357d1e3bc7
Currently, the MMIO space for accessing PCI on pseries guests begins at
1 TiB in guest address space. Each PCI host bridge (PHB) has a 64 GiB
chunk of address space in which it places its outbound PIO and 32-bit and
64-bit MMIO windows.
This scheme as several problems:
- It limits guest RAM to 1 TiB (though we have a limited fix for this
now)
- It limits the total MMIO window to 64 GiB. This is not always enough
for some of the large nVidia GPGPU cards
- Putting all the windows into a single 64 GiB area means that naturally
aligning things within there will waste more address space.
In addition there was a miscalculation in some of the defaults, which meant
that the MMIO windows for each PHB actually slightly overran the 64 GiB
region for that PHB. We got away without nasty consequences because
the overrun fit within an unused area at the beginning of the next PHB's
region, but it's not pretty.
This patch implements a new scheme which addresses those problems, and is
also closer to what bare metal hardware and pHyp guests generally use.
Because some guest versions (including most current distro kernels) can't
access PCI MMIO above 64 TiB, we put all the PCI windows between 32 TiB and
64 TiB. This is broken into 1 TiB chunks. The first 1 TiB contains the
PIO (64 kiB) and 32-bit MMIO (2 GiB) windows for all of the PHBs. Each
subsequent TiB chunk contains a naturally aligned 64-bit MMIO window for
one PHB each.
This reduces the number of allowed PHBs (without full manual configuration
of all the windows) from 256 to 31, but this should still be plenty in
practice.
We also change some of the default window sizes for manually configured
PHBs to saner values.
Finally we adjust some tests and libqos so that it correctly uses the new
default locations. Ideally it would parse the device tree given to the
guest, but that's a more complex problem for another time.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
158 lines
4.6 KiB
C
158 lines
4.6 KiB
C
/*
|
|
* QEMU SPAPR PCI BUS definitions
|
|
*
|
|
* Copyright (c) 2011 Alexey Kardashevskiy <aik@au1.ibm.com>
|
|
*
|
|
* This library is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2 of the License, or (at your option) any later version.
|
|
*
|
|
* This library is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public
|
|
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#ifndef PCI_HOST_SPAPR_H
|
|
#define PCI_HOST_SPAPR_H
|
|
|
|
#include "hw/ppc/spapr.h"
|
|
#include "hw/pci/pci.h"
|
|
#include "hw/pci/pci_host.h"
|
|
#include "hw/ppc/xics.h"
|
|
|
|
#define TYPE_SPAPR_PCI_HOST_BRIDGE "spapr-pci-host-bridge"
|
|
|
|
#define SPAPR_PCI_HOST_BRIDGE(obj) \
|
|
OBJECT_CHECK(sPAPRPHBState, (obj), TYPE_SPAPR_PCI_HOST_BRIDGE)
|
|
|
|
#define SPAPR_PCI_DMA_MAX_WINDOWS 2
|
|
|
|
typedef struct sPAPRPHBState sPAPRPHBState;
|
|
|
|
typedef struct spapr_pci_msi {
|
|
uint32_t first_irq;
|
|
uint32_t num;
|
|
} spapr_pci_msi;
|
|
|
|
typedef struct spapr_pci_msi_mig {
|
|
uint32_t key;
|
|
spapr_pci_msi value;
|
|
} spapr_pci_msi_mig;
|
|
|
|
struct sPAPRPHBState {
|
|
PCIHostState parent_obj;
|
|
|
|
uint32_t index;
|
|
uint64_t buid;
|
|
char *dtbusname;
|
|
bool dr_enabled;
|
|
|
|
MemoryRegion memspace, iospace;
