| Message ID | 20110511104615.GM2837@brick.ozlabs.ibm.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
On 11.05.2011, at 12:46, Paul Mackerras wrote: > From: David Gibson <dwg@au1.ibm.com> > > This improves I/O performance for guests using the PAPR paravirtualization > interface by making the H_PUT_TCE hcall faster, by implementing it in > real mode. H_PUT_TCE is used for updating virtual IOMMU tables, and is > used both for virtual I/O and for real I/O in the PAPR interface. > > Since this moves the IOMMU tables into the kernel, we define a new > KVM_CREATE_SPAPR_TCE ioctl to allow qemu to create the tables. > The ioctl returns a file descriptor which can be used to mmap the > newly created table. > > Signed-off-by: Paul Mackerras <paulus@samba.org> > --- > arch/powerpc/include/asm/kvm.h | 9 +++ > arch/powerpc/include/asm/kvm_book3s_64.h | 2 + > arch/powerpc/include/asm/kvm_host.h | 9 +++ > arch/powerpc/include/asm/kvm_ppc.h | 2 + > arch/powerpc/kvm/Makefile | 3 +- > arch/powerpc/kvm/book3s_64_vio_hv.c | 73 +++++++++++++++++++ > arch/powerpc/kvm/book3s_hv.c | 116 +++++++++++++++++++++++++++++- > arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +- > arch/powerpc/kvm/powerpc.c | 18 +++++ > include/linux/kvm.h | 5 ++ This one definitely needs documentation :). > 10 files changed, 236 insertions(+), 3 deletions(-) > create mode 100644 arch/powerpc/kvm/book3s_64_vio_hv.c > > diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h > index 18ea696..a9e641b 100644 > --- a/arch/powerpc/include/asm/kvm.h > +++ b/arch/powerpc/include/asm/kvm.h > @@ -22,6 +22,9 @@ > > #include <linux/types.h> > > +/* Select powerpc specific features in <linux/kvm.h> */ > +#define __KVM_HAVE_SPAPR_TCE > + > struct kvm_regs { > __u64 pc; > __u64 cr; > @@ -88,4 +91,10 @@ struct kvm_guest_debug_arch { > #define KVM_INTERRUPT_UNSET -2U > #define KVM_INTERRUPT_SET_LEVEL -3U > > +/* for KVM_CAP_SPAPR_TCE */ > +struct kvm_create_spapr_tce { > + __u64 liobn; > + __u32 window_size; > +}; > + > #endif /* __LINUX_KVM_POWERPC_H */ > diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h > index 4cadd61..e1a096b 100644 > --- a/arch/powerpc/include/asm/kvm_book3s_64.h > +++ b/arch/powerpc/include/asm/kvm_book3s_64.h > @@ -25,4 +25,6 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) > return &get_paca()->shadow_vcpu; > } > > +#define SPAPR_TCE_SHIFT 12 > + > #endif /* __ASM_KVM_BOOK3S_64_H__ */ > diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h > index af6703e..cda183e 100644 > --- a/arch/powerpc/include/asm/kvm_host.h > +++ b/arch/powerpc/include/asm/kvm_host.h > @@ -144,6 +144,14 @@ struct kvmppc_pginfo { > atomic_t refcnt; > }; > > +struct kvmppc_spapr_tce_table { > + struct list_head list; > + struct kvm *kvm; > + u64 liobn; > + u32 window_size; > + struct page *pages[0]; > +}; > + > struct kvm_arch { > unsigned long hpt_virt; > unsigned long ram_npages; > @@ -157,6 +165,7 @@ struct kvm_arch { > unsigned long host_sdr1; > int tlbie_lock; > unsigned short last_vcpu[NR_CPUS]; > + struct list_head spapr_tce_tables; > }; > > struct kvmppc_pte { > diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h > index b4ee11a..de683fa 100644 > --- a/arch/powerpc/include/asm/kvm_ppc.h > +++ b/arch/powerpc/include/asm/kvm_ppc.h > @@ -117,6 +117,8 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm, > extern void kvmppc_map_vrma(struct kvm *kvm, > struct kvm_userspace_memory_region *mem); > extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); > +extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, > + struct kvm_create_spapr_tce *args); > extern int kvmppc_core_init_vm(struct kvm *kvm); > extern void kvmppc_core_destroy_vm(struct kvm *kvm); > extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, > diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile > index 37c1a60..8ba062f 100644 > --- a/arch/powerpc/kvm/Makefile > +++ b/arch/powerpc/kvm/Makefile > @@ -59,7 +59,8 @@ kvm-book3s_64_hv-objs := \ > book3s.o \ > book3s_hv.o \ > book3s_hv_interrupts.o \ > - book3s_64_mmu_hv.o > + book3s_64_mmu_hv.o \ > + book3s_64_vio_hv.o > kvm-objs-$(CONFIG_KVM_BOOK3S_64_HV) := $(kvm-book3s_64_hv-objs) > > kvm-book3s_32-objs := \ > diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c > new file mode 100644 > index 0000000..ea0f8c5 > --- /dev/null > +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c > @@ -0,0 +1,73 @@ > +/* > + * 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. