linux_dsm_epyc7002/arch/powerpc/include/asm/pci-bridge.h

296 lines
9.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _ASM_POWERPC_PCI_BRIDGE_H
#define _ASM_POWERPC_PCI_BRIDGE_H
#ifdef __KERNEL__
/*
*/
#include <linux/pci.h>
#include <linux/list.h>
#include <linux/ioport.h>
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 06:42:58 +07:00
#include <linux/numa.h>
struct device_node;
/*
* PCI controller operations
*/
struct pci_controller_ops {
void (*dma_dev_setup)(struct pci_dev *pdev);
void (*dma_bus_setup)(struct pci_bus *bus);
bool (*iommu_bypass_supported)(struct pci_dev *pdev,
u64 mask);
int (*probe_mode)(struct pci_bus *bus);
/* Called when pci_enable_device() is called. Returns true to
* allow assignment/enabling of the device. */
bool (*enable_device_hook)(struct pci_dev *pdev);
void (*disable_device)(struct pci_dev *pdev);
void (*release_device)(struct pci_dev *pdev);
/* Called during PCI resource reassignment */
resource_size_t (*window_alignment)(struct pci_bus *bus,
unsigned long type);
void (*setup_bridge)(struct pci_bus *bus,
unsigned long type);
void (*reset_secondary_bus)(struct pci_dev *pdev);
#ifdef CONFIG_PCI_MSI
int (*setup_msi_irqs)(struct pci_dev *pdev,
int nvec, int type);
void (*teardown_msi_irqs)(struct pci_dev *pdev);
#endif
void (*shutdown)(struct pci_controller *hose);
};
/*
* Structure of a PCI controller (host bridge)
*/
struct pci_controller {
struct pci_bus *bus;
char is_dynamic;
#ifdef CONFIG_PPC64
int node;
#endif
struct device_node *dn;
struct list_head list_node;
struct device *parent;
int first_busno;
int last_busno;
int self_busno;
struct resource busn;
void __iomem *io_base_virt;
#ifdef CONFIG_PPC64
void *io_base_alloc;
#endif
resource_size_t io_base_phys;
resource_size_t pci_io_size;
/* Some machines have a special region to forward the ISA
* "memory" cycles such as VGA memory regions. Left to 0
* if unsupported
*/
resource_size_t isa_mem_phys;
resource_size_t isa_mem_size;
struct pci_controller_ops controller_ops;
struct pci_ops *ops;
unsigned int __iomem *cfg_addr;
void __iomem *cfg_data;
/*
* Used for variants of PCI indirect handling and possible quirks:
* SET_CFG_TYPE - used on 4xx or any PHB that does explicit type0/1
* EXT_REG - provides access to PCI-e extended registers
* SURPRESS_PRIMARY_BUS - we suppress the setting of PCI_PRIMARY_BUS
* on Freescale PCI-e controllers since they used the PCI_PRIMARY_BUS
* to determine which bus number to match on when generating type0
* config cycles
* NO_PCIE_LINK - the Freescale PCI-e controllers have issues with
* hanging if we don't have link and try to do config cycles to
* anything but the PHB. Only allow talking to the PHB if this is
* set.
* BIG_ENDIAN - cfg_addr is a big endian register
* BROKEN_MRM - the 440EPx/GRx chips have an errata that causes hangs on
* the PLB4. Effectively disable MRM commands by setting this.
