From 4e13c1ac6baa1d6c2b650d66ca89e1e12727ec19 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 21 May 2013 13:33:09 +1000 Subject: powerpc/vfio: Enable on PowerNV platform This initializes IOMMU groups based on the IOMMU configuration discovered during the PCI scan on POWERNV (POWER non virtualized) platform. The IOMMU groups are to be used later by the VFIO driver, which is used for PCI pass through. It also implements an API for mapping/unmapping pages for guest PCI drivers and providing DMA window properties. This API is going to be used later by QEMU-VFIO to handle h_put_tce hypercalls from the KVM guest. The iommu_put_tce_user_mode() does only a single page mapping as an API for adding many mappings at once is going to be added later. Although this driver has been tested only on the POWERNV platform, it should work on any platform which supports TCE tables. As h_put_tce hypercall is received by the host kernel and processed by the QEMU (what involves calling the host kernel again), performance is not the best - circa 220MB/s on 10Gb ethernet network. To enable VFIO on POWER, enable SPAPR_TCE_IOMMU config option and configure VFIO as required. Cc: David Gibson Signed-off-by: Alexey Kardashevskiy Signed-off-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- drivers/iommu/Kconfig | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index c332fb98480d..3f3abde8a7f9 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -261,4 +261,12 @@ config SHMOBILE_IOMMU_L1SIZE default 256 if SHMOBILE_IOMMU_ADDRSIZE_64MB default 128 if SHMOBILE_IOMMU_ADDRSIZE_32MB +config SPAPR_TCE_IOMMU + bool "sPAPR TCE IOMMU Support" + depends on PPC_POWERNV + select IOMMU_API + help + Enables bits of IOMMU API required by VFIO. The iommu_ops + is not implemented as it is not necessary for VFIO. + endif # IOMMU_SUPPORT -- cgit v1.2.3 From 5ffd229c02731a91d08ca21e76b503c5bbb5c095 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 21 May 2013 13:33:10 +1000 Subject: powerpc/vfio: Implement IOMMU driver for VFIO VFIO implements platform independent stuff such as a PCI driver, BAR access (via read/write on a file descriptor or direct mapping when possible) and IRQ signaling. The platform dependent part includes IOMMU initialization and handling. This implements an IOMMU driver for VFIO which does mapping/unmapping pages for the guest IO and provides information about DMA window (required by a POWER guest). Cc: David Gibson Signed-off-by: Alexey Kardashevskiy Signed-off-by: Paul Mackerras Acked-by: Alex Williamson Signed-off-by: Benjamin Herrenschmidt --- Documentation/vfio.txt | 63 ++++++ drivers/vfio/Kconfig | 6 + drivers/vfio/Makefile | 1 + drivers/vfio/vfio.c | 1 + drivers/vfio/vfio_iommu_spapr_tce.c | 377 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/vfio.h | 34 ++++ 6 files changed, 482 insertions(+) create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c (limited to 'drivers') diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt index 8eda3635a17d..c55533c0adb3 100644 --- a/Documentation/vfio.txt +++ b/Documentation/vfio.txt @@ -283,6 +283,69 @@ a direct pass through for VFIO_DEVICE_* ioctls. The read/write/mmap interfaces implement the device region access defined by the device's own VFIO_DEVICE_GET_REGION_INFO ioctl. + +PPC64 sPAPR implementation note +------------------------------------------------------------------------------- + +This implementation has some specifics: + +1) Only one IOMMU group per container is supported as an IOMMU group +represents the minimal entity which isolation can be guaranteed for and +groups are allocated statically, one per a Partitionable Endpoint (PE) +(PE is often a PCI domain but not always). + +2) The hardware supports so called DMA windows - the PCI address range +within which DMA transfer is allowed, any attempt to access address space +out of the window leads to the whole PE isolation. + +3) PPC64 guests are paravirtualized but not fully emulated. There is an API +to map/unmap pages for DMA, and it normally maps 1..32 pages per call and +currently there is no way to reduce the number of calls. In order to make things +faster, the map/unmap handling has been implemented in real mode which provides +an excellent performance which has limitations such as inability to do +locked pages accounting in real time. + +So 3 additional ioctls have been added: + + VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start + of the DMA window on the PCI bus. + + VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting + is done at