PCI: Linux kernel SR-IOV support
Subsystems (3)
v9 cover PCI: Linux kernel SR-IOV support
Greetings,
Following patches are intended to support SR-IOV capability in the Linux kernel. With these patches, people can turn a PCI device with the capability into multiple ones from software perspective, which will benefit KVM and achieve other purposes such as QoS, security, and etc.
SR-IOV specification can be found at:
http://www.pcisig.com/members/downloads/specifications/iov/sr-iov1.0_11Sep07.pdf
(it requires membership.)
Devices that support SR-IOV are available from following vendors:
http://download.intel.com/design/network/ProdBrf/320025.pdf
http://www.myri.com/vlsi/Lanai_Z8ES_Datasheet.pdf
http://www.neterion.com/products/pdfs/X3100ProductBrief.pdf
Physical Function driver for Intel 82576 NIC (based on drivers/net/igb/) will come soon.
Major changes from v8 to v9:
1, put a might_sleep() into SR-IOV API which sleeps (Andi Kleen) 2, block user config accesses before clearing VF Enable bit (Matthew Wilcox)
Yu Zhao (7):
PCI: initialize and release SR-IOV capability
PCI: restore saved SR-IOV state
PCI: reserve bus range for SR-IOV device
PCI: add SR-IOV API for Physical Function driver
PCI: handle SR-IOV Virtual Function Migration
PCI: document SR-IOV sysfs entries
PCI: manual for SR-IOV user and driver developer
Documentation/ABI/testing/sysfs-bus-pci | 27 ++ Documentation/DocBook/kernel-api.tmpl | 1 + Documentation/PCI/pci-iov-howto.txt | 99 +++++ drivers/pci/Kconfig | 13 + drivers/pci/Makefile | 3 + drivers/pci/iov.c | 707 +++++++++++++++++++++++++++++++ drivers/pci/pci.c | 8 + drivers/pci/pci.h | 53 +++ drivers/pci/probe.c | 7 + include/linux/pci.h | 28 ++ include/linux/pci_regs.h | 33 ++ 11 files changed, 979 insertions(+), 0 deletions(-) create mode 100644 Documentation/PCI/pci-iov-howto.txt create mode 100644 drivers/pci/iov.c
PATCH v9 1/7 PCI: initialize and release SR-IOV capability
--- drivers/pci/Kconfig | 13 ++++ drivers/pci/Makefile | 3 + drivers/pci/iov.c | 181 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.c | 7 ++ drivers/pci/pci.h | 37 ++++++++++ drivers/pci/probe.c | 4 + include/linux/pci.h | 8 ++ include/linux/pci_regs.h | 33 +++++++++ 8 files changed, 286 insertions(+), 0 deletions(-) create mode 100644 drivers/pci/iov.c
drivers/pci/Kconfig +13 -0
@@ -59,3 +59,16 @@ config HT_IRQ This allows native hypertransport devices to use interrupts. If unsure say Y. + +config PCI_IOV + bool "PCI IOV support" + depends on PCI + select PCI_MSI + default n + help + PCI-SIG I/O Virtualization (IOV) Specifications support. + Single Root IOV: allows the Physical Function driver to enable + the hardware capability, so the Virtual Function is accessible + via the PCI Configuration Space using its own Bus, Device and + Function Numbers. Each Virtual Function also has the PCI Memory + Space to map the device specific register set.
drivers/pci/Makefile +3 -0
@@ -29,6 +29,9 @@ obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o +# PCI IOV support +obj-$(CONFIG_PCI_IOV) += iov.o + # # Some architectures use the generic PCI setup functions #
drivers/pci/iov.c new file +181 -0
181 lines not on this page · raw message
drivers/pci/pci.c +7 -0
@@ -2341,12 +2341,19 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags)*/ int pci_resource_bar (struct pci_dev *dev,int resno,enum pci_bar_type *type) { +int reg; +if (resno <PCI_ROM_RESOURCE ) { *type = pci_bar_unknown;return PCI_BASE_ADDRESS_0 +4 * resno; }else if (resno ==PCI_ROM_RESOURCE ) { *type = pci_bar_mem32;return dev->rom_base_reg; + }else if (resno <PCI_BRIDGE_RESOURCES ) { +/* device specific resource */ + reg =pci_iov_resource_bar (dev, resno, type); +if (reg) +return reg; }dev_err (&dev->dev,"BAR: invalid resource #%d\n" , resno);
drivers/pci/pci.h +37 -0
@@ -195,4 +195,41 @@ static inline int pci_ari_enabled(struct pci_bus *bus) return bus->self && bus->self->ari_enabled; } +/* Single Root I/O Virtualization */ +struct pci_sriov { +int pos;/* capability position */ +int nres;/* number of resources */ +u32 cap;/* SR-IOV Capabilities */ +u16 ctrl;/* SR-IOV Control */ +u16 total;/* total VFs associated with the PF */ +u16 offset;/* first VF Routing ID offset */ +u16 stride;/* following VF stride */ +u32 pgsz;/* page size for BAR alignment */ +u8 link;/* Function Dependency Link */ +struct pci_dev *pdev;/* lowest numbered PF */ +struct pci_dev *self;/* this PF */ +struct mutex lock;/* lock for VF bus */ +}; + +#ifdef CONFIG_PCI_IOV +extern int pci_iov_init (struct pci_dev *dev); +extern void pci_iov_release (struct pci_dev *dev); +extern int pci_iov_resource_bar (struct pci_dev *dev,int resno, +enum pci_bar_type *type); +#else +static inline int pci_iov_init (struct pci_dev *dev) +{ +return -ENODEV ; +} +static inline void pci_iov_release (struct pci_dev *dev) + +{ +} +static inline int pci_iov_resource_bar (struct pci_dev *dev,int resno, +enum pci_bar_type *type) +{ +return 0 ; +} +#endif /* CONFIG_PCI_IOV */ +#endif /* DRIVERS_PCI_H */
drivers/pci/probe.c +4 -0
@@ -785,6 +785,7 @@ static int pci_setup_device(struct pci_dev * dev)static void pci_release_capabilities (struct pci_dev *dev) {pci_vpd_release (dev); +pci_iov_release (dev); }/**
@@ -972,6 +973,9 @@ static void pci_init_capabilities(struct pci_dev *dev)/* Alternative Routing-ID Forwarding */ pci_enable_ari (dev); + +/* Single Root I/O Virtualization */ +pci_iov_init (dev); }void pci_device_add (struct pci_dev *dev,struct pci_bus *bus)
include/linux/pci.h +8 -0
@@ -93,6 +93,12 @@ enum {/* #6: expansion ROM resource */ PCI_ROM_RESOURCE, +/* device specific resources */ +#ifdef CONFIG_PCI_IOV + PCI_SRIOV_RESOURCES, + PCI_SRIOV_RESOURCE_END = PCI_SRIOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1, +#endif +/* resources assigned to buses behind the bridge */ #define PCI_BRIDGE_RESOURCE_NUM 4
@@ -180,6 +186,7 @@ struct pci_cap_saved_state {struct pcie_link_state ;struct pci_vpd ; +struct pci_sriov ;/* * The pci_dev structure is used to describe PCI devices.
