From 6675a601d72be408025e675599702e30a99188aa Mon Sep 17 00:00:00 2001 From: Murali Karicheri Date: Tue, 3 Mar 2015 12:52:11 -0500 Subject: PCI: Add helper functions pci_get[put]_host_bridge_device() Add helper functions to get/put the root bus's host bridge device. Tested-by: Suravee Suthikulpanit (AMD Seattle) Signed-off-by: Murali Karicheri Signed-off-by: Bjorn Helgaas Reviewed-by: Catalin Marinas Acked-by: Will Deacon CC: Joerg Roedel CC: Grant Likely CC: Rob Herring CC: Russell King CC: Arnd Bergmann --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/pci.h') diff --git a/include/linux/pci.h b/include/linux/pci.h index 211e9da8a7d7..a379513bddef 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -510,6 +510,9 @@ static inline struct pci_dev *pci_upstream_bridge(struct pci_dev *dev) return dev->bus->self; } +struct device *pci_get_host_bridge_device(struct pci_dev *dev); +void pci_put_host_bridge_device(struct device *dev); + #ifdef CONFIG_PCI_MSI static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { -- cgit v1.2.3 From 0e6c9122a6ec96d19f1db61e9750287d86b6829c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 25 Mar 2015 16:23:44 +0800 Subject: PCI: Keep individual VF BAR size in struct pci_sriov Currently we don't store the individual VF BAR size. We calculate it when needed by dividing the PF's IOV resource size (which contains space for *all* the VFs) by total_VFs or by reading the BAR in the SR-IOV capability again. Keep the individual VF BAR size in struct pci_sriov.barsz[], add pci_iov_resource_size() to retrieve it, and use that instead of doing the division or reading the SR-IOV capability BAR. [bhelgaas: rename to "barsz[]", simplify barsz[] index computation, remove SR-IOV capability BAR sizing] Signed-off-by: Wei Yang Acked-by: Bjorn Helgaas Signed-off-by: Benjamin Herrenschmidt --- drivers/pci/iov.c | 39 ++++++++++++++++++++------------------- drivers/pci/pci.h | 1 + include/linux/pci.h | 3 +++ 3 files changed, 24 insertions(+), 19 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 05f9d97e4175..5bca0e1a2799 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -57,6 +57,14 @@ static void virtfn_remove_bus(struct pci_bus *physbus, struct pci_bus *virtbus) pci_remove_bus(virtbus); } +resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) +{ + if (!dev->is_physfn) + return 0; + + return dev->sriov->barsz[resno - PCI_IOV_RESOURCES]; +} + static int virtfn_add(struct pci_dev *dev, int id, int reset) { int i; @@ -92,8 +100,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset) continue; virtfn->resource[i].name = pci_name(virtfn); virtfn->resource[i].flags = res->flags; - size = resource_size(res); - do_div(size, iov->total_VFs); + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); 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]); @@ -311,7 +318,7 @@ static void sriov_disable(struct pci_dev *dev) static int sriov_init(struct pci_dev *dev, int pos) { - int i; + int i, bar64; int rc; int nres; u32 pgsz; @@ -360,29 +367,29 @@ found: pgsz &= ~(pgsz - 1); pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz); + iov = kzalloc(sizeof(*iov), GFP_KERNEL); + if (!iov) + return -ENOMEM; + 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); + bar64 = __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; } + iov->barsz[i] = resource_size(res); res->end = res->start + resource_size(res) * total - 1; dev_info(&dev->dev, "VF(n) BAR%d space: %pR (contains BAR%d for %d VFs)\n", i, res, i, total); + i += bar64; nres++; } - iov = kzalloc(sizeof(*iov), GFP_KERNEL); - if (!iov) { - rc = -ENOMEM; - goto failed; - } - iov->pos = pos; iov->nres = nres; iov->ctrl = ctrl; @@ -414,6 +421,7 @@ failed: res->flags = 0; } + kfree(iov); return rc; } @@ -510,14 +518,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno) */ resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno) { - struct resource tmp; - int reg = pci_iov_resource_bar(dev, resno); - - if (!reg) - return 0; - - __pci_read_base(dev, pci_bar_unknown, &tmp, reg); - return resource_alignment(&tmp); + return pci_iov_resource_size(dev, resno); } /** diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4091f82239cd..57329645dd01 