this point. This lets user first to know what + the DMA window is and adjust rlimit before doing any real job. + + VFIO_IOMMU_DISABLE - disables the container. + + +The code flow from the example above should be slightly changed: + + ..... + /* Add the group to the container */ + ioctl(group, VFIO_GROUP_SET_CONTAINER, &container); + + /* Enable the IOMMU model we want */ + ioctl(container, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU) + + /* Get addition sPAPR IOMMU info */ + vfio_iommu_spapr_tce_info spapr_iommu_info; + ioctl(container, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &spapr_iommu_info); + + if (ioctl(container, VFIO_IOMMU_ENABLE)) + /* Cannot enable container, may be low rlimit */ + + /* Allocate some space and setup a DMA mapping */ + dma_map.vaddr = mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + + dma_map.size = 1024 * 1024; + dma_map.iova = 0; /* 1MB starting at 0x0 from device view */ + dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; + + /* Check here is .iova/.size are within DMA window from spapr_iommu_info */ + + ioctl(container, VFIO_IOMMU_MAP_DMA, &dma_map); + ..... + ------------------------------------------------------------------------------- [1] VFIO was originally an acronym for "Virtual Function I/O" in its diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 7cd5dec0abd1..b464687f6e14 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -3,10 +3,16 @@ config VFIO_IOMMU_TYPE1 depends on VFIO default n +config VFIO_IOMMU_SPAPR_TCE + tristate + depends on VFIO && SPAPR_TCE_IOMMU + default n + menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" depends on IOMMU_API select VFIO_IOMMU_TYPE1 if X86 + select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV help VFIO provides a framework for secure userspace device drivers. See Documentation/vfio.txt for more details. diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index 2398d4a0e38b..72bfabc8629e 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_VFIO) += vfio.o obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o +obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o obj-$(CONFIG_VFIO_PCI) += pci/ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6d78736563de..259ad282ae5d 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1415,6 +1415,7 @@ static int __init vfio_init(void) * drivers. */ request_module_nowait("vfio_iommu_type1"); + request_module_nowait("vfio_iommu_spapr_tce"); return 0; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c new file mode 100644 index 000000000000..bdae7a04af75 --- /dev/null +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -0,0 +1,377 @@ +/* + * VFIO: IOMMU DMA mapping support for TCE on POWER + * + * Copyright (C) 2013 IBM Corp. All rights reserved. + * Author: Alexey Kardashevskiy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Derived from original vfio_iommu_type1.c: + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_VERSION "0.1" +#define DRIVER_AUTHOR "aik@ozlabs.ru" +#define DRIVER_DESC "VFIO IOMMU SPAPR TCE" + +static void tce_iommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group); + +/* + * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation + * + * This code handles mapping and unmapping of user data buffers + * into DMA'ble space using the IOMMU + */ + +/* + * The container descriptor supports only a single group per container. + * Required by the API as the container is not supplied with the IOMMU group + * at the moment of initialization. + */ +struct tce_container { + struct mutex lock; + struct iommu_table *tbl; + bool enabled; +}; + +static int tce_iommu_enable(struct tce_container *container) +{ + int ret = 0; + unsigned long locked, lock_limit, npages; + struct iommu_table *tbl = container->tbl; + + if (!container->tbl) + return -ENXIO; + + if (!current->mm) + return -ESRCH; /* process exited */ + + if (container->enabled) + return -EBUSY; + + /* + * When userspace pages are mapped into the IOMMU, they are effectively + * locked memory, so, theoretically, we need to update the accounting + * of locked pages on each map and unmap. For powerpc, the map unmap + * paths can be very hot, though, and the accounting would kill + * performance, especially since it would be difficult to impossible + * to handle the accounting in real mode only. + * + * To address that, rather than precisely accounting every page, we + * instead account for a worst case on locked memory when the iommu is + * enabled and disabled. The worst case upper bound on locked memory + * is the size of the whole iommu window, which is usually relatively + * small (compared to total memory sizes) on POWER hardware. + * + * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits, + * that would effectively kill the guest at random points, much better + * enforcing the limit based on the max that the guest can map. + */ + down_write(¤t->mm->mmap_sem); + npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + locked = current->mm->locked_vm + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n", + rlimit(RLIMIT_MEMLOCK)); + ret = -ENOMEM; + } else { + + current->mm->locked_vm += npages; + container->enabled = true; + } + up_write(¤t->mm->mmap_sem); + + return ret; +} + +static void tce_iommu_disable(struct tce_container *container) +{ + if (!container->enabled) + return; + + container->enabled = false; + + if (!container->tbl || !current->mm) + return; + + down_write(¤t->mm->mmap_sem); + current->mm->locked_vm -= (container->tbl->it_size << + IOMMU_PAGE_SHIFT) >> PAGE_SHIFT; + up_write(¤t->mm->mmap_sem); +} + +static void *tce_iommu_open(unsigned long arg) +{ + struct tce_container *container; + + if (arg != VFIO_SPAPR_TCE_IOMMU) { + pr_err("tce_vfio: Wrong IOMMU type\n"); + return ERR_PTR(-EINVAL); + } + + container = kzalloc(sizeof(*container), GFP_KERNEL); + if (!container) + return ERR_PTR(-ENOMEM); + + mutex_init(&container->lock); + + return container; +} + +static void tce_iommu_release(void *iommu_data) +{ + struct tce_container *container = iommu_data; + + WARN_ON(container->tbl && !container->tbl->it_group); + tce_iommu_disable(container); + + if (container->tbl && container->tbl->it_group) + tce_iommu_detach_group(iommu_data, container->tbl->it_group); + + mutex_destroy(&container->lock); + + kfree(container); +} + +static long tce_iommu_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + struct tce_container *container = iommu_data; + unsigned long minsz; + long ret; + + switch (cmd) { + case VFIO_CHECK_EXTENSION: + return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0; + + case VFIO_IOMMU_SPAPR_TCE_GET_INFO: { + struct vfio_iommu_spapr_tce_info info; + struct iommu_table *tbl = container->tbl; + + if (WARN_ON(!tbl)) + return -ENXIO; + + minsz = offsetofend(struct vfio_iommu_spapr_tce_info, + dma32_window_size); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT; + info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT; + info.flags = 0; + + if (copy_to_user((void __user *)arg, &info, minsz)) + return -EFAULT; + + return 0; + } + case VFIO_IOMMU_MAP_DMA: { + struct vfio_iommu_type1_dma_map param; + struct iommu_table *tbl = container->tbl; + unsigned long tce, i; + + if (!tbl) + return -ENXIO; + + BUG_ON(!tbl->it_group); + + minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); + + if (copy_from_user(¶m, (void __user *)arg, minsz)) + return -EFAULT; + + if (param.argsz < minsz) + return -EINVAL; + + if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ | + VFIO_DMA_MAP_FLAG_WRITE)) + return -EINVAL; + + if ((param.size & ~IOMMU_PAGE_MASK) || + (param.vaddr & ~IOMMU_PAGE_MASK)) + return -EINVAL; + + /* iova is checked by the IOMMU API */ + tce = param.vaddr; + if (param.flags & VFIO_DMA_MAP_FLAG_READ) + tce |= TCE_PCI_READ; + if (param.flags & VFIO_DMA_MAP_FLAG_WRITE) + tce |= TCE_PCI_WRITE; + + ret = iommu_tce_put_param_check(tbl, param.iova, tce); + if (ret) + return ret; + + for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) { + ret = iommu_put_tce_user_mode(tbl, + (param.iova >> IOMMU_PAGE_SHIFT) + i, + tce); + if (ret) + break; + tce += IOMMU_PAGE_SIZE; + } + if (ret) + iommu_clear_tces_and_put_pages(tbl, + param.iova >> IOMMU_PAGE_SHIFT, i); + + iommu_flush_tce(tbl); + + return ret; + } + case VFIO_IOMMU_UNMAP_DMA: { + struct vfio_iommu_type1_dma_unmap param; + struct iommu_table *tbl = container->tbl; + + if (WARN_ON(!tbl)) + return -ENXIO; + + minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, + size); + + if (copy_from_user(¶m, (void __user *)arg, minsz)) + return -EFAULT; + + if (param.argsz < minsz) + return -EINVAL; + + /* No flag is supported now */ + if (param.flags) + return -EINVAL; + + if (param.size & ~IOMMU_PAGE_MASK) + return -EINVAL; + + ret = iommu_tce_clear_param_check(tbl, param.iova, 0, + param.size >> IOMMU_PAGE_SHIFT); + if (ret) + return ret; + + ret = iommu_clear_tces_and_put_pages(tbl, + param.iova >> IOMMU_PAGE_SHIFT, + param.size >> IOMMU_PAGE_SHIFT); + iommu_flush_tce(tbl); + + return ret; + } + case VFIO_IOMMU_ENABLE: + mutex_lock(&container->lock); + ret = tce_iommu_enable(container); + mutex_unlock(&container->lock); + return ret; + + + case VFIO_IOMMU_DISABLE: + mutex_lock(&container->lock); + tce_iommu_disable(container); + mutex_unlock(&container->lock); + return 0; + } + + return -ENOTTY; +} + +static int tce_iommu_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + int ret; + struct tce_container *container = iommu_data; + struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group); + + BUG_ON(!tbl); + mutex_lock(&container->lock); + + /* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n", + iommu_group_id(iommu_group), iommu_group); */ + if (container->tbl) { + pr_warn("tce_vfio: Only one group per IOMMU container is allowed, existing id=%d, attaching id=%d\n", + iommu_group_id(container->tbl->it_group), + iommu_group_id(iommu_group)); + ret = -EBUSY; + } else if (container->enabled) { + pr_err("tce_vfio: attaching group #%u to enabled container\n", + iommu_group_id(iommu_group)); + ret = -EBUSY; + } else { + ret = iommu_take_ownership(tbl); + if (!ret) + container->tbl = tbl; + } + + mutex_unlock(&container->lock); + + return ret; +} + +static void tce_iommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + struct tce_container *container = iommu_data; + struct iommu_table *tbl = iommu_group_get_iommudata(iommu_group); + + BUG_ON(!tbl); + mutex_lock(&container->lock); + if (tbl != container->tbl) { + pr_warn("tce_vfio: detaching group #%u, expected group is #%u\n", + iommu_group_id(iommu_group), + iommu_group_id(tbl->it_group)); + } else { + if (container->enabled) { + pr_warn("tce_vfio: detaching group #%u from enabled container, forcing disable\n", + iommu_group_id(tbl->it_group)); + tce_iommu_disable(container); + } + + /* pr_debug("tce_vfio: detaching group #%u from iommu %p\n", + iommu_group_id(iommu_group), iommu_group); */ + container->tbl = NULL; + iommu_release_ownership(tbl); + } + mutex_unlock(&container->lock); +} + +const struct vfio_iommu_driver_ops tce_iommu_driver_ops = { + .name = "iommu-vfio-powerpc", + .owner = THIS_MODULE, + .open = tce_iommu_open, + .release = tce_iommu_release, + .ioctl = tce_iommu_ioctl, + .attach_group = tce_iommu_attach_group, + .detach_group = tce_iommu_detach_group, +}; + +static int __init tce_iommu_init(void) +{ + return vfio_register_iommu_driver(&tce_iommu_driver_ops); +} + +static void __exit tce_iommu_cleanup(void) +{ + vfio_unregister_iommu_driver(&tce_iommu_driver_ops); +} + +module_init(tce_iommu_init); +module_exit(tce_iommu_cleanup); + +MODULE_VERSION(DRIVER_VERSION); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); + diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 284ff2436829..87ee4f4cff25 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -22,6 +22,7 @@ /* Extensions */ #define VFIO_TYPE1_IOMMU 1 +#define VFIO_SPAPR_TCE_IOMMU 2 /* * The IOCTL interface is designed for extensibility by embedding the @@ -375,4 +376,37 @@ struct vfio_iommu_type1_dma_unmap { #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) +/* + * IOCTLs to enable/disable IOMMU container usage. + * No parameters are supported. + */ +#define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15) +#define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16) + +/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */ + +/* + * The SPAPR TCE info struct provides the information about the PCI bus + * address ranges available for DMA, these values are programmed into + * the hardware so the guest has to know that information. + * + * The DMA 32 bit window start is an absolute PCI bus address. + * The IOVA address passed via map/unmap ioctls are absolute PCI bus + * addresses too so the window works as a filter rather than an offset + * for IOVA addresses. + * + * A flag will need to be added if other page sizes are supported, + * so as defined here, it is always 4k. + */ +struct vfio_iommu_spapr_tce_info { + __u32 argsz; + __u32 flags; /* reserved for future use */ + __u32 dma32_window_start; /* 32 bit window start (bytes) */ + __u32 dma32_window_size; /* 32 bit window size (bytes) */ +}; + +#define VFIO_IOMMU_SPAPR_TCE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) + +/* ***************************************************************** */ + #endif /* _UAPIVFIO_H */ -- cgit v1.2.3 From 5b25199eff8e124297e6e95392f1719d20daca89 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Tue, 21 May 2013 13:33:11 +1000 Subject: powerpc/vfio: Enable on pSeries platform The enables VFIO on the pSeries platform, enabling user space programs to access PCI devices