@@ -270,6 +277,7 @@ struct pci_dev {struct list_head msi_list;#endif struct pci_vpd *vpd; +struct pci_sriov *sriov;/* SR-IOV capability related */ };extern struct pci_dev *alloc_pci_dev (void );
include/linux/pci_regs.h +33 -0
@@ -375,6 +375,7 @@#define PCI_EXP_TYPE_UPSTREAM 0x5/* Upstream Port */ #define PCI_EXP_TYPE_DOWNSTREAM 0x6/* Downstream Port */ #define PCI_EXP_TYPE_PCI_BRIDGE 0x7/* PCI/PCI-X Bridge */ +#define PCI_EXP_TYPE_RC_END 0x9/* Root Complex Integrated Endpoint */ #define PCI_EXP_FLAGS_SLOT 0x0100/* Slot implemented */ #define PCI_EXP_FLAGS_IRQ 0x3e00/* Interrupt message number */ #define PCI_EXP_DEVCAP 4/* Device capabilities */
@@ -498,6 +499,7 @@#define PCI_EXT_CAP_ID_DSN 3#define PCI_EXT_CAP_ID_PWR 4#define PCI_EXT_CAP_ID_ARI 14 +#define PCI_EXT_CAP_ID_SRIOV 16/* Advanced Error Reporting */ #define PCI_ERR_UNCOR_STATUS 4/* Uncorrectable Error Status */
@@ -615,4 +617,35 @@#define PCI_ARI_CTRL_ACS 0x0002/* ACS Function Groups Enable */ #define PCI_ARI_CTRL_FG (x) (((x) >> 4) & 7)/* Function Group */ +/* Single Root I/O Virtualization */ +#define PCI_SRIOV_CAP 0x04/* SR-IOV Capabilities */ +#define PCI_SRIOV_CAP_VFM 0x01/* VF Migration Capable */ +#define PCI_SRIOV_CAP_INTR (x) ((x) >> 21)/* Interrupt Message Number */ +#define PCI_SRIOV_CTRL 0x08/* SR-IOV Control */ +#define PCI_SRIOV_CTRL_VFE 0x01/* VF Enable */ +#define PCI_SRIOV_CTRL_VFM 0x02/* VF Migration Enable */ +#define PCI_SRIOV_CTRL_INTR 0x04/* VF Migration Interrupt Enable */ +#define PCI_SRIOV_CTRL_MSE 0x08/* VF Memory Space Enable */ +#define PCI_SRIOV_CTRL_ARI 0x10/* ARI Capable Hierarchy */ +#define PCI_SRIOV_STATUS 0x0a/* SR-IOV Status */ +#define PCI_SRIOV_STATUS_VFM 0x01/* VF Migration Status */ +#define PCI_SRIOV_INITIAL_VF 0x0c/* Initial VFs */ +#define PCI_SRIOV_TOTAL_VF 0x0e/* Total VFs */ +#define PCI_SRIOV_NUM_VF 0x10/* Number of VFs */ +#define PCI_SRIOV_FUNC_LINK 0x12/* Function Dependency Link */ +#define PCI_SRIOV_VF_OFFSET 0x14/* First VF Offset */ +#define PCI_SRIOV_VF_STRIDE 0x16/* Following VF Stride */ +#define PCI_SRIOV_VF_DID 0x1a/* VF Device ID */ +#define PCI_SRIOV_SUP_PGSIZE 0x1c/* Supported Page Sizes */ +#define PCI_SRIOV_SYS_PGSIZE 0x20/* System Page Size */ +#define PCI_SRIOV_BAR 0x24/* VF BAR0 */ +#define PCI_SRIOV_NUM_BARS 6/* Number of VF BARs */ +#define PCI_SRIOV_VFM 0x3c/* VF Migration State Array Offset*/ +#define PCI_SRIOV_VFM_BIR (x) ((x) & 7)/* State BIR */ +#define PCI_SRIOV_VFM_OFFSET (x) ((x) & ~7)/* State Offset */ +#define PCI_SRIOV_VFM_UA 0x0/* Inactive.Unavailable */ +#define PCI_SRIOV_VFM_MI 0x1/* Dormant.MigrateIn */ +#define PCI_SRIOV_VFM_MO 0x2/* Active.MigrateOut */ +#define PCI_SRIOV_VFM_AV 0x3/* Active.Available */ +#endif /* LINUX_PCI_REGS_H */
Signature · 1 line
1.5.6.4
PATCH v9 2/7 PCI: restore saved SR-IOV state
In reply to Yu Zhao--- drivers/pci/iov.c | 25 +++++++++++++++++++++++++ drivers/pci/pci.c | 1 + drivers/pci/pci.h | 4 ++++ 3 files changed, 30 insertions(+), 0 deletions(-)
drivers/pci/iov.c +25 -0
@@ -128,6 +128,21 @@ static void sriov_release(struct pci_dev *dev) dev->sriov =NULL ; } +static void sriov_restore_state (struct pci_dev *dev) +{ +u16 ctrl; +struct pci_sriov *iov = dev->sriov; + +pci_read_config_word (dev, iov->pos +PCI_SRIOV_CTRL , &ctrl); +if (ctrl &PCI_SRIOV_CTRL_VFE ) +return ; + +pci_write_config_dword (dev, iov->pos +PCI_SRIOV_SYS_PGSIZE , iov->pgsz); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); +if (iov->ctrl &PCI_SRIOV_CTRL_VFE ) +msleep (100 ); +} +/** * pci_iov_init - initialize the IOV capability * @dev: the PCI device