* FSL_CFG_REG_LINK - Freescale controller version in which the PCIe
* link status is in a RC PCIe cfg register (vs being a SoC register)
*/
#define PPC_INDIRECT_TYPE_SET_CFG_TYPE 0x00000001
#define PPC_INDIRECT_TYPE_EXT_REG 0x00000002
#define PPC_INDIRECT_TYPE_SURPRESS_PRIMARY_BUS 0x00000004
#define PPC_INDIRECT_TYPE_NO_PCIE_LINK 0x00000008
#define PPC_INDIRECT_TYPE_BIG_ENDIAN 0x00000010
#define PPC_INDIRECT_TYPE_BROKEN_MRM 0x00000020
#define PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK 0x00000040
u32 indirect_type;
/* Currently, we limit ourselves to 1 IO range and 3 mem
* ranges since the common pci_bus structure can't handle more
*/
struct resource io_resource;
struct resource mem_resources[3];
resource_size_t mem_offset[3];
int global_number; /* PCI domain number */
resource_size_t dma_window_base_cur;
resource_size_t dma_window_size;
#ifdef CONFIG_PPC64
unsigned long buid;
struct pci_dn *pci_data;
#endif /* CONFIG_PPC64 */
void *private_data;
struct npu *npu;
};
/* These are used for config access before all the PCI probing
has been done. */
extern int early_read_config_byte(struct pci_controller *hose, int bus,
int dev_fn, int where, u8 *val);
extern int early_read_config_word(struct pci_controller *hose, int bus,
int dev_fn, int where, u16 *val);
extern int early_read_config_dword(struct pci_controller *hose, int bus,
int dev_fn, int where, u32 *val);
extern int early_write_config_byte(struct pci_controller *hose, int bus,
int dev_fn, int where, u8 val);
extern int early_write_config_word(struct pci_controller *hose, int bus,
int dev_fn, int where, u16 val);
extern int early_write_config_dword(struct pci_controller *hose, int bus,
int dev_fn, int where, u32 val);
extern int early_find_capability(struct pci_controller *hose, int bus,
int dev_fn, int cap);
extern void setup_indirect_pci(struct pci_controller* hose,
resource_size_t cfg_addr,
resource_size_t cfg_data, u32 flags);
extern int indirect_read_config(struct pci_bus *bus, unsigned int devfn,
int offset, int len, u32 *val);
extern int __indirect_read_config(struct pci_controller *hose,
unsigned char bus_number, unsigned int devfn,
int offset, int len, u32 *val);
extern int indirect_write_config(struct pci_bus *bus, unsigned int devfn,
int offset, int len, u32 val);
static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
{
return bus->sysdata;
}
#ifndef CONFIG_PPC64
extern int pci_device_from_OF_node(struct device_node *node,
u8 *bus, u8 *devfn);
extern void pci_create_OF_bus_map(void);
#else /* CONFIG_PPC64 */
/*
* PCI stuff, for nodes representing PCI devices, pointed to
* by device_node->data.
*/
struct iommu_table;
struct pci_dn {
int flags;
#define PCI_DN_FLAG_IOV_VF 0x01
int busno; /* pci bus number */
int devfn; /* pci device and function number */
int vendor_id; /* Vendor ID */
int device_id; /* Device ID */
int class_code; /* Device class code */
struct pci_dn *parent;
struct pci_controller *phb; /* for pci devices */
powerpc/spapr: vfio: Replace iommu_table with iommu_table_group Modern IBM POWERPC systems support multiple (currently two) TCE tables per IOMMU group (a.k.a. PE). This adds a iommu_table_group container for TCE tables. Right now just one table is supported. This defines iommu_table_group struct which stores pointers to iommu_group and iommu_table(s). This replaces iommu_table with iommu_table_group where iommu_table was used to identify a group: - iommu_register_group(); - iommudata of generic iommu_group; This removes @data from iommu_table as it_table_group provides same access to pnv_ioda_pe. For IODA, instead of embedding iommu_table, the new iommu_table_group keeps pointers to those. The iommu_table structs are allocated dynamically. For P5IOC2, both iommu_table_group and iommu_table are embedded into PE struct. As there is no EEH and SRIOV support for P5IOC2, iommu_free_table() should not be called on iommu_table struct pointers so we can keep it embedded in pnv_phb::p5ioc2. For pSeries, this replaces multiple calls of kzalloc_node() with a new iommu_pseries_alloc_group() helper and stores the table group struct pointer into the pci_dn struct. For release, a iommu_table_free_group() helper is added. This moves iommu_table struct allocation from SR-IOV code to the generic DMA initialization code in pnv_pci_ioda_setup_dma_pe and pnv_pci_ioda2_setup_dma_pe as this is where DMA is actually initialized. This change is here because those lines had to be changed anyway. This should cause no behavioural change. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> [aw: for the vfio related changes] Acked-by: Alex Williamson <alex.williamson@redhat.com> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-06-05 13:35:08 +07:00