directly. Signed-off-by: Alexey Kardashevskiy Cc: David Gibson Signed-off-by: Paul Mackerras Acked-by: Alex Williamson Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 4 ++++ drivers/iommu/Kconfig | 2 +- drivers/vfio/Kconfig | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 86ae364900d6..23fc1dcf4434 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -614,6 +614,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) iommu_table_setparms(pci->phb, dn, tbl); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); + iommu_register_group(tbl, pci_domain_nr(bus), 0); /* Divide the rest (1.75GB) among the children */ pci->phb->dma_window_size = 0x80000000ul; @@ -658,6 +659,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) ppci->phb->node); iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window); ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node); + iommu_register_group(tbl, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->iommu_table); } } @@ -684,6 +686,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) phb->node); iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); + iommu_register_group(tbl, pci_domain_nr(phb->bus), 0); set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table); return; } @@ -1184,6 +1187,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pci->phb->node); iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window); pci->iommu_table = iommu_init_table(tbl, pci->phb->node); + iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0); pr_debug(" created table: %p\n", pci->iommu_table); } else { pr_debug(" found DMA window, table: %p\n", pci->iommu_table); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 3f3abde8a7f9..01730b2b9954 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -263,7 +263,7 @@ config SHMOBILE_IOMMU_L1SIZE config SPAPR_TCE_IOMMU bool "sPAPR TCE IOMMU Support" - depends on PPC_POWERNV + depends on PPC_POWERNV || PPC_PSERIES select IOMMU_API help Enables bits of IOMMU API required by VFIO. The iommu_ops diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index b464687f6e14..26b3d9d1409f 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -12,7 +12,7 @@ menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" depends on IOMMU_API select VFIO_IOMMU_TYPE1 if X86 - select VFIO_IOMMU_SPAPR_TCE if PPC_POWERNV + select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES) help VFIO provides a framework for secure userspace device drivers. See Documentation/vfio.txt for more details. -- cgit v1.2.3 From e7f345a2a36754e43673e86870a7a89101fb13e3 Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Sat, 22 Jun 2013 04:29:48 -0400 Subject: macintosh/adb: Replace __WAITQUEUE_INITIALIZER with more standard DECLARE_WAITQUEUE. Signed-off-by: Robert P. J. Day Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/adb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index b026896206ca..04a50498f257 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -697,7 +697,7 @@ static ssize_t adb_read(struct file *file, char __user *buf, int ret = 0; struct adbdev_state *state = file->private_data; struct adb_request *req; - wait_queue_t wait = __WAITQUEUE_INITIALIZER(wait,current); + DECLARE_WAITQUEUE(wait,current); unsigned long flags; if (count < 2) -- cgit v1.2.3 From a16d8aa4726a944ffc1616689ae34ff6a902faba Mon Sep 17 00:00:00 2001 From: Sachin Surendran Date: Mon, 26 Nov 2012 11:20:01 +1300 Subject: i2c-cpm: Fix to takeback i2c bus master-ship after a collision In case of collision on i2c bus the controller which lost bus mastership stays as a slave for all subsequent transfers. This results in the i2c controller never writing to the bus for future transactions, resulting in i2c transfer timeouts. This fix checks for a collision on last I2C transaction and sets the I2COM_MASTER bit for the new transaction. Signed-off-by: Sachin Surendran Signed-off-by: Scott Wood --- drivers/i2c/busses/i2c-cpm.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers') diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 3823623baa48..9e6002108720 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -338,6 +338,14 @@ static int cpm_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) tptr = 0; rptr = 0; + /* + * If there was a collision in the last i2c transaction, + * Set I2COM_MASTER as it was cleared during collision. + */ + if (in_be16(&tbdf->cbd_sc) & BD_SC_CL) { + out_8(&cpm->i2c_reg->i2com, I2COM_MASTER); + } + while (tptr < num) { pmsg = &msgs[tptr]; dev_dbg(&adap->dev, "R: %d T: %d\n", rptr, tptr); -- cgit v1.2.3 From 3978bdb4ed653342b0be66c031bf61b72cc55d60 Mon Sep 17 00:00:00 2001 From: Tudor Laurentiu Date: Tue, 5 Mar 2013 17:52:49 +0200 Subject: powerpc/watchdog: Don't enable interrupt on PPC64 BookE Critical interrupts are not handled on PPC64 BookE machines, so when the first watchdog interrupt fires the machine will freeze without a warning until it's rebooted by the second watchdog trigger. Plus, the interrupt isn't used anyway since the driver expects a usermode app to ping the watchdog periodically. Signed-off-by: Laurentiu Tudor Signed-off-by: Scott Wood --- drivers/watchdog/booke_wdt.