From a52e2e3513d4beafe8fe8699f1519b021c2d05ba Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 24 Jan 2009 00:21:14 +0100 Subject: PCI/MSI: Introduce pci_msix_table_size() Introduce new function pci_msix_table_size() returning the size of the MSI-X table of given PCI device or 0 if the device doesn't support MSI-X. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hidetoshi Seto Signed-off-by: Jesse Barnes --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/pci.h') diff --git a/include/linux/pci.h b/include/linux/pci.h index 7bd624bfdcfd..b5d6d0e0f1cb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -799,6 +799,10 @@ static inline void pci_msi_shutdown(struct pci_dev *dev) static inline void pci_disable_msi(struct pci_dev *dev) { } +static inline int pci_msix_table_size(struct pci_dev *dev) +{ + return 0; +} static inline int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec) { @@ -823,6 +827,7 @@ static inline int pci_msi_enabled(void) extern int pci_enable_msi(struct pci_dev *dev); extern void pci_msi_shutdown(struct pci_dev *dev); extern void pci_disable_msi(struct pci_dev *dev); +extern int pci_msix_table_size(struct pci_dev *dev); extern int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); extern void pci_msix_shutdown(struct pci_dev *dev); -- cgit v1.2.3 From c48f1670f42b71f39f4a3bfba01ffb691cc9206c Mon Sep 17 00:00:00 2001 From: "akpm@linux-foundation.org" Date: Tue, 3 Feb 2009 15:45:26 -0800 Subject: PCI: constify pci_bus_add_devices() drivers/pci/hotplug/fakephp.c:283: warning: passing argument 1 of 'pci_bus_add_devices' discards qualifiers from pointer target type Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- drivers/pci/bus.c | 2 +- include/linux/pci.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 52b54f053be0..118c77778d29 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -133,7 +133,7 @@ int pci_bus_add_child(struct pci_bus *bus) * * Call hotplug for each new devices. */ -void pci_bus_add_devices(struct pci_bus *bus) +void pci_bus_add_devices(const struct pci_bus *bus) { struct pci_dev *dev; struct pci_bus *child; diff --git a/include/linux/pci.h b/include/linux/pci.h index b5d6d0e0f1cb..a1af2fe00639 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -528,7 +528,7 @@ void pcibios_update_irq(struct pci_dev *, int irq); /* Generic PCI functions used internally */ extern struct pci_bus *pci_find_bus(int domain, int busnr); -void pci_bus_add_devices(struct pci_bus *bus); +void pci_bus_add_devices(const struct pci_bus *bus); struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus, struct pci_ops *ops, void *sysdata); static inline struct pci_bus * __devinit pci_scan_bus(int bus, struct pci_ops *ops, -- cgit v1.2.3 From ea7415512a07add2b09c070c9a5d1950833cf9b3 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 18 Feb 2009 10:44:29 -0800 Subject: PCI: constify pci_bus_assign_resources() drivers/pci/hotplug/fakephp.c: In function 'pci_rescan_bus': drivers/pci/hotplug/fakephp.c:271: warning: passing argument 1 of 'pci_bus_assign_resources' discards qualifiers from pointer target type Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- drivers/pci/setup-bus.c | 4 ++-- include/linux/pci.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 704608945780..170a3eda9dd3 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -27,7 +27,7 @@ #include -static void pbus_assign_resources_sorted(struct pci_bus *bus) +static void pbus_assign_resources_sorted(const struct pci_bus *bus) { struct pci_dev *dev; struct resource *res; @@ -495,7 +495,7 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) } EXPORT_SYMBOL(pci_bus_size_bridges); -void __ref pci_bus_assign_resources(struct pci_bus *bus) +void __ref pci_bus_assign_resources(const struct pci_bus *bus) { struct pci_bus *b; struct pci_dev *dev; diff --git a/include/linux/pci.h b/include/linux/pci.h index a1af2fe00639..7baf2a5db12a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -708,7 +708,7 @@ ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void int pci_vpd_truncate(struct pci_dev *dev, size_t size); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ -void pci_bus_assign_resources(struct pci_bus *bus); +void pci_bus_assign_resources(const struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); void pci_assign_unassigned_resources(void); -- cgit v1.2.3 From 1c8d7b0a562da06d3ebe83f01b1ed553205d1ae4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 17 Mar 2009 08:54:10 -0400 Subject: PCI MSI: Add support for multiple MSI Add the new API pci_enable_msi_block() to allow drivers to request multiple