From 6e031ec0e5a2dda53e12e0d2a7e9b15b47a3c502 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 24 Jan 2022 16:11:37 -0700 Subject: vfio/pci: Stub vfio_pci_vga_rw when !CONFIG_VFIO_PCI_VGA Resolve build errors reported against UML build for undefined ioport_map() and ioport_unmap() functions. Without this config option a device cannot have vfio_pci_core_device.has_vga set, so the existing function would always return -EINVAL anyway. Reported-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20220123125737.2658758-1-geert@linux-m68k.org Link: https://lore.kernel.org/r/164306582968.3758255.15192949639574660648.stgit@omen Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..ae6f4838ab75 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -159,8 +159,17 @@ extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#ifdef CONFIG_VFIO_PCI_VGA extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#else +static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, + char __user *buf, size_t count, + loff_t *ppos, bool iswrite) +{ + return -EINVAL; +} +#endif extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, uint64_t data, int count, int fd); -- cgit v1.2.3 From 21ca9fb62d4688da41825e0f05d8e7e26afc69d6 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:10 +0200 Subject: PCI/IOV: Add pci_iov_vf_id() to get VF index The PCI core uses the VF index internally, often called the vf_id, during the setup of the VF, eg pci_iov_add_virtfn(). This index is needed for device drivers that implement live migration for their internal operations that configure/control their VFs. Specifically, mlx5_vfio_pci driver that is introduced in coming patches from this series needs it and not the bus/device/function which is exposed today. Add pci_iov_vf_id() which computes the vf_id by reversing the math that was used to create the bus/device/function. Link: https://lore.kernel.org/all/20220224142024.147653-2-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/pci/iov.c | 14 ++++++++++++++ include/linux/pci.h | 8 +++++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 0267977c9f17..2e9f3d70803a 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -33,6 +33,20 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id) } EXPORT_SYMBOL_GPL(pci_iov_virtfn_devfn); +int pci_iov_vf_id(struct pci_dev *dev) +{ + struct pci_dev *pf; + + if (!dev->is_virtfn) + return -EINVAL; + + pf = pci_physfn(dev); + return (((dev->bus->number << 8) + dev->devfn) - + ((pf->bus->number << 8) + pf->devfn + pf->sriov->offset)) / + pf->sriov->stride; +} +EXPORT_SYMBOL_GPL(pci_iov_vf_id); + /* * Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may * change when NumVFs changes. diff --git a/include/linux/pci.h b/include/linux/pci.h index 8253a5413d7c..3d4ff7b35ad1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2166,7 +2166,7 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); - +int pci_iov_vf_id(struct pci_dev *dev); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2194,6 +2194,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) { return -ENOSYS; } + +static inline int pci_iov_vf_id(struct pci_dev *dev) +{ + return -ENOSYS; +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } -- cgit v1.2.3 From a7e9f240c0da4fb73a353c603daf4beba04c6ecf Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:13 +0200 Subject: PCI/IOV: Add pci_iov_get_pf_drvdata() to allow VF reaching the drvdata of a PF There are some cases where a SR-IOV VF driver will need to reach into and interact with the PF driver. This requires accessing the drvdata of the PF. Provide a function pci_iov_get_pf_drvdata() to return this PF drvdata in a safe way. Normally accessing a drvdata of a foreign struct device would be done using the device_lock() to protect against device driver probe()/remove() races. However, due to the design of pci_enable_sriov() this will result in a ABBA deadlock on the device_lock as the PF's device_lock is held during PF sriov_configure() while calling pci_enable_sriov() which in turn holds the VF's device_lock while calling VF probe(), and similarly for remove. This means the VF driver can never obtain the PF's device_lock. Instead use the implicit locking created by pci_enable/disable_sriov(). A VF driver can access its PF drvdata only while its own driver is attached, and the PF driver can control access to its own drvdata based on when it calls pci_enable/disable_sriov(). To use this API the PF driver will setup the PF drvdata in the probe() function. pci_enable_sriov() is only called from sriov_configure() which cannot happen until probe() completes, ensuring no VF races with drvdata setup. For removal, the PF driver must call pci_disable_sriov() in its remove function before destroying any of the drvdata. This ensures that all VF drivers are unbound before returning, fencing concurrent access to the drvdata. The introduction of a new function to do this access makes clear the special locking scheme and the documents the requirements on the PF/VF drivers using this. Link: https://lore.kernel.org/all/20220224142024.147653-5-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/pci/iov.c | 29 +++++++++++++++++++++++++++++ include/linux/pci.h | 7 +++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 2e9f3d70803a..28ec952e1221 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -47,6 +47,35 @@ int pci_iov_vf_id(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_iov_vf_id); +/** + * pci_iov_get_pf_drvdata - Return the drvdata of a PF + * @dev - VF pci_dev + * @pf_driver - Device driver required to own the PF + * + * This must be called from a context that ensures that a VF driver is attached. + * The value returned is invalid once the VF driver completes its remove() + * callback. + * + * Locking is achieved by the driver core. A VF driver cannot be probed until + * pci_enable_sriov() is called and pci_disable_sriov() does not return until + * all VF drivers have completed their remove(). + * + * The PF driver must call pci_disable_sriov() before it begins to destroy the + * drvdata. + */ +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver) +{ + struct pci_dev *pf_dev; + + if (!dev->is_virtfn) + return ERR_PTR(-EINVAL); + pf_dev = dev->physfn; + if (pf_dev->driver != pf_driver) + return ERR_PTR(-EINVAL); + return pci_get_drvdata(pf_dev); +} +EXPORT_SYMBOL_GPL(pci_iov_get_pf_drvdata); + /* * Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may * change when NumVFs changes. diff --git a/include/linux/pci.h b/include/linux/pci.h index 3d4ff7b35ad1..60d423d8f0c4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2167,6 +2167,7 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); int pci_iov_vf_id(struct pci_dev *dev); +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2200,6 +2201,12 @@ static inline int pci_iov_vf_id(struct pci_dev *dev) return -ENOSYS; } +static inline void *pci_iov_get_pf_drvdata(struct pci_dev *dev, + struct pci_driver *pf_driver) +{ + return ERR_PTR(-EINVAL); +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } -- cgit v1.2.3 From 1695b97b291e79295bf5c26cba5ecc4b443d8ac7 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:14 +0200 Subject: net/mlx5: Expose APIs to get/put the mlx5 core device Expose an API to get the mlx5 core device from a given VF PCI device if mlx5_core is its driver. Upon the get API we stay with the intf_state_mutex locked to make sure that the device can't be gone/unloaded till the caller will complete its job over the device, this expects to be for a short period of time for any flow that the lock is taken. Upon the put API we unlock the intf_state_mutex. The use case for those APIs is the migration flow of a VF over VFIO PCI. In that case the VF doesn't ride on mlx5_core, because the device is driving *two* different PCI devices, the PF owned by mlx5_core and the VF owned by the vfio driver. The mlx5_core of the PF is accessed only during the narrow window of the VF's ioctl that requires its services. This allows the PF driver to be more independent of the VF driver, so long as it doesn't reset the FW. Link: https://lore.kernel.org/all/20220224142024.147653-6-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 44 ++++++++++++++++++++++++++ include/linux/mlx5/driver.h | 3 ++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5b8958186157..e9aeba4267ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1881,6 +1881,50 @@ static struct pci_driver mlx5_core_driver = { .sriov_set_msix_vec_count = mlx5_core_sriov_set_msix_vec_count, }; +/** + * mlx5_vf_get_core_dev - Get the mlx5 core device from a given VF PCI device if + * mlx5_core is its driver. + * @pdev: The associated PCI device. + * + * Upon return the interface state lock stay held to let caller uses it safely. + * Caller must ensure to use the returned mlx5 device for a narrow window + * and put it back with mlx5_vf_put_core_dev() immediately once usage was over. + * + * Return: Pointer to the associated mlx5_core_dev or NULL. + */ +struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev) + __acquires(&mdev->intf_state_mutex) +{ + struct mlx5_core_dev *mdev; + + mdev = pci_iov_get_pf_drvdata(pdev, &mlx5_core_driver); + if (IS_ERR(mdev)) + return NULL; + + mutex_lock(&mdev->intf_state_mutex); + if (!test_bit(MLX5_INTERFACE_STATE_UP, &mdev->intf_state)) { + mutex_unlock(&mdev->intf_state_mutex); + return NULL; + } + + return mdev; +} +EXPORT_SYMBOL(mlx5_vf_get_core_dev); + +/** + * mlx5_vf_put_core_dev - Put the mlx5 core device back. + * @mdev: The mlx5 core device. + * + * Upon return the interface state lock is unlocked and caller should not + * access the mdev any more. + */ +void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev) + __releases(&mdev->intf_state_mutex) +{ + mutex_unlock(&mdev->intf_state_mutex); +} +EXPORT_SYMBOL(mlx5_vf_put_core_dev); + static void mlx5_core_verify_params(void) { if (prof_sel >= ARRAY_SIZE(profile)) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 78655d8d13a7..319322a8ff94 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1143,6 +1143,9 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); +struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); +void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); + #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, -- cgit v1.2.3 From adfdaff3d14fe819a0420d81788f7ebbcd954940 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:15 +0200 Subject: net/mlx5: Introduce migration bits and structures Introduce migration IFC related stuff to enable migration commands. Link: https://lore.kernel.org/all/20220224142024.147653-7-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 147 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 146 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..b1c27409c997 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -127,6 +127,11 @@ enum { MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, MLX5_CMD_OP_ALLOC_SF = 0x113, MLX5_CMD_OP_DEALLOC_SF = 0x114, + MLX5_CMD_OP_SUSPEND_VHCA = 0x115, + MLX5_CMD_OP_RESUME_VHCA = 0x116, + MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE = 0x117, + MLX5_CMD_OP_SAVE_VHCA_STATE = 0x118, + MLX5_CMD_OP_LOAD_VHCA_STATE = 0x119, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -1757,7 +1762,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; u8 apu[0x1]; - u8 reserved_at_689[0x7]; + u8 reserved_at_689[0x4]; + u8 migration[0x1]; + u8 reserved_at_68e[0x2]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -11519,4 +11526,142 @@ enum { MLX5_MTT_PERM_RW = MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE, }; +enum { + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR = 0x0, + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER = 0x1, +}; + +struct mlx5_ifc_suspend_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_suspend_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER = 0x0, + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR = 0x1, +}; + +struct mlx5_ifc_resume_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_resume_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_vhca_migration_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_vhca_migration_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 required_umem_size[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_save_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_save_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 actual_image_size[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 445ad495f0ff71553693e6a2a9d7a3bc6917ca36 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:17 +0200 Subject: vfio: Have the core code decode the VFIO_DEVICE_FEATURE ioctl Invoke a new device op 'device_feature' to handle just the data array portion of the command. This lifts the ioctl validation to the core code and makes it simpler for either the core code, or layered drivers, to implement their own feature values. Provide vfio_check_feature() to consolidate checking the flags/etc against what the driver supports. Link: https://lore.kernel.org/all/20220224142024.147653-9-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Alex Williamson Reviewed-by: Cornelia Huck Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/vfio_pci.c | 1 + drivers/vfio/pci/vfio_pci_core.c | 94 ++++++++++++++++------------------------ drivers/vfio/vfio.c | 46 ++++++++++++++++++-- include/linux/vfio.h | 32 ++++++++++++++ include/linux/vfio_pci_core.h | 2 + 5 files changed, 114 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index a5ce92beb655..2b047469e02f 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -130,6 +130,7 @@ static const struct vfio_device_ops vfio_pci_ops = { .open_device = vfio_pci_open_device, .close_device = vfio_pci_core_close_device, .ioctl = vfio_pci_core_ioctl, + .device_feature = vfio_pci_core_ioctl_feature, .read = vfio_pci_core_read, .write = vfio_pci_core_write, .mmap = vfio_pci_core_mmap, diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index f948e6cd2993..106e1970d653 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1114,70 +1114,50 @@ hot_reset_release: return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, ioeventfd.fd); - } else if (cmd == VFIO_DEVICE_FEATURE) { - struct vfio_device_feature feature; - uuid_t uuid; - - minsz = offsetofend(struct vfio_device_feature, flags); - - if (copy_from_user(&feature, (void __user *)arg, minsz)) - return -EFAULT; - - if (feature.argsz < minsz) - return -EINVAL; - - /* Check unknown flags */ - if (feature.flags & ~(VFIO_DEVICE_FEATURE_MASK | - VFIO_DEVICE_FEATURE_SET | - VFIO_DEVICE_FEATURE_GET | - VFIO_DEVICE_FEATURE_PROBE)) - return -EINVAL; - - /* GET & SET are mutually exclusive except with PROBE */ - if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) && - (feature.flags & VFIO_DEVICE_FEATURE_SET) && - (feature.flags & VFIO_DEVICE_FEATURE_GET)) - return -EINVAL; - - switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) { - case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: - if (!vdev->vf_token) - return -ENOTTY; - - /* - * We do not support GET of the VF Token UUID as this - * could expose the token of the previous device user. - */ - if (feature.flags & VFIO_DEVICE_FEATURE_GET) - return -EINVAL; - - if (feature.flags & VFIO_DEVICE_FEATURE_PROBE) - return 0; + } + return -ENOTTY; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); - /* Don't SET unless told to do so */ - if (!(feature.flags & VFIO_DEVICE_FEATURE_SET)) - return -EINVAL; +static int vfio_pci_core_feature_token(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + uuid_t uuid; + int ret; - if (feature.argsz < minsz + sizeof(uuid)) - return -EINVAL; + if (!vdev->vf_token) + return -ENOTTY; + /* + * We do not support GET of the VF Token UUID as this could + * expose the token of the previous device user. + */ + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, + sizeof(uuid)); + if (ret != 1) + return ret; - if (copy_from_user(&uuid, (void __user *)(arg + minsz), - sizeof(uuid))) - return -EFAULT; + if (copy_from_user(&uuid, arg, sizeof(uuid))) + return -EFAULT; - mutex_lock(&vdev->vf_token->lock); - uuid_copy(&vdev->vf_token->uuid, &uuid); - mutex_unlock(&vdev->vf_token->lock); + mutex_lock(&vdev->vf_token->lock); + uuid_copy(&vdev->vf_token->uuid, &uuid); + mutex_unlock(&vdev->vf_token->lock); + return 0; +} - return 0; - default: - return -ENOTTY; - } +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + switch (flags & VFIO_DEVICE_FEATURE_MASK) { + case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: + return vfio_pci_core_feature_token(device, flags, arg, argsz); + default: + return -ENOTTY; } - - return -ENOTTY; } -EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl_feature); static ssize_t vfio_pci_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 735d1d344af9..71763e2ac561 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1557,15 +1557,53 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep) return 0; } +static int vfio_ioctl_device_feature(struct vfio_device *device, + struct vfio_device_feature __user *arg) +{ + size_t minsz = offsetofend(struct vfio_device_feature, flags); + struct vfio_device_feature feature; + + if (copy_from_user(&feature, arg, minsz)) + return -EFAULT; + + if (feature.argsz < minsz) + return -EINVAL; + + /* Check unknown flags */ + if (feature.flags & + ~(VFIO_DEVICE_FEATURE_MASK | VFIO_DEVICE_FEATURE_SET | + VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_PROBE)) + return -EINVAL; + + /* GET & SET are mutually exclusive except with PROBE */ + if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) && + (feature.flags & VFIO_DEVICE_FEATURE_SET) && + (feature.flags & VFIO_DEVICE_FEATURE_GET)) + return -EINVAL; + + switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) { + default: + if (unlikely(!device->ops->device_feature)) + return -EINVAL; + return device->ops->device_feature(device, feature.flags, + arg->data, + feature.argsz - minsz); + } +} + static long vfio_device_fops_unl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct vfio_device *device = filep->private_data; - if (unlikely(!device->ops->ioctl)) - return -EINVAL; - - return device->ops->ioctl(device, cmd, arg); + switch (cmd) { + case VFIO_DEVICE_FEATURE: + return vfio_ioctl_device_feature(device, (void __user *)arg); + default: + if (unlikely(!device->ops->ioctl)) + return -EINVAL; + return device->ops->ioctl(device, cmd, arg); + } } static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 76191d7abed1..550c28f2ef60 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -55,6 +55,7 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl */ struct vfio_device_ops { char *name; @@ -69,8 +70,39 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + int (*device_feature)(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); }; +/** + * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl + * @flags: Arg from the device_feature op + * @argsz: Arg from the device_feature op + * @supported_ops: Combination of VFIO_DEVICE_FEATURE_GET and SET the driver + * supports + * @minsz: Minimum data size the driver accepts + * + * For use in a driver's device_feature op. Checks that the inputs to the + * VFIO_DEVICE_FEATURE ioctl are correct for the driver's feature. Returns 1 if + * the driver should execute the get or set, otherwise the relevant + * value should be returned. + */ +static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, + size_t minsz) +{ + if ((flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET)) & + ~supported_ops) + return -EINVAL; + if (flags & VFIO_DEVICE_FEATURE_PROBE) + return 0; + /* Without PROBE one of GET or SET must be requested */ + if (!(flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET))) + return -EINVAL; + if (argsz < minsz) + return -EINVAL; + return 1; +} + void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..beba0b2ed87d 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -220,6 +220,8 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, -- cgit v1.2.3 From 115dcec65f61d53e25e1bed5e380468b30f98b14 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:18 +0200 Subject: vfio: Define device migration protocol v2 Replace the existing region based migration protocol with an ioctl based protocol. The two protocols have the same general semantic behaviors, but the way the data is transported is changed. This is the STOP_COPY portion of the new protocol, it defines the 5 states for basic stop and copy migration and the protocol to move the migration data in/out of the kernel. Compared to the clarification of the v1 protocol Alex proposed: https://lore.kernel.org/r/163909282574.728533.7460416142511440919.stgit@omen This has a few deliberate functional differences: - ERROR arcs allow the device function to remain unchanged. - The protocol is not required to return to the original state on transition failure. Instead userspace can execute an unwind back to the original state, reset, or do something else without needing kernel support. This simplifies the kernel design and should userspace choose a policy like always reset, avoids doing useless work in the kernel on error handling paths. - PRE_COPY is made optional, userspace must discover it before using it. This reflects the fact that the majority of drivers we are aware of right now will not implement PRE_COPY. - segmentation is not part of the data stream protocol, the receiver does not have to reproduce the framing boundaries. The hybrid FSM for the device_state is described as a Mealy machine by documenting each of the arcs the driver is required to implement. Defining the remaining set of old/new device_state transitions as 'combination transitions' which are naturally defined as taking multiple FSM arcs along the shortest path within the FSM's digraph allows a complete matrix of transitions. A new VFIO_DEVICE_FEATURE of VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE is defined to replace writing to the device_state field in the region. This allows returning a brand new FD whenever the requested transition opens a data transfer session. The VFIO core code implements the new feature and provides a helper function to the driver. Using the helper the driver only has to implement 6 of the FSM arcs and the other combination transitions are elaborated consistently from those arcs. A new VFIO_DEVICE_FEATURE of VFIO_DEVICE_FEATURE_MIGRATION is defined to report the capability for migration and indicate which set of states and arcs are supported by the device. The FSM provides a lot of flexibility to make backwards compatible extensions but the VFIO_DEVICE_FEATURE also allows for future breaking extensions for scenarios that cannot support even the basic STOP_COPY requirements. The VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE with the GET option (i.e. VFIO_DEVICE_FEATURE_GET) can be used to read the current migration state of the VFIO device. Data transfer sessions are now carried over a file descriptor, instead of the region. The FD functions for the lifetime of