mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-17 17:24:17 +08:00
f9f8345674
NPU devices are emulated in firmware and mainly used for NPU NVLink training; one NPU device is per a hardware link. Their DMA/TCE setup must match the GPU which is connected via PCIe and NVLink so any changes to the DMA/TCE setup on the GPU PCIe device need to be propagated to the NVLink device as this is what device drivers expect and it doesn't make much sense to do anything else. This makes NPU DMA setup explicit. pnv_npu_ioda_controller_ops::pnv_npu_dma_set_mask is moved to pci-ioda, made static and prints warning as dma_set_mask() should never be called on this function as in any case it will not configure GPU; so we make this explicit. Instead of using PNV_IODA_PE_PEER and peers[] (which the next patch will remove), we test every PCI device if there are corresponding NVLink devices. If there are any, we propagate bypass mode to just found NPU devices by calling the setup helper directly (which takes @bypass) and avoid guessing (i.e. calculating from DMA mask) whether we need bypass or not on NPU devices. Since DMA setup happens in very rare occasion, this will not slow down booting or VFIO start/stop much. This renames pnv_npu_disable_bypass to pnv_npu_dma_set_32 to make it more clear what the function really does which is programming 32bit table address to the TVT ("disabling bypass" means writing zeroes to the TVT). This removes pnv_npu_dma_set_bypass() from pnv_npu_ioda_fixup() as the DMA configuration on NPU does not matter until dma_set_mask() is called on GPU and that will do the NPU DMA configuration. This removes phb->dma_dev_setup initialization for NPU as pnv_pci_ioda_dma_dev_setup is no-op for it anyway. This stops using npe->tce_bypass_base as it never changes and values other than zero are not supported. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Alistair Popple <alistair@popple.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
227 lines
6.6 KiB
C
227 lines
6.6 KiB
C
#ifndef __POWERNV_PCI_H
|
|
#define __POWERNV_PCI_H
|
|
|
|
struct pci_dn;
|
|
|
|
enum pnv_phb_type {
|
|
PNV_PHB_IODA1 = 0,
|
|
PNV_PHB_IODA2 = 1,
|
|
PNV_PHB_NPU = 2,
|
|
};
|
|
|
|
/* Precise PHB model for error management */
|
|
enum pnv_phb_model {
|
|
PNV_PHB_MODEL_UNKNOWN,
|
|
PNV_PHB_MODEL_P7IOC,
|
|
PNV_PHB_MODEL_PHB3,
|
|
PNV_PHB_MODEL_NPU,
|
|
};
|
|
|
|
#define PNV_PCI_DIAG_BUF_SIZE 8192
|
|
#define PNV_IODA_PE_DEV (1 << 0) /* PE has single PCI device */
|
|
#define PNV_IODA_PE_BUS (1 << 1) /* PE has primary PCI bus */
|
|
#define PNV_IODA_PE_BUS_ALL (1 << 2) /* PE has subordinate buses */
|
|
#define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */
|
|
#define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */
|
|
#define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */
|
|
#define PNV_IODA_PE_PEER (1 << 6) /* PE has peers */
|
|
|
|
/* Data associated with a PE, including IOMMU tracking etc.. */
|
|
struct pnv_phb;
|
|
struct pnv_ioda_pe {
|
|
unsigned long flags;
|
|
struct pnv_phb *phb;
|
|
|
|
#define PNV_IODA_MAX_PEER_PES 8
|
|
struct pnv_ioda_pe *peers[PNV_IODA_MAX_PEER_PES];
|
|
|
|
/* A PE can be associated with a single device or an
|
|
* entire bus (& children). In the former case, pdev
|
|
* is populated, in the later case, pbus is.
|
|
*/
|
|
#ifdef CONFIG_PCI_IOV
|
|
struct pci_dev *parent_dev;
|
|
#endif
|
|
struct pci_dev *pdev;
|
|
struct pci_bus *pbus;
|
|
|
|
/* Effective RID (device RID for a device PE and base bus
|
|
* RID with devfn 0 for a bus PE)
|
|
*/
|
|
unsigned int rid;
|
|
|
|
/* PE number */
|
|
unsigned int pe_number;
|
|
|
|
/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
|
|
struct iommu_table_group table_group;
|
|
|
|
/* 64-bit TCE bypass region */
|
|
bool tce_bypass_enabled;
|
|
uint64_t tce_bypass_base;
|
|
|
|
/* MSIs. MVE index is identical for for 32 and 64 bit MSI
|
|
* and -1 if not supported. (It's actually identical to the
|
|
* PE number)
|
|
*/
|
|
int mve_number;
|
|
|
|
/* PEs in compound case */
|
|
struct pnv_ioda_pe *master;
|
|
struct list_head slaves;
|
|
|
|
/* Link in list of PE#s */
|
|
struct list_head list;
|
|
};
|
|
|
|
#define PNV_PHB_FLAG_EEH (1 << 0)
|
|
|
|
struct pnv_phb {
|
|
struct pci_controller *hose;
|
|
enum pnv_phb_type type;
|
|
enum pnv_phb_model model;
|
|
u64 hub_id;
|
|
u64 opal_id;
|
|
int flags;
|
|
void __iomem *regs;
|
|
int initialized;
|
|
spinlock_t lock;
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
int has_dbgfs;
|
|
struct dentry *dbgfs;
|
|
#endif
|
|
|
|
#ifdef CONFIG_PCI_MSI
|
