linux/arch/powerpc/platforms/powernv/pci.h
Alexey Kardashevskiy c37c792dec powerpc/powernv/ioda2: Allocate TCE table levels on demand for default DMA window
We allocate only the first level of multilevel TCE tables for KVM
already (alloc_userspace_copy==true), and the rest is allocated on demand.
This is not enabled though for bare metal.

This removes the KVM limitation (implicit, via the alloc_userspace_copy
parameter) and always allocates just the first level. The on-demand
allocation of missing levels is already implemented.

As from now on DMA map might happen with disabled interrupts, this
allocates TCEs with GFP_ATOMIC; otherwise lockdep reports errors 1].
In practice just a single page is allocated there so chances for failure
are quite low.

To save time when creating a new clean table, this skips non-allocated
indirect TCE entries in pnv_tce_free just like we already do in
the VFIO IOMMU TCE driver.

This changes the default level number from 1 to 2 to reduce the amount
of memory required for the default 32bit DMA window at the boot time.
The default window size is up to 2GB which requires 4MB of TCEs which is
unlikely to be used entirely or at all as most devices these days are
64bit capable so by switching to 2 levels by default we save 4032KB of
RAM per a device.

While at this, add __GFP_NOWARN to alloc_pages_node() as the userspace
can trigger this path via VFIO, see the failure and try creating a table
again with different parameters which might succeed.

[1]:
===
BUG: sleeping function called from invalid context at mm/page_alloc.c:4596
in_atomic(): 1, irqs_disabled(): 1, pid: 1038, name: scsi_eh_1
2 locks held by scsi_eh_1/1038:
 #0: 000000005efd659a (&host->eh_mutex){+.+.}, at: ata_eh_acquire+0x34/0x80
 #1: 0000000006cf56a6 (&(&host->lock)->rlock){....}, at: ata_exec_internal_sg+0xb0/0x5c0
irq event stamp: 500
hardirqs last  enabled at (499): [<c000000000cb8a74>] _raw_spin_unlock_irqrestore+0x94/0xd0
hardirqs last disabled at (500): [<c000000000cb85c4>] _raw_spin_lock_irqsave+0x44/0x120
softirqs last  enabled at (0): [<c000000000101120>] copy_process.isra.4.part.5+0x640/0x1a80
softirqs last disabled at (0): [<0000000000000000>] 0x0
CPU: 73 PID: 1038 Comm: scsi_eh_1 Not tainted 5.2.0-rc6-le_nv2_aikATfstn1-p1 #634
Call Trace:
[c000003d064cef50] [c000000000c8e6c4] dump_stack+0xe8/0x164 (unreliable)
[c000003d064cefa0] [c00000000014ed78] ___might_sleep+0x2f8/0x310
[c000003d064cf020] [c0000000003ca084] __alloc_pages_nodemask+0x2a4/0x1560
[c000003d064cf220] [c0000000000c2530] pnv_alloc_tce_level.isra.0+0x90/0x130
[c000003d064cf290] [c0000000000c2888] pnv_tce+0x128/0x3b0
[c000003d064cf360] [c0000000000c2c00] pnv_tce_build+0xb0/0xf0
[c000003d064cf3c0] [c0000000000bbd9c] pnv_ioda2_tce_build+0x3c/0xb0
[c000003d064cf400] [c00000000004cfe0] ppc_iommu_map_sg+0x210/0x550
[c000003d064cf510] [c00000000004b7a4] dma_iommu_map_sg+0x74/0xb0
[c000003d064cf530] [c000000000863944] ata_qc_issue+0x134/0x470
[c000003d064cf5b0] [c000000000863ec4] ata_exec_internal_sg+0x244/0x5c0
[c000003d064cf700] [c0000000008642d0] ata_exec_internal+0x90/0xe0
[c000003d064cf780] [c0000000008650ac] ata_dev_read_id+0x2ec/0x640
[c000003d064cf8d0] [c000000000878e28] ata_eh_recover+0x948/0x16d0
[c000003d064cfa10] [c00000000087d760] sata_pmp_error_handler+0x480/0xbf0
[c000003d064cfbc0] [c000000000884624] ahci_error_handler+0x74/0xe0
[c000003d064cfbf0] [c000000000879fa8] ata_scsi_port_error_handler+0x2d8/0x7c0
[c000003d064cfca0] [c00000000087a544] ata_scsi_error+0xb4/0x100
[c000003d064cfd00] [c000000000802450] scsi_error_handler+0x120/0x510
[c000003d064cfdb0] [c000000000140c48] kthread+0x1b8/0x1c0
[c000003d064cfe20] [c00000000000bd8c] ret_from_kernel_thread+0x5c/0x70
ata1: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
irq event stamp: 2305

========================================================
hardirqs last  enabled at (2305): [<c00000000000e4c8>] fast_exc_return_irq+0x28/0x34
hardirqs last disabled at (2303): [<c000000000cb9fd0>] __do_softirq+0x4a0/0x654
WARNING: possible irq lock inversion dependency detected
5.2.0-rc6-le_nv2_aikATfstn1-p1 #634 Tainted: G        W
softirqs last  enabled at (2304): [<c000000000cba054>] __do_softirq+0x524/0x654
softirqs last disabled at (2297): [<c00000000010f278>] irq_exit+0x128/0x180
--------------------------------------------------------
swapper/0/0 just changed the state of lock:
0000000006cf56a6 (&(&host->lock)->rlock){-...}, at: ahci_single_level_irq_intr+0xac/0x120
but this lock took another, HARDIRQ-unsafe lock in the past:
 (fs_reclaim){+.+.}

and interrupts could create inverse lock ordering between them.

