ret) + return ret; + if (stdev_id) + *stdev_id = cmd.mock_domain_flags.out_stdev_id; + assert(cmd.id != 0); + if (hwpt_id) + *hwpt_id = cmd.mock_domain_flags.out_hwpt_id; + if (idev_id) + *idev_id = cmd.mock_domain_flags.out_idev_id; + return 0; +} +#define test_err_mock_domain_flags(_errno, ioas_id, flags, stdev_id, hwpt_id) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_mock_domain_flags(self->fd, ioas_id, flags, \ + stdev_id, hwpt_id, NULL)) + static int _test_cmd_mock_domain_replace(int fd, __u32 stdev_id, __u32 pt_id, __u32 *hwpt_id) { -- Gitee From d8086722a4ddab1437fbfa9bc48a7415e5bec267 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:05 +0100 Subject: [PATCH 23/31] iommufd/selftest: Test IOMMU_HWPT_ALLOC_DIRTY_TRACKING mainline inclusion from mainline-v6.7-rc1 commit 266ce58989ba05e2a24460fdbf402d766c2e3870 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?266ce58989ba05e2a24460fdbf402d766c2e3870 -------------------------------- In order to selftest the iommu domain dirty enforcing implement the mock_domain necessary support and add a new dev_flags to test that the hwpt_alloc/attach_device fails as expected. Expand the existing mock_domain fixture with a enforce_dirty test that exercises the hwpt_alloc and device attachment. Intel-SIG: 266ce58989ba iommufd/selftest: Test IOMMU_HWPT_ALLOC_DIRTY_TRACKING Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-15-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 37 +++++++++++++- tools/testing/selftests/iommu/iommufd.c | 49 +++++++++++++++++++ tools/testing/selftests/iommu/iommufd_utils.h | 3 ++ 3 files changed, 88 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index bd3704b28bfb..78362f2334f5 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -119,6 +119,11 @@ static void mock_domain_blocking_free(struct iommu_domain *domain) static int mock_domain_nop_attach(struct iommu_domain *domain, struct device *dev) { + struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + + if (domain->dirty_ops && (mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY)) + return -EINVAL; + return 0; } @@ -147,6 +152,25 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) return info; } +static int mock_domain_set_dirty_tracking(struct iommu_domain *domain, + bool enable) +{ + return 0; +} + +static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, + unsigned long iova, size_t size, + unsigned long flags, + struct iommu_dirty_bitmap *dirty) +{ + return 0; +} + +const struct iommu_dirty_ops dirty_ops = { + .set_dirty_tracking = mock_domain_set_dirty_tracking, + .read_and_clear_dirty = mock_domain_read_and_clear_dirty, +}; + static const struct iommu_ops mock_ops; static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type) @@ -174,12 +198,20 @@ static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type) static struct iommu_domain * mock_domain_alloc_user(struct device *dev, u32 flags) { + struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); struct iommu_domain *domain; - if (flags & (~IOMMU_HWPT_ALLOC_NEST_PARENT)) + if (flags & + (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING))) + return ERR_PTR(-EOPNOTSUPP); + + if ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) && + (mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY)) return ERR_PTR(-EOPNOTSUPP); domain = mock_domain_alloc(IOMMU_DOMAIN_UNMANAGED); + if (domain && !(mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY)) + domain->dirty_ops = &dirty_ops; if (!domain) domain = ERR_PTR(-ENOMEM); return domain; @@ -387,6 +419,9 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) struct mock_dev *mdev; int rc; + if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY)) + return ERR_PTR(-EINVAL); + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(-ENOMEM); diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 7a29d68bd1d2..131af0a39c9e 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1433,6 +1433,55 @@ TEST_F(iommufd_mock_domain, alloc_hwpt) } } +FIXTURE(iommufd_dirty_tracking) +{ + int fd; + uint32_t ioas_id; + uint32_t hwpt_id; + uint32_t stdev_id; + uint32_t idev_id; +}; + +FIXTURE_SETUP(iommufd_dirty_tracking) +{ + self->fd = open("/dev/iommu", O_RDWR); + ASSERT_NE(-1, self->fd); + + test_ioctl_ioas_alloc(&self->ioas_id); + test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id, + &self->idev_id); +} + +FIXTURE_TEARDOWN(iommufd_dirty_tracking) +{ + teardown_iommufd(self->fd, _metadata); +} + +TEST_F(iommufd_dirty_tracking, enforce_dirty) +{ + uint32_t ioas_id, stddev_id, idev_id; + uint32_t hwpt_id, _hwpt_id; + uint32_t dev_flags; + + /* Regular case */ + dev_flags = MOCK_FLAGS_DEVICE_NO_DIRTY; + test_cmd_hwpt_alloc(self->idev_id, self->ioas_id, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + test_err_mock_domain_flags(EINVAL, hwpt_id, dev_flags, &stddev_id, + NULL); + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); + + /* IOMMU device does not support dirty tracking */ + test_ioctl_ioas_alloc(&ioas_id); + test_cmd_mock_domain_flags(ioas_id, dev_flags, &stddev_id, &_hwpt_id, + &idev_id); + test_err_hwpt_alloc(EOPNOTSUPP, idev_id, ioas_id, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); + test_ioctl_destroy(stddev_id); +} + /* VFIO compatibility IOCTLs */ TEST_F(iommufd, simple_ioctls) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 1e0736adc991..4ddafa29e638 