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -247,6 +247,7 @@ struct pci_sriov { struct pci_dev *dev; /* lowest numbered PF */ struct pci_dev *self; /* this PF */ struct mutex lock; /* lock for VF bus */ + resource_size_t barsz[PCI_SRIOV_NUM_BARS]; /* VF BAR size */ }; #ifdef CONFIG_PCI_ATS diff --git a/include/linux/pci.h b/include/linux/pci.h index 211e9da8a7d7..15596582e575 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1675,6 +1675,7 @@ int pci_num_vf(struct pci_dev *dev); int pci_vfs_assigned(struct pci_dev *dev); int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); int pci_sriov_get_totalvfs(struct pci_dev *dev); +resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno); #else static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } @@ -1686,6 +1687,8 @@ static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { return 0; } static inline int pci_sriov_get_totalvfs(struct pci_dev *dev) { return 0; } +static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) +{ return 0; } #endif #if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE) -- cgit v1.2.3 From b07579c0924eee1543eb6cd2c19544d15a4b5236 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 25 Mar 2015 16:23:48 +0800 Subject: PCI: Export pci_iov_virtfn_bus() and pci_iov_virtfn_devfn() On PowerNV, some resource reservation is needed for SR-IOV VFs that don't exist at the bootup stage. To do the match between resources and VFs, the code need to get the VF's BDF in advance. Rename virtfn_bus() and virtfn_devfn() to pci_iov_virtfn_bus() and pci_iov_virtfn_devfn() and export them. [bhelgaas: changelog, make "busnr" int] Signed-off-by: Wei Yang Acked-by: Bjorn Helgaas Signed-off-by: Benjamin Herrenschmidt --- drivers/pci/iov.c | 28 ++++++++++++++++------------ include/linux/pci.h | 11 +++++++++++ 2 files changed, 27 insertions(+), 12 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 2ae921f84bd3..5643a1011e23 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -19,16 +19,20 @@ #define VIRTFN_ID_LEN 16 -static inline u8 virtfn_bus(struct pci_dev *dev, int id) +int pci_iov_virtfn_bus(struct pci_dev *dev, int vf_id) { + if (!dev->is_physfn) + return -EINVAL; return dev->bus->number + ((dev->devfn + dev->sriov->offset + - dev->sriov->stride * id) >> 8); + dev->sriov->stride * vf_id) >> 8); } -static inline u8 virtfn_devfn(struct pci_dev *dev, int id) +int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id) { + if (!dev->is_physfn) + return -EINVAL; return (dev->devfn + dev->sriov->offset + - dev->sriov->stride * id) & 0xff; + dev->sriov->stride * vf_id) & 0xff; } /* @@ -58,11 +62,11 @@ static inline u8 virtfn_max_buses(struct pci_dev *dev) struct pci_sriov *iov = dev->sriov; int nr_virtfn; u8 max = 0; - u8 busnr; + int busnr; for (nr_virtfn = 1; nr_virtfn <= iov->total_VFs; nr_virtfn++) { pci_iov_set_numvfs(dev, nr_virtfn); - busnr = virtfn_bus(dev, nr_virtfn - 1); + busnr = pci_iov_virtfn_bus(dev, nr_virtfn - 1); if (busnr > max) max = busnr; } @@ -116,7 +120,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset) struct pci_bus *bus; mutex_lock(&iov->dev->sriov->lock); - bus = virtfn_add_bus(dev->bus, virtfn_bus(dev, id)); + bus = virtfn_add_bus(dev->bus, pci_iov_virtfn_bus(dev, id)); if (!bus) goto failed; @@ -124,7 +128,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset) if (!virtfn) goto failed0; - virtfn->devfn = virtfn_devfn(dev, id); + virtfn->devfn = pci_iov_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); @@ -186,8 +190,8 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset) struct pci_sriov *iov = dev->sriov; virtfn = pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus), - virtfn_bus(dev, id), - virtfn_devfn(dev, id)); + pci_iov_virtfn_bus(dev, id), + pci_iov_virtfn_devfn(dev, id)); if (!virtfn) return; @@ -226,7 +230,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) struct pci_dev *pdev; struct pci_sriov *iov = dev->sriov; int bars = 0; - u8 bus; + int bus; if (!nr_virtfn) return 0; @@ -263,7 +267,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) iov->offset = offset; iov->stride = stride; - bus = virtfn_bus(dev, nr_virtfn - 1); + bus = pci_iov_virtfn_bus(dev, nr_virtfn - 1); if (bus > dev->bus->busn_res.end) { dev_err(&dev->dev, "can't enable %d VFs (bus %02x out of range of %pR)\n", nr_virtfn, bus, &dev->bus->busn_res); diff --git a/include/linux/pci.h b/include/linux/pci.h index 15596582e575..99ea94835fb6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1669,6 +1669,9 @@ int pci_ext_cfg_avail(void); void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV +int pci_iov_virtfn_bus(struct pci_dev *dev, int id); +int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); + int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); int pci_num_vf(struct pci_dev *dev); @@ -1677,6 +1680,14 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); int pci_sriov_get_totalvfs(struct pci_dev *dev); resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno); #else +static inline int pci_iov_virtfn_bus(struct pci_dev *dev, int id) +{ + return -ENOSYS; +} +static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) +{ + return -ENOSYS; +} 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) { } -- cgit v1.2.3 From 978d2d68312326b715a5913aaab1eaf24fe99108 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 25 Mar 2015 16:23:50 +0800 Subject: PCI: Add pcibios_iov_resource_alignment() interface Per the SR-IOV spec r1.1, sec 3.3.14, the required alignment of a PF's IOV BAR is the size of an individual VF BAR, and the size consumed is the individual VF BAR size times NumVFs. The PowerNV platform has additional alignment requirements to help support its Partitionable Endpoint device isolation feature (see Documentation/powerpc/pci_iov_resource_on_powernv.txt). Add a pcibios_iov_resource_alignment() interface to allow platforms to request additional alignment. [bhelgaas: changelog, adapt to reworked pci_sriov_resource_alignment(), drop "align" parameter] Signed-off-by: Wei Yang Acked-by: Bjorn Helgaas Signed-off-by: Benjamin Herrenschmidt --- drivers/pci/iov.c | 8 +++++++- include/linux/pci.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 64c46925c62d..ee0ebff103a4 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -569,6 +569,12 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno) 4 * (resno - PCI_IOV_RESOURCES); } +resource_size_t __weak pcibios_iov_resource_alignment(struct pci_dev *dev, + int resno) +{ + return pci_iov_resource_size(dev, resno); +} + /** * pci_sriov_resource_alignment - get resource alignment for VF BAR * @dev: the PCI device @@ -581,7 +587,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno) */ resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno) { - return pci_iov_resource_size(dev, resno); + return pcibios_iov_resource_alignment(dev, resno); } /** diff --git a/include/linux/pci.h b/include/linux/pci.h index 99ea94835fb6..4e1f17db1a81 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1174,6 +1174,7 @@ unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); resource_size_t pcibios_window_alignment(struct pci_bus *bus, unsigned long type); +resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); #define PCI_VGA_STATE_CHANGE_BRIDGE (1 << 0) #define PCI_VGA_STATE_CHANGE_DECODES (1 << 1) -- cgit v1.2.3 From e33caa82e221b0bbeba373b507e3f134dc2efa1a Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Wed, 25 Mar 2015 14:37:06 +0800 Subject: PCI/ACPI: Optimize device state transition delays The PCI "ACPI additions for FW latency optimizations" ECN (link below) defines two functions in the PCI _DSM: Function 8, "Reset Delay," applies to the entire hierarchy below a PCI host bridge. If it returns one, the OS may assume that all devices in the hierarchy have already completed power-on reset delays. Function 9, "Device Readiness Durations," applies only to the object where it is located. It returns delay durations required after various events if the device requires less time than the spec requires. Delays from this function take precedence over the Reset Delay function. Add support for Reset Delay and part of Device Readiness Durations. [bhelgaas: changelog, comments] Link: https://www.pcisig.com/specifications/conventional/pci_firmware/ECN_fw_latency_optimization_final.pdf Signed-off-by: Aaron Lu Signed-off-by: Bjorn Helgaas --- drivers/pci/pci-acpi.