the data transfer session. read() and write() transfer the data with normal Linux stream FD semantics. This design allows future expansion to support poll(), io_uring, and other performance optimizations. The complicated mmap mode for data transfer is discarded as current qemu doesn't take meaningful advantage of it, and the new qemu implementation avoids substantially all the performance penalty of using a read() on the region. Link: https://lore.kernel.org/all/20220224142024.147653-10-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Reviewed-by: Cornelia Huck Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/vfio/vfio.c | 199 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/vfio.h | 20 +++++ include/uapi/linux/vfio.h | 174 +++++++++++++++++++++++++++++++++++++--- 3 files changed, 380 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 71763e2ac561..b37ab27b511f 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1557,6 +1557,197 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep) return 0; } +/* + * vfio_mig_get_next_state - Compute the next step in the FSM + * @cur_fsm - The current state the device is in + * @new_fsm - The target state to reach + * @next_fsm - Pointer to the next step to get to new_fsm + * + * Return 0 upon success, otherwise -errno + * Upon success the next step in the state progression between cur_fsm and + * new_fsm will be set in next_fsm. + * + * This breaks down requests for combination transitions into smaller steps and + * returns the next step to get to new_fsm. The function may need to be called + * multiple times before reaching new_fsm. + * + */ +int vfio_mig_get_next_state(struct vfio_device *device, + enum vfio_device_mig_state cur_fsm, + enum vfio_device_mig_state new_fsm, + enum vfio_device_mig_state *next_fsm) +{ + enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RESUMING + 1 }; + /* + * The coding in this table requires the driver to implement 6 + * FSM arcs: + * RESUMING -> STOP + * RUNNING -> STOP + * STOP -> RESUMING + * STOP -> RUNNING + * STOP -> STOP_COPY + * STOP_COPY -> STOP + * + * The coding will step through multiple states for these combination + * transitions: + * RESUMING -> STOP -> RUNNING + * RESUMING -> STOP -> STOP_COPY + * RUNNING -> STOP -> RESUMING + * RUNNING -> STOP -> STOP_COPY + * STOP_COPY -> STOP -> RESUMING + * STOP_COPY -> STOP -> RUNNING + */ + static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = { + [VFIO_DEVICE_STATE_STOP] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_RUNNING] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_STOP_COPY] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_RESUMING] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_ERROR] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + }; + + if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table))) + return -EINVAL; + + if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table)) + return -EINVAL; + + *next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm]; + return (*next_fsm != VFIO_DEVICE_STATE_ERROR) ? 0 : -EINVAL; +} +EXPORT_SYMBOL_GPL(vfio_mig_get_next_state); + +/* + * Convert the drivers's struct file into a FD number and return it to userspace + */ +static int vfio_ioct_mig_return_fd(struct file *filp, void __user *arg, + struct vfio_device_feature_mig_state *mig) +{ + int ret; + int fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + ret = fd; + goto out_fput; + } + + mig->data_fd = fd; + if (copy_to_user(arg, mig, sizeof(*mig))) { + ret = -EFAULT; + goto out_put_unused; + } + fd_install(fd, filp); + return 0; + +out_put_unused: + put_unused_fd(fd); +out_fput: + fput(filp); + return ret; +} + +static int +vfio_ioctl_device_feature_mig_device_state(struct vfio_device *device, + u32 flags, void __user *arg, + size_t argsz) +{ + size_t minsz = + offsetofend(struct vfio_device_feature_mig_state, data_fd); + struct vfio_device_feature_mig_state mig; + struct file *filp = NULL; + int ret; + + if (!device->ops->migration_set_state || + !device->ops->migration_get_state) + return -ENOTTY; + + ret = vfio_check_feature(flags, argsz, + VFIO_DEVICE_FEATURE_SET | + VFIO_DEVICE_FEATURE_GET, + sizeof(mig)); + if (ret != 1) + return ret; + + if (copy_from_user(&mig, arg, minsz)) + return -EFAULT; + + if (flags & VFIO_DEVICE_FEATURE_GET) { + enum vfio_device_mig_state curr_state; + + ret = device->ops->migration_get_state(device, &curr_state); + if (ret) + return ret; + mig.device_state = curr_state; + goto out_copy; + } + + /* Handle the VFIO_DEVICE_FEATURE_SET */ + filp = device->ops->migration_set_state(device, mig.device_state); + if (IS_ERR(filp) || !filp) + goto out_copy; + + return vfio_ioct_mig_return_fd(filp, arg, &mig); +out_copy: + mig.data_fd = -1; + if (copy_to_user(arg, &mig, sizeof(mig))) + return -EFAULT; + if (IS_ERR(filp)) + return PTR_ERR(filp); + return 0; +} + +static int vfio_ioctl_device_feature_migration(struct vfio_device *device, + u32 flags, void __user *arg, + size_t argsz) +{ + struct vfio_device_feature_migration mig = { + .flags = VFIO_MIGRATION_STOP_COPY, + }; + int ret; + + if (!device->ops->migration_set_state || + !device->ops->migration_get_state) + return -ENOTTY; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, + sizeof(mig)); + if (ret != 1) + return ret; + if (copy_to_user(arg, &mig, sizeof(mig))) + return -EFAULT; + return 0; +} + static int vfio_ioctl_device_feature(struct vfio_device *device, struct vfio_device_feature __user *arg) { @@ -1582,6 +1773,14 @@ static int vfio_ioctl_device_feature(struct vfio_device *device, return -EINVAL; switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) { + case VFIO_DEVICE_FEATURE_MIGRATION: + return vfio_ioctl_device_feature_migration( + device, feature.flags, arg->data, + feature.argsz - minsz); + case VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE: + return vfio_ioctl_device_feature_mig_device_state( + device, feature.flags, arg->data, + feature.argsz - minsz); default: if (unlikely(!device->ops->device_feature)) return -EINVAL; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 550c28f2ef60..c44e80bbbd3b 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -56,6 +56,16 @@ struct vfio_device { * match, -errno for abort (ex. match with insufficient or incorrect * additional args) * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl + * @migration_set_state: Optional callback to change the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * The returned FD is used for data transfer according to the FSM + * definition. The driver is responsible to ensure that FD reaches end + * of stream or error whenever the migration FSM leaves a data transfer + * state or before close_device() returns. + * @migration_get_state: Optional callback to get the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. */ struct vfio_device_ops { char *name; @@ -72,6 +82,11 @@ struct vfio_device_ops { int (*match)(struct vfio_device *vdev, char *buf); int (*device_feature)(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz); + struct file *(*migration_set_state)( + struct vfio_device *device, + enum vfio_device_mig_state new_state); + int (*migration_get_state)(struct vfio_device *device, + enum vfio_device_mig_state *curr_state); }; /** @@ -114,6 +129,11 @@ extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +int vfio_mig_get_next_state(struct vfio_device *device, + enum vfio_device_mig_state cur_fsm, + enum vfio_device_mig_state new_fsm, + enum vfio_device_mig_state *next_fsm); + /* * External user API */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ef33ea002b0b..22ed358c04c5 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -605,25 +605,25 @@ struct vfio_region_gfx_edid { struct vfio_device_migration_info { __u32 device_state; /* VFIO device state */ -#define VFIO_DEVICE_STATE_STOP (0) -#define VFIO_DEVICE_STATE_RUNNING (1 << 0) -#define VFIO_DEVICE_STATE_SAVING (1 << 1) -#define VFIO_DEVICE_STATE_RESUMING (1 << 2) -#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ - VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) +#define VFIO_DEVICE_STATE_V1_STOP (0) +#define VFIO_DEVICE_STATE_V1_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_V1_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_V1_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_V1_RUNNING | \ + VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) #define VFIO_DEVICE_STATE_VALID(state) \ - (state & VFIO_DEVICE_STATE_RESUMING ? \ - (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1) + (state & VFIO_DEVICE_STATE_V1_RESUMING ? \ + (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_V1_RESUMING : 1) #define VFIO_DEVICE_STATE_IS_ERROR(state) \ - ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING)) + ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING)) #define VFIO_DEVICE_STATE_SET_ERROR(state) \ - ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) __u32 reserved; __u64 pending_bytes; @@ -1002,6 +1002,154 @@ struct vfio_device_feature { */ #define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0) +/* + * Indicates the device can support the migration API through + * VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. If this GET succeeds, the RUNNING and + * ERROR states are always supported. Support for additional states is + * indicated via the flags field; at least VFIO_MIGRATION_STOP_COPY must be + * set. + * + * VFIO_MIGRATION_STOP_COPY means that STOP, STOP_COPY and + * RESUMING are supported. + */ +struct vfio_device_feature_migration { + __aligned_u64 flags; +#define VFIO_MIGRATION_STOP_COPY (1 << 0) +}; +#define VFIO_DEVICE_FEATURE_MIGRATION 1 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, execute a migration state change on the VFIO + * device. The new state is supplied in device_state, see enum + * vfio_device_mig_state for details + * + * The kernel migration driver must fully transition the device to the new state + * value before the operation returns to the user. + * + * The kernel migration driver must not generate asynchronous device state + * transitions outside of manipulation by the user or the VFIO_DEVICE_RESET + * ioctl as described above. + * + * If this function fails then current device_state may be the original + * operating state or some other state along the combination transition path. + * The user can then decide if it should execute a VFIO_DEVICE_RESET, attempt + * to return to the original state, or attempt to return to some other state + * such as RUNNING or STOP. + * + * If the new_state starts a new data transfer session then the FD associated + * with that session is returned in data_fd. The user is responsible to close + * this FD when it is finished. The user must consider the migration data stream + * carried over the FD to be opaque and must preserve the byte order of the + * stream. The user is not required to preserve buffer segmentation when writing + * the data stream during the RESUMING operation. + * + * Upon VFIO_DEVICE_FEATURE_GET, get the current migration state of the VFIO + * device, data_fd will be -1. + */ +struct vfio_device_feature_mig_state { + __u32 device_state; /* From enum vfio_device_mig_state */ + __s32 data_fd; +}; +#define VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE 2 + +/* + * The device migration Finite State Machine is described by the enum + * vfio_device_mig_state. Some of the FSM arcs will create a migration data + * transfer session by returning a FD, in this case the migration data will + * flow over the FD using