From 29ed1f29b68a8395d5679b3c4e38352b617b3236 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 19 Jul 2013 12:14:16 -0700 Subject: PCI: pciehp: Fix null pointer deref when hot-removing SR-IOV device Hot-removing a device with SR-IOV enabled causes a null pointer dereference in v3.9 and v3.10. This is a regression caused by ba518e3c17 ("PCI: pciehp: Iterate over all devices in slot, not functions 0-7"). When we iterate over the bus->devices list, we first remove the PF, which also removes all the VFs from the list. Then the list iterator blows up because more than just the current entry was removed from the list. ac205b7bb7 ("PCI: make sriov work with hotplug remove") works around a similar problem in pci_stop_bus_devices() by iterating over the list in reverse, so the VFs are stopped and removed from the list first, before the PF. This patch changes pciehp_unconfigure_device() to iterate over the list in reverse, too. [bhelgaas: bugzilla, changelog] Reference: https://bugzilla.kernel.org/show_bug.cgi?id=60604 Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas Acked-by: Yijing Wang CC: stable@vger.kernel.org # v3.9+--- drivers/pci/hotplug/pciehp_pci.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c index aac7a40e4a4a..0e0d0f7f63fd 100644 --- a/drivers/pci/hotplug/pciehp_pci.c +++ b/drivers/pci/hotplug/pciehp_pci.c @@ -92,7 +92,14 @@ int pciehp_unconfigure_device(struct slot *p_slot) if (ret) presence = 0; - list_for_each_entry_safe(dev, temp, &parent->devices, bus_list) { + /* + * Stopping an SR-IOV PF device removes all the associated VFs, + * which will update the bus->devices list and confuse the + * iterator. Therefore, iterate in reverse so we remove the VFs + * first, then the PF. We do the same in pci_stop_bus_device(). + */ + list_for_each_entry_safe_reverse(dev, temp, &parent->devices, + bus_list) { pci_dev_get(dev); if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && presence) { pci_read_config_byte(dev, PCI_BRIDGE_CONTROL, &bctl); -- cgit v1.2.3 From 7cd29f4b22be3c3468871f5240621a32d9bc903a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 24 Jul 2013 11:36:31 -0600 Subject: PCI: hotplug: Convert to be builtin only, not modular Convert CONFIG_HOTPLUG_PCI from tristate to bool. This only affects the hotplug core; several of the hotplug drivers can still be modules. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki Acked-by: Yinghai Lu --- arch/ia64/configs/generic_defconfig | 2 +- arch/ia64/configs/gensparse_defconfig | 2 +- arch/ia64/configs/tiger_defconfig | 2 +- arch/ia64/configs/xen_domu_defconfig | 2 +- arch/powerpc/configs/ppc64_defconfig | 2 +- arch/powerpc/configs/ppc64e_defconfig | 2 +- arch/powerpc/configs/pseries_defconfig | 2 +- arch/sh/configs/sh03_defconfig | 2 +- drivers/pci/hotplug/Kconfig | 5 +---- 9 files changed, 9 insertions(+), 12 deletions(-) diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig index 7913695b2fcb..efbd2929aeb7 100644 --- a/arch/ia64/configs/generic_defconfig +++ b/arch/ia64/configs/generic_defconfig @@ -31,7 +31,7 @@ CONFIG_ACPI_FAN=m CONFIG_ACPI_DOCK=y CONFIG_ACPI_PROCESSOR=m CONFIG_ACPI_CONTAINER=m -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_ACPI=m CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/ia64/configs/gensparse_defconfig b/arch/ia64/configs/gensparse_defconfig index f8e913365423..f64980dd20c3 100644 --- a/arch/ia64/configs/gensparse_defconfig +++ b/arch/ia64/configs/gensparse_defconfig @@ -25,7 +25,7 @@ CONFIG_ACPI_BUTTON=m CONFIG_ACPI_FAN=m CONFIG_ACPI_PROCESSOR=m CONFIG_ACPI_CONTAINER=m -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_ACPI=m CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/ia64/configs/tiger_defconfig b/arch/ia64/configs/tiger_defconfig index