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci-acpi.h | 2 ++ include/linux/pci.h | 1 + 3 files changed, 77 insertions(+) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index bea6be4992c3..5eba74716900 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -537,11 +537,32 @@ static struct pci_platform_pm_ops acpi_pci_platform_pm = { void acpi_pci_add_bus(struct pci_bus *bus) { + union acpi_object *obj; + struct pci_host_bridge *bridge; + if (acpi_pci_disabled || !bus->bridge) return; acpi_pci_slot_enumerate(bus); acpiphp_enumerate_slots(bus); + + /* + * For a host bridge, check its _DSM for function 8 and if + * that is available, mark it in pci_host_bridge. + */ + if (!pci_is_root_bus(bus)) + return; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(bus->bridge), pci_acpi_dsm_uuid, 3, + RESET_DELAY_DSM, NULL); + if (!obj) + return; + + if (obj->type == ACPI_TYPE_INTEGER && obj->integer.value == 1) { + bridge = pci_find_host_bridge(bus); + bridge->ignore_reset_delay = 1; + } + ACPI_FREE(obj); } void acpi_pci_remove_bus(struct pci_bus *bus) @@ -567,6 +588,57 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev) check_children); } +/** + * pci_acpi_optimize_delay - optimize PCI D3 and D3cold delay from ACPI + * @pdev: the PCI device whose delay is to be updated + * @adev: the companion ACPI device of this PCI device + * + * Update the d3_delay and d3cold_delay of a PCI device from the ACPI _DSM + * control method of either the device itself or the PCI host bridge. + * + * Function 8, "Reset Delay," applies to the entire hierarchy below a PCI + * host bridge. If it returns one, the OS may assume that all devices in + * the hierarchy have already completed power-on reset delays. + * + * Function 9, "Device Readiness Durations," applies only to the object + * where it is located. It returns delay durations required after various + * events if the device requires less time than the spec requires. Delays + * from this function take precedence over the Reset Delay function. + * + * These _DSM functions are defined by the draft ECN of January 28, 2014, + * titled "ACPI additions for FW latency optimizations." + */ +static void pci_acpi_optimize_delay(struct pci_dev *pdev, + acpi_handle handle) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); + int value; + union acpi_object *obj, *elements; + + if (bridge->ignore_reset_delay) + pdev->d3cold_delay = 0; + + obj = acpi_evaluate_dsm(handle, pci_acpi_dsm_uuid, 3, + FUNCTION_DELAY_DSM, NULL); + if (!obj) + return; + + if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 5) { + elements = obj->package.elements; + if (elements[0].type == ACPI_TYPE_INTEGER) { + value = (int)elements[0].integer.value / 1000; + if (value < PCI_PM_D3COLD_WAIT) + pdev->d3cold_delay = value; + } + if (elements[3].type == ACPI_TYPE_INTEGER) { + value = (int)elements[3].integer.value / 1000; + if (value < PCI_PM_D3_WAIT) + pdev->d3_delay = value; + } + } + ACPI_FREE(obj); +} + static void pci_acpi_setup(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -575,6 +647,8 @@ static void pci_acpi_setup(struct device *dev) if (!adev) return; + pci_acpi_optimize_delay(pci_dev, adev->handle); + pci_acpi_add_pm_notifier(adev, pci_dev); if (!adev->wakeup.flags.valid) return; diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 3801c704a945..a965efa52152 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -79,6 +79,8 @@ static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { } extern const u8 pci_acpi_dsm_uuid[]; #define DEVICE_LABEL_DSM 0x07 +#define RESET_DELAY_DSM 0x08 +#define FUNCTION_DELAY_DSM 0x09 #else /* CONFIG_ACPI */ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } diff --git a/include/linux/pci.h b/include/linux/pci.h index 211e9da8a7d7..c5aa7b8a40c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -406,6 +406,7 @@ struct pci_host_bridge { struct list_head windows; /* resource_entry */ void (*release_fn)(struct pci_host_bridge *); void *release_data; + unsigned int ignore_reset_delay:1; /* for entire hierarchy */ }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) -- cgit v1.2.3