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + * > + * You should have received a copy of the GNU General Public License > + * along with this program; if not, write to the Free Software > + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. > + * > + * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> > + * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> > + */ > + > +#include <linux/types.h> > +#include <linux/string.h> > +#include <linux/kvm.h> > +#include <linux/kvm_host.h> > +#include <linux/highmem.h> > +#include <linux/gfp.h> > +#include <linux/slab.h> > +#include <linux/hugetlb.h> > +#include <linux/list.h> > + > +#include <asm/tlbflush.h> > +#include <asm/kvm_ppc.h> > +#include <asm/kvm_book3s.h> > +#include <asm/mmu-hash64.h> > +#include <asm/hvcall.h> > +#include <asm/synch.h> > +#include <asm/ppc-opcode.h> > +#include <asm/kvm_host.h> > +#include <asm/udbg.h> > + > +#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) > + It would be great to somehow mark code that runs in real mode as such - either by an attribute in the function header or by a simple comment. > +long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, > + unsigned long ioba, unsigned long tce) > +{ > + struct kvm *kvm = vcpu->kvm; > + struct kvmppc_spapr_tce_table *stt; > + > + /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ > + /* liobn, ioba, tce); */ > + > + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { > + if (stt->liobn == liobn) { > + unsigned long idx = ioba >> SPAPR_TCE_SHIFT; > + struct page *page; > + u64 *tbl; > + > + /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */ > + /* liobn, stt, stt->window_size); */ > + if (ioba >= stt->window_size) > + return H_PARAMETER; > + > + page = stt->pages[idx / TCES_PER_PAGE]; > + tbl = (u64 *)page_address(page); > + > + /* FIXME: Need to validate the TCE itself */ > + /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */ > + tbl[idx % TCES_PER_PAGE] = tce; > + return H_SUCCESS; > + } > + } > + > + /* Didn't find the liobn, punt it to userspace */ > + return H_TOO_HARD; > +} > diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c > index 377a35a..eed2c10 100644 > --- a/arch/powerpc/kvm/book3s_hv.c > +++ b/arch/powerpc/kvm/book3s_hv.c > @@ -506,6 +506,116 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) > return r; > } > > +static long kvmppc_stt_npages(unsigned long window_size) > +{ > + return ALIGN((window_size >> SPAPR_TCE_SHIFT) > + * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; > +} > + > +static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt) > +{ > + struct kvm *kvm = stt->kvm; > + int i; > + > + mutex_lock(&kvm->lock); > + list_del(&stt->list); > + for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++) > + __free_page(stt->pages[i]); > + kfree(stt); > + mutex_unlock(&kvm->lock); > + > + kvm_put_kvm(kvm); > +} > + > +static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) > +{ > + struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data; > + struct page *page; > + > + if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size)) > + return VM_FAULT_SIGBUS; > + > + page = stt->pages[vmf->pgoff]; > + get_page(page); > + vmf->page = page; > + return 0; > +} > + > +static const struct vm_operations_struct kvm_spapr_tce_vm_ops = { > + .fault = kvm_spapr_tce_fault, > +}; > + > +static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma) > +{ > + vma->vm_ops = &kvm_spapr_tce_vm_ops; > + return 0; > +} > + > +static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) > +{ > + struct kvmppc_spapr_tce_table *stt = filp->private_data; > + > + release_spapr_tce_table(stt); > + return 