a5a9e02e60a0..0f4e9e41f130 100644 --- a/arch/ia64/configs/tiger_defconfig +++ b/arch/ia64/configs/tiger_defconfig @@ -31,7 +31,7 @@ CONFIG_ACPI_BUTTON=m CONFIG_ACPI_FAN=m CONFIG_ACPI_PROCESSOR=m CONFIG_ACPI_CONTAINER=m -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_ACPI=m CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/ia64/configs/xen_domu_defconfig b/arch/ia64/configs/xen_domu_defconfig index 37b9b422caad..b025acfde5c1 100644 --- a/arch/ia64/configs/xen_domu_defconfig +++ b/arch/ia64/configs/xen_domu_defconfig @@ -32,7 +32,7 @@ CONFIG_ACPI_BUTTON=m CONFIG_ACPI_FAN=m CONFIG_ACPI_PROCESSOR=m CONFIG_ACPI_CONTAINER=m -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_ACPI=m CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index c86fcb92358e..0e8cfd09da2f 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -58,7 +58,7 @@ CONFIG_SCHED_SMT=y CONFIG_PPC_DENORMALISATION=y CONFIG_PCCARD=y CONFIG_ELECTRA_CF=y -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m CONFIG_PACKET=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 4b20f76172e2..0085dc4642c5 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -32,7 +32,7 @@ CONFIG_IRQ_ALL_CPUS=y CONFIG_SPARSEMEM_MANUAL=y CONFIG_PCI_MSI=y CONFIG_PCCARD=y -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_XFRM_USER=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index bea8587c3af5..1d4b9763895d 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -53,7 +53,7 @@ CONFIG_PPC_64K_PAGES=y CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y CONFIG_PPC_DENORMALISATION=y -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m CONFIG_PACKET=y diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index 2051821724c6..0cf4097b71e8 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -22,7 +22,7 @@ CONFIG_PREEMPT=y CONFIG_CMDLINE_OVERWRITE=y CONFIG_CMDLINE="console=ttySC1,115200 mem=64M root=/dev/nfs" CONFIG_PCI=y -CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI=y CONFIG_BINFMT_MISC=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/drivers/pci/hotplug/Kconfig b/drivers/pci/hotplug/Kconfig index bb7ebb22db01..d85009de713d 100644 --- a/drivers/pci/hotplug/Kconfig +++ b/drivers/pci/hotplug/Kconfig @@ -3,16 +3,13 @@ # menuconfig HOTPLUG_PCI - tristate "Support for PCI Hotplug" + bool "Support for PCI Hotplug" depends on PCI && SYSFS ---help--- Say Y here if you have a motherboard with a PCI Hotplug controller. This allows you to add and remove PCI cards while the machine is powered up and running. - To compile this driver as a module, choose M here: the - module will be called pci_hotplug. - When in doubt, say N. if HOTPLUG_PCI -- cgit v1.2.3 From c10cc483bf3f1d0e8f9f077ca36ecc053de9bbbc Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 23 Jul 2013 10:55:56 -0600 Subject: PCI: pciehp: Convert pciehp to be builtin only, not modular Convert pciehp to be builtin only, with no module option. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki Acked-by: Yinghai Lu --- drivers/pci/pcie/Kconfig | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 569f82fc9e22..3b94cfcfa03b 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -14,15 +14,12 @@ config PCIEPORTBUS # Include service Kconfig here # config HOTPLUG_PCI_PCIE - tristate "PCI Express Hotplug driver" + bool "PCI Express Hotplug driver" depends on HOTPLUG_PCI && PCIEPORTBUS help Say Y here if you have a motherboard that supports PCI Express Native Hotplug - To compile this driver as a module, choose M here: the - module will be called pciehp. - When in doubt, say N. source "drivers/pci/pcie/aer/Kconfig" -- cgit v1.2.3 From aa914f5ec25e4371ba18b312971314be1b9b1076 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 25 Jul 2013 06:31:38 -0700 Subject: PCI: Retry allocation of