[Deepin-Kernel-SIG] [linux 6.6-y] [Upstream] [Intel] Intel: Backport to support QuickAssist Technology(QAT) live migration for in-tree driver

MAINTAINERS

@@ -22742,6 +22742,14 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/platform/
 
+VFIO QAT PCI DRIVER
+M:	Xin Zeng <xin.zeng@intel.com>
+M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
+L:	kvm@vger.kernel.org
+L:	qat-linux@intel.com
+S:	Supported
+F:	drivers/vfio/pci/qat/
+
 VGA_SWITCHEROO
 R:	Lukas Wunner <lukas@wunner.de>
 S:	Maintained

drivers/crypto/intel/qat/qat_420xx/adf_420xx_hw_data.c

@@ -10,12 +10,14 @@
 #include <adf_fw_config.h>
 #include <adf_gen4_config.h>
 #include <adf_gen4_dc.h>
+#include <adf_gen4_hw_csr_data.h>
 #include <adf_gen4_hw_data.h>
 #include <adf_gen4_pfvf.h>
 #include <adf_gen4_pm.h>
 #include <adf_gen4_ras.h>
 #include <adf_gen4_timer.h>
 #include <adf_gen4_tl.h>
+#include <adf_gen4_vf_mig.h>
 #include "adf_420xx_hw_data.h"
 #include "icp_qat_hw.h"
 
@@ -296,7 +298,7 @@ static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
 	if (adf_gen4_init_thd2arb_map(accel_dev))
 		dev_warn(&GET_DEV(accel_dev),
-			 "Generate of the thread to arbiter map failed");
+			 "Failed to generate thread to arbiter mapping");
 
 	return GET_HW_DATA(accel_dev)->thd_to_arb_map;
 }
@@ -487,6 +489,7 @@ void adf_init_hw_data_420xx(struct adf_hw_device_data *hw_data, u32 dev_id)
 	adf_gen4_init_dc_ops(&hw_data->dc_ops);
 	adf_gen4_init_ras_ops(&hw_data->ras_ops);
 	adf_gen4_init_tl_data(&hw_data->tl_data);
+	adf_gen4_init_vf_mig_ops(&hw_data->vfmig_ops);
 	adf_init_rl_data(&hw_data->rl_data);
 }
 

drivers/crypto/intel/qat/qat_4xxx/adf_4xxx_hw_data.c

@@ -10,12 +10,14 @@
 #include <adf_fw_config.h>
 #include <adf_gen4_config.h>
 #include <adf_gen4_dc.h>
+#include <adf_gen4_hw_csr_data.h>
 #include <adf_gen4_hw_data.h>
 #include <adf_gen4_pfvf.h>
 #include <adf_gen4_pm.h>
 #include "adf_gen4_ras.h"
 #include <adf_gen4_timer.h>
 #include <adf_gen4_tl.h>
+#include <adf_gen4_vf_mig.h>
 #include "adf_4xxx_hw_data.h"
 #include "icp_qat_hw.h"
 
@@ -208,7 +210,7 @@ static const u32 *adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev)
 {
 	if (adf_gen4_init_thd2arb_map(accel_dev))
 		dev_warn(&GET_DEV(accel_dev),
-			 "Generate of the thread to arbiter map failed");
+			 "Failed to generate thread to arbiter mapping");
 
 	return GET_HW_DATA(accel_dev)->thd_to_arb_map;
 }
@@ -454,6 +456,8 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 	hw_data->get_ring_to_svc_map = adf_gen4_get_ring_to_svc_map;
 	hw_data->disable_iov = adf_disable_sriov;
 	hw_data->ring_pair_reset = adf_gen4_ring_pair_reset;
+	hw_data->bank_state_save = adf_gen4_bank_state_save;
+	hw_data->bank_state_restore = adf_gen4_bank_state_restore;
 	hw_data->enable_pm = adf_gen4_enable_pm;
 	hw_data->handle_pm_interrupt = adf_gen4_handle_pm_interrupt;
 	hw_data->dev_config = adf_gen4_dev_config;
@@ -469,6 +473,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data, u32 dev_id)
 	adf_gen4_init_dc_ops(&hw_data->dc_ops);
 	adf_gen4_init_ras_ops(&hw_data->ras_ops);
 	adf_gen4_init_tl_data(&hw_data->tl_data);
+	adf_gen4_init_vf_mig_ops(&hw_data->vfmig_ops);
 	adf_init_rl_data(&hw_data->rl_data);
 }
 