0; > +} > + > +static struct file_operations kvm_spapr_tce_fops = { > + .mmap = kvm_spapr_tce_mmap, > + .release = kvm_spapr_tce_release, > +}; > + > +long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, > + struct kvm_create_spapr_tce *args) > +{ > + struct kvmppc_spapr_tce_table *stt = NULL; > + long npages; > + int ret = -ENOMEM; > + int i; > + > + /* Check this LIOBN hasn't been previously allocated */ > + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { > + if (stt->liobn == args->liobn) > + return -EBUSY; > + } > + > + npages = kvmppc_stt_npages(args->window_size); > + > + stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *), > + GFP_KERNEL); > + if (!stt) > + goto fail; > + > + stt->liobn = args->liobn; > + stt->window_size = args->window_size; > + stt->kvm = kvm; > + > + for (i = 0; i < npages; i++) { > + stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); > + if (!stt->pages[i]) > + goto fail; > + } > + > + kvm_get_kvm(kvm); > + > + mutex_lock(&kvm->lock); > + list_add(&stt->list, &kvm->arch.spapr_tce_tables); > + > + mutex_unlock(&kvm->lock); > + > + return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, > + stt, O_RDONLY); > + > +fail: > + if (stt) { > + for (i = 0; i < npages; i++) > + if (stt->pages[i]) > + __free_page(stt->pages[i]); > + > + kfree(stt); > + } > + return ret; > +} > + > int kvmppc_core_prepare_memory_region(struct kvm *kvm, > struct kvm_userspace_memory_region *mem) > { > @@ -527,13 +637,17 @@ int kvmppc_core_init_vm(struct kvm *kvm) > > /* Allocate hashed page table */ > r = kvmppc_alloc_hpt(kvm); > + if (r) > + return r; > > - return r; > + INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); > + return 0; > } > > void kvmppc_core_destroy_vm(struct kvm *kvm) > { > kvmppc_free_hpt(kvm); > + WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); > } > > /* These are stubs for now */ > diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S > index e8a8f3c..95f6386 100644 > --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S > +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S > @@ -722,7 +722,7 @@ hcall_real_table: > .long 0 /* 0x14 - H_CLEAR_REF */ > .long .kvmppc_h_protect - hcall_real_table > .long 0 /* 0x1c - H_GET_TCE */ > - .long 0 /* 0x20 - H_SET_TCE */ > + .long .kvmppc_h_put_tce - hcall_real_table > .long 0 /* 0x24 - H_SET_SPRG0 */ > .long .kvmppc_h_set_dabr - hcall_real_table > .long 0 /* 0x2c */ > diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c > index 7bfe413..10f777a 100644 > --- a/arch/powerpc/kvm/powerpc.c > +++ b/arch/powerpc/kvm/powerpc.c > @@ -196,6 +196,11 @@ int kvm_dev_ioctl_check_extension(long ext) > r = KVM_COALESCED_MMIO_PAGE_OFFSET; > break; > #endif > +#ifdef CONFIG_KVM_BOOK3S_64_HV > + case KVM_CAP_SPAPR_TCE: > + r = 1; > + break; > +#endif > default: > r = 0; > break; > @@ -628,6 +633,19 @@ long kvm_arch_vm_ioctl(struct file *filp, > > break; > } > +#ifdef CONFIG_KVM_BOOK3S_64_HV > + case KVM_CREATE_SPAPR_TCE: { > + struct kvm_create_spapr_tce create_tce; > + struct kvm *kvm = filp->private_data; > + > + r = -EFAULT; > + if (copy_from_user(&create_tce, argp, sizeof(create_tce))) > + goto out; > + r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce); > + goto out; > + } I'm not sure I fully understand how this is supposed to work. If the tables are kept inside the kernel, how does userspace get to know where to DMA to? Alex
On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote: > I'm not sure I fully understand how this is supposed to work. If the > tables are kept inside the kernel, how does userspace get to know > where to DMA to? The guest gets a dma range from the device-tree which is the range of device-side dma addresses it can use that correspond to the table. The guest kernel uses the normal linux iommu space allocator to allocate space in that region and uses H_PUT_TCE to populate the corresponding table entries. This is the same interface that is used for "real" iommu's with PCI devices btw. Cheers, Ben.