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -98,6 +98,9 @@ static int _test_cmd_mock_domain_flags(int fd, unsigned int ioas_id, *idev_id = cmd.mock_domain_flags.out_idev_id; return 0; } +#define test_cmd_mock_domain_flags(ioas_id, flags, stdev_id, hwpt_id, idev_id) \ + ASSERT_EQ(0, _test_cmd_mock_domain_flags(self->fd, ioas_id, flags, \ + stdev_id, hwpt_id, idev_id)) #define test_err_mock_domain_flags(_errno, ioas_id, flags, stdev_id, hwpt_id) \ EXPECT_ERRNO(_errno, \ _test_cmd_mock_domain_flags(self->fd, ioas_id, flags, \ -- Gitee From c3528802dcd4d76e4261fc7ed1288687c96414a8 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:06 +0100 Subject: [PATCH 24/31] iommufd/selftest: Test IOMMU_HWPT_SET_DIRTY_TRACKING mainline inclusion from mainline-v6.7-rc1 commit 7adf267d66d1d737ea8318976fd1ce93733fd3a4 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?7adf267d66d1d737ea8318976fd1ce93733fd3a4 -------------------------------- Change mock_domain to supporting dirty tracking and add tests to exercise the new SET_DIRTY_TRACKING API in the iommufd_dirty_tracking selftest fixture. Intel-SIG: 7adf267d66d1 iommufd/selftest: Test IOMMU_HWPT_SET_DIRTY_TRACKING Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-16-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 16 ++++++++++++++++ tools/testing/selftests/iommu/iommufd.c | 15 +++++++++++++++ tools/testing/selftests/iommu/iommufd_utils.h | 17 +++++++++++++++++ 3 files changed, 48 insertions(+) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 78362f2334f5..2773275566af 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -24,6 +24,7 @@ static struct platform_device *selftest_iommu_dev; size_t iommufd_test_memory_limit = 65536; enum { + MOCK_DIRTY_TRACK = 1, MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2, /* @@ -86,6 +87,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, } struct mock_iommu_domain { + unsigned long flags; struct iommu_domain domain; struct xarray pfns; }; @@ -155,6 +157,20 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) static int mock_domain_set_dirty_tracking(struct iommu_domain *domain, bool enable) { + struct mock_iommu_domain *mock = + container_of(domain, struct mock_iommu_domain, domain); + unsigned long flags = mock->flags; + + if (enable && !domain->dirty_ops) + return -EINVAL; + + /* No change? */ + if (!(enable ^ !!(flags & MOCK_DIRTY_TRACK))) + return 0; + + flags = (enable ? flags | MOCK_DIRTY_TRACK : flags & ~MOCK_DIRTY_TRACK); + + mock->flags = flags; return 0; } diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 131af0a39c9e..827c2cc1c148 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1482,6 +1482,21 @@ TEST_F(iommufd_dirty_tracking, enforce_dirty) test_ioctl_destroy(stddev_id); } +TEST_F(iommufd_dirty_tracking, set_dirty_tracking) +{ + uint32_t stddev_id; + uint32_t hwpt_id; + + test_cmd_hwpt_alloc(self->idev_id, self->ioas_id, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + test_cmd_set_dirty_tracking(hwpt_id, true); + test_cmd_set_dirty_tracking(hwpt_id, false); + + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); +} + /* VFIO compatibility IOCTLs */ TEST_F(iommufd, simple_ioctls) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 4ddafa29e638..e37af6291b22 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -179,6 +179,23 @@ static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, #define test_cmd_access_replace_ioas(access_id, ioas_id) \ ASSERT_EQ(0, _test_cmd_access_replace_ioas(self->fd, access_id, ioas_id)) +static int _test_cmd_set_dirty_tracking(int fd, __u32 hwpt_id, bool enabled) +{ + struct iommu_hwpt_set_dirty_tracking cmd = { + .size = sizeof(cmd), + .flags = enabled ? IOMMU_HWPT_DIRTY_TRACKING_ENABLE : 0, + .hwpt_id = hwpt_id, + }; + int ret; + + ret = ioctl(fd, IOMMU_HWPT_SET_DIRTY_TRACKING, &cmd); + if (ret) + return -errno; + return 0; +} +#define test_cmd_set_dirty_tracking(hwpt_id, enabled) \ + ASSERT_EQ(0, _test_cmd_set_dirty_tracking(self->fd, hwpt_id, enabled)) + static int _test_cmd_create_access(int fd, unsigned int ioas_id, __u32 *access_id, unsigned int flags) { -- Gitee From fc6f6a2402fab73f04dd42a380eb6e8948bf62be Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:07 +0100 Subject: [PATCH 25/31] iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP mainline inclusion from mainline-v6.7-rc1 commit a9af47e382a4d517685cb13c780272e7f300ebc5 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?a9af47e382a4d517685cb13c780272e7f300ebc5 -------------------------------- Add a new test ioctl for simulating the dirty IOVAs in the mock domain, and implement the mock iommu domain ops that get the dirty tracking supported. The selftest exercises the usual main workflow of: 1) Setting dirty tracking from the iommu domain 2) Read and clear dirty IOPTEs Different fixtures will test different IOVA range sizes, that exercise corner cases of the bitmaps. Intel-SIG: a9af47e382a4 iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-17-joao.m.martins@oracle.com Signed-off-by: Joao Martins Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/iommufd_test.h | 9 ++ drivers/iommu/iommufd/selftest.c | 107 ++++++++++++++- tools/testing/selftests/iommu/iommufd.c | 96 +++++++++++++ tools/testing/selftests/iommu/iommufd_utils.h | 127 ++++++++++++++++++ 4 files changed, 334 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 