VFIO PPC64: add VFIO support on POWERPC64
Subsystems (6)
v2 cover VFIO PPC64: add VFIO support on POWERPC64
The series adds support for VFIO on POWERPC in user space (such as QEMU). The in-kernel real mode IOMMU support is added by another series posted separately.
As the first and main aim of this series is the POWERNV platform support, the "Enable on POWERNV platform" patch goes first and introduces an API to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch simply registers PHBs in the IOMMU subsystem and expects the API to be present, it enables VFIO support in fully emulated QEMU guests.
The main change is that this series was changed and tested against v3.10-rc1. It also contains some bugfixes which are mentioned (if any) in the patch messages.
Alexey Kardashevskiy (3):
powerpc/vfio: Enable on POWERNV platform
powerpc/vfio: Implement IOMMU driver for VFIO
powerpc/vfio: Enable on pSeries platform
Documentation/vfio.txt | 63 +++++ arch/powerpc/include/asm/iommu.h | 26 ++ arch/powerpc/kernel/iommu.c | 323 +++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci-p5ioc2.c | 5 +- arch/powerpc/platforms/powernv/pci.c | 2 + arch/powerpc/platforms/pseries/iommu.c | 4 + drivers/iommu/Kconfig | 8 + 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 +++ 13 files changed, 850 insertions(+), 1 deletion(-) create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
Signature · 1 line
1.7.10.4
PATCH 1/3 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.
---
Changes:
* the PCI devices are added to groups from subsys_initcall_sync (used to be done via bus_notifier callback registered for PCI bus)
* fixed parameters checking (the very last page in the address space was not handled correctly)
--- arch/powerpc/include/asm/iommu.h | 26 +++ arch/powerpc/kernel/iommu.c | 323 +++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci-p5ioc2.c | 5 +- arch/powerpc/platforms/powernv/pci.c | 2 + drivers/iommu/Kconfig | 8 + 6 files changed, 364 insertions(+), 1 deletion(-)
arch/powerpc/include/asm/iommu.h +26 -0
@@ -76,6 +76,9 @@ struct iommu_table {struct iommu_pool large_pool;struct iommu_pool pools[IOMMU_NR_POOLS ];unsigned long *it_map;/* A simple allocation bitmap for now */ +#ifdef CONFIG_IOMMU_API +struct iommu_group *it_group; +#endif };struct scatterlist ;
@@ -98,6 +101,8 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);*/ extern struct iommu_table *iommu_init_table (struct iommu_table * tbl,int nid); +extern void iommu_register_group (struct iommu_table *tbl, +int pci_domain_number,unsigned long pe_num); extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct scatterlist *sglist, int nelems,
@@ -147,5 +152,26 @@ static inline void iommu_restore(void) }#endif +/* The API to support IOMMU operations for VFIO */ +extern int iommu_tce_clear_param_check (struct iommu_table *tbl, +unsigned long ioba,unsigned long tce_value, +unsigned long npages); +extern int iommu_tce_put_param_check (struct iommu_table *tbl, +unsigned long ioba,unsigned long tce); +extern int iommu_tce_build (struct iommu_table *tbl,unsigned long entry, +unsigned long hwaddr,enum dma_data_direction direction); +extern unsigned long iommu_clear_tce (struct iommu_table *tbl, +unsigned long entry); +extern int iommu_clear_tces_and_put_pages (struct iommu_table *tbl, +unsigned long entry,unsigned long pages); +extern int iommu_put_tce_user_mode (struct iommu_table *tbl, +unsigned long entry,unsigned long tce); + +extern void iommu_flush_tce (struct iommu_table *tbl); +extern int iommu_take_ownership (struct iommu_table *tbl); +extern void iommu_release_ownership (struct iommu_table *tbl); + +extern enum dma_data_direction iommu_tce_direction (unsigned long tce); +#endif /* __KERNEL__ */ #endif /* _ASM_IOMMU_H */
arch/powerpc/kernel/iommu.c +323 -0
344 lines not on this page · raw message
arch/powerpc/platforms/powernv/pci-ioda.c +1 -0