@@ -179,3 +194,13 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno,return dev->sriov->pos +PCI_SRIOV_BAR +4 * (resno -PCI_SRIOV_RESOURCES ); } + +/** +* pci_restore_iov_state - restore the state of the IOV capability +* @dev: the PCI device +*/ +void pci_restore_iov_state (struct pci_dev *dev) +{ +if (dev->sriov) +sriov_restore_state (dev); +}
drivers/pci/pci.c +1 -0
@@ -773,6 +773,7 @@ pci_restore_state(struct pci_dev *dev) }pci_restore_pcix_state (dev);pci_restore_msi_state (dev); +pci_restore_iov_state (dev);return 0 ; }
drivers/pci/pci.h +4 -0
@@ -216,6 +216,7 @@ extern int pci_iov_init(struct pci_dev *dev);extern void pci_iov_release (struct pci_dev *dev);extern int pci_iov_resource_bar (struct pci_dev *dev,int resno,enum pci_bar_type *type); +extern void pci_restore_iov_state (struct pci_dev *dev);#else static inline int pci_iov_init (struct pci_dev *dev) {
@@ -230,6 +231,9 @@ static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno, {return 0 ; } +static inline void pci_restore_iov_state (struct pci_dev *dev) +{ +}#endif /* CONFIG_PCI_IOV */ #endif /* DRIVERS_PCI_H */
Signature · 1 line
1.5.6.4
PATCH v9 3/7 PCI: reserve bus range for SR-IOV device
In reply to Yu Zhao--- drivers/pci/iov.c | 34 ++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 5 +++++ drivers/pci/probe.c | 3 +++ 3 files changed, 42 insertions(+), 0 deletions(-)
drivers/pci/iov.c +34 -0
@@ -14,6 +14,16 @@#include "pci.h" +static inline void virtfn_bdf (struct pci_dev *dev,int id,u8 *busnr,u8 *devfn) +{ +u16 bdf; + + bdf = (dev->bus->number <<8 ) + dev->devfn + + dev->sriov->offset + dev->sriov->stride * id; + *busnr = bdf >>8 ; + *devfn = bdf &0xff ; +} +static int sriov_init (struct pci_dev *dev,int pos) {int i;
@@ -204,3 +214,27 @@ void pci_restore_iov_state(struct pci_dev *dev)if (dev->sriov)sriov_restore_state (dev); } + +/** +* pci_iov_bus_range - find bus range used by Virtual Function +* @bus: the PCI bus +* +* Returns max number of buses (exclude current one) used by Virtual +* Functions. +*/ +int pci_iov_bus_range (struct pci_bus *bus) +{ +int max =0 ; +u8 busnr, devfn; +struct pci_dev *dev; + +list_for_each_entry (dev, &bus->devices, bus_list) { +if (!dev->sriov) +continue ; +virtfn_bdf (dev, dev->sriov->total -1 , &busnr, &devfn); +if (busnr > max) + max = busnr; + } + +return max ? max - bus->number :0 ; +}
drivers/pci/pci.h +5 -0
@@ -217,6 +217,7 @@ extern void pci_iov_release(struct pci_dev *dev);extern int pci_iov_resource_bar (struct pci_dev *dev,int resno,enum pci_bar_type *type);extern void pci_restore_iov_state (struct pci_dev *dev); +extern int pci_iov_bus_range (struct pci_bus *bus);#else static inline int pci_iov_init (struct pci_dev *dev) {
@@ -234,6 +235,10 @@ static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno,static inline void pci_restore_iov_state (struct pci_dev *dev) { } +static inline int pci_iov_bus_range (struct pci_bus *bus) +{ +return 0 ; +}#endif /* CONFIG_PCI_IOV */ #endif /* DRIVERS_PCI_H */
drivers/pci/probe.c +3 -0
@@ -1078,6 +1078,9 @@ unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus)for (devfn =0 ; devfn <0x100 ; devfn +=8 )pci_scan_slot (bus, devfn); +/* Reserve buses for SR-IOV capability. */ + max +=pci_iov_bus_range (bus); +/* * After performing arch-dependent fixup of the bus, look behind * all PCI-to-PCI bridges on this bus.
