diff options
41 files changed, 1365 insertions, 647 deletions
diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h index 04ff8e7b37df..95251512e2c4 100644 --- a/arch/arm/include/asm/xen/hypervisor.h +++ b/arch/arm/include/asm/xen/hypervisor.h @@ -26,4 +26,14 @@ void __init xen_early_init(void); static inline void xen_early_init(void) { return; } #endif +#ifdef CONFIG_HOTPLUG_CPU +static inline void xen_arch_register_cpu(int num) +{ +} + +static inline void xen_arch_unregister_cpu(int num) +{ +} +#endif + #endif /* _ASM_ARM_XEN_HYPERVISOR_H */ diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index efd562412850..0375c8caa061 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,11 +35,15 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = PFN_DOWN(dev_addr) == page_to_pfn(page); - /* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise - * is a foreign page grant-mapped in dom0. If the page is local we - * can safely call the native dma_ops function, otherwise we call - * the xen specific function. */ + bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + /* + * Dom0 is mapped 1:1, while the Linux page can be spanned accross + * multiple Xen page, it's not possible to have a mix of local and + * foreign Xen page. So if the first xen_pfn == mfn the page is local + * otherwise it's a foreign page grant-mapped in dom0. If the page is + * local we can safely call the native dma_ops function, otherwise we + * call the xen specific function. + */ if (local) __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); else @@ -51,10 +55,14 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, struct dma_attrs *attrs) { unsigned long pfn = PFN_DOWN(handle); - /* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will - * always return false. If the page is local we can safely call the - * native dma_ops function, otherwise we call the xen specific - * function. */ + /* + * Dom0 is mapped 1:1, while the Linux page can be spanned accross + * multiple Xen page, it's not possible to have a mix of local and + * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a + * foreign mfn will always return false. If the page is local we can + * safely call the native dma_ops function, otherwise we call the xen + * specific function. + */ if (pfn_valid(pfn)) { if (__generic_dma_ops(hwdev)->unmap_page) __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 127956353b00..415dbc6e43fd 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -13,9 +13,6 @@ #define phys_to_machine_mapping_valid(pfn) (1) -#define pte_mfn pte_pfn -#define mfn_pte pfn_pte - /* Xen machine address */ typedef struct xmaddr { phys_addr_t maddr; @@ -31,6 +28,17 @@ typedef struct xpaddr { #define INVALID_P2M_ENTRY (~0UL) +/* + * The pseudo-physical frame (pfn) used in all the helpers is always based + * on Xen page granularity (i.e 4KB). + * + * A Linux page may be split across multiple non-contiguous Xen page so we + * have to keep track with frame based on 4KB page granularity. + * + * PV drivers should never make a direct usage of those helpers (particularly + * pfn_to_gfn and gfn_to_pfn). + */ + unsigned long __pfn_to_mfn(unsigned long pfn); extern struct rb_root phys_to_mach; @@ -67,8 +75,8 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) #define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) /* VIRT <-> GUEST conversion */ -#define virt_to_gfn(v) (pfn_to_gfn(virt_to_pfn(v))) -#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << PAGE_SHIFT)) +#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) +#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) /* Only used in PV code. But ARM guests are always HVM. */ static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) @@ -107,8 +115,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) #define xen_unmap(cookie) iounmap((cookie)) bool xen_arch_need_swiotlb(struct device *dev, - unsigned long pfn, - unsigned long bfn); + phys_addr_t phys, + dma_addr_t dev_addr); unsigned long xen_get_swiotlb_free_pages(unsigned int order); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index eeeab074e154..fc7ea529f462 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -86,16 +86,25 @@ static void xen_percpu_init(void) int err; int cpu = get_cpu(); + /* + * VCPUOP_register_vcpu_info cannot be called twice for the same + * vcpu, so if vcpu_info is already registered, just get out. This + * can happen with cpu-hotplug. + */ + if (per_cpu(xen_vcpu, cpu) != NULL) + goto after_register_vcpu_info; + pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); - info.mfn = __pa(vcpup) >> PAGE_SHIFT; - info.offset = offset_in_page(vcpup); + info.mfn = virt_to_gfn(vcpup); + info.offset = xen_offset_in_page(vcpup); err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info); BUG_ON(err); per_cpu(xen_vcpu, cpu) = vcpup; +after_register_vcpu_info: enable_percpu_irq(xen_events_irq, 0); put_cpu(); } @@ -124,6 +133,9 @@ static int xen_cpu_notification(struct notifier_block *self, case CPU_STARTING: xen_percpu_init(); break; + case CPU_DYING: + disable_percpu_irq(xen_events_irq); + break; default: break; } @@ -213,7 +225,7 @@ static int __init xen_guest_init(void) xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + xatp.gpfn = virt_to_gfn(shared_info_page); if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); @@ -284,7 +296,7 @@ void xen_arch_resume(void) { } void xen_arch_suspend(void) { } -/* In the hypervisor.S file. */ +/* In the hypercall.S file. */ EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op); EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op); EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 6dd911d1f0ac..7c34f7126b04 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -48,22 +48,22 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset, size_t size, enum dma_data_direction dir, enum dma_cache_op op) { struct gnttab_cache_flush cflush; - unsigned long pfn; + unsigned long xen_pfn; size_t left = size; - pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE; - offset %= PAGE_SIZE; + xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE; + offset %= XEN_PAGE_SIZE; do { size_t len = left; /* buffers in highmem or foreign pages cannot cross page * boundaries */ - if (len + offset > PAGE_SIZE) - len = PAGE_SIZE - offset; + if (len + offset > XEN_PAGE_SIZE) + len = XEN_PAGE_SIZE - offset; cflush.op = 0; - cflush.a.dev_bus_addr = pfn << PAGE_SHIFT; + cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT; cflush.offset = offset; cflush.length = len; @@ -79,7 +79,7 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset, HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1); offset = 0; - pfn++; + xen_pfn++; left -= len; } while (left); } @@ -138,10 +138,29 @@ void __xen_dma_sync_single_for_device(struct device *hwdev, } bool xen_arch_need_swiotlb(struct device *dev, - unsigned long pfn, - unsigned long bfn) + phys_addr_t phys, + dma_addr_t dev_addr) { - return (!hypercall_cflush && (pfn != bfn) && !is_device_dma_coherent(dev)); + unsigned int xen_pfn = XEN_PFN_DOWN(phys); + unsigned int bfn = XEN_PFN_DOWN(dev_addr); + + /* + * The swiotlb buffer should be used if + * - Xen doesn't have the cache flush hypercall + * - The Linux page refers to foreign memory + * - The device doesn't support coherent DMA request + * + * The Linux page may be spanned acrros multiple Xen page, although + * it's not possible to have a mix of local and foreign Xen page. + * Furthermore, range_straddles_page_boundary is already checking + * if buffer is physically contiguous in the host RAM. + * + * Therefore we only need to check the first Xen page to know if we + * require a bounce buffer because the device doesn't support coherent + * memory and we are not able to flush the cache. + */ + return (!hypercall_cflush && (xen_pfn != bfn) && + !is_device_dma_coherent(dev)); } int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 887596c67b12..0ed01f2d5ee4 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -93,8 +93,8 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, for (i = 0; i < count; i++) { if (map_ops[i].status) continue; - set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, - map_ops[i].dev_bus_addr >> PAGE_SHIFT); + set_phys_to_machine(map_ops[i].host_addr >> XEN_PAGE_SHIFT, + map_ops[i].dev_bus_addr >> XEN_PAGE_SHIFT); } return 0; @@ -108,7 +108,7 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, int i; for (i = 0; i < count; i++) { - set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, + set_phys_to_machine(unmap_ops[i].host_addr >> XEN_PAGE_SHIFT, INVALID_P2M_ENTRY); } diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index d866959e5685..8b2d4bea9962 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -57,4 +57,9 @@ static inline bool