@@ -605,6 +605,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,TCE_PCI_SWINV_PAIR ; }iommu_init_table (tbl, phb->hose->node); +iommu_register_group (tbl,pci_domain_nr (pe->pbus), pe->pe_number);return ; fail:
arch/powerpc/platforms/powernv/pci-p5ioc2.c +4 -1
@@ -86,8 +86,11 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }static void pnv_pci_p5ioc2_dma_dev_setup (struct pnv_phb *phb,struct pci_dev *pdev) { -if (phb->p5ioc2.iommu_table.it_map ==NULL ) +if (phb->p5ioc2.iommu_table.it_map ==NULL ) {iommu_init_table (&phb->p5ioc2.iommu_table, phb->hose->node); +iommu_register_group (&phb->p5ioc2.iommu_table, +pci_domain_nr (phb->hose->bus), phb->opal_id); + }set_iommu_table_base (&pdev->dev, &phb->p5ioc2.iommu_table); }
arch/powerpc/platforms/powernv/pci.c +2 -0
@@ -20,6 +20,7 @@#include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> +#include <linux/iommu.h> #include <asm/sections.h> #include <asm/io.h>
@@ -408,6 +409,7 @@ static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)pnv_pci_setup_iommu_table (tbl,__va (be64_to_cpup (basep)),be32_to_cpup (sizep),0 );iommu_init_table (tbl, hose->node); +iommu_register_group (tbl,pci_domain_nr (hose->bus),0 );/* Deal with SW invalidated TCEs when needed (BML way) */ swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",
drivers/iommu/Kconfig +8 -0
@@ -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
Signature · 1 line
1.7.10.4
Re: [1/3] powerpc/vfio: Enable on POWERNV platform
Quoted 11 lines · Alexey Kardashevskiy
arch/powerpc/kernel/iommu.c +11
-0+static int iommu_add_device (struct device *dev) +{ +struct iommu_table *tbl; +int ret =0 ; + +if (WARN_ON (dev->iommu_group)) { +pr_warn ("iommu_tce: device %s is already in iommu group %d, skipping\n" , +dev_name (dev), +iommu_group_id (dev->iommu_group)); +return -EBUSY ; + }
[snip]
Quoted 4 lines
arch/powerpc/kernel/iommu.c +4
-0+static int __init tce_iommu_init (void ) +{ +struct pci_dev *pdev =NULL ; +
arch/powerpc/kernel/iommu.c void iommu_free_coherent(struct iommu_table *tbl, size_t size, · line 1176
Quoted 10 lines
arch/powerpc/kernel/iommu.c +10
-0+BUILD_BUG_ON (PAGE_SIZE <IOMMU_PAGE_SIZE ); + +for_each_pci_dev (pdev) +iommu_add_device (&pdev->dev); + +bus_register_notifier (&pci_bus_type, &tce_iommu_bus_nb); +return 0 ; +} + +subsys_initcall_sync (tce_iommu_init);
This is missing a check to see whether the appropriate hardware is present. This file should also be renamed to something less generic, and depend on a kconfig symbol more specific than CONFIG_PPC64.
When this is combined with CONFIG_FSL_PAMU on hardware with a PAMU, I get a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already got to them. Presumably without PAMU it silently (or with just pr_debug) bails out at some other point.
-Scott
Re: [1/3] powerpc/vfio: Enable on POWERNV platform
Quoted 32 lines · Scott Wood
Quoted 11 lines · Alexey Kardashevskiy
arch/powerpc/kernel/iommu.c +11
-0+static int iommu_add_device (struct device *dev) +{ +struct iommu_table *tbl; +int ret =0 ; + +if (WARN_ON (dev->iommu_group)) { +pr_warn ("iommu_tce: device %s is already in iommu group %d, skipping\n" , +dev_name (dev), +iommu_group_id (dev->iommu_group)); +return -EBUSY ; + }[snip]
Quoted 4 lines
arch/powerpc/kernel/iommu.c +4
-0+static int __init tce_iommu_init (void ) +{ +struct pci_dev *pdev =NULL ; +arch/powerpc/kernel/iommu.c void iommu_free_coherent(struct iommu_table *tbl, size_t size, · line 1176
Quoted 10 lines
arch/powerpc/kernel/iommu.c +10
-0+BUILD_BUG_ON (PAGE_SIZE <IOMMU_PAGE_SIZE ); + +for_each_pci_dev (pdev) +iommu_add_device (&pdev->dev); + +bus_register_notifier (&pci_bus_type, &tce_iommu_bus_nb); +return 0 ; +} + +subsys_initcall_sync (tce_iommu_init);This is missing a check to see whether the appropriate hardware is present. This file should also be renamed to something less generic, and depend on a kconfig symbol more specific than
CONFIG_PPC64.
