mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 17:36:25 +07:00
5b0e2cb020
Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, William A. Kennington III. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJaDXGuAAoJEFHr6jzI4aWAEqwP/0TA35KFAK6wqfkCf67z4q+O I+5piI4eDV4jdCakfoIN1JfjhQRULNePSoCHTccan30mu/bm30p69xtOLL2/h5xH Mhz/eDBAOo0lrT20nyZfYMW3FnM66wnNf++qJ0O+8L052r4WOB02J0k1uM1ST01D 5Lb5mUoxRLRzCgKRYAYWJifn+IFPUB9NMsvMTym94krAFlIjIzMEQXhDoln+jJMr QmY5f1BTA/fLfXobn0zwoc/C1oa2PUtxd+rxbwGrLoZ6G843mMqUi90SMr5ybhXp RzepnBTj4by3vOsnk/X1mANyaZfLsunp75FwnjHdPzKrAS/TuPp8D/iSxxE/PzEq cLwJFBnFXSgQMefDErXxhHSDz2dAg5r14rsTpDcq2Ko8TPV4rPsuSfmbd9Txekb0 yWHsjoJUBBMl2QcWqIHl+AlV8j1RklF6solcTBcGnH1CZJMfa05VKXV7xGEvOHa0 RJ+/xPyR9KjoB/SUp++9Vmx/M6SwQYFOJlr3Zpg9LNtR8WpoPYu1E6eO+u1Hhzny eJqaNstH+i+VdY9eqszkAsEBh8o9M/+b+7Wx7TetvU+v368CbXtgFYs9qy2oZjPF t9sY/BHaHZ8eZ7I00an77a0fVV5B1PVASUtIz5CqkwGpMvX6Z6W2K/XUUFI61kuu E06HS6Ht8UPJAzrAPUMl =Rq81 -----END PGP SIGNATURE----- Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux Pull powerpc updates from Michael Ellerman: "A bit of a small release, I suspect in part due to me travelling for KS. But my backlog of patches to review is smaller than usual, so I think in part folks just didn't send as much this cycle. Non-highlights: - Five fixes for the >128T address space handling, both to fix bugs in our implementation and to bring the semantics exactly into line with x86. Highlights: - Support for a new OPAL call on bare metal machines which gives us a true NMI (ie. is not masked by MSR[EE]=0) for debugging etc. - Support for Power9 DD2 in the CXL driver. - Improvements to machine check handling so that uncorrectable errors can be reported into the generic memory_failure() machinery. - Some fixes and improvements for VPHN, which is used under PowerVM to notify the Linux partition of topology changes. - Plumbing to enable TM (transactional memory) without suspend on some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND). - Support for emulating vector loads form cache-inhibited memory, on some Power9 revisions. - Disable the fast-endian switch "syscall" by default (behind a CONFIG), we believe it has never had any users. - A major rework of the API drivers use when initiating and waiting for long running operations performed by OPAL firmware, and changes to the powernv_flash driver to use the new API. - Several fixes for the handling of FP/VMX/VSX while processes are using transactional memory. - Optimisations of TLB range flushes when using the radix MMU on Power9. - Improvements to the VAS facility used to access coprocessors on Power9, and related improvements to the way the NX crypto driver handles requests. - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit. Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard, Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven, Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley, Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu, Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee, Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A. Kennington III" * tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits) powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature powerpc/64s: Fix masking of SRR1 bits on instruction fault powerpc/64s: mm_context.addr_limit is only used on hash powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary powerpc/64s/hash: Fix fork() with 512TB process address space powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation powerpc/64s/hash: Fix 512T hint detection to use >= 128T powerpc: Fix DABR match on hash based systems powerpc/signal: Properly handle return value from uprobe_deny_signal() powerpc/fadump: use kstrtoint to handle sysfs store powerpc/lib: Implement UACCESS_FLUSHCACHE API powerpc/lib: Implement PMEM API powerpc/powernv/npu: Don't explicitly flush nmmu tlb powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm() powerpc/powernv/idle: Round up latency and residency values powerpc/kprobes: refactor kprobe_lookup_name for safer string operations powerpc/kprobes: Blacklist emulate_update_regs() from kprobes powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace powerpc/kprobes: Disable preemption before invoking probe handler for optprobes ...