other info that might help us debug this:
 Possible interrupt unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(fs_reclaim);
                               local_irq_disable();
                               lock(&(&host->lock)->rlock);
                               lock(fs_reclaim);
  <Interrupt>
    lock(&(&host->lock)->rlock);

 *** DEADLOCK ***

no locks held by swapper/0/0.

the shortest dependencies between 2nd lock and 1st lock:
 -> (fs_reclaim){+.+.} ops: 167579 {
    HARDIRQ-ON-W at:
                      lock_acquire+0xf8/0x2a0
                      fs_reclaim_acquire.part.23+0x44/0x60
                      kmem_cache_alloc_node_trace+0x80/0x590
                      alloc_desc+0x64/0x270
                      __irq_alloc_descs+0x2e4/0x3a0
                      irq_domain_alloc_descs+0xb0/0x150
                      irq_create_mapping+0x168/0x2c0
                      xics_smp_probe+0x2c/0x98
                      pnv_smp_probe+0x40/0x9c
                      smp_prepare_cpus+0x524/0x6c4
                      kernel_init_freeable+0x1b4/0x650
                      kernel_init+0x2c/0x148
                      ret_from_kernel_thread+0x5c/0x70
    SOFTIRQ-ON-W at:
                      lock_acquire+0xf8/0x2a0
                      fs_reclaim_acquire.part.23+0x44/0x60
                      kmem_cache_alloc_node_trace+0x80/0x590
                      alloc_desc+0x64/0x270
                      __irq_alloc_descs+0x2e4/0x3a0
                      irq_domain_alloc_descs+0xb0/0x150
                      irq_create_mapping+0x168/0x2c0
                      xics_smp_probe+0x2c/0x98
                      pnv_smp_probe+0x40/0x9c
                      smp_prepare_cpus+0x524/0x6c4
                      kernel_init_freeable+0x1b4/0x650
                      kernel_init+0x2c/0x148
                      ret_from_kernel_thread+0x5c/0x70
    INITIAL USE at:
                     lock_acquire+0xf8/0x2a0
                     fs_reclaim_acquire.part.23+0x44/0x60
                     kmem_cache_alloc_node_trace+0x80/0x590
                     alloc_desc+0x64/0x270
                     __irq_alloc_descs+0x2e4/0x3a0
                     irq_domain_alloc_descs+0xb0/0x150
                     irq_create_mapping+0x168/0x2c0
                     xics_smp_probe+0x2c/0x98
                     pnv_smp_probe+0x40/0x9c
                     smp_prepare_cpus+0x524/0x6c4
                     kernel_init_freeable+0x1b4/0x650
                     kernel_init+0x2c/0x148
                     ret_from_kernel_thread+0x5c/0x70
  }
===

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190718051139.74787-4-aik@ozlabs.ru
2019-08-19 13:20:23 +10:00

251 lines
7.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __POWERNV_PCI_H
#define __POWERNV_PCI_H
#include <linux/compiler.h> /* for __printf */
#include <linux/iommu.h>
#include <asm/iommu.h>
#include <asm/msi_bitmap.h>
struct pci_dn;
enum pnv_phb_type {
PNV_PHB_IODA1 = 0,
PNV_PHB_IODA2 = 1,
PNV_PHB_NPU_NVLINK = 2,
PNV_PHB_NPU_OCAPI = 3,
};
/* 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;
struct npu_comp *npucomp;
/* 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;
u64 regs_phys;
int initialized;
spinlock_t lock;
#ifdef CONFIG_DEBUG_FS
int has_dbgfs;
struct dentry *dbgfs;
#endif
unsigned int msi_base;
unsigned int msi32_support;
struct msi_bitmap msi_bmp;
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);
int (*init_m64)(struct pnv_phb *phb);
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;
};
extern struct pci_ops pnv_pci_ops;
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 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_init_npu2_opencapi_phb(struct device_node *np);
extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
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 unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
__u64 window_size, __u32 levels);
extern int pnv_eeh_post_init(void);
__printf(3, 4)
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 struct iommu_table_group *pnv_try_setup_npu_table_group(
struct pnv_ioda_pe *pe);
extern struct iommu_table_group *pnv_npu_compound_attach(
struct pnv_ioda_pe *pe);
/* pci-ioda-tce.c */
#define POWERNV_IOMMU_DEFAULT_LEVELS 2
#define POWERNV_IOMMU_MAX_LEVELS 5
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,
bool alloc);
extern __be64 *pnv_tce_useraddrptr(struct iommu_table *tbl, long index,
bool alloc);
extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);
extern long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
__u32 page_shift, __u64 window_size, __u32 levels,
bool alloc_userspace_copy, struct iommu_table *tbl);
extern void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
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 int page_shift);
#endif /* __POWERNV_PCI_H */