drivers/crypto/intel/qat/qat_c3xxx/adf_c3xxx_hw_data.c

@@ -6,6 +6,7 @@
 #include <adf_common_drv.h>
 #include <adf_gen2_config.h>
 #include <adf_gen2_dc.h>
+#include <adf_gen2_hw_csr_data.h>
 #include <adf_gen2_hw_data.h>
 #include <adf_gen2_pfvf.h>
 #include "adf_c3xxx_hw_data.h"

drivers/crypto/intel/qat/qat_c3xxxvf/adf_c3xxxvf_hw_data.c

@@ -4,6 +4,7 @@
 #include <adf_common_drv.h>
 #include <adf_gen2_config.h>
 #include <adf_gen2_dc.h>
+#include <adf_gen2_hw_csr_data.h>
 #include <adf_gen2_hw_data.h>
 #include <adf_gen2_pfvf.h>
 #include <adf_pfvf_vf_msg.h>

drivers/crypto/intel/qat/qat_c62x/adf_c62x_hw_data.c

@@ -6,6 +6,7 @@
 #include <adf_common_drv.h>
 #include <adf_gen2_config.h>
 #include <adf_gen2_dc.h>
+#include <adf_gen2_hw_csr_data.h>
 #include <adf_gen2_hw_data.h>
 #include <adf_gen2_pfvf.h>
 #include "adf_c62x_hw_data.h"

drivers/crypto/intel/qat/qat_c62xvf/adf_c62xvf_hw_data.c

@@ -4,6 +4,7 @@
 #include <adf_common_drv.h>
 #include <adf_gen2_config.h>
 #include <adf_gen2_dc.h>
+#include <adf_gen2_hw_csr_data.h>
 #include <adf_gen2_hw_data.h>
 #include <adf_gen2_pfvf.h>
 #include <adf_pfvf_vf_msg.h>

drivers/crypto/intel/qat/qat_common/Makefile

@@ -14,16 +14,20 @@ intel_qat-objs := adf_cfg.o \
 	adf_hw_arbiter.o \
 	adf_sysfs.o \
 	adf_sysfs_ras_counters.o \
+	adf_gen2_hw_csr_data.o \
 	adf_gen2_hw_data.o \
 	adf_gen2_config.o \
 	adf_gen4_config.o \
+	adf_gen4_hw_csr_data.o \
 	adf_gen4_hw_data.o \
+	adf_gen4_vf_mig.o \
 	adf_gen4_pm.o \
 	adf_gen2_dc.o \
 	adf_gen4_dc.o \
 	adf_gen4_ras.o \
 	adf_gen4_timer.o \
 	adf_clock.o \
+	adf_mstate_mgr.o \
 	qat_crypto.o \
 	qat_compression.o \
 	qat_comp_algs.o \
@@ -52,6 +56,6 @@ intel_qat-$(CONFIG_DEBUG_FS) += adf_transport_debug.o \
 intel_qat-$(CONFIG_PCI_IOV) += adf_sriov.o adf_vf_isr.o adf_pfvf_utils.o \
 			       adf_pfvf_pf_msg.o adf_pfvf_pf_proto.o \
 			       adf_pfvf_vf_msg.o adf_pfvf_vf_proto.o \
-			       adf_gen2_pfvf.o adf_gen4_pfvf.o
+			       adf_gen2_pfvf.o adf_gen4_pfvf.o qat_mig_dev.o
 
 intel_qat-$(CONFIG_CRYPTO_DEV_QAT_ERROR_INJECTION) += adf_heartbeat_inject.o

drivers/crypto/intel/qat/qat_common/adf_accel_devices.h

@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/ratelimit.h>
 #include <linux/types.h>
+#include <linux/qat/qat_mig_dev.h>
 #include "adf_cfg_common.h"
 #include "adf_rl.h"
 #include "adf_telemetry.h"
@@ -140,6 +141,40 @@ struct admin_info {
 	u32 mailbox_offset;
 };
 