MSI and reimplement pci_enable_msi in terms of pci_enable_msi_block. Ensure that the architecture back ends don't have to know about multiple MSI. Signed-off-by: Matthew Wilcox Signed-off-by: Jesse Barnes --- Documentation/PCI/MSI-HOWTO.txt | 45 +++++++++++++++++--- arch/powerpc/kernel/msi.c | 4 ++ arch/x86/kernel/io_apic.c | 4 ++ drivers/pci/msi.c | 91 +++++++++++++++++++++++++++++------------ drivers/pci/msi.h | 6 --- include/linux/msi.h | 1 + include/linux/pci.h | 6 ++- 7 files changed, 116 insertions(+), 41 deletions(-) (limited to 'include/linux/pci.h') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 1c02431f1d1a..9494f6dc38eb 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,15 +94,48 @@ This function should be called before the driver calls request_irq() since enabling MSIs disables the pin-based IRQ and the driver will not receive interrupts on the old interrupt. -4.2.2 pci_disable_msi +4.2.2 pci_enable_msi_block + +int pci_enable_msi_block(struct pci_dev *dev, int count) + +This variation on the above call allows a device driver to request multiple +MSIs. The MSI specification only allows interrupts to be allocated in +powers of two, up to a maximum of 2^5 (32). + +If this function returns 0, it has succeeded in allocating at least as many +interrupts as the driver requested (it may have allocated more in order +to satisfy the power-of-two requirement). In this case, the function +enables MSI on this device and updates dev->irq to be the lowest of +the new interrupts assigned to it. The other interrupts assigned to +the device are in the range dev->irq to dev->irq + count - 1. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to request any more MSI interrupts for +this device. If this function returns a positive number, it will be +less than 'count' and indicate the number of interrupts that could have +been allocated. In neither case will the irq value have been +updated, nor will the device have been switched into MSI mode. + +The device driver must decide what action to take if +pci_enable_msi_block() returns a value less than the number asked for. +Some devices can make use of fewer interrupts than the maximum they +request; in this case the driver should call pci_enable_msi_block() +again. Note that it is not guaranteed to succeed, even when the +'count' has been reduced to the value returned from a previous call to +pci_enable_msi_block(). This is because there are multiple constraints +on the number of vectors that can be allocated; pci_enable_msi_block() +will return as soon as it finds any constraint that doesn't allow the +call to succeed. + +4.2.3 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) -This function should be used to undo the effect of pci_enable_msi(). -Calling it restores dev->irq to the pin-based interrupt number and frees -the previously allocated message signaled interrupt(s). The interrupt -may subsequently be assigned to another device, so drivers should not -cache the value of dev->irq. +This function should be used to undo the effect of pci_enable_msi() or +pci_enable_msi_block(). Calling it restores dev->irq to the pin-based +interrupt number and frees the previously allocated message signaled +interrupt(s). The interrupt may subsequently be assigned to another +device, so drivers should not cache the value of dev->irq. A device driver must always call free_irq() on the interrupt(s) for which it has called request_irq() before calling this function. diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c index 3bb7d3dd28be..0c16e2a854e5 100644 --- a/arch/powerpc/kernel/msi.c +++ b/arch/powerpc/kernel/msi.c @@ -19,6 +19,10 @@ int arch_msi_check_device(struct pci_dev* dev, int nvec, int type) return -ENOSYS; } + /* PowerPC doesn't support multiple MSI yet */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; + if (ppc_md.msi_check_device) { pr_debug("msi: Using platform check routine.