On 17.05.2011, at 11:11, Benjamin Herrenschmidt wrote: > On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote: >> I'm not sure I fully understand how this is supposed to work. If the >> tables are kept inside the kernel, how does userspace get to know >> where to DMA to? > > The guest gets a dma range from the device-tree which is the range of > device-side dma addresses it can use that correspond to the table. > > The guest kernel uses the normal linux iommu space allocator to allocate > space in that region and uses H_PUT_TCE to populate the corresponding > table entries. > > This is the same interface that is used for "real" iommu's with PCI > devices btw. I'm still slightly puzzled here :). IIUC the main point of an IOMMU is for the kernel to change where device accesses actually go to. So device DMAs address A, goes through the IOMMU, in reality accesses address B. Now, how do we tell the devices implemented in qemu that they're supposed to DMA to address B instead of A if the mapping table is kept in-kernel? Alex
On Tue, 2011-05-17 at 11:31 +0200, Alexander Graf wrote: > On 17.05.2011, at 11:11, Benjamin Herrenschmidt wrote: > > > On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote: > >> I'm not sure I fully understand how this is supposed to work. If the > >> tables are kept inside the kernel, how does userspace get to know > >> where to DMA to? > > > > The guest gets a dma range from the device-tree which is the range of > > device-side dma addresses it can use that correspond to the table. > > > > The guest kernel uses the normal linux iommu space allocator to allocate > > space in that region and uses H_PUT_TCE to populate the corresponding > > table entries. > > > > This is the same interface that is used for "real" iommu's with PCI > > devices btw. > > I'm still slightly puzzled here :). IIUC the main point of an IOMMU is for the kernel > to change where device accesses actually go to. So device DMAs address A, goes through > the IOMMU, in reality accesses address B. Right :-) > Now, how do we tell the devices implemented in qemu that they're supposed to DMA to > address B instead of A if the mapping table is kept in-kernel? Oh, bcs qemu mmaps the table :-) Cheers, Ben.
On 17.05.2011, at 11:35, Benjamin Herrenschmidt wrote: > On Tue, 2011-05-17 at 11:31 +0200, Alexander Graf wrote: >> On 17.05.2011, at 11:11, Benjamin Herrenschmidt wrote: >> >>> On Tue, 2011-05-17 at 10:01 +0200, Alexander Graf wrote: >>>> I'm not sure I fully understand how this is supposed to work. If the >>>> tables are kept inside the kernel, how does userspace get to know >>>> where to DMA to? >>> >>> The guest gets a dma range from the device-tree which is the range of >>> device-side dma addresses it can use that correspond to the table. >>> >>> The guest kernel uses the normal linux iommu space allocator to allocate >>> space in that region and uses H_PUT_TCE to populate the corresponding >>> table entries. >>> >>> This is the same interface that is used for "real" iommu's with PCI >>> devices btw. >> >> I'm still slightly puzzled here :). IIUC the main point of an IOMMU is for the kernel >> to change where device accesses actually go to. So device DMAs address A, goes through >> the IOMMU, in reality accesses address B. > > Right :-) > >> Now, how do we tell the devices implemented in qemu that they're supposed to DMA to >> address B instead of A if the mapping table is kept in-kernel? > > Oh, bcs qemu mmaps the table :-) That's the piece to the puzzle I was missing. Please document that interface properly - it needs to be rock stable :) Alex