9817edcd8968..1f2e93d3d4e8 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -20,6 +20,7 @@ enum { IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE, IOMMU_TEST_OP_ACCESS_REPLACE_IOAS, IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS, + IOMMU_TEST_OP_DIRTY, }; enum { @@ -107,6 +108,14 @@ struct iommu_test_cmd { struct { __u32 ioas_id; } access_replace_ioas; + struct { + __u32 flags; + __aligned_u64 iova; + __aligned_u64 length; + __aligned_u64 page_size; + __aligned_u64 uptr; + __aligned_u64 out_nr_dirty; + } dirty; }; __u32 last; }; diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 2773275566af..4eb86025dde9 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -37,6 +37,7 @@ enum { _MOCK_PFN_START = MOCK_PFN_MASK + 1, MOCK_PFN_START_IOVA = _MOCK_PFN_START, MOCK_PFN_LAST_IOVA = _MOCK_PFN_START, + MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1, }; /* @@ -179,6 +180,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, unsigned long flags, struct iommu_dirty_bitmap *dirty) { + struct mock_iommu_domain *mock = + container_of(domain, struct mock_iommu_domain, domain); + unsigned long i, max = size / MOCK_IO_PAGE_SIZE; + void *ent, *old; + + if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap) + return -EINVAL; + + for (i = 0; i < max; i++) { + unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE; + + ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE); + if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) { + unsigned long val; + + /* Clear dirty */ + val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; + old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE, + xa_mk_value(val), GFP_KERNEL); + WARN_ON_ONCE(ent != old); + iommu_dirty_bitmap_record(dirty, cur, + MOCK_IO_PAGE_SIZE); + } + } + return 0; } @@ -310,7 +336,7 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, for (cur = 0; cur != pgsize; cur += MOCK_IO_PAGE_SIZE) { ent = xa_erase(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); - WARN_ON(!ent); + /* * iommufd generates unmaps that must be a strict * superset of the map's performend So every starting @@ -320,13 +346,13 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, * passed to map_pages */ if (first) { - WARN_ON(!(xa_to_value(ent) & - MOCK_PFN_START_IOVA)); + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_START_IOVA)); first = false; } if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) - WARN_ON(!(xa_to_value(ent) & - MOCK_PFN_LAST_IOVA)); + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_LAST_IOVA)); iova += MOCK_IO_PAGE_SIZE; ret += MOCK_IO_PAGE_SIZE; @@ -1053,6 +1079,71 @@ static_assert((unsigned int)MOCK_ACCESS_RW_WRITE == IOMMUFD_ACCESS_RW_WRITE); static_assert((unsigned int)MOCK_ACCESS_RW_SLOW_PATH == __IOMMUFD_ACCESS_RW_SLOW_PATH); +static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, + unsigned long iova, size_t length, + unsigned long page_size, void __user *uptr, + u32 flags) +{ + unsigned long bitmap_size, i, max = length / page_size; + struct iommu_test_cmd *cmd = ucmd->cmd; + struct iommufd_hw_pagetable *hwpt; + struct mock_iommu_domain *mock; + int rc, count = 0; + void *tmp; + + if (iova % page_size || length % page_size || !uptr) + return -EINVAL; + + hwpt = get_md_pagetable(ucmd, mockpt_id, &mock); + if (IS_ERR(hwpt)) + return PTR_ERR(hwpt); + + if (!(mock->flags & MOCK_DIRTY_TRACK)) { + rc = -EINVAL; + goto out_put; + } + + bitmap_size = max / BITS_PER_BYTE; + + tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT); + if (!tmp) { + rc = -ENOMEM; + goto out_put; + } + + if (copy_from_user(tmp, uptr, bitmap_size)) { + rc = -EFAULT; + goto out_free; + } + + for (i = 0; i < max; i++) { + unsigned long cur = iova + i * page_size; + void *ent, *old; + + if (!test_bit(i, (unsigned long *)tmp)) + continue; + + ent = xa_load(&mock->pfns, cur / page_size); + if (ent) { + unsigned long val; + + val = xa_to_value(ent) | MOCK_PFN_DIRTY_IOVA; + old = xa_store(&mock->pfns, cur / page_size, + xa_mk_value(val), GFP_KERNEL); + WARN_ON_ONCE(ent != old); + count++; + } + } + + cmd->dirty.out_nr_dirty = count; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_free: + kvfree(tmp); +out_put: + iommufd_put_object(&hwpt->obj); + return rc; +} + void iommufd_selftest_destroy(struct iommufd_object *obj) { struct selftest_obj *sobj = container_of(obj, struct selftest_obj, obj); @@ -1118,6 +1209,12 @@ int iommufd_test(struct iommufd_ucmd *ucmd) return -EINVAL; iommufd_test_memory_limit = cmd->memory_limit.limit; return 0; + case IOMMU_TEST_OP_DIRTY: + return iommufd_test_dirty(ucmd, cmd->id, cmd->dirty.iova, + cmd->dirty.length, + cmd->dirty.page_size, + u64_to_user_ptr(cmd->dirty.uptr), + cmd->dirty.flags); default: return -EOPNOTSUPP; } diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 827c2cc1c148..9535d043b80a 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1440,13 +1440,47 @@ FIXTURE(iommufd_dirty_tracking) uint32_t hwpt_id; uint32_t stdev_id; uint32_t idev_id; + unsigned long page_size; + unsigned long bitmap_size; + void *bitmap; + void *buffer; +}; + +FIXTURE_VARIANT(iommufd_dirty_tracking) +{ + unsigned long buffer_size; }; FIXTURE_SETUP(iommufd_dirty_tracking) { + void *vrc; + int rc; + self->fd = open("/dev/iommu", O_RDWR); ASSERT_NE(-1, self->fd); + rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size); + if (rc || !self->buffer) { + SKIP(return, "Skipping buffer_size=%lu due to errno=%d", + variant->buffer_size, rc); + } + + assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0); + vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + assert(vrc == self->buffer); + + self->page_size = MOCK_PAGE_SIZE; + self->bitmap_size = + variant->buffer_size / self->page_size / BITS_PER_BYTE; + + /* Provision with an extra (MOCK_PAGE_SIZE) for the unaligned case */ + rc = posix_memalign(&self->bitmap, PAGE_SIZE, + self->bitmap_size + MOCK_PAGE_SIZE); + assert(!rc); + assert(self->bitmap); + assert((uintptr_t)self->bitmap % PAGE_SIZE == 0); + test_ioctl_ioas_alloc(&self->ioas_id); test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id, &self->idev_id); @@ -1454,9 +1488,41 @@ FIXTURE_SETUP(iommufd_dirty_tracking) FIXTURE_TEARDOWN(iommufd_dirty_tracking) { + munmap(self->buffer, variant->buffer_size); + munmap(self->bitmap, self->bitmap_size); teardown_iommufd(self->fd, _metadata); } +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128k) +{ + /* one u32 index bitmap */ + .buffer_size = 128UL * 1024UL, +}; + +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256k) +{ + /* one u64 index bitmap */ + .buffer_size = 256UL * 1024UL, +}; + +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty640k) +{ + /* two u64 index and trailing end bitmap */ + .buffer_size = 640UL * 1024UL, +}; + +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M) +{ + /* 4K bitmap (128M IOVA range) */ + .buffer_size = 128UL * 1024UL * 1024UL, +}; + +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M) +{ + /* 8K bitmap (256M IOVA range) */ + .buffer_size = 256UL * 1024UL * 1024UL, +}; + TEST_F(iommufd_dirty_tracking, enforce_dirty) { uint32_t ioas_id, stddev_id, idev_id; @@ -1497,6 +1563,36 @@ TEST_F(iommufd_dirty_tracking, set_dirty_tracking) test_ioctl_destroy(hwpt_id); } +TEST_F(iommufd_dirty_tracking, get_dirty_bitmap) +{ + uint32_t stddev_id; + uint32_t hwpt_id; + uint32_t ioas_id; + + test_ioctl_ioas_alloc(&ioas_id); + test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer, + variant->buffer_size, MOCK_APERTURE_START); + + test_cmd_hwpt_alloc(self->idev_id, ioas_id, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + + test_cmd_set_dirty_tracking(hwpt_id, true); + + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, + self->bitmap, self->bitmap_size, _metadata); + + /* PAGE_SIZE unaligned bitmap */ + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, + self->bitmap + MOCK_PAGE_SIZE, + self->bitmap_size, _metadata); + + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); +} + /* VFIO compatibility IOCTLs */ TEST_F(iommufd, simple_ioctls) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index e37af6291b22..b129cf23b824 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -16,6 +16,25 @@ /* Hack to make assertions more readable */ #define _IOMMU_TEST_CMD(x) IOMMU_TEST_CMD +/* Imported from include/asm-generic/bitops/generic-non-atomic.h */ +#define BITS_PER_BYTE 8 +#define BITS_PER_LONG __BITS_PER_LONG +#define BIT_MASK(nr) (1UL << ((nr) % __BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / __BITS_PER_LONG) + +static inline void set_bit(unsigned int nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p |= mask; +} + +static inline bool test_bit(unsigned int nr, unsigned long *addr) +{ + return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1))); +} + static void *buffer; static unsigned long BUFFER_SIZE; @@ -196,6 +215,103 @@ static int _test_cmd_set_dirty_tracking(int fd, __u32 hwpt_id, bool enabled) #define test_cmd_set_dirty_tracking(hwpt_id, enabled) \ ASSERT_EQ(0, _test_cmd_set_dirty_tracking(self->fd, hwpt_id, enabled)) +static int _test_cmd_get_dirty_bitmap(int fd, __u32 hwpt_id, size_t length, + __u64 iova, size_t page_size, + __u64 *bitmap) +{ + struct iommu_hwpt_get_dirty_bitmap cmd = { + .size = sizeof(cmd), + .hwpt_id = hwpt_id, + .iova = iova, + .length = length, + .page_size = page_size, + .data = (uintptr_t)bitmap, + }; + int ret; + + ret = ioctl(fd, IOMMU_HWPT_GET_DIRTY_BITMAP, &cmd); + if (ret) + return ret; + return 0; +} + +#define test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, \ + bitmap) \ + ASSERT_EQ(0, _test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, \ + page_size, bitmap)) + +static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length, + __u64 iova, size_t page_size, + __u64 *bitmap, __u64 *dirty) +{ + struct iommu_test_cmd cmd = { + .size = sizeof(cmd), + .op = IOMMU_TEST_OP_DIRTY, + .id = hwpt_id, + .dirty = { + .iova = iova, + .length = length, + .page_size = page_size, + .uptr = (uintptr_t)bitmap, + } + }; + int ret; + + ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_DIRTY), &cmd); + if (ret) + return -ret; + if (dirty) + *dirty = cmd.dirty.out_nr_dirty; + return 0; +} + +#define test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size, \ + bitmap, nr) \ + ASSERT_EQ(0, \ + _test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, \ + page_size, bitmap, nr)) + +static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, + __u64 iova, size_t page_size, __u64 *bitmap, + __u64 bitmap_size, + struct __test_metadata *_metadata) +{ + unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE; + unsigned long nr = nbits / 2; + __u64 out_dirty = 0; + + /* Mark all even bits as dirty in the mock domain */ + for (count = 0, i = 0; i < nbits; count += !