\n"); return ppc_md.msi_check_device(dev, nvec, type); diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index bc7ac4da90d7..a09549a6321b 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3510,6 +3510,10 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) int index = 0; #endif + /* x86 doesn't support multiple MSI yet */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; + irq_want = nr_irqs_gsi; sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index adcc78242571..6f2e6295e773 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -40,6 +40,13 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct msi_desc *entry; int ret; + /* + * If an architecture wants to support multiple MSI, it needs to + * override arch_setup_msi_irqs() + */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; + list_for_each_entry(entry, &dev->msi_list, list) { ret = arch_setup_msi_irq(dev, entry); if (ret < 0) @@ -58,8 +65,12 @@ void arch_teardown_msi_irqs(struct pci_dev *dev) struct msi_desc *entry; list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq != 0) - arch_teardown_msi_irq(entry->irq); + int i, nvec; + if (entry->irq == 0) + continue; + nvec = 1 << entry->msi_attrib.multiple; + for (i = 0; i < nvec; i++) + arch_teardown_msi_irq(entry->irq + i); } } #endif @@ -163,7 +174,8 @@ static void msi_set_mask_bit(unsigned irq, u32 flag) msix_mask_irq(desc, flag); readl(desc->mask_base); /* Flush write to device */ } else { - msi_mask_irq(desc, 1, flag); + unsigned offset = irq - desc->dev->irq; + msi_mask_irq(desc, 1 << offset, flag << offset); } } @@ -229,6 +241,12 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg) } else { struct pci_dev *dev = entry->dev; int pos = entry->msi_attrib.pos; + u16 msgctl; + + pci_read_config_word(dev, msi_control_reg(pos), &msgctl); + msgctl &= ~PCI_MSI_FLAGS_QSIZE; + msgctl |= entry->msi_attrib.multiple << 4; + pci_write_config_word(dev, msi_control_reg(pos), msgctl); pci_write_config_dword(dev, msi_lower_address_reg(pos), msg->address_lo); @@ -291,7 +309,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev) pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control); msi_mask_irq(entry, msi_capable_mask(control), entry->masked); control &= ~PCI_MSI_FLAGS_QSIZE; - control |= PCI_MSI_FLAGS_ENABLE; + control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control); } @@ -332,13 +350,15 @@ EXPORT_SYMBOL_GPL(pci_restore_msi_state); /** * msi_capability_init - configure device's MSI capability structure * @dev: pointer to the pci_dev data structure of MSI device function + * @nvec: number of interrupts to allocate * - * Setup the MSI capability structure of device function with a single - * MSI irq, regardless of device function is capable of handling - * multiple messages. A return of zero indicates the successful setup - * of an entry zero with the new MSI irq or non-zero for otherwise. - **/ -static int msi_capability_init(struct pci_dev *dev) + * Setup the MSI capability structure of the device with the requested + * number of interrupts. A return value of zero indicates the successful + * setup of an entry with the new MSI irq. A negative return value indicates + * an error, and a positive return value indicates the number of interrupts + * which could have been allocated. + */ +static int msi_capability_init(struct pci_dev *dev, int nvec) { struct msi_desc *entry; int pos, ret; @@ -371,7 +391,7 @@ static int msi_capability_init(struct pci_dev *dev) list_add_tail(&entry->list, &dev->msi_list); /* Configure MSI capability structure */ - ret = arch_setup_msi_irqs(dev, 1, PCI_CAP_ID_MSI); + ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { msi_free_irqs(dev); return ret; @@ -524,35 +544,48 @@ static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type) } /** - * pci_enable_msi - configure device's MSI capability structure - * @dev: pointer to the pci_dev data structure of MSI device function + * pci_enable_msi_block - configure device's MSI capability structure + * @dev: device to configure + * @nvec: number of interrupts to configure * - * Setup the MSI capability structure of device function with - * a single MSI irq upon its software driver call to request for - * MSI mode enabled on its hardware device function. A return of zero - * indicates the successful setup of an entry zero with the new MSI - * irq or non-zero for otherwise. - **/ -int pci_enable_msi(struct pci_dev* dev) + * Allocate IRQs for a device with the MSI capability. + * This function returns a negative errno if an error occurs. If it + * is unable to allocate the number of interrupts requested, it returns + * the number of interrupts it might be able to allocate. If it successfully + * allocates at least the number of interrupts requested, it returns 0 and + * updates the @dev's irq member to the lowest new interrupt number; the + * other interrupt numbers allocated to this device are consecutive. + */ +int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec) { - int status; + int status, pos, maxvec; + u16 msgctl; + + pos = pci_find_capability(dev, PCI_CAP_ID_MSI); + if (!pos) + return -EINVAL; + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + if (nvec > maxvec) + return maxvec; - status = pci_msi_check_device(dev, 