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'drivers') diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c index a8dbceb32914..f1b8d555080e 100644 --- a/drivers/watchdog/booke_wdt.c +++ b/drivers/watchdog/booke_wdt.c @@ -138,6 +138,14 @@ static void __booke_wdt_enable(void *data) val &= ~WDTP_MASK; val |= (TCR_WIE|TCR_WRC(WRC_CHIP)|WDTP(booke_wdt_period)); +#ifdef CONFIG_PPC_BOOK3E_64 + /* + * Crit ints are currently broken on PPC64 Book-E, so + * just disable them for now. + */ + val &= ~TCR_WIE; +#endif + mtspr(SPRN_TCR, val); } -- cgit v1.2.3 From 4bb297113433048169c30a32c1e58b6a1b61b621 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 30 Jun 2013 22:00:42 +0300 Subject: powerpc/windfarm: Fix overtemperature clearing With pm81/pm91/pm121, when the overtemperature state is entered, and when it remains on after skipped ticks, the driver will try to leave it too soon (immediately on the next tick). This is because the active FAILURE_OVERTEMP state is not visible in "new_failure" variable of the current tick. Furthermore, the driver will keep trying to clear condition in subsequent ticks as FAILURE_OVERTEMP remains set in the "last_failure" variable. These will start to trigger WARNINGS from windfarm core: [ 100.082735] windfarm: Clamping CPU frequency to minimum ! [ 100.108132] windfarm: Overtemp condition detected ! [ 101.952908] windfarm: Overtemp condition cleared ! [...] [ 102.980388] WARNING: at drivers/macintosh/windfarm_core.c:463 [...] [ 103.982227] WARNING: at drivers/macintosh/windfarm_core.c:463 [...] [ 105.030494] WARNING: at drivers/macintosh/windfarm_core.c:463 [...] [ 105.973666] WARNING: at drivers/macintosh/windfarm_core.c:463 [...] [ 106.977913] WARNING: at drivers/macintosh/windfarm_core.c:463 Fix by adding a helper global variable. We leave the overtemp state only after all failure bits have been cleared. I saw this error on iMac G5 iSight (pm121). Also pm81/pm91 are fixed based on the observation that these are almost identical/copy-pasted code. Signed-off-by: Aaro Koskinen Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/windfarm_pm121.c | 6 +++++- drivers/macintosh/windfarm_pm81.c | 6 +++++- drivers/macintosh/windfarm_pm91.c | 6 +++++- 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c index af605e915d41..7fe58b0ae8b4 100644 --- a/drivers/macintosh/windfarm_pm121.c +++ b/drivers/macintosh/windfarm_pm121.c @@ -276,6 +276,7 @@ static const char *loop_names[N_LOOPS] = { static unsigned int pm121_failure_state; static int pm121_readjust, pm121_skipping; +static bool pm121_overtemp; static s32 average_power; struct pm121_correction { @@ -847,6 +848,7 @@ static void pm121_tick(void) if (new_failure & FAILURE_OVERTEMP) { wf_set_overtemp(); pm121_skipping = 2; + pm121_overtemp = true; } /* We only clear the overtemp condition if overtemp is cleared @@ -855,8 +857,10 @@ static void pm121_tick(void) * the control loop levels, but we don't want to keep it clear * here in this case */ - if (new_failure == 0 && last_failure & FAILURE_OVERTEMP) + if (!pm121_failure_state && pm121_overtemp) { wf_clear_overtemp(); + pm121_overtemp = false; + } } diff --git a/drivers/macintosh/windfarm_pm81.c b/drivers/macintosh/windfarm_pm81.c index f84933ff3298..2a5e1b15b1d2 100644 --- a/drivers/macintosh/windfarm_pm81.c +++ b/drivers/macintosh/windfarm_pm81.c @@ -149,6 +149,7 @@ static int wf_smu_all_controls_ok, wf_smu_all_sensors_ok, wf_smu_started; static unsigned int wf_smu_failure_state; static int wf_smu_readjust, wf_smu_skipping; +static bool wf_smu_overtemp; /* * ****** System Fans Control Loop ****** @@ -593,6 +594,7 @@ static void wf_smu_tick(void) if (new_failure & FAILURE_OVERTEMP) { wf_set_overtemp(); wf_smu_skipping = 2; + wf_smu_overtemp = true; } /* We only clear the overtemp condition if overtemp is cleared @@ -601,8 +603,10 @@ static void wf_smu_tick(void) * the control loop levels, but we don't want to keep it clear * here in this case */ - if (new_failure == 0 && last_failure & FAILURE_OVERTEMP) + if (!wf_smu_failure_state && wf_smu_overtemp) { wf_clear_overtemp(); + wf_smu_overtemp = false; + } } static void wf_smu_new_control(struct wf_control *ct) diff --git a/drivers/macintosh/windfarm_pm91.c b/drivers/macintosh/windfarm_pm91.c index 2eb484f213c8..a8ac66cd3b13 100644 --- a/drivers/macintosh/windfarm_pm91.c +++ b/drivers/macintosh/windfarm_pm91.c @@ -76,6 +76,7 @@ static struct wf_control *cpufreq_clamp; /* Set to kick the control loop into life */ static int wf_smu_all_controls_ok, wf_smu_all_sensors_ok, wf_smu_started; +static bool wf_smu_overtemp; /* Failure handling.. could be nicer */ #define FAILURE_FAN 0x01 @@ -517,6 +518,7 @@ static void wf_smu_tick(void) if (new_failure & FAILURE_OVERTEMP) { wf_set_overtemp(); wf_smu_skipping = 2; + wf_smu_overtemp = true; } /* We only clear the overtemp condition if overtemp is cleared @@ -525,8 +527,10 @@ static void wf_smu_tick(void) * the control loop levels, but we don't want to keep it clear * here in this case */ - if (new_failure == 0 && last_failure & FAILURE_OVERTEMP) + if (!wf_smu_failure_state && wf_smu_overtemp) { wf_clear_overtemp(); + wf_smu_overtemp = false; + } } -- cgit v1.2.3 From 5eb969d0e8b8f38fca0b2c6c76f5dca01449664a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 13 Jun 2013 19:37:37 -0700 Subject: macintosh: Convert use of typedef ctl_table to struct ctl_table This typedef is unnecessary and should just be removed. Signed-off-by: Joe Perches Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/mac_hid.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c index 6a82388505f0..80d30e8e3389 100644 --- a/drivers/macintosh/mac_hid.c +++ b/drivers/macintosh/mac_hid.c @@ -181,7 +181,7 @@ static void mac_hid_stop_emulation(void) mac_hid_destroy_emumouse(); } -static int mac_hid_toggle_emumouse(ctl_table *table, int write, +static int mac_hid_toggle_emumouse(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -214,7 +214,7 @@ static int mac_hid_toggle_emumouse(ctl_table *table, int write, } /* file(s) in /proc/sys/dev/mac_hid */ -static ctl_table mac_hid_files[] = { +static struct ctl_table mac_hid_files[] = { { .procname = "mouse_button_emulation", .data = &mouse_emulate_buttons, @@ -240,7 +240,7 @@ static ctl_table mac_hid_files[] = { }; /* dir in /proc/sys/dev */ -static ctl_table mac_hid_dir[] = { +static struct ctl_table mac_hid_dir[] = { { .procname = "mac_hid", .maxlen = 0, @@ -251,7 +251,7 @@ static ctl_table mac_hid_dir[] = { }; /* /proc/sys/dev itself, in case that is not there yet */ -static ctl_table mac_hid_root_dir[] = { +static struct ctl_table mac_hid_root_dir[] = { { .procname = "dev", .maxlen = 0, -- cgit v1.2.3 From 330dae19998072e97f550885a0087df6d6556816 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 30 Jun 2013 12:03:23 +0200 Subject: mac: Make cuda_init_via() __init cuda_init_via() is called from find_via_cuda() only, which is __init. Signed-off-by: Geert Uytterhoeven Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/via-cuda.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c index 86511c570dd8..d61f271d2207 100644 --- a/drivers/macintosh/via-cuda.c +++ b/drivers/macintosh/via-cuda.c @@ -259,7 +259,7 @@ cuda_probe(void) } while (0) static int -cuda_init_via(void) +__init cuda_init_via(void) { out_8(&via[DIRB], (in_8(&via[DIRB]) | TACK | TIP) & ~TREQ); /* TACK & TIP out */ out_8(&via[B], in_8(&via[B]) | TACK | TIP); /* negate them */ -- cgit v1.2.3 From 91f5af2e6524f795c0ee5d2fdc3be40d0e427ae2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 21 May 2013 20:45:40 +0200 Subject: macintosh/windfarm: Remove obsolete cleanup for clientdata A few new i2c-drivers came into the kernel which clear the clientdata-pointer on exit or error. This is obsolete meanwhile, the core will do it. Signed-off-by: Wolfram Sang Signed-off-by: Benjamin Herrenschmidt --- drivers/macintosh/windfarm_smu_sat.