Signature · 1 line
1.5.6.4
PATCH v9 4/7 PCI: add SR-IOV API for Physical Function driver
In reply to Yu Zhao--- drivers/pci/iov.c | 348 +++++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 3 + include/linux/pci.h | 14 ++ 3 files changed, 365 insertions(+), 0 deletions(-)
drivers/pci/iov.c +348 -0
@@ -13,6 +13,8 @@#include <linux/delay.h> #include "pci.h" +#define VIRTFN_ID_LEN 8 +static inline void virtfn_bdf (struct pci_dev *dev,int id,u8 *busnr,u8 *devfn) {
@@ -24,6 +26,319 @@ static inline void virtfn_bdf(struct pci_dev *dev, int id, u8 *busnr, u8 *devfn) *devfn = bdf &0xff ; } +static struct pci_bus *virtfn_add_bus (struct pci_bus *bus,int busnr) +{ +int rc; +struct pci_bus *child; + +if (bus->number == busnr) +return bus; + + child =pci_find_bus (pci_domain_nr (bus), busnr); +if (child) +return child; + + child =pci_add_new_bus (bus,NULL , busnr); +if (!child) +return NULL ; + + child->subordinate = busnr; + child->dev.parent = bus->bridge; + rc =pci_bus_add_child (child); +if (rc) { +pci_remove_bus (child); +return NULL ; + } + +return child; +} + +static void virtfn_remove_bus (struct pci_bus *bus,int busnr) +{ +struct pci_bus *child; + +if (bus->number == busnr) +return ; + + child =pci_find_bus (pci_domain_nr (bus), busnr); +BUG_ON (!child); + +if (list_empty (&child->devices)) +pci_remove_bus (child); +} + +static int virtfn_add (struct pci_dev *dev,int id,int reset) +{ +int i; +int rc; +u64 size; +u8 busnr, devfn; +char buf[VIRTFN_ID_LEN ]; +struct pci_dev *virtfn; +struct resource *res; +struct pci_sriov *iov = dev->sriov; + + virtfn =alloc_pci_dev (); +if (!virtfn) +return -ENOMEM ; + +virtfn_bdf (dev, id, &busnr, &devfn); +mutex_lock (&iov->pdev->sriov->lock); + virtfn->bus =virtfn_add_bus (dev->bus, busnr); +if (!virtfn->bus) { +kfree (virtfn); +mutex_unlock (&iov->pdev->sriov->lock); +return -ENOMEM ; + } + + virtfn->sysdata = dev->bus->sysdata; + virtfn->dev.parent = dev->dev.parent; + virtfn->dev.bus = dev->dev.bus; + virtfn->devfn = devfn; + virtfn->hdr_type =PCI_HEADER_TYPE_NORMAL ; + virtfn->cfg_size =PCI_CFG_SPACE_EXP_SIZE ; + virtfn->error_state = pci_channel_io_normal; + virtfn->current_state =PCI_UNKNOWN ; + virtfn->is_pcie =1 ; + virtfn->pcie_type =PCI_EXP_TYPE_ENDPOINT ; + virtfn->dma_mask =0xffffffff ; + virtfn->vendor = dev->vendor; + virtfn->subsystem_vendor = dev->subsystem_vendor; + virtfn->class = dev->class; +pci_read_config_word (dev, iov->pos +PCI_SRIOV_VF_DID , &virtfn->device); +pci_read_config_byte (virtfn,PCI_REVISION_ID , &virtfn->revision); +pci_read_config_word (virtfn,PCI_SUBSYSTEM_ID , + &virtfn->subsystem_device); + +dev_set_name (&virtfn->dev,"%04x:%02x:%02x.%d" , +pci_domain_nr (virtfn->bus), busnr, +PCI_SLOT (devfn),PCI_FUNC (devfn)); + +for (i =0 ; i <PCI_SRIOV_NUM_BARS ; i++) { + res = dev->resource +PCI_SRIOV_RESOURCES + i; +if (!res->parent) +continue ; + virtfn->resource[i].name =pci_name (virtfn); + virtfn->resource[i].flags = res->flags; + size =resource_size (res); +do_div (size, iov->total); + virtfn->resource[i].start = res->start + size * id; + virtfn->resource[i].end = virtfn->resource[i].start + size -1 ; + rc =request_resource (res, &virtfn->resource[i]); +BUG_ON (rc); + } + +if (reset) +pci_execute_reset_function (virtfn); + +pci_device_add (virtfn, virtfn->bus); +mutex_unlock (&iov->pdev->sriov->lock); + + virtfn->physfn =pci_dev_get (dev); + + rc =pci_bus_add_device (virtfn); +if (rc) + goto failed1; +sprintf (buf,"%d" , id); + rc =sysfs_create_link (&iov->dev.kobj, &virtfn->dev.kobj, buf); +if (rc) + goto failed1; + rc =sysfs_create_link (&virtfn->dev.kobj, &dev->dev.kobj,"physfn" ); +if (rc) + goto failed2; + +kobject_uevent (&virtfn->dev.kobj,KOBJ_CHANGE ); + +return 0 ; + +failed2: +sysfs_remove_link (&iov->dev.kobj, buf); +failed1: +pci_dev_put (dev); +mutex_lock (&iov->pdev->sriov->lock); +pci_remove_bus_device (virtfn); +virtfn_remove_bus (dev->bus, busnr); +mutex_unlock (&iov->pdev->sriov->lock); + +return rc; +} + +static void virtfn_remove (struct pci_dev *dev,int id,int reset) +{ +u8 busnr, devfn; +char buf[VIRTFN_ID_LEN ]; +struct pci_bus *bus; +struct pci_dev *virtfn; +struct pci_sriov *iov = dev->sriov; + +virtfn_bdf (dev, id, &busnr, &devfn); + bus =pci_find_bus (pci_domain_nr (dev->bus), busnr); +if (!bus) +return ; + + virtfn =pci_get_slot (bus, devfn); +if (!virtfn) +return ; + +pci_dev_put (virtfn); + +if (reset) { +device_release_driver (&virtfn->dev); +pci_execute_reset_function (virtfn); + } + +sprintf (buf,"%d" , id); +sysfs_remove_link (&iov->dev.kobj, buf); +sysfs_remove_link (&virtfn->dev.kobj,"physfn" ); + +mutex_lock (&iov->pdev->sriov->lock); +pci_remove_bus_device (virtfn); +virtfn_remove_bus (dev->bus, busnr); +mutex_unlock (&iov->pdev->sriov->lock); + +pci_dev_put (dev); +} + +static void sriov_release_dev (struct device *dev) +{ + struct pci_sriov *iov = container_of(dev, struct pci_sriov, dev); + + iov->nr_virtfn =0 ; +} + +static int sriov_enable (struct pci_dev *dev,int nr_virtfn) +{ +int rc; +int i, j; +int nres; +u8 busnr, devfn; +u16 offset, stride, initial; +struct resource *res; +struct pci_dev *link; +struct pci_sriov *iov = dev->sriov; + +if (!nr_virtfn) +return 0 ; + +if (iov->nr_virtfn) +return -EINVAL ; + +pci_read_config_word (dev, iov->pos +PCI_SRIOV_INITIAL_VF , &initial); +if (initial > iov->total || + (!