From 5ebc77de83c7b74543de774afa7395b3b790e65e Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Wed, 10 Sep 2014 22:49:30 +0000 Subject: xen/arm: introduce XENFEAT_grant_map_identity The flag tells us that the hypervisor maps a grant page to guest physical address == machine address of the page in addition to the normal grant mapping address. It is needed to properly issue cache maintenance operation at the completion of a DMA operation involving a foreign grant. Signed-off-by: Stefano Stabellini Tested-by: Denis Schneider --- arch/arm/xen/enlighten.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/arm') diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 98544c5f86e9..0e15f011f9c8 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -260,6 +260,12 @@ static int __init xen_guest_init(void) xen_domain_type = XEN_HVM_DOMAIN; xen_setup_features(); + + if (!xen_feature(XENFEAT_grant_map_identity)) { + pr_warn("Please upgrade your Xen.\n" + "If your platform has any non-coherent DMA devices, they won't work properly.\n"); + } + if (xen_feature(XENFEAT_dom0)) xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; else -- cgit v1.2.3 From 340720be32d458ee11d1117719a8e4b6b82981b2 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Wed, 10 Sep 2014 22:49:41 +0000 Subject: xen/arm: reimplement xen_dma_unmap_page & friends xen_dma_unmap_page, xen_dma_sync_single_for_cpu and xen_dma_sync_single_for_device are currently implemented by calling into the corresponding generic ARM implementation of these functions. In order to do this, firstly the dma_addr_t handle, that on Xen is a machine address, needs to be translated into a physical address. The operation is expensive and inaccurate, given that a single machine address can correspond to multiple physical addresses in one domain, because the same page can be granted multiple times by the frontend. To avoid this problem, we introduce a Xen specific implementation of xen_dma_unmap_page, xen_dma_sync_single_for_cpu and xen_dma_sync_single_for_device, that can operate on machine addresses directly. The new implementation relies on the fact that the hypervisor creates a second p2m mapping of any grant pages at physical address == machine address of the page for dom0. Therefore we can access memory at physical address == dma_addr_r handle and perform the cache flushing there. Some cache maintenance operations require a virtual address. Instead of using ioremap_cache, that is not safe in interrupt context, we allocate a per-cpu PAGE_KERNEL scratch page and we manually update the pte for it. arm64 doesn't need cache maintenance operations on unmap for now. Signed-off-by: Stefano Stabellini Tested-by: Denis Schneider --- arch/arm/include/asm/xen/page-coherent.h | 25 ++-- arch/arm/xen/Makefile | 2 +- arch/arm/xen/mm32.c | 202 +++++++++++++++++++++++++++++++ 3 files changed, 210 insertions(+), 19 deletions(-) create mode 100644 arch/arm/xen/mm32.c (limited to 'arch/arm') diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 1109017499e5..e8275ea88e88 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -26,25 +26,14 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs); } -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, +void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - if (__generic_dma_ops(hwdev)->unmap_page) - __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); -} + struct dma_attrs *attrs); -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - if (__generic_dma_ops(hwdev)->sync_single_for_cpu) - __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); -} +void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir); + +void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir); -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - if (__generic_dma_ops(hwdev)->sync_single_for_device) - __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); -} #endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile index 12969523414c..1f85bfe6b470 100644 --- a/arch/arm/xen/Makefile +++ b/arch/arm/xen/Makefile @@ -1 +1 @@ -obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o +obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o mm32.o diff --git a/arch/arm/xen/mm32.c b/arch/arm/xen/mm32.c new file mode 100644 index 000000000000..3b99860fd7ae --- /dev/null +++ b/arch/arm/xen/mm32.c @@ -0,0 +1,202 @@ +#include +#include +#include +#include + +#include + +static DEFINE_PER_CPU(unsigned long, xen_mm32_scratch_virt); +static DEFINE_PER_CPU(pte_t *, xen_mm32_scratch_ptep); + +static int alloc_xen_mm32_scratch_page(int cpu) +{ + struct page *page; + unsigned long virt; + pmd_t *pmdp; + pte_t *ptep; + + if (per_cpu(xen_mm32_scratch_ptep, cpu) != NULL) + return 0; + + page = alloc_page(GFP_KERNEL); + if (page == NULL) { + pr_warn("Failed to allocate xen_mm32_scratch_page for cpu %d\n", cpu); + return -ENOMEM; + } + + virt = (unsigned long)__va(page_to_phys(page)); + pmdp = pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt); + ptep = pte_offset_kernel(pmdp, virt); + + per_cpu(xen_mm32_scratch_virt, cpu) = virt; + per_cpu(xen_mm32_scratch_ptep, cpu) = ptep; + + return 0; +} + +static int xen_mm32_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + switch (action) { + case CPU_UP_PREPARE: + if (alloc_xen_mm32_scratch_page(cpu)) + return NOTIFY_BAD; + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block xen_mm32_cpu_notifier = { + .notifier_call = xen_mm32_cpu_notify, +}; + +static void* xen_mm32_remap_page(dma_addr_t handle) +{ + unsigned long virt = get_cpu_var(xen_mm32_scratch_virt); + pte_t *ptep = __get_cpu_var(xen_mm32_scratch_ptep); + + *ptep = pfn_pte(handle >> PAGE_SHIFT, PAGE_KERNEL); + local_flush_tlb_kernel_page(virt); + + return (void*)virt; +} + +static void xen_mm32_unmap(void *vaddr) +{ + put_cpu_var(xen_mm32_scratch_virt); +} + + +/* functions called by SWIOTLB */ + +static void dma_cache_maint(dma_addr_t handle, unsigned long offset, + size_t size, enum dma_data_direction dir, + void (*op)(const void *, size_t, int)) +{ + unsigned long pfn; + size_t left = size; + + pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE; + offset %= PAGE_SIZE; + + do { + size_t len = left; + void *vaddr; + + if (!pfn_valid(pfn)) + { + /* Cannot map the page, we don't know its physical address. + * Return and hope for the best */ + if (!xen_feature(XENFEAT_grant_map_identity)) + return; + vaddr = xen_mm32_remap_page(handle) + offset; + op(vaddr, len, dir); + xen_mm32_unmap(vaddr - offset); + } else { + struct page *page = pfn_to_page(pfn); + + if (PageHighMem(page)) { + if (len + offset > PAGE_SIZE) + len = PAGE_SIZE - offset; + + if (cache_is_vipt_nonaliasing()) { + vaddr = kmap_atomic(page); + op(vaddr + offset, len, dir); + kunmap_atomic(vaddr); + } else { + vaddr = kmap_high_get(page); + if (vaddr) { + op(vaddr + offset, len, dir); + kunmap_high(page); + } + } + } else { + vaddr = page_address(page) + offset; + op(vaddr, len, dir); + } + } + + offset = 0; + pfn++; + left -= len; + } while (left); +} + +static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + /* Cannot use __dma_page_dev_to_cpu because we don't have a + * struct page for handle */ + + if (dir != DMA_TO_DEVICE) + outer_inv_range(handle, handle + size); + + dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_unmap_area); +} + +static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + + dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, dmac_map_area); + + if (dir == DMA_FROM_DEVICE) { + outer_inv_range(handle, handle + size); + } else { + outer_clean_range(handle, handle + size); + } +} + +void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) + +{ + if (!__generic_dma_ops(hwdev)->unmap_page) + return; + if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + return; + + __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir); +} + +void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (!__generic_dma_ops(hwdev)->sync_single_for_cpu) + return; + __xen_dma_page_dev_to_cpu(hwdev, handle, size, dir); +} + +void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + if (!