only the resource type that failed Ben Herrenschmidt reported the following problem: - The bus has space for all desired MMIO resources, including optional space for SR-IOV devices - We attempt to allocate I/O port space, but it fails because the bus has no I/O space - Because of the I/O allocation failure, we retry MMIO allocation, requesting only the required space, without the optional SR-IOV space This means we don't allocate the optional SR-IOV space, even though we could. This is related to 0c5be0cb0e ("PCI: Retry on IORESOURCE_IO type allocations"). This patch changes how we handle allocation failures. We will now retry allocation of only the resource type that failed. If MMIO allocation fails, we'll retry only MMIO allocation. If I/O port allocation fails, we'll retry only I/O port allocation. [bhelgaas: changelog] Reference: https://lkml.kernel.org/r/1367712653.11982.19.camel@pasglop Reported-by: Benjamin Herrenschmidt Tested-by: Gavin Shan Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.10+--- drivers/pci/setup-bus.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 68 insertions(+), 1 deletion(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index d254e2379533..64a7de22d9af 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -300,6 +300,47 @@ static void assign_requested_resources_sorted(struct list_head *head, } } +static unsigned long pci_fail_res_type_mask(struct list_head *fail_head) +{ + struct pci_dev_resource *fail_res; + unsigned long mask = 0; + + /* check failed type */ + list_for_each_entry(fail_res, fail_head, list) + mask |= fail_res->flags; + + /* + * one pref failed resource will set IORESOURCE_MEM, + * as we can allocate pref in non-pref range. + * Will release all assigned non-pref sibling resources + * according to that bit. + */ + return mask & (IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH); +} + +static bool pci_need_to_release(unsigned long mask, struct resource *res) +{ + if (res->flags & IORESOURCE_IO) + return !!(mask & IORESOURCE_IO); + + /* check pref at first */ + if (res->flags & IORESOURCE_PREFETCH) { + if (mask & IORESOURCE_PREFETCH) + return true; + /* count pref if its parent is non-pref */ + else if ((mask & IORESOURCE_MEM) && + !(res->parent->flags & IORESOURCE_PREFETCH)) + return true; + else + return false; + } + + if (res->flags & IORESOURCE_MEM) + return !!(mask & IORESOURCE_MEM); + + return false; /* should not get here */ +} + static void __assign_resources_sorted(struct list_head *head, struct list_head *realloc_head, struct list_head *fail_head) @@ -312,11 +353,24 @@ static void __assign_resources_sorted(struct list_head *head, * if could do that, could get out early. * if could not do that, we still try to assign requested at first, * then try to reassign add_size for some resources. + * + * Separate three resource type checking if we need to release + * assigned resource after requested + add_size try. + * 1. if there is io port assign fail, will release assigned + * io port. + * 2. if there is pref mmio assign fail, release assigned + * pref mmio. + * if assigned pref mmio's parent is non-pref mmio and there + * is non-pref mmio assign fail, will release that assigned + * pref mmio. + * 3. if there is non-pref mmio assign fail or pref mmio + * assigned fail, will release assigned non-pref mmio. */ LIST_HEAD(save_head); LIST_HEAD(local_fail_head); struct pci_dev_resource *save_res; - struct pci_dev_resource *dev_res; + struct pci_dev_resource *dev_res, *tmp_res; + unsigned long fail_type; /* Check if optional add_size is there */ if (!realloc_head || list_empty(realloc_head)) @@ -348,6 +402,19 @@ static void __assign_resources_sorted(struct list_head *head, return; } + /* check failed type */ + fail_type = pci_fail_res_type_mask(&local_fail_head); + /* remove not need to be released assigned res from head list etc */ + list_for_each_entry_safe(dev_res, tmp_res, head, list) + if (dev_res->res->parent && + !pci_need_to_release(fail_type, dev_res->res)) { + /* remove it from realloc_head list */ + remove_from_list(realloc_head, dev_res->res); + remove_from_list(&save_head, dev_res->res); + list_del(&dev_res->list); + kfree(dev_res); + } + free_list(&local_fail_head); /* Release assigned resource */ list_for_each_entry(dev_res, head, list) -- cgit v1.2.3 From 36dd1f3e02a4aed850a7b7318d7abd4f4d50528c Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 1 Aug 2013 15:44:19 +0200 Subject: PCI: mvebu: Disable prefetchable memory support in PCI-to-PCI bridge The Marvell PCIe driver uses an emulated PCI-to-PCI bridge to be able to dynamically set up MBus address decoding windows for PCI I/O and memory regions depending on the PCI devices enumerated by Linux. However, this emulated PCI-to-PCI bridge logic makes the Linux PCI core believe that prefetchable memory regions are supported (because the registers are read/write), while in fact no adress decoding window is ever created for such regions. Since the Marvell MBus address decoding windows do not distinguish memory regions and prefetchable memory regions, this patch takes a simple approach: change the PCI-to-PCI bridge emulation to let the Linux PCI core know that we don't support prefetchable memory regions. To achieve this, we simply make the prefetchable memory base a read-only register that always returns 0. Reading/writing all the other prefetchable memory related registers has no effect. This problem was originally reported by Finn Hoffmann , who couldn't get a RTL8111/8168B PCI NIC working on the NSA310 Kirkwood platform after updating to 3.11-rc. The problem was that the PCI-to-PCI bridge emulation was making the Linux PCI core believe that we support prefetchable memory, so the Linux PCI core was only filling the prefetchable memory base and limit registers, which does not lead to a MBus window being created. The below patch has been confirmed by Finn Hoffmann to fix his problem on Kirkwood, and has otherwise been successfully tested on the Armada XP GP platform with a e1000e PCIe NIC and a Marvell SATA PCIe card. Reported-by: Finn Hoffmann Signed-off-by: Thomas Petazzoni Signed-off-by: Bjorn Helgaas --- drivers/pci/host/pci-mvebu.c | 27 +-------------------------- 1 file changed, 1 insertion(+), 26 deletions(-) diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 13a633b1612e..7bf3926aecc0 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -86,10 +86,6 @@ struct mvebu_sw_pci_bridge { u16 secondary_status; u16 membase; u16 memlimit; - u16 prefmembase; - u16 prefmemlimit; - u32 prefbaseupper; - u32 preflimitupper; u16 iobaseupper; u16 iolimitupper; u8 cappointer; @@ -419,15 +415,7 @@ static int mvebu_sw_pci_bridge_read(struct mvebu_pcie_port *port, break; case PCI_PREF_MEMORY_BASE: - *value = (bridge->prefmemlimit << 16 | bridge->prefmembase); - break; - - case PCI_PREF_BASE_UPPER32: - *value = bridge->prefbaseupper; - break; - - case PCI_PREF_LIMIT_UPPER32: - *value = bridge->preflimitupper; + *value = 0; break; case PCI_IO_BASE_UPPER16: @@ -501,19 +489,6 @@ static int mvebu_sw_pci_bridge_write(struct mvebu_pcie_port *port, mvebu_pcie_handle_membase_change(port); break; - case PCI_PREF_MEMORY_BASE: - bridge->prefmembase = value & 0xffff; - bridge->prefmemlimit = value >> 16; - break; - - case PCI_PREF_BASE_UPPER32: - bridge->prefbaseupper = value; - break; - - case PCI_PREF_LIMIT_UPPER32: - bridge->preflimitupper = value; - break; - case PCI_IO_BASE_UPPER16: bridge->iobaseupper = value & 0xffff; bridge->iolimitupper = value >> 16; -- cgit v1.2.3