(iov->cap &PCI_SRIOV_CAP_VFM ) && (initial != iov->total))) +return -EIO ; + +if (nr_virtfn <0 || nr_virtfn > iov->total || + (!(iov->cap &PCI_SRIOV_CAP_VFM ) && (nr_virtfn > initial))) +return -EINVAL ; + +pci_write_config_word (dev, iov->pos +PCI_SRIOV_NUM_VF , nr_virtfn); +pci_read_config_word (dev, iov->pos +PCI_SRIOV_VF_OFFSET , &offset); +pci_read_config_word (dev, iov->pos +PCI_SRIOV_VF_STRIDE , &stride); +if (!offset || (nr_virtfn >1 && !stride)) +return -EIO ; + + nres =0 ; +for (i =0 ; i <PCI_SRIOV_NUM_BARS ; i++) { + res = dev->resource +PCI_SRIOV_RESOURCES + i; +if (!res->parent) +continue ; + nres++; + } +if (nres != iov->nres) { +dev_err (&dev->dev,"no enough MMIO for SR-IOV\n" ); +return -ENOMEM ; + } + + iov->offset = offset; + iov->stride = stride; + +virtfn_bdf (dev, nr_virtfn -1 , &busnr, &devfn); +if (busnr > dev->bus->subordinate) { +dev_err (&dev->dev,"no enough bus range for SR-IOV\n" ); +return -ENOMEM ; + } + +memset (&iov->dev,0 ,sizeof (iov->dev)); +strcpy (iov->dev.bus_id,"virtfn" ); + iov->dev.parent = &dev->dev; + iov->dev.release = sriov_release_dev; + rc =device_register (&iov->dev); +if (rc) +return rc; + +if (iov->link != dev->devfn) { + rc = -ENODEV ; +list_for_each_entry (link, &dev->bus->devices, bus_list) { +if (link->sriov && link->devfn == iov->link) + rc =sysfs_create_link (&iov->dev.kobj, + &link->dev.kobj,"dep_link" ); + } +if (rc) + goto failed1; + } + + iov->ctrl |=PCI_SRIOV_CTRL_VFE |PCI_SRIOV_CTRL_MSE ; +pci_block_user_cfg_access (dev); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); +msleep (100 ); +pci_unblock_user_cfg_access (dev); + + iov->initial = initial; +if (nr_virtfn < initial) + initial = nr_virtfn; + +for (i =0 ; i < initial; i++) { + rc =virtfn_add (dev, i,0 ); +if (rc) + goto failed2; + } + +kobject_uevent (&dev->dev.kobj,KOBJ_CHANGE ); + iov->nr_virtfn = nr_virtfn; + +return 0 ; + +failed2: +for (j =0 ; j < i; j++) +virtfn_remove (dev, j,0 ); + + iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE |PCI_SRIOV_CTRL_MSE ); +pci_block_user_cfg_access (dev); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); +ssleep (1 ); +pci_unblock_user_cfg_access (dev); + +if (iov->link != dev->devfn) +sysfs_remove_link (&iov->dev.kobj,"dep_link" ); +failed1: +device_unregister (&iov->dev); + +return rc; +} + +static void sriov_disable (struct pci_dev *dev) +{ +int i; +struct pci_sriov *iov = dev->sriov; + +if (!iov->nr_virtfn) +return ; + +for (i =0 ; i < iov->nr_virtfn; i++) +virtfn_remove (dev, i,0 ); + + iov->ctrl &= ~(PCI_SRIOV_CTRL_VFE |PCI_SRIOV_CTRL_MSE ); +pci_block_user_cfg_access (dev); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); +ssleep (1 ); +pci_unblock_user_cfg_access (dev); + +if (iov->link != dev->devfn) +sysfs_remove_link (&iov->dev.kobj,"dep_link" ); +device_unregister (&iov->dev); +} +static int sriov_init (struct pci_dev *dev,int pos) {int i;
@@ -129,6 +444,8 @@ failed:static void sriov_release (struct pci_dev *dev) { +BUG_ON (dev->sriov->nr_virtfn); +if (dev == dev->sriov->pdev)mutex_destroy (&dev->sriov->lock);else
@@ -148,6 +465,7 @@ static void sriov_restore_state(struct pci_dev *dev)return ;pci_write_config_dword (dev, iov->pos +PCI_SRIOV_SYS_PGSIZE , iov->pgsz); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_NUM_VF , iov->nr_virtfn);pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl);if (iov->ctrl &PCI_SRIOV_CTRL_VFE )msleep (100 );
@@ -238,3 +556,33 @@ int pci_iov_bus_range(struct pci_bus *bus)return max ? max - bus->number :0 ; } + +/** +* pci_enable_sriov - enable the SR-IOV capability +* @dev: the PCI device +* +* Returns 0 on success, or negative on failure. +*/ +int pci_enable_sriov (struct pci_dev *dev,int nr_virtfn) +{ +might_sleep (); + +if (!dev->sriov) +return -ENODEV ; + +return sriov_enable (dev, nr_virtfn); +} +EXPORT_SYMBOL_GPL (pci_enable_sriov); + +/** +* pci_disable_sriov - disable the SR-IOV capability +* @dev: the PCI device +*/ +void pci_disable_sriov (struct pci_dev *dev) +{ +might_sleep (); + +if (dev->sriov) +sriov_disable (dev); +} +EXPORT_SYMBOL_GPL (pci_disable_sriov);
drivers/pci/pci.h +3 -0
@@ -202,6 +202,8 @@ struct pci_sriov {u32 cap;/* SR-IOV Capabilities */ u16 ctrl;/* SR-IOV Control */ u16 total;/* total VFs associated with the PF */ +u16 initial;/* initial VFs associated with the PF */ +u16 nr_virtfn;/* number of VFs available */ u16 offset;/* first VF Routing ID offset */ u16 stride;/* following VF stride */ u32 pgsz;/* page size for BAR alignment */
@@ -209,6 +211,7 @@ struct pci_sriov {struct pci_dev *pdev;/* lowest numbered PF */ struct pci_dev *self;/* this PF */ struct mutex lock;/* lock for VF bus */ +struct device dev; };#ifdef CONFIG_PCI_IOV
include/linux/pci.h +14 -0
@@ -278,6 +278,7 @@ struct pci_dev {#endif struct pci_vpd *vpd;struct pci_sriov *sriov;/* SR-IOV capability related */ +struct pci_dev *physfn;/* Physical Function the device belongs to */ };extern struct pci_dev *alloc_pci_dev (void );