1, PCI_CAP_ID_MSI); + status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI); if (status) return status; WARN_ON(!!dev->msi_enabled); - /* Check whether driver already requested for MSI-X irqs */ + /* Check whether driver already requested MSI-X irqs */ if (dev->msix_enabled) { dev_info(&dev->dev, "can't enable MSI " "(MSI-X already enabled)\n"); return -EINVAL; } - status = msi_capability_init(dev); + + status = msi_capability_init(dev, nvec); return status; } -EXPORT_SYMBOL(pci_enable_msi); +EXPORT_SYMBOL(pci_enable_msi_block); void pci_msi_shutdown(struct pci_dev *dev) { @@ -599,8 +632,12 @@ static int msi_free_irqs(struct pci_dev* dev) struct msi_desc *entry, *tmp; list_for_each_entry(entry, &dev->msi_list, list) { - if (entry->irq) - BUG_ON(irq_has_action(entry->irq)); + int i, nvec; + if (!entry->irq) + continue; + nvec = 1 << entry->msi_attrib.multiple; + for (i = 0; i < nvec; i++) + BUG_ON(irq_has_action(entry->irq + i)); } arch_teardown_msi_irqs(dev); diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h index 3898f5237144..71f4df2ef654 100644 --- a/drivers/pci/msi.h +++ b/drivers/pci/msi.h @@ -20,14 +20,8 @@ #define msi_mask_bits_reg(base, is64bit) \ ( (is64bit == 1) ? base+PCI_MSI_MASK_BIT : base+PCI_MSI_MASK_BIT-4) #define msi_disable(control) control &= ~PCI_MSI_FLAGS_ENABLE -#define multi_msi_capable(control) \ - (1 << ((control & PCI_MSI_FLAGS_QMASK) >> 1)) -#define multi_msi_enable(control, num) \ - control |= (((num >> 1) << 4) & PCI_MSI_FLAGS_QSIZE); #define is_64bit_address(control) (!!(control & PCI_MSI_FLAGS_64BIT)) #define is_mask_bit_support(control) (!!(control & PCI_MSI_FLAGS_MASKBIT)) -#define msi_enable(control, num) multi_msi_enable(control, num); \ - control |= PCI_MSI_FLAGS_ENABLE #define msix_table_offset_reg(base) (base + 0x04) #define msix_pba_offset_reg(base) (base + 0x08) diff --git a/include/linux/msi.h b/include/linux/msi.h index 37c1bbe546e5..6991ab5b24d1 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -21,6 +21,7 @@ extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { __u8 is_msix : 1; + __u8 multiple: 3; /* log2 number of messages */ __u8 maskbit : 1; /* mask-pending bit supported ? */ __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ __u8 pos; /* Location of the msi capability */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 7baf2a5db12a..1f6c5ddaae36 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -789,7 +789,7 @@ struct msix_entry { #ifndef CONFIG_PCI_MSI -static inline int pci_enable_msi(struct pci_dev *dev) +static inline int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec) { return -1; } @@ -824,7 +824,7 @@ static inline int pci_msi_enabled(void) return 0; } #else -extern int pci_enable_msi(struct pci_dev *dev); +extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec); extern void pci_msi_shutdown(struct pci_dev *dev); extern void pci_disable_msi(struct pci_dev *dev); extern int pci_msix_table_size(struct pci_dev *dev); @@ -846,6 +846,8 @@ static inline int pcie_aspm_enabled(void) extern int pcie_aspm_enabled(void); #endif +#define pci_enable_msi(pdev) pci_enable_msi_block(pdev, 1) + #ifdef CONFIG_HT_IRQ /* The functions a driver should call */ int ht_create_irq(struct pci_dev *dev, int idx); -- cgit v1.2.3 From d1b054da8f599905f3c18a218961dcf17f9d5f13 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:11 +0800 Subject: PCI: initialize and release SR-IOV capability If a device has the SR-IOV capability, initialize it (set the ARI Capable Hierarchy in the lowest numbered PF if necessary; calculate the System Page Size for the VF MMIO, probe the VF Offset, Stride and BARs). A lock for the VF bus allocation is also initialized if a PF is the lowest numbered PF. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- drivers/pci/Kconfig | 10 +++ drivers/pci/Makefile | 2 + drivers/pci/iov.c | 182 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.c | 7 ++ drivers/pci/pci.h | 37 ++++++++++ drivers/pci/probe.c | 4 ++ include/linux/pci.h | 11 +++ include/linux/pci_regs.h | 33 +++++++++ 8 files changed, 286 insertions(+) create mode 100644 drivers/pci/iov.c (limited to 'include/linux/pci.h') diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 2a4501dd2515..fdc864f9cf23 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -59,3 +59,13 @@ 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 + help + I/O Virtualization is a PCI feature supported by some devices + which allows them to create virtual devices which share their + physical resources. + + If unsure, say N. diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 