read() and write() as discussed below. + * + * There are 5 states to support VFIO_MIGRATION_STOP_COPY: + * RUNNING - The device is running normally + * STOP - The device does not change the internal or external state + * STOP_COPY - The device internal state can be read out + * RESUMING - The device is stopped and is loading a new internal state + * ERROR - The device has failed and must be reset + * + * The FSM takes actions on the arcs between FSM states. The driver implements + * the following behavior for the FSM arcs: + * + * RUNNING -> STOP + * STOP_COPY -> STOP + * While in STOP the device must stop the operation of the device. The device + * must not generate interrupts, DMA, or any other change to external state. + * It must not change its internal state. When stopped the device and kernel + * migration driver must accept and respond to interaction to support external + * subsystems in the STOP state, for example PCI MSI-X and PCI config space. + * Failure by the user to restrict device access while in STOP must not result + * in error conditions outside the user context (ex. host system faults). + * + * The STOP_COPY arc will terminate a data transfer session. + * + * RESUMING -> STOP + * Leaving RESUMING terminates a data transfer session and indicates the + * device should complete processing of the data delivered by write(). The + * kernel migration driver should complete the incorporation of data written + * to the data transfer FD into the device internal state and perform + * final validity and consistency checking of the new device state. If the + * user provided data is found to be incomplete, inconsistent, or otherwise + * invalid, the migration driver must fail the SET_STATE ioctl and + * optionally go to the ERROR state as described below. + * + * While in STOP the device has the same behavior as other STOP states + * described above. + * + * To abort a RESUMING session the device must be reset. + * + * STOP -> RUNNING + * While in RUNNING the device is fully operational, the device may generate + * interrupts, DMA, respond to MMIO, all vfio device regions are functional, + * and the device may advance its internal state. + * + * STOP -> STOP_COPY + * This arc begin the process of saving the device state and will return a + * new data_fd. + * + * While in the STOP_COPY state the device has the same behavior as STOP + * with the addition that the data transfers session continues to stream the + * migration state. End of stream on the FD indicates the entire device + * state has been transferred. + * + * The user should take steps to restrict access to vfio device regions while + * the device is in STOP_COPY or risk corruption of the device migration data + * stream. + * + * STOP -> RESUMING + * Entering the RESUMING state starts a process of restoring the device state + * and will return a new data_fd. The data stream fed into the data_fd should + * be taken from the data transfer output of a single FD during saving from + * a compatible device. The migration driver may alter/reset the internal + * device state for this arc if required to prepare the device to receive the + * migration data. + * + * any -> ERROR + * ERROR cannot be specified as a device state, however any transition request + * can be failed with an errno return and may then move the device_state into + * ERROR. In this case the device was unable to execute the requested arc and + * was also unable to restore the device to any valid device_state. + * To recover from ERROR VFIO_DEVICE_RESET must be used to return the + * device_state back to RUNNING. + * + * The remaining possible transitions are interpreted as combinations of the + * above FSM arcs. As there are multiple paths through the FSM arcs the path + * should be selected based on the following rules: + * - Select the shortest path. + * Refer to vfio_mig_get_next_state() for the result of the algorithm. + * + * The automatic transit through the FSM arcs that make up the combination + * transition is invisible to the user. When working with combination arcs the + * user may see any step along the path in the device_state if SET_STATE + * fails. When handling these types of errors users should anticipate future + * revisions of this protocol using new states and those states becoming + * visible in this case. + */ +enum vfio_device_mig_state { + VFIO_DEVICE_STATE_ERROR = 0, + VFIO_DEVICE_STATE_STOP = 1, + VFIO_DEVICE_STATE_RUNNING = 2, + VFIO_DEVICE_STATE_STOP_COPY = 3, + VFIO_DEVICE_STATE_RESUMING = 4, +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit v1.2.3 From 8cb3d83b959be0631cd719b995c40c3cda21cd47 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:19 +0200 Subject: vfio: Extend the device migration protocol with RUNNING_P2P The RUNNING_P2P state is designed to support multiple devices in the same VM that are doing P2P transactions between themselves. When in RUNNING_P2P the device must be able to accept incoming P2P transactions but should not generate outgoing P2P transactions. As an optional extension to the mandatory states it is defined as in between STOP and RUNNING: STOP -> RUNNING_P2P -> RUNNING -> RUNNING_P2P -> STOP For drivers that are unable to support RUNNING_P2P the core code silently merges RUNNING_P2P and RUNNING together. Unless driver support is present, the new state cannot be used in SET_STATE. Drivers that support this will be required to implement 4 FSM arcs beyond the basic FSM. 2 of the basic FSM arcs become combination transitions. Compared to the v1 clarification, NDMA is redefined into FSM states and is described in terms of the desired P2P quiescent behavior, noting that halting all DMA is an acceptable implementation. Link: https://lore.kernel.org/all/20220224142024.147653-11-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/vfio/vfio.c | 87 +++++++++++++++++++++++++++++++++++++---------- include/linux/vfio.h | 1 + include/uapi/linux/vfio.h | 36 ++++++++++++++++++-- 3 files changed, 104 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index b37ab27b511f..a4555014bd1e 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1577,39 +1577,56 @@ int vfio_mig_get_next_state(struct vfio_device *device, enum vfio_device_mig_state new_fsm, enum vfio_device_mig_state *next_fsm) { - enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RESUMING + 1 }; + enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 }; /* - * The coding in this table requires the driver to implement 6 - * FSM arcs: + * The coding in this table requires the driver to implement the + * following FSM arcs: * RESUMING -> STOP - * RUNNING -> STOP * STOP -> RESUMING - * STOP -> RUNNING * STOP -> STOP_COPY * STOP_COPY -> STOP * - * The coding will step through multiple states for these combination - * transitions: - * RESUMING -> STOP -> RUNNING + * If P2P is supported then the driver must also implement these FSM + * arcs: + * RUNNING -> RUNNING_P2P + * RUNNING_P2P -> RUNNING + * RUNNING_P2P -> STOP + * STOP -> RUNNING_P2P + * Without P2P the driver must implement: + * RUNNING -> STOP + * STOP -> RUNNING + * + * The coding will step through multiple states for some combination + * transitions; if all optional features are supported, this means the + * following ones: + * RESUMING -> STOP -> RUNNING_P2P + * RESUMING -> STOP -> RUNNING_P2P -> RUNNING * RESUMING -> STOP -> STOP_COPY - * RUNNING -> STOP -> RESUMING - * RUNNING -> STOP -> STOP_COPY + * RUNNING -> RUNNING_P2P -> STOP + * RUNNING -> RUNNING_P2P -> STOP -> RESUMING + * RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY + * RUNNING_P2P -> STOP -> RESUMING + * RUNNING_P2P -> STOP -> STOP_COPY + * STOP -> RUNNING_P2P -> RUNNING * STOP_COPY -> STOP -> RESUMING - * STOP_COPY -> STOP -> RUNNING + * STOP_COPY -> STOP -> RUNNING_P2P + * STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING */ static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = { [VFIO_DEVICE_STATE_STOP] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, - [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_RUNNING] = { - [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, - [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, - [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_STOP_COPY] = { @@ -1617,6 +1634,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_RESUMING] = { @@ -1624,6 +1642,15 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_RUNNING_P2P] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, [VFIO_DEVICE_STATE_ERROR] = { @@ -1631,17 +1658,41 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, }; - if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table))) + static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY, + [VFIO_DEVICE_STATE_RUNNING_P2P] = + VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P, + [VFIO_DEVICE_STATE_ERROR] = ~0U, + }; + + if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table) || + (state_flags_table[cur_fsm] & device->migration_flags) != + state_flags_table[cur_fsm])) return -EINVAL; - if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table)) + if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table) || + (state_flags_table[new_fsm] & device->migration_flags) != + state_flags_table[new_fsm]) return -EINVAL; + /* + * Arcs touching optional and unsupported states are skipped over. The + * driver will instead see an arc from the original state to the next + * logical state, as per the above comment. + */ *next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm]; + while ((state_flags_table[*next_fsm] & device->migration_flags) != + state_flags_table[*next_fsm]) + *next_fsm = vfio_from_fsm_table[*next_fsm][new_fsm]; + return (*next_fsm != VFIO_DEVICE_STATE_ERROR) ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(vfio_mig_get_next_state); @@ -1731,7 +1782,7 @@ static int vfio_ioctl_device_feature_migration(struct vfio_device *device, size_t argsz) { struct vfio_device_feature_migration mig = { - .flags = VFIO_MIGRATION_STOP_COPY, + .flags = device->migration_flags, }; int ret; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index c44e80bbbd3b..66dda06ec42d 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -33,6 +33,7 @@ struct vfio_device { struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; + unsigned int migration_flags; /* Members below here are private, not for driver use */ refcount_t refcount; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 22ed358c04c5..26a66f68371d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1011,10 +1011,16 @@ struct vfio_device_feature { * * VFIO_MIGRATION_STOP_COPY means that STOP, STOP_COPY and * RESUMING are supported. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P + * is supported in addition to the STOP_COPY states. + * + * Other combinations of flags have behavior to be defined in the future. */ struct vfio_device_feature_migration { __aligned_u64 flags; #define VFIO_MIGRATION_STOP_COPY (1 << 0) +#define VFIO_MIGRATION_P2P (1 << 1) }; #define VFIO_DEVICE_FEATURE_MIGRATION 1 @@ -1065,10 +1071,13 @@ struct vfio_device_feature_mig_state { * RESUMING - The device is stopped and is loading a new internal state * ERROR - The device has failed and must be reset * + * And 1 optional state to support VFIO_MIGRATION_P2P: + * RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA + * * The FSM takes actions on the arcs between FSM states. The driver implements * the following behavior for the FSM arcs: * - * RUNNING -> STOP + * RUNNING_P2P -> STOP * STOP_COPY -> STOP * While in STOP the device must stop the operation of the device. The device * must not generate interrupts, DMA, or any other change to external state. @@ -1095,11 +1104,16 @@ struct vfio_device_feature_mig_state { * * To abort a RESUMING session the device must be reset. * - * STOP -> RUNNING + * RUNNING_P2P -> RUNNING * While in RUNNING the device is fully operational, the device may generate * interrupts, DMA, respond to MMIO, all vfio device regions are functional, * and the device may advance its internal state. * + * RUNNING -> RUNNING_P2P + * STOP -> RUNNING_P2P + * While in RUNNING_P2P the device is partially running in the P2P quiescent + * state defined below. + * * STOP -> STOP_COPY * This arc begin the process of saving the device state and will return a * new data_fd. @@ -1129,6 +1143,18 @@ struct vfio_device_feature_mig_state { * To recover from ERROR VFIO_DEVICE_RESET must be used to return the * device_state back to RUNNING. * + * The optional peer to peer (P2P) quiescent state is intended to be a quiescent + * state for the device for the purposes of managing multiple devices within a + * user context where peer-to-peer DMA between devices may be active. The + * RUNNING_P2P states must prevent the device from initiating + * any new P2P DMA transactions. If the device can identify P2P transactions + * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration + * driver must complete any such outstanding operations prior to completing the + * FSM arc into a P2P state. For the purpose of specification the states + * behave as though the device was fully running if not supported. Like while in + * STOP or STOP_COPY the user must not touch the device, otherwise the state + * can be exited. + * * The remaining possible transitions are interpreted as combinations of the * above FSM arcs. As there are multiple paths through the FSM arcs the path * should be selected based on the following rules: @@ -1141,6 +1167,11 @@ struct vfio_device_feature_mig_state { * fails. When handling these types of errors users should anticipate future * revisions of this protocol using new states and those states becoming * visible in this case. + * + * The optional states cannot be used with SET_STATE if the device does not + * support them. The user can discover if these states are supported by using + * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can + * avoid knowing about these optional states if the kernel driver supports them. */ enum vfio_device_mig_state { VFIO_DEVICE_STATE_ERROR = 0, @@ -1148,6 +1179,7 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING = 2, VFIO_DEVICE_STATE_STOP_COPY = 3, VFIO_DEVICE_STATE_RESUMING = 4, + VFIO_DEVICE_STATE_RUNNING_P2P = 5, }; /* -------- API for Type1 VFIO IOMMU -------- */ -- cgit v1.2.3 From 915076f70efad04bf6fc843970a3c7763487011a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:23 +0200 Subject: vfio/pci: Expose vfio_pci_core_aer_err_detected() Expose vfio_pci_core_aer_err_detected() to be used by drivers as part of their pci_error_handlers structure. Next patch for mlx5 driver will use it. Link: https://lore.kernel.org/all/20220224142024.147653-15-yishaih@nvidia.com Reviewed-by: Alex Williamson Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/vfio_pci_core.c | 7 ++++--- include/linux/vfio_pci_core.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 106e1970d653..e301092e94ef 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1871,8 +1871,8 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) } EXPORT_SYMBOL_GPL(vfio_pci_core_unregister_device); -static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, - pci_channel_state_t state) +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state) { struct vfio_pci_core_device *vdev; struct vfio_device *device; @@ -1894,6 +1894,7 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_CAN_RECOVER; } +EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) { @@ -1916,7 +1917,7 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); const struct pci_error_handlers vfio_pci_core_err_handlers = { - .error_detected = vfio_pci_aer_err_detected, + .error_detected = vfio_pci_core_aer_err_detected, }; EXPORT_SYMBOL_GPL(vfio_pci_core_err_handlers); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index beba0b2ed87d..9f1bf8e49d43 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -232,6 +232,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); static inline bool vfio_pci_is_vga(struct pci_dev *pdev) { -- cgit v1.2.3 From ff5812e00d5e7bdeae68784d99686eff67896931 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:54 +0000 Subject: crypto: hisilicon/qm: Move the QM header to include/linux Since we are going to introduce VFIO PCI HiSilicon ACC driver for live migration in subsequent patches, move the ACC QM header file to a common include dir. Acked-by: Zhou Wang Acked-by: Longfang Liu Acked-by: Kai Ye Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-2-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- drivers/crypto/hisilicon/hpre/hpre.h | 2 +- drivers/crypto/hisilicon/qm.c | 2 +- drivers/crypto/hisilicon/qm.h | 441 ----------------------------------- drivers/crypto/hisilicon/sec2/sec.h | 2 +- drivers/crypto/hisilicon/sgl.c | 2 +- drivers/crypto/hisilicon/zip/zip.h | 2 +- include/linux/hisi_acc_qm.h | 441 +++++++++++++++++++++++++++++++++++ 7 files changed, 446 insertions(+), 446 deletions(-) delete mode 100644 drivers/crypto/hisilicon/qm.h create mode 100644 include/linux/hisi_acc_qm.h (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h index e0b4a1982ee9..9a0558ed82f9 100644 --- a/drivers/crypto/hisilicon/hpre/hpre.h +++ b/drivers/crypto/hisilicon/hpre/hpre.h @@ -4,7 +4,7 @@ #define __HISI_HPRE_H #include -#include "../qm.h" +#include #define HPRE_SQE_SIZE sizeof(struct hpre_sqe) #define HPRE_PF_DEF_Q_NUM 64 diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index c5b84a5ea350..ed23e1d3fa27 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -15,7 +15,7 @@ #include #include #include -#include "qm.h" +#include /* eq/aeq irq enable */ #define QM_VF_AEQ_INT_SOURCE 0x0 diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h deleted file mode 100644 index 3068093229a5..000000000000 --- a/drivers/crypto/hisilicon/qm.h +++ /dev/null @@ -1,441 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2019 HiSilicon Limited. */ -#ifndef HISI_ACC_QM_H -#define HISI_ACC_QM_H - -#include -#include -#include -#include -#include - -#define QM_QNUM_V1 4096 -#define QM_QNUM_V2 1024 -#define QM_MAX_VFS_NUM_V2 63 - -/* qm user domain */ -#define QM_ARUSER_M_CFG_1 0x100088 -#define AXUSER_SNOOP_ENABLE BIT(30) -#define AXUSER_CMD_TYPE GENMASK(14, 12) -#define AXUSER_CMD_SMMU_NORMAL 1 -#define AXUSER_NS BIT(6) -#define AXUSER_NO BIT(5) -#define AXUSER_FP BIT(4) -#define AXUSER_SSV BIT(0) -#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ - FIELD_PREP(AXUSER_CMD_TYPE, \ - AXUSER_CMD_SMMU_NORMAL) | \ - AXUSER_NS | AXUSER_NO | AXUSER_FP) -#define QM_ARUSER_M_CFG_ENABLE 0x100090 -#define ARUSER_M_CFG_ENABLE 0xfffffffe -#define QM_AWUSER_M_CFG_1 0x100098 -#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 -#define AWUSER_M_CFG_ENABLE 0xfffffffe -#define QM_WUSER_M_CFG_ENABLE 0x1000a8 -#define WUSER_M_CFG_ENABLE 0xffffffff - -/* qm cache */ -#define QM_CACHE_CTL 0x100050 -#define SQC_CACHE_ENABLE BIT(0) -#define CQC_CACHE_ENABLE BIT(1) -#define SQC_CACHE_WB_ENABLE BIT(4) -#define SQC_CACHE_WB_THRD GENMASK(10, 5) -#define CQC_CACHE_WB_ENABLE BIT(11) -#define CQC_CACHE_WB_THRD GENMASK(17, 12) -#define QM_AXI_M_CFG 0x1000ac -#define AXI_M_CFG 0xffff -#define QM_AXI_M_CFG_ENABLE 0x1000b0 -#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 -#define AXI_M_CFG_ENABLE 0xffffffff -#define QM_PEH_AXUSER_CFG 0x1000cc -#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 -#define PEH_AXUSER_CFG 0x401001 -#define PEH_AXUSER_CFG_ENABLE 0xffffffff - -#define QM_AXI_RRESP BIT(0) -#define QM_AXI_BRESP BIT(1) -#define QM_ECC_MBIT BIT(2) -#define QM_ECC_1BIT BIT(3) -#define QM_ACC_GET_TASK_TIMEOUT BIT(4) -#define QM_ACC_DO_TASK_TIMEOUT BIT(5) -#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) -#define QM_SQ_CQ_VF_INVALID BIT(7) -#define QM_CQ_VF_INVALID BIT(8) -#define QM_SQ_VF_INVALID BIT(9) -#define QM_DB_TIMEOUT BIT(10) -#define QM_OF_FIFO_OF BIT(11) -#define QM_DB_RANDOM_INVALID BIT(12) -#define QM_MAILBOX_TIMEOUT BIT(13) -#define QM_FLR_TIMEOUT BIT(14) - -#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ - QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ - QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ - QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) -#define QM_BASE_CE QM_ECC_1BIT - -#define QM_Q_DEPTH 1024 -#define QM_MIN_QNUM 2 -#define HISI_ACC_SGL_SGE_NR_MAX 255 -#define QM_SHAPER_CFG 0x100164 -#define QM_SHAPER_ENABLE BIT(30) -#define QM_SHAPER_TYPE1_OFFSET 10 - -/* page number for queue file region */ -#define QM_DOORBELL_PAGE_NR 1 - -/* uacce mode of the driver */ -#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ -#define UACCE_MODE_SVA 1 /* use uacce sva mode */ -#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" - -enum qm_stop_reason { - QM_NORMAL, - QM_SOFT_RESET, - QM_FLR, -}; - -enum qm_state { - QM_INIT = 0, - QM_START, - QM_CLOSE, - QM_STOP, -}; - -enum qp_state { - QP_INIT = 1, - QP_START, - QP_STOP, - QP_CLOSE, -}; - -enum qm_hw_ver { - QM_HW_UNKNOWN = -1, - QM_HW_V1 = 0x20, - QM_HW_V2 = 0x21, - QM_HW_V3 = 0x30, -}; - -enum qm_fun_type { - QM_HW_PF, - QM_HW_VF, -}; - -enum qm_debug_file { - CURRENT_QM, - CURRENT_Q, - CLEAR_ENABLE, - DEBUG_FILE_NUM, -}; - -struct qm_dfx { - atomic64_t err_irq_cnt; - atomic64_t aeq_irq_cnt; - atomic64_t abnormal_irq_cnt; - atomic64_t create_qp_err_cnt; - atomic64_t mb_err_cnt; -}; - -struct debugfs_file { - enum qm_debug_file index; - struct mutex lock; - struct qm_debug *debug; -}; - -struct qm_debug { - u32 curr_qm_qp_num; - u32 sqe_mask_offset; - u32 sqe_mask_len; - struct qm_dfx dfx; - struct dentry *debug_root; - struct dentry *qm_d; - struct debugfs_file files[DEBUG_FILE_NUM]; -}; - -struct qm_shaper_factor { - u32 func_qos; - u64 cir_b; - u64 cir_u; - u64 cir_s; - u64 cbs_s; -}; - -struct qm_dma { - void *va; - dma_addr_t dma; - size_t size; -}; - -struct hisi_qm_status { - u32 eq_head; - bool eqc_phase; - u32 aeq_head; - bool aeqc_phase; - atomic_t flags; - int stop_reason; -}; - -struct hisi_qm; - -struct hisi_qm_err_info { - char *acpi_rst; - u32 msi_wr_port; - u32 ecc_2bits_mask; - u32 dev_ce_mask; - u32 ce; - u32 nfe; - u32 fe; -}; - -struct hisi_qm_err_status { - u32 is_qm_ecc_mbit; - u32 is_dev_ecc_mbit; -}; - -struct hisi_qm_err_ini { - int (*hw_init)(struct hisi_qm *qm); - void (*hw_err_enable)(struct hisi_qm *qm); - void (*hw_err_disable)(struct hisi_qm *qm); - u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); - void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); - void (*open_axi_master_ooo)(struct hisi_qm *qm); - void (*close_axi_master_ooo)(struct hisi_qm *qm); - void (*open_sva_prefetch)(struct hisi_qm *qm); - void (*close_sva_prefetch)(struct hisi_qm *qm); - void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); - void (*err_info_init)(struct hisi_qm *qm); -}; - -struct hisi_qm_list { - struct mutex lock; - struct list_head list; - int (*register_to_crypto)(struct hisi_qm *qm); - void (*unregister_from_crypto)(struct hisi_qm *qm); -}; - -struct hisi_qm { - enum qm_hw_ver ver; - enum qm_fun_type fun_type; - const char *dev_name; - struct pci_dev *pdev; - void __iomem *io_base; - void __iomem *db_io_base; - u32 sqe_size; - u32 qp_base; - u32 qp_num; - u32 qp_in_used; - u32 ctrl_qp_num; - u32 max_qp_num; - u32 vfs_num; - u32 db_interval; - struct list_head list; - struct hisi_qm_list *qm_list; - - struct qm_dma qdma; - struct qm_sqc *sqc; - struct qm_cqc *cqc; - struct qm_eqe *eqe; - struct qm_aeqe *aeqe; - dma_addr_t sqc_dma; - dma_addr_t cqc_dma; - dma_addr_t eqe_dma; - dma_addr_t aeqe_dma; - - struct hisi_qm_status status; - const struct hisi_qm_err_ini *err_ini; - struct hisi_qm_err_info err_info; - struct hisi_qm_err_status err_status; - unsigned long misc_ctl; /* driver removing and reset sched */ - - struct rw_semaphore qps_lock; - struct idr qp_idr; - struct hisi_qp *qp_array; - - struct mutex mailbox_lock; - - const struct hisi_qm_hw_ops *ops; - - struct qm_debug debug; - - u32 error_mask; - - struct workqueue_struct *wq; - struct work_struct work; - struct work_struct rst_work; - struct work_struct cmd_process; - - const char *algs; - bool use_sva; - bool is_frozen; - - /* doorbell isolation enable */ - bool use_db_isolation; - resource_size_t phys_base; - resource_size_t db_phys_base; - struct uacce_device *uacce; - int mode; - struct qm_shaper_factor *factor; - u32 mb_qos; - u32 type_rate; -}; - -struct hisi_qp_status { - atomic_t used; - u16 sq_tail; - u16 cq_head; - bool cqc_phase; - atomic_t flags; -}; - -struct hisi_qp_ops { - int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); -}; - -struct hisi_qp { - u32 qp_id; - u8 alg_type; - u8 req_type; - - struct qm_dma qdma; - void *sqe; - struct qm_cqe *cqe; - dma_addr_t sqe_dma; - dma_addr_t cqe_dma; - - struct hisi_qp_status qp_status; - struct hisi_qp_ops *hw_ops; - void *qp_ctx; - void (*req_cb)(struct hisi_qp *qp, void *data); - void (*event_cb)(struct hisi_qp *qp); - - struct hisi_qm *qm; - bool is_resetting; - bool is_in_kernel; - u16 pasid; - struct uacce_queue *uacce_q; -}; - -static inline int q_num_set(const char *val, const struct kernel_param *kp, - unsigned int device) -{ - struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, - device, NULL); - u32 n, q_num; - int ret; - - if (!val) - return -EINVAL; - - if (!pdev) { - q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); - pr_info("No device found currently, suppose queue number is %u\n", - q_num); - } else { - if (pdev->revision == QM_HW_V1) - q_num = QM_QNUM_V1; - else - q_num = QM_QNUM_V2; - } - - ret = kstrtou32(val, 10, &n); - if (ret || n < QM_MIN_QNUM || n > q_num) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int vfs_num_set(const char *val, const struct kernel_param *kp) -{ - u32 n; - int ret; - - if (!val) - return -EINVAL; - - ret = kstrtou32(val, 10, &n); - if (ret < 0) - return ret; - - if (n > QM_MAX_VFS_NUM_V2) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int mode_set(const char *val, const struct kernel_param *kp) -{ - u32 n; - int ret; - - if (!val) - return -EINVAL; - - ret = kstrtou32(val, 10, &n); - if (ret != 0 || (n != UACCE_MODE_SVA && - n != UACCE_MODE_NOUACCE)) - return -EINVAL; - - return param_set_int(val, kp); -} - -static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) -{ - return mode_set(val, kp); -} - -static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) -{ - INIT_LIST_HEAD(&qm_list->list); - mutex_init(&qm_list->lock); -} - -int hisi_qm_init(struct hisi_qm *qm); -void hisi_qm_uninit(struct hisi_qm *qm); -int hisi_qm_start(struct hisi_qm *qm); -int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); -struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); -int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); -int hisi_qm_stop_qp(struct hisi_qp *qp); -void hisi_qm_release_qp(struct hisi_qp *qp); -int hisi_qp_send(struct hisi_qp *qp, const void *msg); -int hisi_qm_get_free_qp_num(struct hisi_qm *qm); -int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); -void hisi_qm_debug_init(struct hisi_qm *qm); -enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); -void hisi_qm_debug_regs_clear(struct hisi_qm *qm); -int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); -int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); -void hisi_qm_dev_err_init(struct hisi_qm *qm); -void hisi_qm_dev_err_uninit(struct hisi_qm *qm); -pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, - pci_channel_state_t state); -pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); -void hisi_qm_reset_prepare(struct pci_dev *pdev); -void hisi_qm_reset_done(struct pci_dev *pdev); - -struct hisi_acc_sgl_pool; -struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, - struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, - u32 index, dma_addr_t *hw_sgl_dma); -void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, - struct hisi_acc_hw_sgl *hw_sgl); -struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, - u32 count, u32 sge_nr); -void hisi_acc_free_sgl_pool(struct device *dev, - struct hisi_acc_sgl_pool *pool); -int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, - u8 alg_type, int node, struct hisi_qp **qps); -void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); -void hisi_qm_dev_shutdown(struct pci_dev *pdev); -void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); -int hisi_qm_resume(struct device *dev); -int hisi_qm_suspend(struct device *dev); -void hisi_qm_pm_uninit(struct hisi_qm *qm); -void hisi_qm_pm_init(struct hisi_qm *qm); -int hisi_qm_get_dfx_access(struct hisi_qm *qm); -void hisi_qm_put_dfx_access(struct hisi_qm *qm); -void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); -#endif diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index d97cf02b1df7..c2e9b01187a7 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -4,7 +4,7 @@ #ifndef __HISI_SEC_V2_H #define __HISI_SEC_V2_H -#include "../qm.h" +#include #include "sec_crypto.h" /* Algorithm resource per hardware SEC queue */ diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 057273769f26..f7efc02b065f 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 HiSilicon Limited. */ #include +#include #include #include -#include "qm.h" #define HISI_ACC_SGL_SGE_NR_MIN 1 #define HISI_ACC_SGL_NR_MAX 256 diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h index 517fdbdff3ea..3dfd3bac5a33 100644 --- a/drivers/crypto/hisilicon/zip/zip.h +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -7,7 +7,7 @@ #define pr_fmt(fmt) "hisi_zip: " fmt #include -#include "../qm.h" +#include enum hisi_zip_error_type { /* negative compression */ diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h new file mode 100644 index 000000000000..3068093229a5 --- /dev/null +++ b/include/linux/hisi_acc_qm.h @@ -0,0 +1,441 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include +#include +#include +#include +#include + +#define QM_QNUM_V1 4096 +#define QM_QNUM_V2 1024 +#define QM_MAX_VFS_NUM_V2 63 + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define AXUSER_SNOOP_ENABLE BIT(30) +#define AXUSER_CMD_TYPE GENMASK(14, 12) +#define AXUSER_CMD_SMMU_NORMAL 1 +#define AXUSER_NS BIT(6) +#define AXUSER_NO BIT(5) +#define AXUSER_FP BIT(4) +#define AXUSER_SSV BIT(0) +#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ + FIELD_PREP(AXUSER_CMD_TYPE, \ + AXUSER_CMD_SMMU_NORMAL) | \ + AXUSER_NS | AXUSER_NO | AXUSER_FP) +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define ARUSER_M_CFG_ENABLE 0xfffffffe +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define AWUSER_M_CFG_ENABLE 0xfffffffe +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 +#define WUSER_M_CFG_ENABLE 0xffffffff + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define SQC_CACHE_ENABLE BIT(0) +#define CQC_CACHE_ENABLE BIT(1) +#define SQC_CACHE_WB_ENABLE BIT(4) +#define SQC_CACHE_WB_THRD GENMASK(10, 5) +#define CQC_CACHE_WB_ENABLE BIT(11) +#define CQC_CACHE_WB_THRD GENMASK(17, 12) +#define QM_AXI_M_CFG 0x1000ac +#define AXI_M_CFG 0xffff +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 +#define AXI_M_CFG_ENABLE 0xffffffff +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 +#define PEH_AXUSER_CFG 0x401001 +#define PEH_AXUSER_CFG_ENABLE 0xffffffff + +#define QM_AXI_RRESP BIT(0) +#define QM_AXI_BRESP BIT(1) +#define QM_ECC_MBIT BIT(2) +#define QM_ECC_1BIT BIT(3) +#define QM_ACC_GET_TASK_TIMEOUT BIT(4) +#define QM_ACC_DO_TASK_TIMEOUT BIT(5) +#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) +#define QM_SQ_CQ_VF_INVALID BIT(7) +#define QM_CQ_VF_INVALID BIT(8) +#define QM_SQ_VF_INVALID BIT(9) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) +#define QM_DB_RANDOM_INVALID BIT(12) +#define QM_MAILBOX_TIMEOUT BIT(13) +#define QM_FLR_TIMEOUT BIT(14) + +#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ + QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ + QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ + QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) +#define QM_BASE_CE QM_ECC_1BIT + +#define QM_Q_DEPTH 1024 +#define QM_MIN_QNUM 2 +#define HISI_ACC_SGL_SGE_NR_MAX 255 +#define QM_SHAPER_CFG 0x100164 +#define QM_SHAPER_ENABLE BIT(30) +#define QM_SHAPER_TYPE1_OFFSET 10 + +/* page number for queue file region */ +#define QM_DOORBELL_PAGE_NR 1 + +/* uacce mode of the driver */ +#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ +#define UACCE_MODE_SVA 1 /* use uacce sva mode */ +#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" + +enum qm_stop_reason { + QM_NORMAL, + QM_SOFT_RESET, + QM_FLR, +}; + +enum qm_state { + QM_INIT = 0, + QM_START, + QM_CLOSE, + QM_STOP, +}; + +enum qp_state { + QP_INIT = 1, + QP_START, + QP_STOP, + QP_CLOSE, +}; + +enum qm_hw_ver { + QM_HW_UNKNOWN = -1, + QM_HW_V1 = 0x20, + QM_HW_V2 = 0x21, + QM_HW_V3 = 0x30, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_QM, + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +struct qm_dfx { + atomic64_t err_irq_cnt; + atomic64_t aeq_irq_cnt; + atomic64_t abnormal_irq_cnt; + atomic64_t create_qp_err_cnt; + atomic64_t mb_err_cnt; +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + u32 curr_qm_qp_num; + u32 sqe_mask_offset; + u32 sqe_mask_len; + struct qm_dfx dfx; + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; +}; + +struct qm_shaper_factor { + u32 func_qos; + u64 cir_b; + u64 cir_u; + u64 cir_s; + u64 cbs_s; +}; + +struct qm_dma { + void *va; + dma_addr_t dma; + size_t size; +}; + +struct hisi_qm_status { + u32 eq_head; + bool eqc_phase; + u32 aeq_head; + bool aeqc_phase; + atomic_t flags; + int stop_reason; +}; + +struct hisi_qm; + +struct hisi_qm_err_info { + char *acpi_rst; + u32 msi_wr_port; + u32 ecc_2bits_mask; + u32 dev_ce_mask; + u32 ce; + u32 nfe; + u32 fe; +}; + +struct hisi_qm_err_status { + u32 is_qm_ecc_mbit; + u32 is_dev_ecc_mbit; +}; + +struct hisi_qm_err_ini { + int (*hw_init)(struct hisi_qm *qm); + void (*hw_err_enable)(struct hisi_qm *qm); + void (*hw_err_disable)(struct hisi_qm *qm); + u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); + void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); + void (*open_axi_master_ooo)(struct hisi_qm *qm); + void (*close_axi_master_ooo)(struct hisi_qm *qm); + void (*open_sva_prefetch)(struct hisi_qm *qm); + void (*close_sva_prefetch)(struct hisi_qm *qm); + void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*err_info_init)(struct hisi_qm *qm); +}; + +struct hisi_qm_list { + struct mutex lock; + struct list_head list; + int (*register_to_crypto)(struct hisi_qm *qm); + void (*unregister_from_crypto)(struct hisi_qm *qm); +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + void __iomem *db_io_base; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + u32 qp_in_used; + u32 