@@ -1202,5 +1203,18 @@ int pci_ext_cfg_avail(struct pci_dev *dev);void __iomem *pci_ioremap_bar (struct pci_dev *pdev,int bar); +#ifdef CONFIG_PCI_IOV +extern int pci_enable_sriov (struct pci_dev *dev,int nr_virtfn); +extern void pci_disable_sriov (struct pci_dev *dev); +#else +static inline int pci_enable_sriov (struct pci_dev *dev,int nr_virtfn) +{ +return -ENODEV ; +} +static inline void pci_disable_sriov (struct pci_dev *dev) +{ +} +#endif +#endif /* __KERNEL__ */ #endif /* LINUX_PCI_H */
Signature · 1 line
1.5.6.4
PATCH v9 5/7 PCI: handle SR-IOV Virtual Function Migration
In reply to Yu Zhao--- drivers/pci/iov.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 4 ++ include/linux/pci.h | 6 +++ 3 files changed, 129 insertions(+), 0 deletions(-)
drivers/pci/iov.c +119 -0
@@ -206,6 +206,97 @@ static void sriov_release_dev(struct device *dev) iov->nr_virtfn =0 ; } +static int sriov_migration (struct pci_dev *dev) +{ +u16 status; +struct pci_sriov *iov = dev->sriov; + +if (!iov->nr_virtfn) +return 0 ; + +if (!(iov->cap &PCI_SRIOV_CAP_VFM )) +return 0 ; + +pci_read_config_word (iov->self, iov->pos +PCI_SRIOV_STATUS , &status); +if (!(status &PCI_SRIOV_STATUS_VFM )) +return 0 ; + +schedule_work (&iov->mtask); + +return 1 ; +} + +static void sriov_migration_task (struct work_struct *work) +{ +int i; +u8 state; +u16 status; + struct pci_sriov *iov = container_of(work, struct pci_sriov, mtask); + +for (i = iov->initial; i < iov->nr_virtfn; i++) { + state =readb (iov->mstate + i); +if (state ==PCI_SRIOV_VFM_MI ) { +writeb (PCI_SRIOV_VFM_AV , iov->mstate + i); + state =readb (iov->mstate + i); +if (state ==PCI_SRIOV_VFM_AV ) +virtfn_add (iov->self, i,1 ); + }else if (state ==PCI_SRIOV_VFM_MO ) { +virtfn_remove (iov->self, i,1 ); +writeb (PCI_SRIOV_VFM_UA , iov->mstate + i); + state =readb (iov->mstate + i); +if (state ==PCI_SRIOV_VFM_AV ) +virtfn_add (iov->self, i,0 ); + } + } + +pci_read_config_word (iov->self, iov->pos +PCI_SRIOV_STATUS , &status); + status &= ~PCI_SRIOV_STATUS_VFM ; +pci_write_config_word (iov->self, iov->pos +PCI_SRIOV_STATUS , status); +} + +static int sriov_enable_migration (struct pci_dev *dev,int nr_virtfn) +{ +int bir; +u32 table; +resource_size_t pa; +struct pci_sriov *iov = dev->sriov; + +if (nr_virtfn <= iov->initial) +return 0 ; + +pci_read_config_dword (dev, iov->pos +PCI_SRIOV_VFM , &table); + bir =PCI_SRIOV_VFM_BIR (table); +if (bir >PCI_STD_RESOURCE_END ) +return -EIO ; + + table =PCI_SRIOV_VFM_OFFSET (table); +if (table + nr_virtfn >pci_resource_len (dev, bir)) +return -EIO ; + + pa =pci_resource_start (dev, bir) + table; + iov->mstate =ioremap (pa, nr_virtfn); +if (!iov->mstate) +return -ENOMEM ; + +INIT_WORK (&iov->mtask, sriov_migration_task); + + iov->ctrl |=PCI_SRIOV_CTRL_VFM |PCI_SRIOV_CTRL_INTR ; +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); + +return 0 ; +} + +static void sriov_disable_migration (struct pci_dev *dev) +{ +struct pci_sriov *iov = dev->sriov; + + iov->ctrl &= ~(PCI_SRIOV_CTRL_VFM |PCI_SRIOV_CTRL_INTR ); +pci_write_config_word (dev, iov->pos +PCI_SRIOV_CTRL , iov->ctrl); + +cancel_work_sync (&iov->mtask); +iounmap (iov->mstate); +} +static int sriov_enable (struct pci_dev *dev,int nr_virtfn) {int rc;
@@ -294,6 +385,12 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) goto failed2; } +if (iov->cap &PCI_SRIOV_CAP_VFM ) { + rc =sriov_enable_migration (dev, nr_virtfn); +if (rc) + goto failed2; + } +kobject_uevent (&dev->dev.kobj,KOBJ_CHANGE ); iov->nr_virtfn = nr_virtfn;
@@ -325,6 +422,9 @@ static void sriov_disable(struct pci_dev *dev)if (!iov->nr_virtfn)return ; +if (iov->cap &PCI_SRIOV_CAP_VFM ) +sriov_disable_migration (dev); +for (i =0 ; i < iov->nr_virtfn; i++)virtfn_remove (dev, i,0 );
@@ -586,3 +686,22 @@ void pci_disable_sriov(struct pci_dev *dev)sriov_disable (dev); }EXPORT_SYMBOL_GPL (pci_disable_sriov); + +/** +* pci_sriov_migration - notify SR-IOV core of Virtual Function Migration +* @dev: the PCI device +* +* Returns IRQ_HANDLED if the IRQ is handled, or IRQ_NONE if not. +* +* Physical Function driver is responsible to register IRQ handler using +* VF Migration Interrupt Message Number, and call this function when the +* interrupt is generated by the hardware. +*/ +irqreturn_t pci_sriov_migration (struct pci_dev *dev) +{ +if (!dev->sriov) +return IRQ_NONE ; + +return sriov_migration (dev) ?IRQ_HANDLED :IRQ_NONE ; +} +EXPORT_SYMBOL_GPL (pci_sriov_migration);
drivers/pci/pci.h +4 -0
@@ -1,6 +1,8 @@#ifndef DRIVERS_PCI_H #define DRIVERS_PCI_H +#include <linux/workqueue.h> +#define PCI_CFG_SPACE_SIZE 256#define PCI_CFG_SPACE_EXP_SIZE 4096
@@ -211,6 +213,8 @@ struct pci_sriov {struct pci_dev *pdev;/* lowest numbered PF */ struct pci_dev *self;/* this PF */ struct mutex lock;/* lock for VF bus */ +struct work_struct mtask;/* VF Migration task */ +u8 __iomem *mstate;/* VF Migration State Array */ struct device dev; };
include/linux/pci.h +6 -0
@@ -52,6 +52,7 @@#include <asm/atomic.h> #include <linux/device.h> #include <linux/io.h> +#include <linux/irqreturn.h> /* Include the ID list */ #include <linux/pci_ids.h>
@@ -1206,6 +1207,7 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);#ifdef CONFIG_PCI_IOV extern int pci_enable_sriov (struct pci_dev *dev,int nr_virtfn);extern void pci_disable_sriov (struct pci_dev *dev); +extern irqreturn_t pci_sriov_migration (struct pci_dev *dev);#else static inline int pci_enable_sriov (struct pci_dev *dev,int nr_virtfn) {