3d07ce24f6a8..ba6af162fd39 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -29,6 +29,8 @@ obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o +obj-$(CONFIG_PCI_IOV) += iov.o + # # Some architectures use the generic PCI setup functions # diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c new file mode 100644 index 000000000000..66cc414ed15f --- /dev/null +++ b/drivers/pci/iov.c @@ -0,0 +1,182 @@ +/* + * drivers/pci/iov.c + * + * Copyright (C) 2009 Intel Corporation, Yu Zhao + * + * PCI Express I/O Virtualization (IOV) support. + * Single Root IOV 1.0 + */ + +#include +#include +#include +#include +#include "pci.h" + + +static int sriov_init(struct pci_dev *dev, int pos) +{ + int i; + int rc; + int nres; + u32 pgsz; + u16 ctrl, total, offset, stride; + struct pci_sriov *iov; + struct resource *res; + struct pci_dev *pdev; + + if (dev->pcie_type != PCI_EXP_TYPE_RC_END && + dev->pcie_type != PCI_EXP_TYPE_ENDPOINT) + return -ENODEV; + + pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl); + if (ctrl & PCI_SRIOV_CTRL_VFE) { + pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, 0); + ssleep(1); + } + + pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total); + if (!total) + return 0; + + ctrl = 0; + list_for_each_entry(pdev, &dev->bus->devices, bus_list) + if (pdev->is_physfn) + goto found; + + pdev = NULL; + if (pci_ari_enabled(dev->bus)) + ctrl |= PCI_SRIOV_CTRL_ARI; + +found: + pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, ctrl); + pci_write_config_word(dev, pos + PCI_SRIOV_NUM_VF, total); + pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &offset); + pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &stride); + if (!offset || (total > 1 && !stride)) + return -EIO; + + pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &pgsz); + i = PAGE_SHIFT > 12 ? PAGE_SHIFT - 12 : 0; + pgsz &= ~((1 << i) - 1); + if (!pgsz) + return -EIO; + + pgsz &= ~(pgsz - 1); + pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz); + + nres = 0; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = dev->resource + PCI_IOV_RESOURCES + i; + i += __pci_read_base(dev, pci_bar_unknown, res, + pos + PCI_SRIOV_BAR + i * 4); + if (!res->flags) + continue; + if (resource_size(res) & (PAGE_SIZE - 1)) { + rc = -EIO; + goto failed; + } + res->end = res->start + resource_size(res) * total - 1; + nres++; + } + + iov = kzalloc(sizeof(*iov), GFP_KERNEL); + if (!iov) { + rc = -ENOMEM; + goto failed; + } + + iov->pos = pos; + iov->nres = nres; + iov->ctrl = ctrl; + iov->total = total; + iov->offset = offset; + iov->stride = stride; + iov->pgsz = pgsz; + iov->self = dev; + pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap); + pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link); + + if (pdev) + iov->dev = pci_dev_get(pdev); + else { + iov->dev = dev; + mutex_init(&iov->lock); + } + + dev->sriov = iov; + dev->is_physfn = 1; + + return 0; + +failed: + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = dev->resource + PCI_IOV_RESOURCES + i; + res->flags = 0; + } + + return rc; +} + +static void sriov_release(struct pci_dev *dev) +{ + if (dev == dev->sriov->dev) + mutex_destroy(&dev->sriov->lock); + else + pci_dev_put(dev->sriov->dev); + + kfree(dev->sriov); + dev->sriov = NULL; +} + +/** + * pci_iov_init - initialize the IOV capability + * @dev: the PCI device + * + * Returns 0 on success, or negative on failure. + */ +int pci_iov_init(struct pci_dev *dev) +{ + int pos; + + if (!dev->is_pcie) + return -ENODEV; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV); + if (pos) + return sriov_init(dev, pos); + + return -ENODEV; +} + +/** + * pci_iov_release - release resources used by the IOV capability + * @dev: the PCI device + */ +void pci_iov_release(struct pci_dev *dev) +{ + if (dev->is_physfn) + sriov_release(dev); +} + +/** + * pci_iov_resource_bar - get position of the SR-IOV BAR + * @dev: the PCI device + * @resno: the resource number + * @type: the BAR type to be filled in + * + * Returns position of the BAR encapsulated in the SR-IOV capability. + */ +int pci_iov_resource_bar(struct pci_dev *dev, int resno, + enum pci_bar_type *type) +{ + if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END) + return 0; + + BUG_ON(!dev->is_physfn); + + *type = pci_bar_unknown; + + return dev->sriov->pos + PCI_SRIOV_BAR + + 4 * (resno - PCI_IOV_RESOURCES); +} diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a35a8b2ba631..2b3201ec2b05 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2360,12 +2360,19 @@ 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); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 