+struct ring_config {
+	u64 base;
+	u32 config;
+	u32 head;
+	u32 tail;
+	u32 reserved0;
+};
+
+struct bank_state {
+	u32 ringstat0;
+	u32 ringstat1;
+	u32 ringuostat;
+	u32 ringestat;
+	u32 ringnestat;
+	u32 ringnfstat;
+	u32 ringfstat;
+	u32 ringcstat0;
+	u32 ringcstat1;
+	u32 ringcstat2;
+	u32 ringcstat3;
+	u32 iaintflagen;
+	u32 iaintflagreg;
+	u32 iaintflagsrcsel0;
+	u32 iaintflagsrcsel1;
+	u32 iaintcolen;
+	u32 iaintcolctl;
+	u32 iaintflagandcolen;
+	u32 ringexpstat;
+	u32 ringexpintenable;
+	u32 ringsrvarben;
+	u32 reserved0;
+	struct ring_config rings[ADF_ETR_MAX_RINGS_PER_BANK];
+};
+
 struct adf_hw_csr_ops {
 	u64 (*build_csr_ring_base_addr)(dma_addr_t addr, u32 size);
 	u32 (*read_csr_ring_head)(void __iomem *csr_base_addr, u32 bank,
@@ -150,22 +185,49 @@ struct adf_hw_csr_ops {
 				  u32 ring);
 	void (*write_csr_ring_tail)(void __iomem *csr_base_addr, u32 bank,
 				    u32 ring, u32 value);
+	u32 (*read_csr_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_uo_stat)(void __iomem *csr_base_addr, u32 bank);
 	u32 (*read_csr_e_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_ne_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_nf_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_f_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_c_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_exp_stat)(void __iomem *csr_base_addr, u32 bank);
+	u32 (*read_csr_exp_int_en)(void __iomem *csr_base_addr, u32 bank);
+	void (*write_csr_exp_int_en)(void __iomem *csr_base_addr, u32 bank,
+				     u32 value);
+	u32 (*read_csr_ring_config)(void __iomem *csr_base_addr, u32 bank,
+				    u32 ring);
 	void (*write_csr_ring_config)(void __iomem *csr_base_addr, u32 bank,
 				      u32 ring, u32 value);
+	dma_addr_t (*read_csr_ring_base)(void __iomem *csr_base_addr, u32 bank,
+					 u32 ring);
 	void (*write_csr_ring_base)(void __iomem *csr_base_addr, u32 bank,
 				    u32 ring, dma_addr_t addr);
+	u32 (*read_csr_int_en)(void __iomem *csr_base_addr, u32 bank);
+	void (*write_csr_int_en)(void __iomem *csr_base_addr, u32 bank,
+				 u32 value);
+	u32 (*read_csr_int_flag)(void __iomem *csr_base_addr, u32 bank);
 	void (*write_csr_int_flag)(void __iomem *csr_base_addr, u32 bank,
 				   u32 value);
+	u32 (*read_csr_int_srcsel)(void __iomem *csr_base_addr, u32 bank);
 	void (*write_csr_int_srcsel)(void __iomem *csr_base_addr, u32 bank);
+	void (*write_csr_int_srcsel_w_val)(void __iomem *csr_base_addr,
+					   u32 bank, u32 value);
+	u32 (*read_csr_int_col_en)(void __iomem *csr_base_addr, u32 bank);
 	void (*write_csr_int_col_en)(void __iomem *csr_base_addr, u32 bank,
 				     u32 value);
+	u32 (*read_csr_int_col_ctl)(void __iomem *csr_base_addr, u32 bank);
 	void (*write_csr_int_col_ctl)(void __iomem *csr_base_addr, u32 bank,
 				      u32 value);
+	u32 (*read_csr_int_flag_and_col)(void __iomem *csr_base_addr,
+					 u32 bank);
 	void (*write_csr_int_flag_and_col)(void __iomem *csr_base_addr,
 					   u32 bank, u32 value);
+	u32 (*read_csr_ring_srv_arb_en)(void __iomem *csr_base_addr, u32 bank);
 	void (*write_csr_ring_srv_arb_en)(void __iomem *csr_base_addr, u32 bank,
 					  u32 value);
+	u32 (*get_int_col_ctl_enable_mask)(void);
 };
 
 struct adf_cfg_device_data;
@@ -197,6 +259,20 @@ struct adf_dc_ops {
 	void (*build_deflate_ctx)(void *ctx);
 };
 