Quoted 4 lines
When this is combined with
CONFIG_FSL_PAMUon hardware with a PAMU, I get a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already got to them. Presumably without PAMU it silently (or with justpr_debug) bails out at some other point.
I posted (yet again) yesterday "[PATCH v11] PPC: POWERNV: move iommu_add_device earlier" which should fix this. And Bharat asked many times for this to get accepted :)
Signature · 1 line
Alexey
Re: [1/3] powerpc/vfio: Enable on POWERNV platform
Quoted 39 lines · Alexey Kardashevskiy
Quoted 32 lines · Scott Wood
Quoted 11 lines · Alexey Kardashevskiy
arch/powerpc/kernel/iommu.c +11
-0+static int iommu_add_device (struct device *dev) +{ +struct iommu_table *tbl; +int ret =0 ; + +if (WARN_ON (dev->iommu_group)) { +pr_warn ("iommu_tce: device %s is already in iommu group %d, skipping\n" , +dev_name (dev), +iommu_group_id (dev->iommu_group)); +return -EBUSY ; + }[snip]
Quoted 4 lines
arch/powerpc/kernel/iommu.c +4
-0+static int __init tce_iommu_init (void ) +{ +struct pci_dev *pdev =NULL ; +arch/powerpc/kernel/iommu.c void iommu_free_coherent(struct iommu_table *tbl, size_t size, · line 1176
Quoted 10 lines
arch/powerpc/kernel/iommu.c +10
-0+BUILD_BUG_ON (PAGE_SIZE <IOMMU_PAGE_SIZE ); + +for_each_pci_dev (pdev) +iommu_add_device (&pdev->dev); + +bus_register_notifier (&pci_bus_type, &tce_iommu_bus_nb); +return 0 ; +} + +subsys_initcall_sync (tce_iommu_init);This is missing a check to see whether the appropriate hardware is present. This file should also be renamed to something less generic, and depend on a kconfig symbol more specific than
CONFIG_PPC64.Quoted 4 lines
When this is combined with
CONFIG_FSL_PAMUon hardware with a PAMU, I get a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already got to them. Presumably without PAMU it silently (or with justpr_debug) bails out at some other point.
Quoted 3 lines
I posted (yet again) yesterday "[PATCH v11] PPC: POWERNV: move
iommu_add_deviceearlier" which should fix this. And Bharat asked many times for this to get accepted :)
I still get the WARN_ONs even with that patch. You're still registering the bus notifier unconditionally.
-Scott
RE: [1/3] powerpc/vfio: Enable on POWERNV platform
Quoted 50 lines
-----Original Message-----
From: Wood Scott-B07421
Sent: Saturday, December 14, 2013 2:33 AM
To: Alexey Kardashevskiy
Cc: [email protected]; [email protected]; linux- [email protected]; Alex Williamson; Paul Mackerras; David Gibson; Sethi Varun-B16395; Bhushan Bharat-R65777
Subject: Re: [1/3] powerpc/vfio: Enable on POWERNV platformQuoted 8 lines · Alexey Kardashevskiy
Quoted 7 lines · Scott Wood
arch/powerpc/kernel/iommu.c void iommu_free_coherent(struct iommu_table *tbl, size_t size,
Quoted 6 lines · Alexey Kardashevskiy
arch/powerpc/kernel/iommu.c +6
-0+static int iommu_add_device (struct device *dev) { +struct iommu_table *tbl; +int ret =0 ; + +if (WARN_ON (dev->iommu_group)) { + pr_warn("iommu_tce: device %s is already in iommu group %d,skipping\n",
Quoted 29 lines
Quoted 27 lines
Quoted 4 lines
arch/powerpc/kernel/iommu.c +4
-0+dev_name (dev), + iommu_group_id(dev->iommu_group)); +return -EBUSY ; + }[snip]
arch/powerpc/kernel/iommu.c void iommu_free_coherent(struct iommu_table *tbl, size_t size, · line 1176
Quoted 13 lines
arch/powerpc/kernel/iommu.c +13
-0+static int __init tce_iommu_init (void ) { +struct pci_dev *pdev =NULL ; + +BUILD_BUG_ON (PAGE_SIZE <IOMMU_PAGE_SIZE ); + +for_each_pci_dev (pdev) +iommu_add_device (&pdev->dev); + +bus_register_notifier (&pci_bus_type, &tce_iommu_bus_nb); +return 0 ; +} + +subsys_initcall_sync (tce_iommu_init);This is missing a check to see whether the appropriate hardware is present. This file should also be renamed to something less generic, and depend on a kconfig symbol more specific than
CONFIG_PPC64.When this is combined with
CONFIG_FSL_PAMUon hardware with a PAMU, I get a bunch of those "WARN_ON(dev->iommu_group)" dumps because PAMU already got to them. Presumably without PAMU it silently (or with justpr_debug) bails out at some other point.