struct iommu_table_group *table_group; /* for phb's or bridges */
int pci_ext_config_space; /* for pci devices */
#ifdef CONFIG_EEH
struct eeh_dev *edev; /* eeh device */
#endif
#define IODA_INVALID_PE 0xFFFFFFFF
unsigned int pe_number;
#ifdef CONFIG_PCI_IOV
int vf_index; /* VF index in the PF */
u16 vfs_expanded; /* number of VFs IOV BAR expanded */
u16 num_vfs; /* number of VFs enabled*/
unsigned int *pe_num_map; /* PE# for the first VF PE or array */
bool m64_single_mode; /* Use M64 BAR in Single Mode */
#define IODA_INVALID_M64 (-1)
int (*m64_map)[PCI_SRIOV_NUM_BARS]; /* Only used on powernv */
int last_allow_rc; /* Only used on pseries */
#endif /* CONFIG_PCI_IOV */
int mps; /* Maximum Payload Size */
struct list_head child_list;
struct list_head list;
struct resource holes[PCI_SRIOV_NUM_BARS];
};
/* Get the pointer to a device_node's pci_dn */
#define PCI_DN(dn) ((struct pci_dn *) (dn)->data)
extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
int devfn);
extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
extern void remove_dev_pci_data(struct pci_dev *pdev);
extern struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
struct device_node *dn);
extern void pci_remove_device_node_info(struct device_node *dn);
static inline int pci_device_from_OF_node(struct device_node *np,
u8 *bus, u8 *devfn)
{
if (!PCI_DN(np))
return -ENODEV;
*bus = PCI_DN(np)->busno;
*devfn = PCI_DN(np)->devfn;
return 0;
}
#if defined(CONFIG_EEH)
static inline struct eeh_dev *pdn_to_eeh_dev(struct pci_dn *pdn)
{
return pdn ? pdn->edev : NULL;
}
#else
#define pdn_to_eeh_dev(x) (NULL)
#endif
/** Find the bus corresponding to the indicated device node */
extern struct pci_bus *pci_find_bus_by_node(struct device_node *dn);
/** Remove all of the PCI devices under this bus */
extern void pci_hp_remove_devices(struct pci_bus *bus);
/** Discover new pci devices under this bus, and add them */
extern void pci_hp_add_devices(struct pci_bus *bus);
[POWERPC] Rewrite IO allocation & mapping on powerpc64 This rewrites pretty much from scratch the handling of MMIO and PIO space allocations on powerpc64. The main goals are: - Get rid of imalloc and use more common code where possible - Simplify the current mess so that PIO space is allocated and mapped in a single place for PCI bridges - Handle allocation constraints of PIO for all bridges including hot plugged ones within the 2GB space reserved for IO ports, so that devices on hotplugged busses will now work with drivers that assume IO ports fit in an int. - Cleanup and separate tracking of the ISA space in the reserved low 64K of IO space. No ISA -> Nothing mapped there. I booted a cell blade with IDE on PIO and MMIO and a dual G5 so far, that's it :-) With this patch, all allocations are done using the code in mm/vmalloc.c, though we use the low level __get_vm_area with explicit start/stop constraints in order to manage separate areas for vmalloc/vmap, ioremap, and PCI IOs. This greatly simplifies a lot of things, as you can see in the diffstat of that patch :-) A new pair of functions pcibios_map/unmap_io_space() now replace all of the previous code that used to manipulate PCI IOs space. The allocation is done at mapping time, which is now called from scan_phb's, just before the devices are probed (instead of after, which is by itself a bug fix). The only other caller is the PCI hotplug code for hot adding PCI-PCI bridges (slots). imalloc is gone, as is the "sub-allocation" thing, but I do beleive that hotplug should still work in the sense that the space allocation is always done by the PHB, but if you unmap a child bus of this PHB (which seems to be possible), then the code should properly tear down all the HPTE mappings for that area of the PHB allocated IO space. I now always reserve the first 64K of IO space for the bridge with the ISA bus on it. I have moved the code for tracking ISA in a separate file which should also make it smarter if we ever are capable of hot unplugging or re-plugging an ISA bridge. This should have a side effect on platforms like powermac where VGA IOs will no longer work. This is done on purpose though as they would have worked semi-randomly before. The idea at this point is to isolate drivers that might need to access those and fix them by providing a proper function to obtain an offset to the legacy IOs of a given bus. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-06-04 12:15:36 +07:00
extern int pcibios_unmap_io_space(struct pci_bus *bus);