@@ -1214,6 +1216,10 @@ static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)static inline void pci_disable_sriov (struct pci_dev *dev) { } +static inline irqreturn_t pci_sriov_migration (struct pci_dev *dev) +{ +return IRQ_NONE ; +}#endif #endif /* __KERNEL__ */
Signature · 1 line
1.5.6.4
PATCH v9 6/7 PCI: document SR-IOV sysfs entries
In reply to Yu Zhao--- Documentation/ABI/testing/sysfs-bus-pci | 27 +++++++++++++++++++++++++++ 1 files changed, 27 insertions(+), 0 deletions(-)
Documentation/ABI/testing/sysfs-bus-pci +27 -0
@@ -9,3 +9,30 @@ Description: that some devices may have malformatted data. If the underlying VPD has a writable section then the corresponding section of this file will be writable. + +What: /sys/bus/pci/devices/.../virtfn/N +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when hardware supports SR-IOV + capability and Physical Function driver has enabled it. + The symbol link points to the PCI device sysfs entry of + Virtual Function whose index is N (0...MaxVFs-1). + +What: /sys/bus/pci/devices/.../virtfn/dep_link +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when hardware supports SR-IOV + capability and Physical Function driver has enabled it, + and this device has vendor specific dependencies with + others. The symbol link points to the PCI device sysfs + entry of Physical Function this device depends on. + +What: /sys/bus/pci/devices/.../physfn +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when a device is Virtual Function. + The symbol link points to the PCI device sysfs entry of + Physical Function this device associates with.
Signature · 1 line
1.5.6.4
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Hi Greg,
The struct device' is preferred over the struct kobject' in all cases that create subdirectory in sysfs, is this true?
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use device' or kobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.
I checked some code and found they use kobject_init_and_add(). Should I use it instead, or keep using the `device'?
Please advise.
Regards,
Yu
Quoted 43 lines · Yu
Signed-off-by Yu Zhao <[email protected]>--- Documentation/ABI/testing/sysfs-bus-pci | 27 +++++++++++++++++++++++++++ 1 files changed, 27 insertions(+), 0 deletions(-)Documentation/ABI/testing/sysfs-bus-pci +27
-0@@ -9,3 +9,30 @@ Description: that some devices may have malformatted data. If the underlying VPD has a writable section then the corresponding section of this file will be writable. + +What: /sys/bus/pci/devices/.../virtfn/N +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when hardware supports SR-IOV + capability and Physical Function driver has enabled it. + The symbol link points to the PCI device sysfs entry of + Virtual Function whose index is N (0...MaxVFs-1). + +What: /sys/bus/pci/devices/.../virtfn/dep_link +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when hardware supports SR-IOV + capability and Physical Function driver has enabled it, + and this device has vendor specific dependencies with + others. The symbol link points to the PCI device sysfs + entry of Physical Function this device depends on. + +What: /sys/bus/pci/devices/.../physfn +Date: February 2009 +Contact: Yu Zhao <[email protected]> +Description: + This symbol link appears when a device is Virtual Function. + The symbol link points to the PCI device sysfs entry of + Physical Function this device associates with.Signature · 1 line
1.5.6.4
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 5 lines · Yu Zhao
Hi Greg,
The
struct device' is preferred over thestruct kobject' in all cases that create subdirectory in sysfs, is this true?
Quoted 7 lines
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.I checked some code and found they use
kobject_init_and_add(). Should
Oh, sorry. I meant to say kobject_create_and_add() here.
Quoted 6 lines
I use it instead, or keep using the `device'?
Please advise.
Regards,
Yu
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
In reply to Yu ZhaoQuoted 4 lines · Yu Zhao
Hi Greg,
The
struct device' is preferred over thestruct kobject' in all cases that create subdirectory in sysfs, is this true?
If you have a parent directory being controlled by a struct device, yes.
Quoted 5 lines
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.
Neither, just use an attribute group, no new struct device should be needed at all.
thanks,
greg k-h
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 7 lines · Greg KH
Quoted 4 lines · Yu Zhao
Hi Greg,
The
struct device' is preferred over thestruct kobject' in all cases that create subdirectory in sysfs, is this true?If you have a parent directory being controlled by a struct device, yes.
Thanks! Do we need to document this somewhere?
Quoted 8 lines
Quoted 5 lines
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.Neither, just use an attribute group, no new struct device should be needed at all.
Yes, I was thinking using an attribute group, however, it looks like we can't put symbol link into a group. Maybe I'm wrong, shed some light, please?