2cd1cba7236f..7d5327c986f5 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -201,4 +201,41 @@ resource_size_t pci_specified_resource_alignment(struct pci_dev *dev); extern void pci_disable_bridge_window(struct pci_dev *dev); #endif +/* 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 *dev; /* 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 */ diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 579a56c8181f..0471f6ea1466 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -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); } /** @@ -979,6 +980,9 @@ 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) diff --git a/include/linux/pci.h b/include/linux/pci.h index 1f6c5ddaae36..8ce2f2d9ab63 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -93,6 +93,12 @@ enum { /* #6: expansion ROM resource */ PCI_ROM_RESOURCE, + /* device specific resources */ +#ifdef CONFIG_PCI_IOV + PCI_IOV_RESOURCES, + PCI_IOV_RESOURCE_END = PCI_IOV_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. @@ -257,6 +264,7 @@ struct pci_dev { unsigned int is_managed:1; unsigned int is_pcie:1; unsigned int state_saved:1; + unsigned int is_physfn:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -270,6 +278,9 @@ struct pci_dev { struct list_head msi_list; #endif struct pci_vpd *vpd; +#ifdef CONFIG_PCI_IOV + struct pci_sriov *sriov; /* SR-IOV capability related */ +#endif }; extern struct pci_dev *alloc_pci_dev(void); diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index b647a4df59fc..d4e663877f45 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -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 */ -- cgit v1.2.3 From dd7cc44d0bcec5e9c42fe52e88dc254ae62eac8d Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:15 +0800 Subject: PCI: add SR-IOV API for Physical Function driver Add or remove the Virtual Function when the SR-IOV is enabled or disabled by the device driver. This can happen anytime rather than only at the device probe stage. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- drivers/pci/iov.c | 314 ++++++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 2 + include/linux/pci.h | 19 +++- 3 files changed, 334 insertions(+), 1 deletion(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 5ddfc09a8d3f..d0ff8ad8f7ba 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -13,6 +13,7 @@ #include #include "pci.h" +#define VIRTFN_ID_LEN 16 static inline u8 virtfn_bus(struct pci_dev *dev, int id) { @@ -26,6 +27,284 @@ static inline u8 virtfn_devfn(struct pci_dev *dev, int id) dev->sriov->stride * id) & 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; + 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; + + mutex_lock(&iov->dev->sriov->lock); + virtfn->bus = virtfn_add_bus(dev->bus, virtfn_bus(dev, id)); + if (!virtfn->bus) { + kfree(virtfn); + mutex_unlock(&iov->dev->sriov->lock); + return -ENOMEM; + } + virtfn->devfn = virtfn_devfn(dev, id); + virtfn->vendor = dev->vendor; + pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device); + pci_setup_device(virtfn); + virtfn->dev.parent = dev->dev.parent; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = dev->resource + PCI_IOV_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->dev->sriov->lock); + + virtfn->physfn = pci_dev_get(dev); + virtfn->is_virtfn = 1; + + rc = pci_bus_add_device(virtfn); + if (rc) + goto failed1; + sprintf(buf, "virtfn%u", id); + rc = sysfs_create_link(&dev->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(&dev->dev.kobj, buf); +failed1: + pci_dev_put(dev); + mutex_lock(&iov->dev->sriov->lock); + pci_remove_bus_device(virtfn); + virtfn_remove_bus(dev->bus, virtfn_bus(dev, id)); + mutex_unlock(&iov->dev->sriov->lock); + + return rc; +} + +static void virtfn_remove(struct pci_dev *dev, int id, int reset) +{ + char buf[VIRTFN_ID_LEN]; + struct pci_bus *bus; + struct pci_dev *virtfn; + struct pci_sriov *iov = dev->sriov; + + bus = pci_find_bus(pci_domain_nr(dev->bus), virtfn_bus(dev, id)); + if (!bus) + return; + + virtfn = pci_get_slot(bus, virtfn_devfn(dev, id)); + if (!virtfn) + return; + + pci_dev_put(virtfn); + + if (reset) { + device_release_driver(&virtfn->dev); + pci_execute_reset_function(virtfn); + } + + sprintf(buf, "virtfn%u", id); + sysfs_remove_link(&dev->dev.kobj, buf); + sysfs_remove_link(&virtfn->dev.kobj, "physfn"); + + mutex_lock(&iov->dev->sriov->lock); + pci_remove_bus_device(virtfn); + virtfn_remove_bus(dev->bus, virtfn_bus(dev, id)); + mutex_unlock(&iov->dev->sriov->lock); + + pci_dev_put(dev); +} + +static int sriov_enable(struct pci_dev *dev, int