Quoted 6 lines
Quoted 3 lines
I posted (yet again) yesterday "[PATCH v11] PPC: POWERNV: move
iommu_add_deviceearlier" which should fix this. And Bharat asked many times for this to get accepted :)I still get the
WARN_ONseven with that patch. You're still registering the bus notifier unconditionally.
I have not tried v11 but tested V9 version of that patch. And yes, in that version the bus notifier was not registered unconditionally in kernel/iommu.c .
Thanks
-Bharat
Quoted 3 lines
-Scott
PATCH 2/3 powerpc/vfio: Implement IOMMU driver for VFIO
In reply to Alexey KardashevskiyVFIO 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).
--- 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
Documentation/vfio.txt +63 -0
@@ -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
drivers/vfio/Kconfig +6 -0
@@ -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.
drivers/vfio/Makefile +1 -0
@@ -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/
drivers/vfio/vfio.c +1 -0
@@ -1428,6 +1428,7 @@ static int __init vfio_init(void)* drivers. */ request_module_nowait ("vfio_iommu_type1" ); +request_module_nowait ("vfio_iommu_spapr_tce" );return 0 ;
drivers/vfio/vfio_iommu_spapr_tce.c new file +377 -0
377 lines not on this page · raw message
include/uapi/linux/vfio.h +34 -0
@@ -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 */
Signature · 1 line
1.7.10.4
Re: [PATCH 2/3] powerpc/vfio: Implement IOMMU driver for VFIO
Quoted 10 lines · Alexey Kardashevskiy
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).
Quoted 3 lines
Cc David Gibson <[email protected]>Signed-off-by Alexey Kardashevskiy <[email protected]>Signed-off-by Paul Mackerras <[email protected]>
Quoted 559 lines
--- 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.cDocumentation/vfio.txt +63
-0@@ -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 itsdrivers/vfio/Kconfig +6
-0@@ -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.drivers/vfio/Makefile +1
-0@@ -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/drivers/vfio/vfio.c +1
-0@@ -1428,6 +1428,7 @@ static int __init vfio_init(void)* drivers. */ request_module_nowait ("vfio_iommu_type1" ); +request_module_nowait ("vfio_iommu_spapr_tce" );return 0 ;drivers/vfio/vfio_iommu_spapr_tce.c new file +377
-0@@ -0,0 +1,377 @@ +/* +* VFIO: IOMMU DMA mapping support for TCE on POWER +* +* Copyright (C) 2013 IBM Corp. All rights reserved. +* Author: Alexey Kardashevskiy <[email protected]> +* +* 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 <[email protected]> +*/ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/err.h> +#include <linux/vfio.h> +#include <asm/iommu.h> +#include <asm/tce.h> + +#define DRIVER_VERSION "0.1" +#define DRIVER_AUTHOR "[email protected]" +#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 ); +include/uapi/linux/vfio.h +34
-0@@ -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 */
PATCH 3/3 powerpc/vfio: Enable on pSeries platform
In reply to Alexey KardashevskiyThe enables VFIO on the pSeries platform, enabling user space programs to access PCI devices directly.
--- arch/powerpc/platforms/pseries/iommu.c | 4 ++++ drivers/iommu/Kconfig | 2 +- drivers/vfio/Kconfig | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-)
arch/powerpc/platforms/pseries/iommu.c +4 -0
@@ -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);
drivers/iommu/Kconfig +1 -1
@@ -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
drivers/vfio/Kconfig +1 -1
@@ -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.
Signature · 1 line
1.7.10.4
Re: [PATCH 3/3] powerpc/vfio: Enable on pSeries platform
Quoted 6 lines · Alexey Kardashevskiy
The enables VFIO on the pSeries platform, enabling user space programs to access PCI devices directly.
Signed-off-by Alexey Kardashevskiy <[email protected]>Cc David Gibson <[email protected]>Signed-off-by Paul Mackerras <[email protected]>
Quoted 68 lines
--- arch/powerpc/platforms/pseries/iommu.c | 4 ++++ drivers/iommu/Kconfig | 2 +- drivers/vfio/Kconfig | 2 +- 3 files changed, 6 insertions(+), 2 deletions(-)arch/powerpc/platforms/pseries/iommu.c +4
-0@@ -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);drivers/iommu/Kconfig +1
-1@@ -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_opsdrivers/vfio/Kconfig +1
-1@@ -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.