|
|
hwaddr mem_win_addr, mem_win_size, mem64_win_addr, mem64_win_size;
|
|
uint64_t mem64_win_pciaddr;
|
|
hwaddr io_win_addr, io_win_size;
|
|
MemoryRegion mem32window, mem64window, iowindow, msiwindow;
|
|
|
|
uint32_t dma_liobn[SPAPR_PCI_DMA_MAX_WINDOWS];
|
|
hwaddr dma_win_addr, dma_win_size;
|
|
AddressSpace iommu_as;
|
|
MemoryRegion iommu_root;
|
|
|
|
struct spapr_pci_lsi {
|
|
uint32_t irq;
|
|
} lsi_table[PCI_NUM_PINS];
|
|
|
|
GHashTable *msi;
|
|
/* Temporary cache for migration purposes */
|
|
int32_t msi_devs_num;
|
|
spapr_pci_msi_mig *msi_devs;
|
|
|
|
QLIST_ENTRY(sPAPRPHBState) list;
|
|
|
|
bool ddw_enabled;
|
|
uint64_t page_size_mask;
|
|
uint64_t dma64_win_addr;
|
|
|
|
uint32_t numa_node;
|
|
};
|
|
|
|
#define SPAPR_PCI_MEM_WIN_BUS_OFFSET 0x80000000ULL
|
|
#define SPAPR_PCI_MEM32_WIN_SIZE \
|
|
((1ULL << 32) - SPAPR_PCI_MEM_WIN_BUS_OFFSET)
|
|
#define SPAPR_PCI_MEM64_WIN_SIZE 0x10000000000ULL /* 1 TiB */
|
|
|
|
/* Without manual configuration, all PCI outbound windows will be
|
|
* within this range */
|
|
#define SPAPR_PCI_BASE (1ULL << 45) /* 32 TiB */
|
|
#define SPAPR_PCI_LIMIT (1ULL << 46) /* 64 TiB */
|
|
|
|
#define SPAPR_PCI_2_7_MMIO_WIN_SIZE 0xf80000000
|
|
#define SPAPR_PCI_IO_WIN_SIZE 0x10000
|
|
|
|
#define SPAPR_PCI_MSI_WINDOW 0x40000000000ULL
|
|
|
|
static inline qemu_irq spapr_phb_lsi_qirq(struct sPAPRPHBState *phb, int pin)
|
|
{
|
|
sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
|
|
|
|
return xics_get_qirq(spapr->xics, phb->lsi_table[pin].irq);
|
|
}
|
|
|
|
PCIHostState *spapr_create_phb(sPAPRMachineState *spapr, int index);
|
|
|
|
int spapr_populate_pci_dt(sPAPRPHBState *phb,
|
|
uint32_t xics_phandle,
|
|
void *fdt);
|
|
|
|
void spapr_pci_rtas_init(void);
|
|
|
|
sPAPRPHBState *spapr_pci_find_phb(sPAPRMachineState *spapr, uint64_t buid);
|
|
PCIDevice *spapr_pci_find_dev(sPAPRMachineState *spapr, uint64_t buid,
|
|
uint32_t config_addr);
|
|
|
|
/* VFIO EEH hooks */
|
|
#ifdef CONFIG_LINUX
|
|
bool spapr_phb_eeh_available(sPAPRPHBState *sphb);
|
|
int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
|
|
unsigned int addr, int option);
|
|
int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb, int *state);
|
|
int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option);
|
|
int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb);
|
|
void spapr_phb_vfio_reset(DeviceState *qdev);
|
|
#else
|
|
static inline bool spapr_phb_eeh_available(sPAPRPHBState *sphb)
|
|
{
|
|
return false;
|
|
}
|
|
static inline int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
|
|
unsigned int addr, int option)
|
|
{
|
|
return RTAS_OUT_HW_ERROR;
|
|
}
|
|
static inline int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb,
|
|
int *state)
|
|
{
|
|
return RTAS_OUT_HW_ERROR;
|
|
}
|
|
static inline int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
|
|
{
|
|
return RTAS_OUT_HW_ERROR;
|
|
}
|
|
static inline int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
|
|
{
|
|
return RTAS_OUT_HW_ERROR;
|
|
}
|
|
static inline void spapr_phb_vfio_reset(DeviceState *qdev)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
void spapr_phb_dma_reset(sPAPRPHBState *sphb);
|
|
|
|
#endif /* PCI_HOST_SPAPR_H */
|