Regards,
Yu
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 10 lines · Yu Zhao
Quoted 7 lines · Greg KH
Quoted 4 lines · Yu Zhao
Hi Greg,
The
struct device' is preferred over thestruct kobject' in all cases that create subdirectory in sysfs, is this true?If you have a parent directory being controlled by a struct device, yes.
Thanks! Do we need to document this somewhere?
Probably, patches gladly accepted for documentation fixes/updates :)
Quoted 6 lines
Quoted 6 lines
Quoted 5 lines
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.
Quoted 6 lines
Quoted 2 lines
Neither, just use an attribute group, no new struct device should be needed at all.
Yes, I was thinking using an attribute group, however, it looks like we can't put symbol link into a group. Maybe I'm wrong, shed some light, please?
Why would you want a symbolic link in an attribute group?
confused,
greg k-h
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 9 lines · Greg KH
Quoted 8 lines · Yu Zhao
Quoted 7 lines · Greg KH
Quoted 5 lines · Yu Zhao
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.
Quoted 8 lines
Quoted 6 lines
Quoted 2 lines
Neither, just use an attribute group, no new struct device should be needed at all.
Yes, I was thinking using an attribute group, however, it looks like we can't put symbol link into a group. Maybe I'm wrong, shed some light, please?
Why would you want a symbolic link in an attribute group?
Sorry I didn't make myself clear. I'd like to create a subdirectory (its parent is controlled by a struct device') to only hold symbol links. Can I use an attribute group' of the parent struct device' for this, or a child struct device', or a bare `struct kobject'?
Regards,
Yu
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 13 lines · Yu Zhao
Quoted 12 lines · Greg KH
Quoted 11 lines · Yu Zhao
Quoted 9 lines · Greg KH
Quoted 5 lines · Yu Zhao
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.Neither, just use an attribute group, no new struct device should be needed at all.
Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
Yes, I was thinking using an attribute group, however, it looks like we can't put symbol link into a group. Maybe I'm wrong, shed some light, please?
Why would you want a symbolic link in an attribute group?
Sorry I didn't make myself clear. I'd like to create a subdirectory (its parent is controlled by a `struct device') to only hold symbol links.
Ick. What would those links be to? And what are they for?
Quoted 2 lines
Can I use an
attribute group' of the parentstruct device' for this, or a childstruct device', or a barestruct kobject'?
You can't use an attribute group for symlinks.
You should use a struct device, but be careful, you are going to be creating uevents that I don't think you really want to.
Care to describe what you are trying to do first?
thanks,
greg k-h
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 23 lines · Greg KH
Quoted 13 lines · Yu Zhao
Quoted 12 lines · Greg KH
Quoted 11 lines · Yu Zhao
Quoted 9 lines · Greg KH
Quoted 5 lines · Yu Zhao
I'd like to create a subdirectory under PCI device sysfs directory and put some symbol links into that directory (only symbol links). Should I use
device' orkobject'? Currently I use `device' and get two extra file/directory (uevent and power) which look like useless for my case because this subdirectory doesn't reflect a real device.Neither, just use an attribute group, no new struct device should be needed at all.
Quoted 8 lines
Quoted 5 lines
Quoted 3 lines
Yes, I was thinking using an attribute group, however, it looks like we can't put symbol link into a group. Maybe I'm wrong, shed some light, please?
Why would you want a symbolic link in an attribute group?
Sorry I didn't make myself clear. I'd like to create a subdirectory (its parent is controlled by a `struct device') to only hold symbol links.
Quoted 8 lines
Ick. What would those links be to? And what are they for?
Quoted 2 lines
Can I use an
attribute group' of the parentstruct device' for this, or a childstruct device', or a barestruct kobject'?You can't use an attribute group for symlinks.
You should use a struct device, but be careful, you are going to be creating uevents that I don't think you really want to.
Thank you for the clarification.
Quoted 2 lines
Care to describe what you are trying to do first?
I'd like to link child PCI devices to their parent PCI device's subdirectory. These child PCI devices are PCI functions that are on the same level as their parent in the PCI hierarchy, so current PCI code won't create symbol links for them in their parent directory as what it does for PCI bridge. For example, device 01:00.0 is the parent and 01:00.1 is the child, I'd like to put a symbol link into /sys/bus/pci/device/0000:01:00.0/child/ which points to /sys/bus/pci/device/0000:01:00.1. This can let user space application know the relationship between this two devices.
Regards,
Yu
Re: [PATCH v9 6/7] PCI: document SR-IOV sysfs entries
Quoted 11 lines · Yu Zhao
Quoted 1 line
Care to describe what you are trying to do first?
I'd like to link child PCI devices to their parent PCI device's subdirectory. These child PCI devices are PCI functions that are on the same level as their parent in the PCI hierarchy, so current PCI code won't create symbol links for them in their parent directory as what it does for PCI bridge. For example, device 01:00.0 is the parent and 01:00.1 is the child, I'd like to put a symbol link into /sys/bus/pci/device/0000:01:00.0/child/ which points to /sys/bus/pci/device/0000:01:00.1. This can let user space application know the relationship between this two devices.
If .1 is really the child of .0, then make it so in the sysfs tree in the first place with the topology of the devices. That way you don't need any special "child" directory, as that would be different from all other device types in the system.
thanks,
greg k-h
PATCH v9 7/7 PCI: manual for SR-IOV user and driver developer
In reply to Yu Zhao--- Documentation/DocBook/kernel-api.tmpl | 1 + Documentation/PCI/pci-iov-howto.txt | 99 +++++++++++++++++++++++++++++++++ 2 files changed, 100 insertions(+), 0 deletions(-) create mode 100644 Documentation/PCI/pci-iov-howto.txt
Documentation/DocBook/kernel-api.tmpl +1 -0
@@ -251,6 +251,7 @@ X!Edrivers/pci/hotplug.c --> !Edrivers/pci/probe.c !Edrivers/pci/rom.c +!Edrivers/pci/iov.c </sect1> <sect1><title>PCI Hotplug Support Library</title> !Edrivers/pci/hotplug/pci_hotplug_core.c
Documentation/PCI/pci-iov-howto.txt new file +99 -0
99 lines not on this page · raw message
Signature · 1 line
1.5.6.4