Oops, wrong subject (cut-n-paste) :)
There are 3 patches, not 5.
Quoted 17 lines · Alexey Kardashevskiy
The series adds support for VFIO on POWERPC in user space (such as QEMU). The in-kernel real mode IOMMU support is added by another series posted separately.
As the first and main aim of this series is the POWERNV platform support, the "Enable on POWERNV platform" patch goes first and introduces an API to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch simply registers PHBs in the IOMMU subsystem and expects the API to be present, it enables VFIO support in fully emulated QEMU guests.
The main change is that this series was changed and tested against v3.10-rc1. It also contains some bugfixes which are mentioned (if any) in the patch messages.
Alexey Kardashevskiy (3):
powerpc/vfio: Enable on POWERNV platform
powerpc/vfio: Implement IOMMU driver for VFIO
powerpc/vfio: Enable on pSeries platform
Signature · 1 line
Alexey
Quoted 18 lines · Alexey Kardashevskiy
The series adds support for VFIO on POWERPC in user space (such as QEMU). The in-kernel real mode IOMMU support is added by another series posted separately.
As the first and main aim of this series is the POWERNV platform support, the "Enable on POWERNV platform" patch goes first and introduces an API to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch simply registers PHBs in the IOMMU subsystem and expects the API to be present, it enables VFIO support in fully emulated QEMU guests.
The main change is that this series was changed and tested against v3.10-rc1. It also contains some bugfixes which are mentioned (if any) in the patch messages.
Alexey Kardashevskiy (3):
powerpc/vfio: Enable on POWERNV platform
powerpc/vfio: Implement IOMMU driver for VFIO
powerpc/vfio: Enable on pSeries platform
Quoted 16 lines
Documentation/vfio.txt | 63 +++++ arch/powerpc/include/asm/iommu.h | 26 ++ arch/powerpc/kernel/iommu.c | 323 +++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci-p5ioc2.c | 5 +- arch/powerpc/platforms/powernv/pci.c | 2 + arch/powerpc/platforms/pseries/iommu.c | 4 + drivers/iommu/Kconfig | 8 + 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 +++ 13 files changed, 850 insertions(+), 1 deletion(-) create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
These look ok to me, how do you want to integrate them? Should I provide Acks on patches 2 & 3 and let them get pushed through the ppc tree or should I wait for patch 1 then push 2 & 3 through my tree? Thanks,
Alex
Quoted 36 lines · Alex Williamson
Quoted 18 lines · Alexey Kardashevskiy
The series adds support for VFIO on POWERPC in user space (such as QEMU). The in-kernel real mode IOMMU support is added by another series posted separately.
As the first and main aim of this series is the POWERNV platform support, the "Enable on POWERNV platform" patch goes first and introduces an API to be used by the VFIO IOMMU driver. The "Enable on pSeries platform" patch simply registers PHBs in the IOMMU subsystem and expects the API to be present, it enables VFIO support in fully emulated QEMU guests.
The main change is that this series was changed and tested against v3.10-rc1. It also contains some bugfixes which are mentioned (if any) in the patch messages.
Alexey Kardashevskiy (3):
powerpc/vfio: Enable on POWERNV platform
powerpc/vfio: Implement IOMMU driver for VFIO
powerpc/vfio: Enable on pSeries platformQuoted 16 lines
Documentation/vfio.txt | 63 +++++ arch/powerpc/include/asm/iommu.h | 26 ++ arch/powerpc/kernel/iommu.c | 323 +++++++++++++++++++++++ arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci-p5ioc2.c | 5 +- arch/powerpc/platforms/powernv/pci.c | 2 + arch/powerpc/platforms/pseries/iommu.c | 4 + drivers/iommu/Kconfig | 8 + 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 +++ 13 files changed, 850 insertions(+), 1 deletion(-) create mode 100644 drivers/vfio/vfio_iommu_spapr_tce.c
Quoted 3 lines
These look ok to me, how do you want to integrate them? Should I provide Acks on patches 2 & 3 and let them get pushed through the ppc tree or should I wait for patch 1 then push 2 & 3 through my tree?
Please ack on 2 & 3 and Ben will merge all three into his tree. Thanks!
Signature · 1 line
Alexey