extern int pcibios_map_io_space(struct pci_bus *bus);
#ifdef CONFIG_NUMA
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE))
#else
mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [ixgbe] Acked-by: Jens Axboe <axboe@kernel.dk> [mtip32xx] Acked-by: Vinod Koul <vkoul@kernel.org> [dmaengine.c] Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Doug Ledford <dledford@redhat.com> [drivers/infiniband] Cc: Joseph Qi <jiangqi903@gmail.com> Cc: Hans Verkuil <hverkuil@xs4all.nl> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-06 06:42:58 +07:00
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE)
#endif
#endif /* CONFIG_PPC64 */
/* Get the PCI host controller for an OF device */
extern struct pci_controller *pci_find_hose_for_OF_device(
struct device_node* node);
extern struct pci_controller *pci_find_controller_for_domain(int domain_nr);
/* Fill up host controller resources from the OF node */
extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
struct device_node *dev, int primary);
/* Allocate & free a PCI host bridge structure */
extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
extern void pcibios_free_controller(struct pci_controller *phb);
powerpc/pseries: use pci_host_bridge.release_fn() to kfree(phb) This patch leverages 'struct pci_host_bridge' from the PCI subsystem in order to free the pci_controller only after the last reference to its devices is dropped (avoiding an oops in pcibios_release_device() if the last reference is dropped after pcibios_free_controller()). The patch relies on pci_host_bridge.release_fn() (and .release_data), which is called automatically by the PCI subsystem when the root bus is released (i.e., the last reference is dropped). Those fields are set via pci_set_host_bridge_release() (e.g. in the platform-specific implementation of pcibios_root_bridge_prepare()). It introduces the 'pcibios_free_controller_deferred()' .release_fn() and it expects .release_data to hold a pointer to the pci_controller. The function implictly calls 'pcibios_free_controller()', so an user must *NOT* explicitly call it if using the new _deferred() callback. The functionality is enabled for pseries (although it isn't platform specific, and may be used by cxl). Details on not-so-elegant design choices: - Use 'pci_host_bridge.release_data' field as pointer to associated 'struct pci_controller' so *not* to 'pci_bus_to_host(bridge->bus)' in pcibios_free_controller_deferred(). That's because pci_remove_root_bus() sets 'host_bridge->bus = NULL' (so, if the last reference is released after pci_remove_root_bus() runs, which eventually reaches pcibios_free_controller_deferred(), that would hit a null pointer dereference). The cxl/vphb.c code calls pci_remove_root_bus(), and the cxl folks are interested in this fix. Test-case #1 (hold references) # ls -ld /sys/block/sd* | grep -m1 0021:01:00.0 <...> /sys/block/sdaa -> ../devices/pci0021:01/0021:01:00.0/<...> # ls -ld /sys/block/sd* | grep -m1 0021:01:00.1 <...> /sys/block/sdab -> ../devices/pci0021:01/0021:01:00.1/<...> # cat >/dev/sdaa & pid1=$! # cat >/dev/sdab & pid2=$! # drmgr -w 5 -d 1 -c phb -s 'PHB 33' -r Validating PHB DLPAR capability...yes. [ 594.306719] pci_hp_remove_devices: PCI: Removing devices on bus 0021:01 [ 594.306738] pci_hp_remove_devices: Removing 0021:01:00.0... ... [ 598.236381] pci_hp_remove_devices: Removing 0021:01:00.1... ... [ 611.972077] pci_bus 0021:01: busn_res: [bus 01-ff] is released [ 611.972140] rpadlpar_io: slot PHB 33 removed # kill -9 $pid1 # kill -9 $pid2 [ 632.918088] pcibios_free_controller_deferred: domain 33, dynamic 1 Test-case #2 (don't hold references) # drmgr -w 5 -d 1 -c phb -s 'PHB 33' -r Validating PHB DLPAR capability...yes. [ 916.357363] pci_hp_remove_devices: PCI: Removing devices on bus 0021:01 [ 916.357386] pci_hp_remove_devices: Removing 0021:01:00.0... ... [ 920.566527] pci_hp_remove_devices: Removing 0021:01:00.1... ... [ 933.955873] pci_bus 0021:01: busn_res: [bus 01-ff] is released [ 933.955977] pcibios_free_controller_deferred: domain 33, dynamic 1 [ 933.955999] rpadlpar_io: slot PHB 33 removed Suggested-By: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Tested-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> # cxl Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2016-08-12 03:25:40 +07:00
extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
#ifdef CONFIG_PCI
extern int pcibios_vaddr_is_ioport(void __iomem *address);
#else
static inline int pcibios_vaddr_is_ioport(void __iomem *address)
{
return 0;
}
#endif /* CONFIG_PCI */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PCI_BRIDGE_H */