xen_x2apic_para_available(void) } #endif +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num); +void xen_arch_unregister_cpu(int num); +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 0679e11d2cf7..f5fb840b43e8 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -12,7 +12,7 @@ #include <asm/pgtable.h> #include <xen/interface/xen.h> -#include <xen/grant_table.h> +#include <xen/interface/grant_table.h> #include <xen/features.h> /* Xen machine address */ @@ -43,6 +43,8 @@ extern unsigned long *xen_p2m_addr; extern unsigned long xen_p2m_size; extern unsigned long xen_max_p2m_pfn; +extern int xen_alloc_p2m_entry(unsigned long pfn); + extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); @@ -296,8 +298,8 @@ void make_lowmem_page_readwrite(void *vaddr); #define xen_unmap(cookie) iounmap((cookie)) static inline bool xen_arch_need_swiotlb(struct device *dev, - unsigned long pfn, - unsigned long bfn) + phys_addr_t phys, + dma_addr_t dev_addr) { return false; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 993b7a71386d..5774800ff583 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -75,6 +75,7 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/pat.h> +#include <asm/cpu.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -1899,3 +1900,17 @@ const struct hypervisor_x86 x86_hyper_xen = { .set_cpu_features = xen_set_cpu_features, }; EXPORT_SYMBOL(x86_hyper_xen); + +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num) +{ + arch_register_cpu(num); +} +EXPORT_SYMBOL(xen_arch_register_cpu); + +void xen_arch_unregister_cpu(int num) +{ + arch_unregister_cpu(num); +} +EXPORT_SYMBOL(xen_arch_unregister_cpu); +#endif diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index 1580e7a5a4cf..e079500b17f3 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -133,7 +133,7 @@ static int __init xlated_setup_gnttab_pages(void) kfree(pages); return -ENOMEM; } - rc = alloc_xenballooned_pages(nr_grant_frames, pages, 0 /* lowmem */); + rc = alloc_xenballooned_pages(nr_grant_frames, pages); if (rc) { pr_warn("%s Couldn't balloon alloc %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 9c479fe40459..ac161db63388 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2888,6 +2888,7 @@ static int do_remap_gfn(struct vm_area_struct *vma, addr += range; if (err_ptr) err_ptr += batch; + cond_resched(); } out: diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 660b3cfef234..cab9f766bb06 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -530,7 +530,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) * the new pages are installed with cmpxchg; if we lose the race then * simply free the page we allocated and use the one that's there. */ -static bool alloc_p2m(unsigned long pfn) +int xen_alloc_p2m_entry(unsigned long pfn) { unsigned topidx; unsigned long *top_mfn_p, *mid_mfn; @@ -540,6 +540,9 @@ static bool alloc_p2m(unsigned long pfn) unsigned long addr = (unsigned long)(xen_p2m_addr + pfn); unsigned long p2m_pfn; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + ptep = lookup_address(addr, &level); BUG_ON(!ptep || level != PG_LEVEL_4K); pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1)); @@ -548,7 +551,7 @@ static bool alloc_p2m(unsigned long pfn) /* PMD level is missing, allocate a new one */ ptep = alloc_p2m_pmd(addr, pte_pg); if (!ptep) - return false; + return -ENOMEM; } if (p2m_top_mfn && pfn < MAX_P2M_PFN) { @@ -566,7 +569,7 @@ static bool alloc_p2m(unsigned long pfn) mid_mfn = alloc_p2m_page(); if (!mid_mfn) - return false; + return -ENOMEM; p2m_mid_mfn_init(mid_mfn, p2m_missing); @@ -592,7 +595,7 @@ static bool alloc_p2m(unsigned long pfn) p2m = alloc_p2m_page(); if (!p2m) - return false; + return -ENOMEM; if (p2m_pfn == PFN_DOWN(__pa(p2m_missing))) p2m_init(p2m); @@ -625,8 +628,9 @@ static bool alloc_p2m(unsigned long pfn) HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; } - return true; + return 0; } +EXPORT_SYMBOL(xen_alloc_p2m_entry); unsigned long __init set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e) @@ -688,7 +692,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!alloc_p2m(pfn)) + int ret; + + ret = xen_alloc_p2m_entry(pfn); + if (ret < 0) return false; return __set_phys_to_machine(pfn, mfn); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 63320b6d35bc..7ab29518a3b9 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -212,7 +212,7 @@ static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn) e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after this */ - if (e_pfn < *min_pfn) + if (e_pfn <= *min_pfn) continue; s_pfn = PFN_UP(entry->addr); @@ -829,6 +829,8 @@ char * __init xen_memory_setup(void) addr = xen_e820_map[0].addr; size = xen_e820_map[0].size; while (i < xen_e820_map_entries) { + bool discard = false; + chunk_size = size; type = xen_e820_map[i].type; @@ -843,10 +845,11 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(pfn_s, n_pfns); xen_max_p2m_pfn = pfn_s + n_pfns; } else - type = E820_UNUSABLE; + discard = true; } - xen_align_and_add_e820_region(addr, chunk_size, type); + if (!discard) + xen_align_and_add_e820_region(addr, chunk_size, type); addr += chunk_size; size -= chunk_size; diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 6a685aec6994..f9099940c272 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(max_persistent_grants, * Maximum order of pages to be used for the shared ring between front and * backend, 4KB page granularity is used. */ -unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER; +unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER; module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO); MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring"); /* @@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, seg[n].nsec = segments[i].last_sect - segments[i].first_sect + 1; seg[n].offset = (segments[i].first_sect << 9); - if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) || + if ((segments[i].last_sect >= (XEN_PAGE_SIZE >> 9)) || (segments[i].last_sect < segments[i].first_sect)) { rc = -EINVAL; goto unmap; @@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, req_operation = req->operation == BLKIF_OP_INDIRECT ? req->u.indirect.indirect_op : req->operation; + if ((req->operation == BLKIF_OP_INDIRECT) && (req_operation != BLKIF_OP_READ) && (req_operation != BLKIF_OP_WRITE)) { @@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, seg[i].nsec = req->u.rw.seg[i].last_sect - req->u.rw.seg[i].first_sect + 1; seg[i].offset = (req->u.rw.seg[i].first_sect << 9); - if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) || + if ((req->u.rw.seg[i].last_sect >= (XEN_PAGE_SIZE >> 9)) || (req->u.rw.seg[i].last_sect < req->u.rw.seg[i].first_sect)) goto fail_response; @@ -1445,10 +1446,10 @@ static int __init xen_blkif_init(void) if (!xen_domain()) return -ENODEV; - if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) { + if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) { pr_info("Invalid max_ring_order (%d), will use default max: %d.\n", - xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER); - xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER; + xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER); + xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER; } rc = xen_blkif_interface_init(); diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 45a044a53d1e..68e87a037b99 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -39,6 +39,7 @@ #include <asm/pgalloc.h> #include <asm/hypervisor.h> #include <xen/grant_table.h> +#include <xen/page.h> #include <xen/xenbus.h> #include <xen/interface/io/ring.h> #include <xen/interface/io/blkif.h> @@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order; */ #define MAX_INDIRECT_SEGMENTS 256 -#define SEGS_PER_INDIRECT_FRAME \ - (PAGE_SIZE/sizeof(struct blkif_request_segment)) +/* + * Xen use 4K pages. The guest may use different page size (4K or 64K) + * Number of Xen pages per segment + */ +#define XEN_PAGES_PER_SEGMENT (PAGE_SIZE / XEN_PAGE_SIZE) + +#define XEN_PAGES_PER_INDIRECT_FRAME \ + (XEN_PAGE_SIZE/sizeof(struct blkif_request_segment)) +#define SEGS_PER_INDIRECT_FRAME \ + (XEN_PAGES_PER_INDIRECT_FRAME / XEN_PAGES_PER_SEGMENT) + #define MAX_INDIRECT_PAGES \ ((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) -#define INDIRECT_PAGES(_segs) \ - ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) +#define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME) /* Not a real protocol. Used to generate ring structs which contain * the elements common to all protocols only. This way we get a diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 767657565de6..f53cff42f8da 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref, { struct blkif_sring *sring; sring = (struct blkif_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE * nr_grefs); + BACK_RING_INIT(&blkif->blk_rings.native, sring, + XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_32: { struct blkif_x86_32_sring *sring_x86_32; sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE * nr_grefs); + BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, + XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_64: { struct blkif_x86_64_sring *sring_x86_64; sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE * nr_grefs); + BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, + XEN_PAGE_SIZE * nr_grefs); break; } default: @@ -826,7 +829,7 @@ again: static int connect_ring(struct backend_info *be) { struct xenbus_device *dev = be->dev; - unsigned int ring_ref[XENBUS_MAX_RING_PAGES]; + unsigned int ring_ref[XENBUS_MAX_RING_GRANTS]; unsigned int evtchn, nr_grefs, ring_page_order; unsigned int pers_grants; char protocol[64] = ""; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a69c02dadec0..2fee2eef988d 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -68,7 +68,7 @@ enum blkif_state { struct grant { grant_ref_t gref; - unsigned long pfn; + struct page *page; struct list_head node; }; @@ -78,6 +78,7 @@ struct blk_shadow { struct grant **grants_used; struct grant **indirect_grants; struct scatterlist *sg; + unsigned int num_sg; }; struct split_bio { @@ -106,8 +107,12 @@ static unsigned int xen_blkif_max_ring_order; module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO); MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring"); -#define BLK_RING_SIZE(info) __CONST_RING_SIZE(blkif, PAGE_SIZE * (info)->nr_ring_pages) -#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE * XENBUS_MAX_RING_PAGES) +#define BLK_RING_SIZE(info) \ + __CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages) + +#define BLK_MAX_RING_SIZE \ + __CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * XENBUS_MAX_RING_GRANTS) + /* * ring-ref%i i=(-1UL) would take 11 characters + 'ring-ref' is 8, so 19 * characters are enough. Define to 20 to keep consist with backend. @@ -128,7 +133,7 @@ struct blkfront_info int vdevice; blkif_vdev_t handle; enum blkif_state connected; - int ring_ref[XENBUS_MAX_RING_PAGES]; + int ring_ref[XENBUS_MAX_RING_GRANTS]; unsigned int nr_ring_pages; struct blkif_front_ring ring; unsigned int evtchn, irq; @@ -146,6 +151,7 @@ struct blkfront_info unsigned int discard_granularity; unsigned int discard_alignment; unsigned int feature_persistent:1; + /* Number of 4KB segments handled */ unsigned int max_indirect_segments; int is_ready; struct blk_mq_tag_set tag_set; @@ -174,10 +180,23 @@ static DEFINE_SPINLOCK(minor_lock); #define DEV_NAME "xvd" /* name in /dev */ -#define SEGS_PER_INDIRECT_FRAME \ - (PAGE_SIZE/sizeof(struct blkif_request_segment)) -#define INDIRECT_GREFS(_segs) \ - ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) +/* + * Grants are always the same size as a Xen page (i.e 4KB). + * A physical segment is always the same size as a Linux page. + * Number of grants per physical segment + */ +#define GRANTS_PER_PSEG (PAGE_SIZE / XEN_PAGE_SIZE) + +#define GRANTS_PER_INDIRECT_FRAME \ + (XEN_PAGE_SIZE / sizeof(struct blkif_request_segment)) + +#define PSEGS_PER_INDIRECT_FRAME \ + (GRANTS_INDIRECT_FRAME / GRANTS_PSEGS) + +#define INDIRECT_GREFS(_grants) \ + DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME) + +#define GREFS(_psegs) ((_psegs) * GRANTS_PER_PSEG) static int blkfront_setup_indirect(struct blkfront_info *info); static int blkfront_gather_backend_features(struct blkfront_info *info); @@ -221,7 +240,7 @@ static int fill_grant_buffer(struct blkfront_info *info, int num) kfree(gnt_list_entry); goto out_of_memory; } - gnt_list_entry->pfn = page_to_pfn(granted_page); + gnt_list_entry->page = granted_page; } gnt_list_entry->gref = GRANT_INVALID_REF; @@ -236,7 +255,7 @@ out_of_memory: &info->grants, node) { list_del(&gnt_list_entry->node); if (info->feature_persistent) - __free_page(pfn_to_page(gnt_list_entry->pfn)); + __free_page(gnt_list_entry->page); kfree(gnt_list_entry); i--; } @@ -244,34 +263,77 @@ out_of_memory: return -ENOMEM; } -static struct grant *get_grant(grant_ref_t *gref_head, - unsigned long pfn, - struct blkfront_info *info) +static struct grant *get_free_grant(struct blkfront_info *info) { struct grant *gnt_list_entry; - unsigned long buffer_gfn; BUG_ON(list_empty(&info->grants)); gn |