ctrl_qp_num; + u32 max_qp_num; + u32 vfs_num; + u32 db_interval; + struct list_head list; + struct hisi_qm_list *qm_list; + + struct qm_dma qdma; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + struct qm_eqe *eqe; + struct qm_aeqe *aeqe; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + dma_addr_t eqe_dma; + dma_addr_t aeqe_dma; + + struct hisi_qm_status status; + const struct hisi_qm_err_ini *err_ini; + struct hisi_qm_err_info err_info; + struct hisi_qm_err_status err_status; + unsigned long misc_ctl; /* driver removing and reset sched */ + + struct rw_semaphore qps_lock; + struct idr qp_idr; + struct hisi_qp *qp_array; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + + struct workqueue_struct *wq; + struct work_struct work; + struct work_struct rst_work; + struct work_struct cmd_process; + + const char *algs; + bool use_sva; + bool is_frozen; + + /* doorbell isolation enable */ + bool use_db_isolation; + resource_size_t phys_base; + resource_size_t db_phys_base; + struct uacce_device *uacce; + int mode; + struct qm_shaper_factor *factor; + u32 mb_qos; + u32 type_rate; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 cq_head; + bool cqc_phase; + atomic_t flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u8 alg_type; + u8 req_type; + + struct qm_dma qdma; + void *sqe; + struct qm_cqe *cqe; + dma_addr_t sqe_dma; + dma_addr_t cqe_dma; + + struct hisi_qp_status qp_status; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + void (*event_cb)(struct hisi_qp *qp); + + struct hisi_qm *qm; + bool is_resetting; + bool is_in_kernel; + u16 pasid; + struct uacce_queue *uacce_q; +}; + +static inline int q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, + device, NULL); + u32 n, q_num; + int ret; + + if (!val) + return -EINVAL; + + if (!pdev) { + q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); + pr_info("No device found currently, suppose queue number is %u\n", + q_num); + } else { + if (pdev->revision == QM_HW_V1) + q_num = QM_QNUM_V1; + else + q_num = QM_QNUM_V2; + } + + ret = kstrtou32(val, 10, &n); + if (ret || n < QM_MIN_QNUM || n > q_num) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int vfs_num_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret < 0) + return ret; + + if (n > QM_MAX_VFS_NUM_V2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int mode_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != UACCE_MODE_SVA && + n != UACCE_MODE_NOUACCE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) +{ + return mode_set(val, kp); +} + +static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) +{ + INIT_LIST_HEAD(&qm_list->list); + mutex_init(&qm_list->lock); +} + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_release_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, const void *msg); +int hisi_qm_get_free_qp_num(struct hisi_qm *qm); +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); +void hisi_qm_debug_init(struct hisi_qm *qm); +enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); +void hisi_qm_debug_regs_clear(struct hisi_qm *qm); +int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); +int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); +int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); +void hisi_qm_dev_err_init(struct hisi_qm *qm); +void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); +pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); +void hisi_qm_reset_prepare(struct pci_dev *pdev); +void hisi_qm_reset_done(struct pci_dev *pdev); + +struct hisi_acc_sgl_pool; +struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma); +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl); +struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, + u32 count, u32 sge_nr); +void hisi_acc_free_sgl_pool(struct device *dev, + struct hisi_acc_sgl_pool *pool); +int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, + u8 alg_type, int node, struct hisi_qp **qps); +void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); +void hisi_qm_dev_shutdown(struct pci_dev *pdev); +void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_resume(struct device *dev); +int hisi_qm_suspend(struct device *dev); +void hisi_qm_pm_uninit(struct hisi_qm *qm); +void hisi_qm_pm_init(struct hisi_qm *qm); +int hisi_qm_get_dfx_access(struct hisi_qm *qm); +void hisi_qm_put_dfx_access(struct hisi_qm *qm); +void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); +#endif -- cgit v1.2.3 From b4b084d7133284e29777ca445e001186259602d4 Mon Sep 17 00:00:00 2001 From: Longfang Liu Date: Tue, 8 Mar 2022 18:48:55 +0000 Subject: crypto: hisilicon/qm: Move few definitions to common header Move Doorbell and Mailbox definitions to common header file. Also export QM mailbox functions. This will be useful when we introduce VFIO PCI HiSilicon ACC live migration driver. Signed-off-by: Longfang Liu Acked-by: Zhou Wang Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-3-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- drivers/crypto/hisilicon/qm.c | 58 ++++++++++++++----------------------------- include/linux/hisi_acc_qm.h | 38 ++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index ed23e1d3fa27..c88e013371af 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -33,23 +33,6 @@ #define QM_ABNORMAL_EVENT_IRQ_VECTOR 3 /* mailbox */ -#define QM_MB_CMD_SQC 0x0 -#define QM_MB_CMD_CQC 0x1 -#define QM_MB_CMD_EQC 0x2 -#define QM_MB_CMD_AEQC 0x3 -#define QM_MB_CMD_SQC_BT 0x4 -#define QM_MB_CMD_CQC_BT 0x5 -#define QM_MB_CMD_SQC_VFT_V2 0x6 -#define QM_MB_CMD_STOP_QP 0x8 -#define QM_MB_CMD_SRC 0xc -#define QM_MB_CMD_DST 0xd - -#define QM_MB_CMD_SEND_BASE 0x300 -#define QM_MB_EVENT_SHIFT 8 -#define QM_MB_BUSY_SHIFT 13 -#define QM_MB_OP_SHIFT 14 -#define QM_MB_CMD_DATA_ADDR_L 0x304 -#define QM_MB_CMD_DATA_ADDR_H 0x308 #define QM_MB_PING_ALL_VFS 0xffff #define QM_MB_CMD_DATA_SHIFT 32 #define QM_MB_CMD_DATA_MASK GENMASK(31, 0) @@ -103,19 +86,12 @@ #define QM_DB_CMD_SHIFT_V1 16 #define QM_DB_INDEX_SHIFT_V1 32 #define QM_DB_PRIORITY_SHIFT_V1 48 -#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 -#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 #define QM_QUE_ISO_CFG_V 0x0030 #define QM_PAGE_SIZE 0x0034 #define QM_QUE_ISO_EN 0x100154 #define QM_CAPBILITY 0x100158 #define QM_QP_NUN_MASK GENMASK(10, 0) #define QM_QP_DB_INTERVAL 0x10000 -#define QM_QP_MAX_NUM_SHIFT 11 -#define QM_DB_CMD_SHIFT_V2 12 -#define QM_DB_RAND_SHIFT_V2 16 -#define QM_DB_INDEX_SHIFT_V2 32 -#define QM_DB_PRIORITY_SHIFT_V2 48 #define QM_MEM_START_INIT 0x100040 #define QM_MEM_INIT_DONE 0x100044 @@ -693,7 +669,7 @@ static void qm_mb_pre_init(struct qm_mailbox *mailbox, u8 cmd, } /* return 0 mailbox ready, -ETIMEDOUT hardware timeout */ -static int qm_wait_mb_ready(struct hisi_qm *qm) +int hisi_qm_wait_mb_ready(struct hisi_qm *qm) { u32 val; @@ -701,6 +677,7 @@ static int qm_wait_mb_ready(struct hisi_qm *qm) val, !((val >> QM_MB_BUSY_SHIFT) & 0x1), POLL_PERIOD, POLL_TIMEOUT); } +EXPORT_SYMBOL_GPL(hisi_qm_wait_mb_ready); /* 128 bit should be written to hardware at one time to trigger a mailbox */ static void qm_mb_write(struct hisi_qm *qm, const void *src) @@ -726,14 +703,14 @@ static void qm_mb_write(struct hisi_qm *qm, const void *src) static int qm_mb_nolock(struct hisi_qm *qm, struct qm_mailbox *mailbox) { - if (unlikely(qm_wait_mb_ready(qm))) { + if (unlikely(hisi_qm_wait_mb_ready(qm))) { dev_err(&qm->pdev->dev, "QM mailbox is busy to start!\n"); goto mb_busy; } qm_mb_write(qm, mailbox); - if (unlikely(qm_wait_mb_ready(qm))) { + if (unlikely(hisi_qm_wait_mb_ready(qm))) { dev_err(&qm->pdev->dev, "QM mailbox operation timeout!\n"); goto mb_busy; } @@ -745,8 +722,8 @@ mb_busy: return -EBUSY; } -static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, - bool op) +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op) { struct qm_mailbox mailbox; int ret; @@ -762,6 +739,7 @@ static int qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, return ret; } +EXPORT_SYMBOL_GPL(hisi_qm_mb); static void qm_db_v1(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) { @@ -1351,7 +1329,7 @@ static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) u64 sqc_vft; int ret; - ret = qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_VFT_V2, 0, 0, 1); if (ret) return ret; @@ -1725,12 +1703,12 @@ static int dump_show(struct hisi_qm *qm, void *info, static int qm_dump_sqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id) { - return qm_mb(qm, QM_MB_CMD_SQC, dma_addr, qp_id, 1); + return hisi_qm_mb(qm, QM_MB_CMD_SQC, dma_addr, qp_id, 1); } static int qm_dump_cqc_raw(struct hisi_qm *qm, dma_addr_t dma_addr, u16 qp_id) { - return qm_mb(qm, QM_MB_CMD_CQC, dma_addr, qp_id, 1); + return hisi_qm_mb(qm, QM_MB_CMD_CQC, dma_addr, qp_id, 1); } static int qm_sqc_dump(struct hisi_qm *qm, const char *s) @@ -1842,7 +1820,7 @@ static int qm_eqc_aeqc_dump(struct hisi_qm *qm, char *s, size_t size, if (IS_ERR(xeqc)) return PTR_ERR(xeqc); - ret = qm_mb(qm, cmd, xeqc_dma, 0, 1); + ret = hisi_qm_mb(qm, cmd, xeqc_dma, 0, 1); if (ret) goto err_free_ctx; @@ -2495,7 +2473,7 @@ unlock: static int qm_stop_qp(struct hisi_qp *qp) { - return qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0); + return hisi_qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0); } static int qm_set_msi(struct hisi_qm *qm, bool set) @@ -2763,7 +2741,7 @@ static int qm_sq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC, sqc_dma, qp_id, 0); dma_unmap_single(dev, sqc_dma, sizeof(struct qm_sqc), DMA_TO_DEVICE); kfree(sqc); @@ -2804,7 +2782,7 @@ static int qm_cq_ctx_cfg(struct hisi_qp *qp, int qp_id, u32 pasid) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_CQC, cqc_dma, qp_id, 0); dma_unmap_single(dev, cqc_dma, sizeof(struct qm_cqc), DMA_TO_DEVICE); kfree(cqc); @@ -3655,7 +3633,7 @@ static int qm_eq_ctx_cfg(struct hisi_qm *qm) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_EQC, eqc_dma, 0, 0); dma_unmap_single(dev, eqc_dma, sizeof(struct qm_eqc), DMA_TO_DEVICE); kfree(eqc); @@ -3684,7 +3662,7 @@ static int qm_aeq_ctx_cfg(struct hisi_qm *qm) return -ENOMEM; } - ret = qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_AEQC, aeqc_dma, 0, 0); dma_unmap_single(dev, aeqc_dma, sizeof(struct qm_aeqc), DMA_TO_DEVICE); kfree(aeqc); @@ -3723,11 +3701,11 @@ static int __hisi_qm_start(struct hisi_qm *qm) if (ret) return ret; - ret = qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_SQC_BT, qm->sqc_dma, 0, 0); if (ret) return ret; - ret = qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc_dma, 0, 0); + ret = hisi_qm_mb(qm, QM_MB_CMD_CQC_BT, qm->cqc_dma, 0, 0); if (ret) return ret; diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 3068093229a5..6a6477c34666 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -34,6 +34,40 @@ #define QM_WUSER_M_CFG_ENABLE 0x1000a8 #define WUSER_M_CFG_ENABLE 0xffffffff +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 +#define QM_MB_CMD_STOP_QP 0x8 +#define QM_MB_CMD_SRC 0xc +#define QM_MB_CMD_DST 0xd + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 +#define QM_MB_MAX_WAIT_CNT 6000 + +/* doorbell */ +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_QP_MAX_NUM_SHIFT 11 +#define QM_DB_CMD_SHIFT_V2 12 +#define QM_DB_RAND_SHIFT_V2 16 +#define QM_DB_INDEX_SHIFT_V2 32 +#define QM_DB_PRIORITY_SHIFT_V2 48 + /* qm cache */ #define QM_CACHE_CTL 0x100050 #define SQC_CACHE_ENABLE BIT(0) @@ -414,6 +448,10 @@ pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); void hisi_qm_reset_prepare(struct pci_dev *pdev); void hisi_qm_reset_done(struct pci_dev *pdev); +int