+struct qat_migdev_ops {
+	int (*init)(struct qat_mig_dev *mdev);
+	void (*cleanup)(struct qat_mig_dev *mdev);
+	void (*reset)(struct qat_mig_dev *mdev);
+	int (*open)(struct qat_mig_dev *mdev);
+	void (*close)(struct qat_mig_dev *mdev);
+	int (*suspend)(struct qat_mig_dev *mdev);
+	int (*resume)(struct qat_mig_dev *mdev);
+	int (*save_state)(struct qat_mig_dev *mdev);
+	int (*save_setup)(struct qat_mig_dev *mdev);
+	int (*load_state)(struct qat_mig_dev *mdev);
+	int (*load_setup)(struct qat_mig_dev *mdev, int size);
+};
+
 struct adf_dev_err_mask {
 	u32 cppagentcmdpar_mask;
 	u32 parerr_ath_cph_mask;
@@ -244,6 +320,10 @@ struct adf_hw_device_data {
 	void (*enable_ints)(struct adf_accel_dev *accel_dev);
 	void (*set_ssm_wdtimer)(struct adf_accel_dev *accel_dev);
 	int (*ring_pair_reset)(struct adf_accel_dev *accel_dev, u32 bank_nr);
+	int (*bank_state_save)(struct adf_accel_dev *accel_dev, u32 bank_number,
+			       struct bank_state *state);
+	int (*bank_state_restore)(struct adf_accel_dev *accel_dev,
+				  u32 bank_number, struct bank_state *state);
 	void (*reset_device)(struct adf_accel_dev *accel_dev);
 	void (*set_msix_rttable)(struct adf_accel_dev *accel_dev);
 	const char *(*uof_get_name)(struct adf_accel_dev *accel_dev, u32 obj_num);
@@ -260,6 +340,7 @@ struct adf_hw_device_data {
 	struct adf_dev_err_mask dev_err_mask;
 	struct adf_rl_hw_data rl_data;
 	struct adf_tl_hw_data tl_data;
+	struct qat_migdev_ops vfmig_ops;
 	const char *fw_name;
 	const char *fw_mmp_name;
 	u32 fuses;
@@ -316,6 +397,7 @@ struct adf_hw_device_data {
 #define GET_CSR_OPS(accel_dev) (&(accel_dev)->hw_device->csr_ops)
 #define GET_PFVF_OPS(accel_dev) (&(accel_dev)->hw_device->pfvf_ops)
 #define GET_DC_OPS(accel_dev) (&(accel_dev)->hw_device->dc_ops)
+#define GET_VFMIG_OPS(accel_dev) (&(accel_dev)->hw_device->vfmig_ops)
 #define GET_TL_DATA(accel_dev) GET_HW_DATA(accel_dev)->tl_data
 #define accel_to_pci_dev(accel_ptr) accel_ptr->accel_pci_dev.pci_dev
 
@@ -330,11 +412,17 @@ struct adf_fw_loader_data {
 struct adf_accel_vf_info {
 	struct adf_accel_dev *accel_dev;
 	struct mutex pf2vf_lock; /* protect CSR access for PF2VF messages */
+	struct mutex pfvf_mig_lock; /* protects PFVF state for migration */
 	struct ratelimit_state vf2pf_ratelimit;
 	u32 vf_nr;
 	bool init;
 	bool restarting;
 	u8 vf_compat_ver;
+	/*
+	 * Private area used for device migration.
+	 * Memory allocation and free is managed by migration driver.
+	 */
+	void *mig_priv;
 };
 
 struct adf_dc_data {

drivers/crypto/intel/qat/qat_common/adf_common_drv.h

@@ -248,6 +248,16 @@ static inline void __iomem *adf_get_pmisc_base(struct adf_accel_dev *accel_dev)
 	return pmisc->virt_addr;
 }
 
+static inline void __iomem *adf_get_etr_base(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *etr;
+
+	etr = &GET_BARS(accel_dev)[hw_data->get_etr_bar_id(hw_data)];
+
+	return etr->virt_addr;
+}
+
 static inline void __iomem *adf_get_aram_base(struct adf_accel_dev *accel_dev)
 {
 	struct adf_hw_device_data *hw_data = accel_dev->hw_device;