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers') diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index d87f5ee04ca9..ad6223e88340 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -343,7 +343,6 @@ static int wf_sat_remove(struct i2c_client *client) wf_unregister_sensor(&sens->sens); } sat->i2c = NULL; - i2c_set_clientdata(client, NULL); kref_put(&sat->ref, wf_sat_release); return 0; -- cgit v1.2.3 From 6bbbca735936e15b9431882eceddcf6dff76e03c Mon Sep 17 00:00:00 2001 From: Aruna Balakrishnaiah Date: Thu, 27 Jun 2013 14:02:56 +0530 Subject: pstore: Pass header size in the pstore write callback Header size is needed to distinguish between header and the dump data. Incorporate the addition of new argument (hsize) in the pstore write callback. Signed-off-by: Aruna Balakrishnaiah Acked-by: Kees Cook Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/nvram.c | 4 +++- drivers/acpi/apei/erst.c | 4 ++-- drivers/firmware/efi/efi-pstore.c | 2 +- fs/pstore/platform.c | 10 ++++++---- fs/pstore/ram.c | 3 ++- include/linux/pstore.h | 8 ++++---- 6 files changed, 18 insertions(+), 13 deletions(-) (limited to 'drivers') diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 14cc486709f6..3f0e7d67d747 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -502,6 +502,7 @@ static int nvram_pstore_open(struct pstore_info *psi) * @part: pstore writes data to registered buffer in parts, * part number will indicate the same. * @count: Indicates oops count + * @hsize: Size of header added by pstore * @size: number of bytes written to the registered buffer * @psi: registered pstore_info structure * @@ -512,7 +513,8 @@ static int nvram_pstore_open(struct pstore_info *psi) static int nvram_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t size, struct pstore_info *psi) + size_t hsize, size_t size, + struct pstore_info *psi) { int rc; struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf; diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 6d894bfd8b8f..a9cf96085f85 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -935,7 +935,7 @@ static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, struct pstore_info *psi); static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, + u64 *id, unsigned int part, int count, size_t hsize, size_t size, struct pstore_info *psi); static int erst_clearer(enum pstore_type_id type, u64 id, int count, struct timespec time, struct pstore_info *psi); @@ -1055,7 +1055,7 @@ out: } static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason, - u64 *id, unsigned int part, int count, + u64 *id, unsigned int part, int count, size_t hsize, size_t size, struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 202d2c85ba2e..452800e005b6 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -104,7 +104,7 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type, static int efi_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t size, + unsigned int part, int count, size_t hsize, size_t size, struct pstore_info *psi) { char name[DUMP_NAME_LEN]; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 86d1038b5a12..4637ec4169cd 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -159,7 +159,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, break; ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - oopscount, hsize + len, psinfo); + oopscount, hsize, hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; @@ -196,7 +196,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) spin_lock_irqsave(&psinfo->buf_lock, flags); } memcpy(psinfo->buf, s, c); - psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, c, psinfo); + psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; @@ -221,9 +221,11 @@ static void pstore_register_console(void) {} static int pstore_write_compat(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t size, struct pstore_info *psi) + size_t hsize, size_t size, + struct pstore_info *psi) { - return psi->write_buf(type, reason, id, part, psinfo->buf, size, psi); + return psi->write_buf(type, reason, id, part, psinfo->buf, hsize, + size, psi); } /* diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 1376e5a8f0d6..c6bb77ca35b5 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -195,7 +195,8 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, - const char *buf, size_t size, + const char *buf, + size_t hsize, size_t size, struct pstore_info *psi) { struct ramoops_context *cxt = psi->data; diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 656699fcc7d7..4aa80ba830a2 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -58,12 +58,12 @@ struct pstore_info { struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, int count, size_t size, - struct pstore_info *psi); + unsigned int part, int count, size_t hsize, + size_t size, struct pstore_info *psi); int (*write_buf)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, - unsigned int part, const char *buf, size_t size, - struct pstore_info *psi); + unsigned int part, const char *buf, size_t hsize, + size_t size, struct pstore_info *psi); int (*erase)(enum pstore_type_id type, u64 id, int count, struct timespec time, struct pstore_info *psi); -- cgit v1.2.3