(i % 2), i++) + if (!(i % 2)) + set_bit(i, (unsigned long *)bitmap); + ASSERT_EQ(nr, count); + + test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size, + bitmap, &out_dirty); + ASSERT_EQ(nr, out_dirty); + + /* Expect all even bits as dirty in the user bitmap */ + memset(bitmap, 0, bitmap_size); + test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap); + for (count = 0, i = 0; i < nbits; count += !(i % 2), i++) + ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap)); + ASSERT_EQ(count, out_dirty); + + memset(bitmap, 0, bitmap_size); + test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap); + + /* It as read already -- expect all zeroes */ + for (i = 0; i < nbits; i++) + ASSERT_EQ(0, test_bit(i, (unsigned long *)bitmap)); + + return 0; +} +#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap, \ + bitmap_size, _metadata) \ + ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \ + page_size, bitmap, bitmap_size, \ + _metadata)) + static int _test_cmd_create_access(int fd, unsigned int ioas_id, __u32 *access_id, unsigned int flags) { @@ -320,6 +436,17 @@ static int _test_ioctl_ioas_map(int fd, unsigned int ioas_id, void *buffer, IOMMU_IOAS_MAP_READABLE)); \ }) +#define test_ioctl_ioas_map_fixed_id(ioas_id, buffer, length, iova) \ + ({ \ + __u64 __iova = iova; \ + ASSERT_EQ(0, \ + _test_ioctl_ioas_map( \ + self->fd, ioas_id, buffer, length, &__iova, \ + IOMMU_IOAS_MAP_FIXED_IOVA | \ + IOMMU_IOAS_MAP_WRITEABLE | \ + IOMMU_IOAS_MAP_READABLE)); \ + }) + #define test_err_ioctl_ioas_map_fixed(_errno, buffer, length, iova) \ ({ \ __u64 __iova = iova; \ -- Gitee From 82fe01e52fb936b93a9b07a2ec90d7c622eb454a Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:08 +0100 Subject: [PATCH 26/31] iommufd/selftest: Test out_capabilities in IOMMU_GET_HW_INFO mainline inclusion from mainline-v6.7-rc1 commit ae36fe70cea4d7c177452ab41e6734fa3cbd4ad8 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?ae36fe70cea4d7c177452ab41e6734fa3cbd4ad8 -------------------------------- Enumerate the capabilities from the mock device and test whether it advertises as expected. Include it as part of the iommufd_dirty_tracking fixture. Intel-SIG: ae36fe70cea4 iommufd/selftest: Test out_capabilities in IOMMU_GET_HW_INFO Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-18-joao.m.martins@oracle.com Signed-off-by: Joao Martins Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 13 +++++++++- tools/testing/selftests/iommu/iommufd.c | 17 +++++++++++++ .../selftests/iommu/iommufd_fail_nth.c | 2 +- tools/testing/selftests/iommu/iommufd_utils.h | 24 ++++++++++++------- 4 files changed, 45 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 4eb86025dde9..0eb01d1f9df8 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -376,7 +376,18 @@ static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain, static bool mock_domain_capable(struct device *dev, enum iommu_cap cap) { - return cap == IOMMU_CAP_CACHE_COHERENCY; + struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return true; + case IOMMU_CAP_DIRTY_TRACKING: + return !(mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY); + default: + break; + } + + return false; } static void mock_domain_set_plaform_dma_ops(struct device *dev) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 9535d043b80a..d982b71c4657 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1563,6 +1563,23 @@ TEST_F(iommufd_dirty_tracking, set_dirty_tracking) test_ioctl_destroy(hwpt_id); } +TEST_F(iommufd_dirty_tracking, device_dirty_capability) +{ + uint32_t caps = 0; + uint32_t stddev_id; + uint32_t hwpt_id; + + test_cmd_hwpt_alloc(self->idev_id, self->ioas_id, 0, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + test_cmd_get_hw_capabilities(self->idev_id, caps, + IOMMU_HW_CAP_DIRTY_TRACKING); + ASSERT_EQ(IOMMU_HW_CAP_DIRTY_TRACKING, + caps & IOMMU_HW_CAP_DIRTY_TRACKING); + + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); +} + TEST_F(iommufd_dirty_tracking, get_dirty_bitmap) { uint32_t stddev_id; diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index 3d7838506bfe..1fcd69cb0e41 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -612,7 +612,7 @@ TEST_FAIL_NTH(basic_fail_nth, device) &idev_id)) return -1; - if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info))) + if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info), NULL)) return -1; if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, &hwpt_id)) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index b129cf23b824..2410d06f5a34 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -535,8 +535,8 @@ static void teardown_iommufd(int fd, struct __test_metadata *_metadata) #endif /* @data can be NULL */ -static int _test_cmd_get_hw_info(int fd, __u32 device_id, - void *data, size_t data_len) +static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data, + size_t data_len, uint32_t *capabilities) { struct iommu_test_hw_info *info = (struct iommu_test_hw_info *)data; struct iommu_hw_info cmd = { @@ -544,6 +544,7 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, .dev_id = device_id, .data_len = data_len, .data_uptr = (uint64_t)data, + .out_capabilities = 0, }; int ret; @@ -580,14 +581,19 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, assert(!info->flags); } + if (capabilities) + *capabilities = cmd.out_capabilities; + return 0; } -#define test_cmd_get_hw_info(device_id, data, data_len) \ - ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, \ - data, data_len)) +#define test_cmd_get_hw_info(device_id, data, data_len) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, data, \ + data_len, NULL)) + +#define test_err_get_hw_info(_errno, device_id, data, data_len) \ + EXPECT_ERRNO(_errno, _test_cmd_get_hw_info(self->fd, device_id, data, \ + data_len, NULL)) -#define test_err_get_hw_info(_errno, device_id, data, data_len) \ - EXPECT_ERRNO(_errno, \ - _test_cmd_get_hw_info(self->fd, device_id, \ - data, data_len)) +#define test_cmd_get_hw_capabilities(device_id, caps, mask) \ + ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, 0, &caps)) -- Gitee From dc751d4180a848df433a1d4a67fe6385d1c3cec2 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 24 Oct 2023 14:51:09 +0100 Subject: [PATCH 27/31] iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR flag mainline inclusion from mainline-v6.7-rc1 commit 0795b305da8902e7d092f90bf9a1a2c98f34b1db category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?0795b305da8902e7d092f90bf9a1a2c98f34b1db -------------------------------- Change test_mock_dirty_bitmaps() to pass a flag where it specifies the flag under test. The test does the same thing as the GET_DIRTY_BITMAP regular test. Except that it tests whether the dirtied bits are fetched all the same a second time, as opposed to observing them cleared. Intel-SIG: 0795b305da89 iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR flag Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231024135109.73787-19-joao.m.martins@oracle.com Signed-off-by: Joao Martins Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 15 +++++--- tools/testing/selftests/iommu/iommufd.c | 38 ++++++++++++++++++- tools/testing/selftests/iommu/iommufd_utils.h | 26 ++++++++----- 3 files changed, 61 insertions(+), 18 deletions(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 0eb01d1f9df8..d8551c9d5b6c 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -193,13 +193,16 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE); if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) { - unsigned long val; - /* Clear dirty */ - val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; - old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE, - xa_mk_value(val), GFP_KERNEL); - WARN_ON_ONCE(ent != old); + if (!(flags & IOMMU_DIRTY_NO_CLEAR)) { + unsigned long val; + + val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; + old = xa_store(&mock->pfns, + cur / MOCK_IO_PAGE_SIZE, + xa_mk_value(val), GFP_KERNEL); + WARN_ON_ONCE(ent != old); + } iommu_dirty_bitmap_record(dirty, cur, MOCK_IO_PAGE_SIZE); } diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index d982b71c4657..de61447b9558 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1598,13 +1598,47 @@ TEST_F(iommufd_dirty_tracking, get_dirty_bitmap) test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, MOCK_APERTURE_START, self->page_size, - self->bitmap, self->bitmap_size, _metadata); + self->bitmap, self->bitmap_size, 0, _metadata); /* PAGE_SIZE unaligned bitmap */ test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, MOCK_APERTURE_START, self->page_size, self->bitmap + MOCK_PAGE_SIZE, - self->bitmap_size, _metadata); + self->bitmap_size, 0, _metadata); + + test_ioctl_destroy(stddev_id); + test_ioctl_destroy(hwpt_id); +} + +TEST_F(iommufd_dirty_tracking, get_dirty_bitmap_no_clear) +{ + uint32_t stddev_id; + uint32_t hwpt_id; + uint32_t ioas_id; + + test_ioctl_ioas_alloc(&ioas_id); + test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer, + variant->buffer_size, MOCK_APERTURE_START); + + test_cmd_hwpt_alloc(self->idev_id, ioas_id, + IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); + test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); + + test_cmd_set_dirty_tracking(hwpt_id, true); + + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, + self->bitmap, self->bitmap_size, + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR, + _metadata); + + /* Unaligned bitmap */ + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, + self->bitmap + MOCK_PAGE_SIZE, + self->bitmap_size, + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR, + _metadata); test_ioctl_destroy(stddev_id); test_ioctl_destroy(hwpt_id); diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 2410d06f5a34..e263bf80a977 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -217,11 +217,12 @@ static int _test_cmd_set_dirty_tracking(int fd, __u32 hwpt_id, bool enabled) static int _test_cmd_get_dirty_bitmap(int fd, __u32 hwpt_id, size_t length, __u64 iova, size_t page_size, - __u64 *bitmap) + __u64 *bitmap, __u32 flags) { struct iommu_hwpt_get_dirty_bitmap cmd = { .size = sizeof(cmd), .hwpt_id = hwpt_id, + .flags = flags, .iova = iova, .length = length, .page_size = page_size, @@ -236,9 +237,9 @@ static int _test_cmd_get_dirty_bitmap(int fd, __u32 hwpt_id, size_t length, } #define test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, \ - bitmap) \ + bitmap, flags) \ ASSERT_EQ(0, _test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, \ - page_size, bitmap)) + page_size, bitmap, flags)) static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length, __u64 iova, size_t page_size, @@ -273,7 +274,7 @@ static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length, static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, __u64 iova, size_t page_size, __u64 *bitmap, - __u64 bitmap_size, + __u64 bitmap_size, __u32 flags, struct __test_metadata *_metadata) { unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE; @@ -292,25 +293,30 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, /* Expect all even bits as dirty in the user bitmap */ memset(bitmap, 0, bitmap_size); - test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap); + test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap, + flags); for (count = 0, i = 0; i < nbits; count += !