274 lines
8.3 KiB
C
274 lines
8.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __POWERNV_PCI_H
|
|
#define __POWERNV_PCI_H
|
|
|
|
#include <linux/iommu.h>
|
|
#include <asm/iommu.h>
|
|
#include <asm/msi_bitmap.h>
|
|
|
|
struct pci_dn;
|
|
|
|
/* Maximum possible number of ATSD MMIO registers per NPU */
|
|
#define NV_NMMU_ATSD_REGS 8
|
|
|
|
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,
|
|
PNV_PHB_MODEL_NPU2,
|
|
};
|
|
|
|
#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 */
|
|
|
|
/* Indicates operations are frozen for a PE: MMIO in PESTA & DMA in PESTB. */
|
|
#define PNV_IODA_STOPPED_STATE 0x8000000000000000
|
|
|
|
/* Data associated with a PE, including IOMMU tracking etc.. */
|
|
struct pnv_phb;
|
|
struct pnv_ioda_pe {
|
|
unsigned long flags;
|
|
struct pnv_phb *phb;
|
|
int device_count;
|
|
|
|
/* 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;
|
|
|
|
/* PCI peer-to-peer*/
|
|
int p2p_initiator_count;
|
|
|
|
/* Link in list of PE#s */
|
|
struct list_head list;
|
|
};
|
|
|
|
#define PNV_PHB_FLAG_EEH (1 << 0)
|
|
#define PNV_PHB_FLAG_CXL (1 << 1) /* Real PHB supporting the cxl kernel API */
|
|
|
|
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;
|
|
u64 regs_phys;
|
|
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;
|
|
unsigned int root_pe_idx;
|
|
bool root_pe_populated;
|
|
|
|
/* 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, indexed by {bus, devfn} */
|
|
unsigned int pe_rmap[0x10000];
|
|
} ioda;
|
|
|
|
/* PHB and hub diagnostics */
|
|
unsigned int diag_data_size;
|
|
u8 *diag_data;
|
|
|
|
/* Nvlink2 data */
|
|
struct npu {
|
|
int index;
|
|
__be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS];
|
|
unsigned int mmio_atsd_count;
|
|
|
|
/* Bitmask for MMIO register usage */
|
|
unsigned long mmio_atsd_usage;
|
|
|
|
/* Do we need to explicitly flush the nest mmu? */
|
|
bool nmmu_flush;
|
|
} npu;
|
|
|
|
#ifdef CONFIG_CXL_BASE
|
|
struct cxl_afu *cxl_afu;
|
|
#endif
|
|
int p2p_target_count;
|
|
};
|
|
|
|
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,
|
|
unsigned long 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_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);
|
|
extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
|
|
extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
|
|
extern bool pnv_pci_enable_device_hook(struct pci_dev *dev);
|
|
extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
|
|
extern int pnv_eeh_post_init(void);
|
|
|
|
extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
|
|
const char *fmt, ...);
|
|
#define pe_err(pe, fmt, ...) \
|
|
pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
|
|
#define pe_warn(pe, fmt, ...) \
|
|
pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
|
|
#define pe_info(pe, fmt, ...) \
|
|
pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
|
|
|
|
/* Nvlink functions */
|
|
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);
|
|
extern struct pnv_ioda_pe *pnv_pci_npu_setup_iommu(struct pnv_ioda_pe *npe);
|
|
extern long pnv_npu_set_window(struct pnv_ioda_pe *npe, int num,
|
|
struct iommu_table *tbl);
|
|
extern long pnv_npu_unset_window(struct pnv_ioda_pe *npe, int num);
|
|
extern void pnv_npu_take_ownership(struct pnv_ioda_pe *npe);
|
|
extern void pnv_npu_release_ownership(struct pnv_ioda_pe *npe);
|
|
extern int pnv_npu2_init(struct pnv_phb *phb);
|
|
|
|
/* cxl functions */
|
|
extern bool pnv_cxl_enable_device_hook(struct pci_dev *dev);
|
|
extern void pnv_cxl_disable_device(struct pci_dev *dev);
|
|
extern int pnv_cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
|
|
extern void pnv_cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev);
|
|
|
|
|
|
/* phb ops (cxl switches these when enabling the kernel api on the phb) */
|
|
extern const struct pci_controller_ops pnv_cxl_cx4_ioda_controller_ops;
|
|
|
|
#endif /* __POWERNV_PCI_H */
|