nr_virtfn) +{ + int rc; + int i, j; + int nres; + u16 offset, stride, initial; + struct resource *res; + struct pci_dev *pdev; + 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_IOV_RESOURCES + i; + if (res->parent) + nres++; + } + if (nres != iov->nres) { + dev_err(&dev->dev, "not enough MMIO resources for SR-IOV\n"); + return -ENOMEM; + } + + iov->offset = offset; + iov->stride = stride; + + if (virtfn_bus(dev, nr_virtfn - 1) > dev->bus->subordinate) { + dev_err(&dev->dev, "SR-IOV: bus number out of range\n"); + return -ENOMEM; + } + + if (iov->link != dev->devfn) { + pdev = pci_get_slot(dev->bus, iov->link); + if (!pdev) + return -ENODEV; + + pci_dev_put(pdev); + + if (!pdev->is_physfn) + return -ENODEV; + + rc = sysfs_create_link(&dev->dev.kobj, + &pdev->dev.kobj, "dep_link"); + if (rc) + return rc; + } + + 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 failed; + } + + kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE); + iov->nr_virtfn = nr_virtfn; + + return 0; + +failed: + 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(&dev->dev.kobj, "dep_link"); + + 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(&dev->dev.kobj, "dep_link"); + + iov->nr_virtfn = 0; +} + static int sriov_init(struct pci_dev *dev, int pos) { int i; @@ -132,6 +411,8 @@ failed: static void sriov_release(struct pci_dev *dev) { + BUG_ON(dev->sriov->nr_virtfn); + if (dev == dev->sriov->dev) mutex_destroy(&dev->sriov->lock); else @@ -155,6 +436,7 @@ static void sriov_restore_state(struct pci_dev *dev) pci_update_resource(dev, i); 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); @@ -245,3 +527,35 @@ 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->is_physfn) + 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->is_physfn) + return; + + sriov_disable(dev); +} +EXPORT_SYMBOL_GPL(pci_disable_sriov); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index f4fc10fc5872..0f1c7d103509 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -209,6 +209,8 @@ 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 */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 8ce2f2d9ab63..c2e491e04063 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -265,6 +265,7 @@ struct pci_dev { unsigned int is_pcie:1; unsigned int state_saved:1; unsigned int is_physfn:1; + unsigned int is_virtfn:1; pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -279,7 +280,10 @@ struct pci_dev { #endif struct pci_vpd *vpd; #ifdef CONFIG_PCI_IOV - struct pci_sriov *sriov; /* SR-IOV capability related */ + union { + struct pci_sriov *sriov; /* SR-IOV capability related */ + struct pci_dev *physfn; /* the PF this VF is associated with */ + }; #endif }; @@ -1212,5 +1216,18 @@ 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 */ -- cgit v1.2.3 From 74bb1bcc7dbbc9ddef773bf3395d7ff92aaaad2e Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 20 Mar 2009 11:25:16 +0800 Subject: PCI: handle SR-IOV Virtual Function Migration Add or remove a Virtual Function after receiving a Migrate In or Out Request. Reviewed-by: Matthew Wilcox Signed-off-by: Yu Zhao Signed-off-by: Jesse Barnes --- drivers/pci/iov.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 4 ++ include/linux/pci.h | 6 +++ 3 files changed, 129 insertions(+) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index d0ff8ad8f7ba..7227efc760db 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -179,6 +179,97 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset) pci_dev_put(dev); } +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(dev, 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; @@ -261,6 +352,12 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) goto failed; } + if (iov->cap & PCI_SRIOV_CAP_VFM) { + rc = sriov_enable_migration(dev, nr_virtfn); + if (rc) + goto failed; + } + kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE); iov->nr_virtfn = nr_virtfn; @@ -290,6 +387,9 @@ 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); @@ -559,3 +659,22 @@ 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->is_physfn) + return IRQ_NONE; + + return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE; +} +EXPORT_SYMBOL_GPL(pci_sriov_migration); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 0f1c7d103509..22dcfdb75d91 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -1,6 +1,8 @@ #ifndef DRIVERS_PCI_H #define DRIVERS_PCI_H +#include + #define PCI_CFG_SPACE_SIZE 256 #define PCI_CFG_SPACE_EXP_SIZE 4096 @@ -218,6 +220,8 @@ struct pci_sriov { struct pci_dev *dev; /* 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 */ }; #ifdef CONFIG_PCI_IOV diff --git a/include/linux/pci.h b/include/linux/pci.h index c2e491e04063..1216843412da 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -52,6 +52,7 @@ #include #include #include +#include /* Include the ID list */ #include @@ -1219,6 +1220,7 @@ 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) { @@ -1227,6 +1229,10 @@ 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__ */ -- cgit v1.2.3 From 79af72d716cf1bb13b175429cf181a6c4d063ee8 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Fri, 20 Mar 2009 14:55:55 -0600 Subject: PCI: pci_is_root_bus helper Introduce pci_is_root_bus helper function. This will help make code more consistent, as well as prevent incorrect assumptions (such as pci_bus->self == NULL on a root bus, which is not always true). Signed-off-by: Kenji Kaneshige Signed-off-by: Alex Chiang Signed-off-by: Jesse Barnes --- include/linux/pci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/pci.h') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1216843412da..50d94388e87c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -357,6 +357,15 @@ struct pci_bus { #define pci_bus_b(n) list_entry(n, struct pci_bus, node) #define to_pci_bus(n) container_of(n, struct pci_bus, dev) +/* + * Returns true if the pci bus is root (behind host-pci bridge), + * false otherwise + */ +static inline bool pci_is_root_bus(struct pci_bus *pbus) +{ + return !(pbus->parent); +} + #ifdef CONFIG_PCI_MSI static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { -- cgit v1.2.3 From 3ed4fd96b3188406ac5357d9290bcffa08c65cf6 Mon Sep 17 00:00:00 2001 From: Alex Chiang Date: Fri, 20 Mar 2009 14:56:25 -0600 Subject: PCI: Introduce pci_rescan_bus() This API is used by the PCI core to rescan a bus and rediscover newly added devices. Over time, it is expected that the various PCI hotplug drivers will migrate to this interface and away from the old pci_do_scan_bus() interface. Signed-off-by: Alex Chiang Signed-off-by: Jesse Barnes --- drivers/pci/hotplug/fakephp.c | 6 +++--- drivers/pci/probe.c | 32 ++++++++++++++++++++++++++++++++ include/linux/pci.h | 3 +++ 3 files changed, 38 insertions(+), 3 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c index d8649e127298..16063745766e 100644 --- a/drivers/pci/hotplug/fakephp.c +++ b/drivers/pci/hotplug/fakephp.c @@ -245,12 +245,12 @@ static int pci_rescan_slot(struct pci_dev *temp) /** - * pci_rescan_bus - Rescan PCI bus + * pci_rescan_bus_local - fakephp version of rescan PCI bus * @bus: the PCI bus to rescan * * Call pci_rescan_slot for each possible function of the bus. */ -static void pci_rescan_bus(const struct pci_bus *bus) +static void pci_rescan_bus_local(const struct pci_bus *bus) { unsigned int devfn; struct pci_dev *dev; @@ -291,7 +291,7 @@ static void pci_rescan_buses(const struct list_head *list) const struct list_head *l; list_for_each(l,list) { const struct pci_bus *b = pci_bus_b(l); - pci_rescan_bus(b); + pci_rescan_bus_local(b); pci_rescan_buses(&b->children); } } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index f69256c63b2b..60a8e5fec6c5 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1212,6 +1212,38 @@ struct pci_bus * __devinit pci_scan_bus_parented(struct device *parent, EXPORT_SYMBOL(pci_scan_bus_parented); #ifdef CONFIG_HOTPLUG +/** + * pci_rescan_bus - scan a PCI bus for devices. + * @bus: PCI bus to scan + * + * Scan a PCI bus and child buses for new devices, adds them, + * and enables them. + * + * Returns the max number of subordinate bus discovered. + */ +unsigned int __devinit pci_rescan_bus(struct pci_bus *bus) +{ + unsigned int max; + struct pci_dev *dev; + + max = pci_scan_child_bus(bus); + + up_read(&pci_bus_sem); + list_for_each_entry(dev, &bus->devices, bus_list) + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) + if (dev->subordinate) + pci_bus_size_bridges(dev->subordinate); + down_read(&pci_bus_sem); + + pci_bus_assign_resources(bus); + pci_enable_bridges(bus); + pci_bus_add_devices(bus); + + return max; +} +EXPORT_SYMBOL_GPL(pci_rescan_bus); + EXPORT_SYMBOL(pci_add_new_bus); EXPORT_SYMBOL(pci_scan_slot); EXPORT_SYMBOL(pci_scan_bridge); diff --git a/include/linux/pci.h b/include/linux/pci.h index 50d94388e87c..6fb335b0d74f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -726,6 +726,9 @@ int pci_back_from_sleep(struct pci_dev *dev); /* Functions for PCI Hotplug drivers to use */ int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap); +#ifdef CONFIG_HOTPLUG +unsigned int pci_rescan_bus(struct pci_bus *bus); +#endif /* Vital product data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); -- cgit v1.2.3