(i % 2), i++) ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap)); ASSERT_EQ(count, out_dirty); memset(bitmap, 0, bitmap_size); - test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap); + test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap, + flags); /* It as read already -- expect all zeroes */ - for (i = 0; i < nbits; i++) - ASSERT_EQ(0, test_bit(i, (unsigned long *)bitmap)); + for (i = 0; i < nbits; i++) { + ASSERT_EQ(!(i % 2) && (flags & + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR), + test_bit(i, (unsigned long *)bitmap)); + } return 0; } #define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap, \ - bitmap_size, _metadata) \ + bitmap_size, flags, _metadata) \ ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \ page_size, bitmap, bitmap_size, \ - _metadata)) + flags, _metadata)) static int _test_cmd_create_access(int fd, unsigned int ioas_id, __u32 *access_id, unsigned int flags) -- Gitee From 89f4f377edd8643c1198639dc1c8ee9ed19fb212 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Tue, 24 Oct 2023 08:00:11 -0700 Subject: [PATCH 28/31] iommu/vt-d: Enhance capability check for nested parent domain allocation mainline inclusion from mainline-v6.7-rc1 commit a2cdecdf9d234455fdfc8f539bbf5818711bc29d category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?a2cdecdf9d234455fdfc8f539bbf5818711bc29d -------------------------------- This adds the scalable mode check before allocating the nested parent domain as checking nested capability is not enough. User may turn off scalable mode which also means no nested support even if the hardware supports it. Intel-SIG: a2cdecdf9d23 iommu/vt-d: Enhance capability check for nested parent domain allocation Backport IOMMUFD Dirty Tracking Fixes: c97d1b20d383 ("iommu/vt-d: Add domain_alloc_user op") Link: https://lore.kernel.org/r/20231024150011.44642-1-yi.l.liu@intel.com Signed-off-by: Yi Liu Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/intel/iommu.c | 2 +- drivers/iommu/intel/iommu.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 47f95833cf62..fbb53763bd17 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4075,7 +4075,7 @@ intel_iommu_domain_alloc_user(struct device *dev, u32 flags) if (!iommu) return ERR_PTR(-ENODEV); - if ((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) && !ecap_nest(iommu->ecap)) + if ((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) && !nested_supported(iommu)) return ERR_PTR(-EOPNOTSUPP); dirty_tracking = (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING); diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 9f8de5df3cc3..8cf451bf3085 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -544,6 +544,8 @@ enum { ecap_pasid((iommu)->ecap)) #define ssads_supported(iommu) (sm_supported(iommu) && \ ecap_slads((iommu)->ecap)) +#define nested_supported(iommu) (sm_supported(iommu) && \ + ecap_nest((iommu)->ecap)) struct pasid_entry; struct pasid_state_entry; -- Gitee From 5fcee25aafd115af58bbcd82b08f48143cff44b6 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Mon, 30 Oct 2023 11:34:46 +0000 Subject: [PATCH 29/31] iommufd/selftest: Fix page-size check in iommufd_test_dirty() mainline inclusion from mainline-v6.7-rc1 commit 2e22aac3ea9cfc0ec3209c96644f60c1806a8117 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?2e22aac3ea9cfc0ec3209c96644f60c1806a8117 -------------------------------- iommufd_test_dirty()/IOMMU_TEST_OP_DIRTY sets the dirty bits in the mock domain implementation that the userspace side validates against what it obtains via the UAPI. However in introducing iommufd_test_dirty() it forgot to validate page_size being 0 leading to two possible divide-by-zero problems: one at the beginning when calculating @max and while calculating the IOVA in the XArray PFN tracking list. While at it, validate the length to require non-zero value as well, as we can't be allocating a 0-sized bitmap. Intel-SIG: 2e22aac3ea9c iommufd/selftest: Fix page-size check in iommufd_test_dirty() Backport IOMMUFD Dirty Tracking Link: https://lore.kernel.org/r/20231030113446.7056-1-joao.m.martins@oracle.com Reported-by: syzbot+25dc7383c30ecdc83c38@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-iommu/00000000000005f6aa0608b9220f@google.com/ Fixes: a9af47e382a4 ("iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP") Signed-off-by: Joao Martins Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/iommufd/selftest.