hisi_qm_wait_mb_ready(struct hisi_qm *qm); +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op); + struct hisi_acc_sgl_pool; struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, -- cgit v1.2.3 From fae74feacd2dfb6172c4862fc760f969a991c06f Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:56 +0000 Subject: hisi_acc_qm: Move VF PCI device IDs to common header Move the PCI Device IDs of HiSilicon ACC VF devices to a common header and also use a uniform naming convention. This will be useful when we introduce the vfio PCI HiSilicon ACC live migration driver in subsequent patches. Cc: Bjorn Helgaas Acked-by: Zhou Wang Acked-by: Longfang Liu Acked-by: Kai Ye Signed-off-by: Shameer Kolothum Acked-by: Bjorn Helgaas # pci_ids.h Link: https://lore.kernel.org/r/20220308184902.2242-4-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- drivers/crypto/hisilicon/hpre/hpre_main.c | 13 ++++++------- drivers/crypto/hisilicon/sec2/sec_main.c | 15 +++++++-------- drivers/crypto/hisilicon/zip/zip_main.c | 11 +++++------ include/linux/pci_ids.h | 3 +++ 4 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index ebfab3e14499..3589d8879b5e 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -68,8 +68,7 @@ #define HPRE_REG_RD_INTVRL_US 10 #define HPRE_REG_RD_TMOUT_US 1000 #define HPRE_DBGFS_VAL_MAX_LEN 20 -#define HPRE_PCI_DEVICE_ID 0xa258 -#define HPRE_PCI_VF_DEVICE_ID 0xa259 +#define PCI_DEVICE_ID_HUAWEI_HPRE_PF 0xa258 #define HPRE_QM_USR_CFG_MASK GENMASK(31, 1) #define HPRE_QM_AXI_CFG_MASK GENMASK(15, 0) #define HPRE_QM_VFG_AX_MASK GENMASK(7, 0) @@ -111,8 +110,8 @@ static const char hpre_name[] = "hisi_hpre"; static struct dentry *hpre_debugfs_root; static const struct pci_device_id hpre_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_DEVICE_ID) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, HPRE_PCI_VF_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_HPRE_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_HPRE_VF) }, { 0, } }; @@ -242,7 +241,7 @@ MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static int pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, HPRE_PCI_DEVICE_ID); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_HPRE_PF); } static const struct kernel_param_ops hpre_pf_q_num_ops = { @@ -921,7 +920,7 @@ static int hpre_debugfs_init(struct hisi_qm *qm) qm->debug.sqe_mask_len = HPRE_SQE_MASK_LEN; hisi_qm_debug_init(qm); - if (qm->pdev->device == HPRE_PCI_DEVICE_ID) { + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_HPRE_PF) { ret = hpre_ctrl_debug_init(qm); if (ret) goto failed_to_create; @@ -958,7 +957,7 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HPRE_SQE_SIZE; qm->dev_name = hpre_name; - qm->fun_type = (pdev->device == HPRE_PCI_DEVICE_ID) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_HPRE_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = HPRE_PF_DEF_Q_BASE; diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 26d3ab1d308b..311a8747b5bf 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -20,8 +20,7 @@ #define SEC_VF_NUM 63 #define SEC_QUEUE_NUM_V1 4096 -#define SEC_PF_PCI_DEVICE_ID 0xa255 -#define SEC_VF_PCI_DEVICE_ID 0xa256 +#define PCI_DEVICE_ID_HUAWEI_SEC_PF 0xa255 #define SEC_BD_ERR_CHK_EN0 0xEFFFFFFF #define SEC_BD_ERR_CHK_EN1 0x7ffff7fd @@ -225,7 +224,7 @@ static const struct debugfs_reg32 sec_dfx_regs[] = { static int sec_pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, SEC_PF_PCI_DEVICE_ID); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_SEC_PF); } static const struct kernel_param_ops sec_pf_q_num_ops = { @@ -313,8 +312,8 @@ module_param_cb(uacce_mode, &sec_uacce_mode_ops, &uacce_mode, 0444); MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static const struct pci_device_id sec_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_PF_PCI_DEVICE_ID) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, SEC_VF_PCI_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_SEC_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_SEC_VF) }, { 0, } }; MODULE_DEVICE_TABLE(pci, sec_dev_ids); @@ -717,7 +716,7 @@ static int sec_core_debug_init(struct hisi_qm *qm) regset->base = qm->io_base; regset->dev = dev; - if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) debugfs_create_file("regs", 0444, tmp_d, regset, &sec_regs_fops); for (i = 0; i < ARRAY_SIZE(sec_dfx_labels); i++) { @@ -735,7 +734,7 @@ static int sec_debug_init(struct hisi_qm *qm) struct sec_dev *sec = container_of(qm, struct sec_dev, qm); int i; - if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) { + if (qm->pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) { for (i = SEC_CLEAR_ENABLE; i < SEC_DEBUG_FILE_NUM; i++) { spin_lock_init(&sec->debug.files[i].lock); sec->debug.files[i].index = i; @@ -877,7 +876,7 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; - qm->fun_type = (pdev->device == SEC_PF_PCI_DEVICE_ID) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_SEC_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = SEC_PF_DEF_Q_BASE; diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 678f8b58ec42..66decfe07282 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -15,8 +15,7 @@ #include #include "zip.h" -#define PCI_DEVICE_ID_ZIP_PF 0xa250 -#define PCI_DEVICE_ID_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_ZIP_PF 0xa250 #define HZIP_QUEUE_NUM_V1 4096 @@ -246,7 +245,7 @@ MODULE_PARM_DESC(uacce_mode, UACCE_MODE_DESC); static int pf_q_num_set(const char *val, const struct kernel_param *kp) { - return q_num_set(val, kp, PCI_DEVICE_ID_ZIP_PF); + return q_num_set(val, kp, PCI_DEVICE_ID_HUAWEI_ZIP_PF); } static const struct kernel_param_ops pf_q_num_ops = { @@ -268,8 +267,8 @@ module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444); MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); static const struct pci_device_id hisi_zip_dev_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_PF) }, - { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_ZIP_VF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_ZIP_PF) }, + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, PCI_DEVICE_ID_HUAWEI_ZIP_VF) }, { 0, } }; MODULE_DEVICE_TABLE(pci, hisi_zip_dev_ids); @@ -838,7 +837,7 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->sqe_size = HZIP_SQE_SIZE; qm->dev_name = hisi_zip_name; - qm->fun_type = (pdev->device == PCI_DEVICE_ID_ZIP_PF) ? + qm->fun_type = (pdev->device == PCI_DEVICE_ID_HUAWEI_ZIP_PF) ? QM_HW_PF : QM_HW_VF; if (qm->fun_type == QM_HW_PF) { qm->qp_base = HZIP_PF_DEF_Q_BASE; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index aad54c666407..31dee2b65a62 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2529,6 +2529,9 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff #define PCI_VENDOR_ID_HUAWEI 0x19e5 +#define PCI_DEVICE_ID_HUAWEI_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_SEC_VF 0xa256 +#define PCI_DEVICE_ID_HUAWEI_HPRE_VF 0xa259 #define PCI_VENDOR_ID_NETRONOME 0x19ee #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 -- cgit v1.2.3 From 442fbc099b839551f8576723da22c1269cc695ce Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:59 +0000 Subject: hisi_acc_vfio_pci: Add helper to retrieve the struct pci_driver struct pci_driver pointer is an input into the pci_iov_get_pf_drvdata(). Introduce helpers to retrieve the ACC PF dev struct pci_driver pointers as we use this in ACC vfio migration driver. Acked-by: Zhou Wang Acked-by: Kai Ye Acked-by: Longfang Liu Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-7-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- drivers/crypto/hisilicon/hpre/hpre_main.c | 6 ++++++ drivers/crypto/hisilicon/sec2/sec_main.c | 6 ++++++ drivers/crypto/hisilicon/zip/zip_main.c | 6 ++++++ include/linux/hisi_acc_qm.h | 5 +++++ 4 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 3589d8879b5e..36ab30e9e654 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -1190,6 +1190,12 @@ static struct pci_driver hpre_pci_driver = { .driver.pm = &hpre_pm_ops, }; +struct pci_driver *hisi_hpre_get_pf_driver(void) +{ + return &hpre_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_hpre_get_pf_driver); + static void hpre_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 311a8747b5bf..421a405ca337 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -1088,6 +1088,12 @@ static struct pci_driver sec_pci_driver = { .driver.pm = &sec_pm_ops, }; +struct pci_driver *hisi_sec_get_pf_driver(void) +{ + return &sec_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_sec_get_pf_driver); + static void sec_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 66decfe07282..4534e1e107d1 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -1012,6 +1012,12 @@ static struct pci_driver hisi_zip_pci_driver = { .driver.pm = &hisi_zip_pm_ops, }; +struct pci_driver *hisi_zip_get_pf_driver(void) +{ + return &hisi_zip_pci_driver; +} +EXPORT_SYMBOL_GPL(hisi_zip_get_pf_driver); + static void hisi_zip_register_debugfs(void) { if (!debugfs_initialized()) diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 6a6477c34666..00f2a4db8723 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -476,4 +476,9 @@ void hisi_qm_pm_init(struct hisi_qm *qm); int hisi_qm_get_dfx_access(struct hisi_qm *qm); void hisi_qm_put_dfx_access(struct hisi_qm *qm); void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); + +/* Used by VFIO ACC live migration driver */ +struct pci_driver *hisi_sec_get_pf_driver(void); +struct pci_driver *hisi_hpre_get_pf_driver(void); +struct pci_driver *hisi_zip_get_pf_driver(void); #endif -- cgit v1.2.3 From 1e459b25081d4f939b8a1fb4c71dab0cec8f974a Mon Sep 17 00:00:00 2001 From: Longfang Liu Date: Tue, 8 Mar 2022 18:49:00 +0000 Subject: crypto: hisilicon/qm: Set the VF QM state register We use VF QM state register to record the status of the QM configuration state. This will be used in the ACC migration driver to determine whether we can safely save and restore the QM data. Signed-off-by: Longfang Liu Acked-by: Zhou Wang Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-8-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- drivers/crypto/hisilicon/qm.c | 8 ++++++++ include/linux/hisi_acc_qm.h | 6 ++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index c88e013371af..6a8776db38b5 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3492,6 +3492,12 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) pci_disable_device(pdev); } +static void hisi_qm_set_state(struct hisi_qm *qm, u8 state) +{ + if (qm->ver > QM_HW_V2 && qm->fun_type == QM_HW_VF) + writel(state, qm->io_base + QM_VF_STATE); +} + /** * hisi_qm_uninit() - Uninitialize qm. * @qm: The qm needed uninit. @@ -3520,6 +3526,7 @@ void hisi_qm_uninit(struct hisi_qm *qm) dma_free_coherent(dev, qm->qdma.size, qm->qdma.va, qm->qdma.dma); } + hisi_qm_set_state(qm, QM_NOT_READY); up_write(&qm->qps_lock); qm_irq_unregister(qm); @@ -3745,6 +3752,7 @@ int hisi_qm_start(struct hisi_qm *qm) if (!ret) atomic_set(&qm->status.flags, QM_START); + hisi_qm_set_state(qm, QM_READY); err_unlock: up_write(&qm->qps_lock); return ret; diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 00f2a4db8723..177f7b7cd414 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -67,6 +67,7 @@ #define QM_DB_RAND_SHIFT_V2 16 #define QM_DB_INDEX_SHIFT_V2 32 #define QM_DB_PRIORITY_SHIFT_V2 48 +#define QM_VF_STATE 0x60 /* qm cache */ #define QM_CACHE_CTL 0x100050 @@ -162,6 +163,11 @@ enum qm_debug_file { DEBUG_FILE_NUM, }; +enum qm_vf_state { + QM_READY = 0, + QM_NOT_READY, +}; + struct qm_dfx { atomic64_t err_irq_cnt; atomic64_t aeq_irq_cnt; -- cgit v1.2.3