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index 18ea696..a9e641b 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -22,6 +22,9 @@ #include <linux/types.h> +/* Select powerpc specific features in <linux/kvm.h> */ +#define __KVM_HAVE_SPAPR_TCE + struct kvm_regs { __u64 pc; __u64 cr; @@ -88,4 +91,10 @@ struct kvm_guest_debug_arch { #define KVM_INTERRUPT_UNSET -2U #define KVM_INTERRUPT_SET_LEVEL -3U +/* for KVM_CAP_SPAPR_TCE */ +struct kvm_create_spapr_tce { + __u64 liobn; + __u32 window_size; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 4cadd61..e1a096b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -25,4 +25,6 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) return &get_paca()->shadow_vcpu; } +#define SPAPR_TCE_SHIFT 12 + #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index af6703e..cda183e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -144,6 +144,14 @@ struct kvmppc_pginfo { atomic_t refcnt; }; +struct kvmppc_spapr_tce_table { + struct list_head list; + struct kvm *kvm; + u64 liobn; + u32 window_size; + struct page *pages[0]; +}; + struct kvm_arch { unsigned long hpt_virt; unsigned long ram_npages; @@ -157,6 +165,7 @@ struct kvm_arch { unsigned long host_sdr1; int tlbie_lock; unsigned short last_vcpu[NR_CPUS]; + struct list_head spapr_tce_tables; }; struct kvmppc_pte { diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index b4ee11a..de683fa 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -117,6 +117,8 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm, extern void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem); extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); +extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, + struct kvm_create_spapr_tce *args); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 37c1a60..8ba062f 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -59,7 +59,8 @@ kvm-book3s_64_hv-objs := \ book3s.o \ book3s_hv.o \ book3s_hv_interrupts.o \ - book3s_64_mmu_hv.o + book3s_64_mmu_hv.o \ + book3s_64_vio_hv.o kvm-objs-$(CONFIG_KVM_BOOK3S_64_HV) := $(kvm-book3s_64_hv-objs) kvm-book3s_32-objs := \ diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c new file mode 100644 index 0000000..ea0f8c5 --- /dev/null +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -0,0 +1,73 @@ +/* + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> + */ + +#include <linux/types.h> +#include <linux/string.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/hugetlb.h> +#include <linux/list.h> + +#include <asm/tlbflush.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> +#include <asm/mmu-hash64.h> +#include <asm/hvcall.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> +#include <asm/kvm_host.h> +#include <asm/udbg.h> + +#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) + +long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, + unsigned long ioba, unsigned long tce) +{ + struct kvm *kvm = vcpu->kvm; + struct kvmppc_spapr_tce_table *stt; + + /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ + /* liobn, ioba, tce); */ + + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { + if (stt->liobn == liobn) { + unsigned long idx = ioba >> SPAPR_TCE_SHIFT; + struct page *page; + u64 *tbl; + + /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */ + /* liobn, stt, stt->window_size); */ + if (ioba >= stt->window_size) + return H_PARAMETER; + + page = stt->pages[idx / TCES_PER_PAGE]; + tbl = (u64 *)page_address(page); + + /* FIXME: Need to validate the TCE itself */ + /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */ + tbl[idx % TCES_PER_PAGE] = tce; + return H_SUCCESS; + } + } + + /* Didn't find the liobn, punt it to userspace */ + return H_TOO_HARD; +} diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 377a35a..eed2c10 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -506,6 +506,116 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } +static long kvmppc_stt_npages(unsigned long window_size) +{ + return ALIGN((window_size >> SPAPR_TCE_SHIFT) + * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; +} + +static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt) +{ + struct kvm *kvm = stt->kvm; + int i; + + mutex_lock(&kvm->lock); + list_del(&stt->list); + for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++) + __free_page(stt->pages[i]); + kfree(stt); + mutex_unlock(&kvm->lock); + + kvm_put_kvm(kvm); +} + +static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data; + struct page *page; + + if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size)) + return