|
unsigned int msi_base;
|
|
unsigned int msi32_support;
|
|
struct msi_bitmap msi_bmp;
|
|
#endif
|
|
int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
|
|
unsigned int hwirq, unsigned int virq,
|
|
unsigned int is_64, struct msi_msg *msg);
|
|
void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
|
|
void (*fixup_phb)(struct pci_controller *hose);
|
|
int (*init_m64)(struct pnv_phb *phb);
|
|
void (*reserve_m64_pe)(struct pci_bus *bus,
|
|
unsigned long *pe_bitmap, bool all);
|
|
struct pnv_ioda_pe *(*pick_m64_pe)(struct pci_bus *bus, bool all);
|
|
int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
|
|
void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
|
|
int (*unfreeze_pe)(struct pnv_phb *phb, int pe_no, int opt);
|
|
|
|
struct {
|
|
/* Global bridge info */
|
|
unsigned int total_pe_num;
|
|
unsigned int reserved_pe_idx;
|
|
|
|
/* 32-bit MMIO window */
|
|
unsigned int m32_size;
|
|
unsigned int m32_segsize;
|
|
unsigned int m32_pci_base;
|
|
|
|
/* 64-bit MMIO window */
|
|
unsigned int m64_bar_idx;
|
|
unsigned long m64_size;
|
|
unsigned long m64_segsize;
|
|
unsigned long m64_base;
|
|
unsigned long m64_bar_alloc;
|
|
|
|
/* IO ports */
|
|
unsigned int io_size;
|
|
unsigned int io_segsize;
|
|
unsigned int io_pci_base;
|
|
|
|
/* PE allocation */
|
|
struct mutex pe_alloc_mutex;
|
|
unsigned long *pe_alloc;
|
|
struct pnv_ioda_pe *pe_array;
|
|
|
|
/* M32 & IO segment maps */
|
|
unsigned int *m64_segmap;
|
|
unsigned int *m32_segmap;
|
|
unsigned int *io_segmap;
|
|
|
|
/* DMA32 segment maps - IODA1 only */
|
|
unsigned int dma32_count;
|
|
unsigned int *dma32_segmap;
|
|
|
|
/* IRQ chip */
|
|
int irq_chip_init;
|
|
struct irq_chip irq_chip;
|
|
|
|
/* Sorted list of used PE's based
|
|
* on the sequence of creation
|
|
*/
|
|
struct list_head pe_list;
|
|
struct mutex pe_list_mutex;
|
|
|
|
/* Reverse map of PEs, will have to extend if
|
|
* we are to support more than 256 PEs, indexed
|
|
* bus { bus, devfn }
|
|
*/
|
|
unsigned char pe_rmap[0x10000];
|
|
|
|
/* TCE cache invalidate registers (physical and
|
|
* remapped)
|
|
*/
|
|
phys_addr_t tce_inval_reg_phys;
|
|
__be64 __iomem *tce_inval_reg;
|
|
} ioda;
|
|
|
|
/* PHB and hub status structure */
|
|
union {
|
|
unsigned char blob[PNV_PCI_DIAG_BUF_SIZE];
|
|
struct OpalIoP7IOCPhbErrorData p7ioc;
|
|
struct OpalIoPhb3ErrorData phb3;
|
|
struct OpalIoP7IOCErrorData hub_diag;
|
|
} diag;
|
|
|
|
};
|
|
|
|
extern struct pci_ops pnv_pci_ops;
|
|
extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
|
|
unsigned long uaddr, enum dma_data_direction direction,
|
|
struct dma_attrs *attrs);
|
|
extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages);
|
|
extern int pnv_tce_xchg(struct iommu_table *tbl, long index,
|
|
unsigned long *hpa, enum dma_data_direction *direction);
|
|
extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);
|
|
|
|
void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
|
|
unsigned char *log_buff);
|
|
int pnv_pci_cfg_read(struct pci_dn *pdn,
|
|
int where, int size, u32 *val);
|
|
int pnv_pci_cfg_write(struct pci_dn *pdn,
|
|
int where, int size, u32 val);
|
|
extern struct iommu_table *pnv_pci_table_alloc(int nid);
|
|
|
|
extern long pnv_pci_link_table_and_group(int node, int num,
|
|
struct iommu_table *tbl,
|
|
struct iommu_table_group *table_group);
|
|
extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
|
|
struct iommu_table_group *table_group);
|
|
extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
|
|
void *tce_mem, u64 tce_size,
|
|
u64 dma_offset, unsigned page_shift);
|
|
extern void pnv_pci_init_ioda_hub(struct device_node *np);
|
|
extern void pnv_pci_init_ioda2_phb(struct device_node *np);
|
|
extern void pnv_pci_init_npu_phb(struct device_node *np);
|
|
extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
|
|
__be64 *startp, __be64 *endp, bool rm);
|
|
extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
|
|
extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
|
|
|
|
extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
|
|
extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
|
|
extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
|
|
extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
|
|
|
|
/* Nvlink functions */
|
|
extern void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe);
|
|
extern void pnv_npu_setup_dma_pe(struct pnv_ioda_pe *npe);
|
|
extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
|
|
extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
|
|
|
|
#endif /* __POWERNV_PCI_H */
|