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index d8551c9d5b6c..22f9fcdfc55a 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -1098,14 +1098,15 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long page_size, void __user *uptr, u32 flags) { - unsigned long bitmap_size, i, max = length / page_size; + unsigned long bitmap_size, i, max; struct iommu_test_cmd *cmd = ucmd->cmd; struct iommufd_hw_pagetable *hwpt; struct mock_iommu_domain *mock; int rc, count = 0; void *tmp; - if (iova % page_size || length % page_size || !uptr) + if (!page_size || !length || iova % page_size || length % page_size || + !uptr) return -EINVAL; hwpt = get_md_pagetable(ucmd, mockpt_id, &mock); @@ -1117,6 +1118,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, goto out_put; } + max = length / page_size; bitmap_size = max / BITS_PER_BYTE; tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT); -- Gitee From 07ad53d0799ed2732d3e87b93b45387bf5a163f0 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 16 Nov 2023 16:52:15 +0000 Subject: [PATCH 30/31] iommufd/selftest: Fix _test_mock_dirty_bitmaps() mainline inclusion from mainline-v6.7-rc5 commit 98594181944daa201481ad63242806beb7c89ff4 category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?98594181944daa201481ad63242806beb7c89ff4 -------------------------------- The ASSERT_EQ() macro sneakily expands to two statements, so the loop here needs braces to ensure it captures both and actually terminates the test upon failure. Where these tests are currently failing on my arm64 machine, this reduces the number of logged lines from a rather unreasonable ~197,000 down to 10. While we're at it, we can also clean up the tautologous "count" calculations whose assertions can never fail unless mathematics and/or the C language become fundamentally broken. Intel-SIG: 98594181944d iommufd/selftest: Fix _test_mock_dirty_bitmaps() Backport IOMMUFD Dirty Tracking Fixes: a9af47e382a4 ("iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP") Link: https://lore.kernel.org/r/90e083045243ef407dd592bb1deec89cd1f4ddf2.1700153535.git.robin.murphy@arm.com Signed-off-by: Robin Murphy Reviewed-by: Kevin Tian Reviewed-by: Joao Martins Tested-by: Joao Martins Signed-off-by: Jason Gunthorpe [ jz: amend commit log ] Signed-off-by: Jason Zeng --- tools/testing/selftests/iommu/iommufd_utils.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index e263bf80a977..70d558e0f0c7 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -277,15 +277,13 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, __u64 bitmap_size, __u32 flags, struct __test_metadata *_metadata) { - unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE; + unsigned long i, nbits = bitmap_size * BITS_PER_BYTE; unsigned long nr = nbits / 2; __u64 out_dirty = 0; /* Mark all even bits as dirty in the mock domain */ - for (count = 0, i = 0; i < nbits; count += !(i % 2), i++) - if (!(i % 2)) - set_bit(i, (unsigned long *)bitmap); - ASSERT_EQ(nr, count); + for (i = 0; i < nbits; i += 2) + set_bit(i, (unsigned long *)bitmap); test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size, bitmap, &out_dirty); @@ -295,9 +293,10 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, memset(bitmap, 0, bitmap_size); test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap, flags); - for (count = 0, i = 0; i < nbits; count += !(i % 2), i++) + /* Beware ASSERT_EQ() is two statements -- braces are not redundant! */ + for (i = 0; i < nbits; i++) { ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap)); - ASSERT_EQ(count, out_dirty); + } memset(bitmap, 0, bitmap_size); test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap, -- Gitee From 46deabcacf1de99329a35585881955547f5892a8 Mon Sep 17 00:00:00 2001 From: Kunwu Chan Date: Wed, 22 Nov 2023 11:26:08 +0800 Subject: [PATCH 31/31] iommu/vt-d: Set variable intel_dirty_ops to static mainline inclusion from mainline-v6.7-rc4 commit e378c7de74620051c3be899a8c2506c25d23049d category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I8Y6AM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?e378c7de74620051c3be899a8c2506c25d23049d -------------------------------- Fix the following warning: drivers/iommu/intel/iommu.c:302:30: warning: symbol 'intel_dirty_ops' was not declared. Should it be static? This variable is only used in its defining file, so it should be static. Intel-SIG: e378c7de7462 iommu/vt-d: Set variable intel_dirty_ops to static Backport IOMMUFD Dirty Tracking Fixes: f35f22cc760e ("iommu/vt-d: Access/Dirty bit support for SS domains") Signed-off-by: Kunwu Chan Reviewed-by: Jason Gunthorpe Reviewed-by: Joao Martins Link: https://lore.kernel.org/r/20231120101025.1103404-1-chentao@kylinos.cn Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel [ jz: amend commit log ] Signed-off-by: Jason Zeng --- drivers/iommu/intel/iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index fbb53763bd17..1af77b46bba0 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -300,7 +300,7 @@ static int iommu_skip_te_disable; #define IDENTMAP_AZALIA 4 const struct iommu_ops intel_iommu_ops; -const struct iommu_dirty_ops intel_dirty_ops; +static const struct iommu_dirty_ops intel_dirty_ops; static bool translation_pre_enabled(struct intel_iommu *iommu) { @@ -4911,7 +4911,7 @@ static int intel_iommu_read_and_clear_dirty(struct iommu_domain *domain, return 0; } -const struct iommu_dirty_ops intel_dirty_ops = { +static const struct iommu_dirty_ops intel_dirty_ops = { .set_dirty_tracking = intel_iommu_set_dirty_tracking, .read_and_clear_dirty = intel_iommu_read_and_clear_dirty, }; -- Gitee