VM_FAULT_SIGBUS; + + page = stt->pages[vmf->pgoff]; + get_page(page); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct kvm_spapr_tce_vm_ops = { + .fault = kvm_spapr_tce_fault, +}; + +static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma) +{ + vma->vm_ops = &kvm_spapr_tce_vm_ops; + return 0; +} + +static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) +{ + struct kvmppc_spapr_tce_table *stt = filp->private_data; + + release_spapr_tce_table(stt); + return 0; +} + +static struct file_operations kvm_spapr_tce_fops = { + .mmap = kvm_spapr_tce_mmap, + .release = kvm_spapr_tce_release, +}; + +long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, + struct kvm_create_spapr_tce *args) +{ + struct kvmppc_spapr_tce_table *stt = NULL; + long npages; + int ret = -ENOMEM; + int i; + + /* Check this LIOBN hasn't been previously allocated */ + list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { + if (stt->liobn == args->liobn) + return -EBUSY; + } + + npages = kvmppc_stt_npages(args->window_size); + + stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *), + GFP_KERNEL); + if (!stt) + goto fail; + + stt->liobn = args->liobn; + stt->window_size = args->window_size; + stt->kvm = kvm; + + for (i = 0; i < npages; i++) { + stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!stt->pages[i]) + goto fail; + } + + kvm_get_kvm(kvm); + + mutex_lock(&kvm->lock); + list_add(&stt->list, &kvm->arch.spapr_tce_tables); + + mutex_unlock(&kvm->lock); + + return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, + stt, O_RDONLY); + +fail: + if (stt) { + for (i = 0; i < npages; i++) + if (stt->pages[i]) + __free_page(stt->pages[i]); + + kfree(stt); + } + return ret; +} + int kvmppc_core_prepare_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem) { @@ -527,13 +637,17 @@ int kvmppc_core_init_vm(struct kvm *kvm) /* Allocate hashed page table */ r = kvmppc_alloc_hpt(kvm); + if (r) + return r; - return r; + INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + return 0; } void kvmppc_core_destroy_vm(struct kvm *kvm) { kvmppc_free_hpt(kvm); + WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables)); } /* These are stubs for now */ diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index e8a8f3c..95f6386 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -722,7 +722,7 @@ hcall_real_table: .long 0 /* 0x14 - H_CLEAR_REF */ .long .kvmppc_h_protect - hcall_real_table .long 0 /* 0x1c - H_GET_TCE */ - .long 0 /* 0x20 - H_SET_TCE */ + .long .kvmppc_h_put_tce - hcall_real_table .long 0 /* 0x24 - H_SET_SPRG0 */ .long .kvmppc_h_set_dabr - hcall_real_table .long 0 /* 0x2c */ diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 7bfe413..10f777a 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -196,6 +196,11 @@ int kvm_dev_ioctl_check_extension(long ext) r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; #endif +#ifdef CONFIG_KVM_BOOK3S_64_HV + case KVM_CAP_SPAPR_TCE: + r = 1; + break; +#endif default: r = 0; break; @@ -628,6 +633,19 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } +#ifdef CONFIG_KVM_BOOK3S_64_HV + case KVM_CREATE_SPAPR_TCE: { + struct kvm_create_spapr_tce create_tce; + struct kvm *kvm = filp->private_data; + + r = -EFAULT; + if (copy_from_user(&create_tce, argp, sizeof(create_tce))) + goto out; + r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce); + goto out; + } +#endif /* CONFIG_KVM_BOOK3S_64_HV */ + default: r = -ENOTTY; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index a4447ce..3d3cdf1 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -547,6 +547,9 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_GET_PVINFO 57 #define KVM_CAP_PPC_IRQ_LEVEL 58 #define KVM_CAP_ASYNC_PF 59 +#ifdef __KVM_HAVE_SPAPR_TCE +#define KVM_CAP_SPAPR_TCE 60 +#endif #ifdef KVM_CAP_IRQ_ROUTING @@ -746,6 +749,8 @@ struct kvm_clock_data { /* Available with KVM_CAP_XCRS */ #define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) #define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) +/* Available with KVM_CAP_SPAPR_TCE */ +#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)