__generic_dma_ops(hwdev)->sync_single_for_device) + return; + __xen_dma_page_cpu_to_dev(hwdev, handle, size, dir); +} + +int __init xen_mm32_init(void) +{ + int cpu; + + if (!xen_initial_domain()) + return 0; + + register_cpu_notifier(&xen_mm32_cpu_notifier); + get_online_cpus(); + for_each_online_cpu(cpu) { + if (alloc_xen_mm32_scratch_page(cpu)) { + put_online_cpus(); + unregister_cpu_notifier(&xen_mm32_cpu_notifier); + return -ENOMEM; + } + } + put_online_cpus(); + + return 0; +} +arch_initcall(xen_mm32_init); -- cgit v1.2.3 From d50582e06fd5a58281151e097ff68b02ca65cf2d Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Wed, 10 Sep 2014 22:49:48 +0000 Subject: xen/arm: remove mach_to_phys rbtree Remove the rbtree used to keep track of machine to physical mappings: the frontend can grant the same page multiple times, leading to errors inserting or removing entries from the mach_to_phys tree. Linux only needed to know the physical address corresponding to a given machine address in swiotlb-xen. Now that swiotlb-xen can call the xen_dma_* functions passing the machine address directly, we can remove it. Signed-off-by: Stefano Stabellini Tested-by: Denis Schneider --- arch/arm/include/asm/xen/page.h | 9 ------ arch/arm/xen/p2m.c | 66 +---------------------------------------- 2 files changed, 1 insertion(+), 74 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index ded062f9b358..135c24a5ba26 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -33,7 +33,6 @@ typedef struct xpaddr { #define INVALID_P2M_ENTRY (~0UL) unsigned long __pfn_to_mfn(unsigned long pfn); -unsigned long __mfn_to_pfn(unsigned long mfn); extern struct rb_root phys_to_mach; static inline unsigned long pfn_to_mfn(unsigned long pfn) @@ -51,14 +50,6 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn) static inline unsigned long mfn_to_pfn(unsigned long mfn) { - unsigned long pfn; - - if (phys_to_mach.rb_node != NULL) { - pfn = __mfn_to_pfn(mfn); - if (pfn != INVALID_P2M_ENTRY) - return pfn; - } - return mfn; } diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 97baf4427817..054857776254 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -21,14 +21,12 @@ struct xen_p2m_entry { unsigned long pfn; unsigned long mfn; unsigned long nr_pages; - struct rb_node rbnode_mach; struct rb_node rbnode_phys; }; static rwlock_t p2m_lock; struct rb_root phys_to_mach = RB_ROOT; EXPORT_SYMBOL_GPL(phys_to_mach); -static struct rb_root mach_to_phys = RB_ROOT; static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new) { @@ -41,8 +39,6 @@ static int xen_add_phys_to_mach_entry(struct xen_p2m_entry *new) parent = *link; entry = rb_entry(parent, struct xen_p2m_entry, rbnode_phys); - if (new->mfn == entry->mfn) - goto err_out; if (new->pfn == entry->pfn) goto err_out; @@ -88,64 +84,6 @@ unsigned long __pfn_to_mfn(unsigned long pfn) } EXPORT_SYMBOL_GPL(__pfn_to_mfn); -static int xen_add_mach_to_phys_entry(struct xen_p2m_entry *new) -{ - struct rb_node **link = &mach_to_phys.rb_node; - struct rb_node *parent = NULL; - struct xen_p2m_entry *entry; - int rc = 0; - - while (*link) { - parent = *link; - entry = rb_entry(parent, struct xen_p2m_entry, rbnode_mach); - - if (new->mfn == entry->mfn) - goto err_out; - if (new->pfn == entry->pfn) - goto err_out; - - if (new->mfn < entry->mfn) - link = &(*link)->rb_left; - else - link = &(*link)->rb_right; - } - rb_link_node(&new->rbnode_mach, parent, link); - rb_insert_color(&new->rbnode_mach, &mach_to_phys); - goto out; - -err_out: - rc = -EINVAL; - pr_warn("%s: cannot add pfn=%pa -> mfn=%pa: pfn=%pa -> mfn=%pa already exists\n", - __func__, &new->pfn, &new->mfn, &entry->pfn, &entry->mfn); -out: - return rc; -} - -unsigned long __mfn_to_pfn(unsigned long mfn) -{ - struct rb_node *n = mach_to_phys.rb_node; - struct xen_p2m_entry *entry; - unsigned long irqflags; - - read_lock_irqsave(&p2m_lock, irqflags); - while (n) { - entry = rb_entry(n, struct xen_p2m_entry, rbnode_mach); - if (entry->mfn <= mfn && - entry->mfn + entry->nr_pages > mfn) { - read_unlock_irqrestore(&p2m_lock, irqflags); - return entry->pfn + (mfn - entry->mfn); - } - if (mfn < entry->mfn) - n = n->rb_left; - else - n = n->rb_right; - } - read_unlock_irqrestore(&p2m_lock, irqflags); - - return INVALID_P2M_ENTRY; -} -EXPORT_SYMBOL_GPL(__mfn_to_pfn); - int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, struct page **pages, unsigned int count) @@ -192,7 +130,6 @@ bool __set_phys_to_machine_multi(unsigned long pfn, p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); if (p2m_entry->pfn <= pfn && p2m_entry->pfn + p2m_entry->nr_pages > pfn) { - rb_erase(&p2m_entry->rbnode_mach, &mach_to_phys); rb_erase(&p2m_entry->rbnode_phys, &phys_to_mach); write_unlock_irqrestore(&p2m_lock, irqflags); kfree(p2m_entry); @@ -217,8 +154,7 @@ bool __set_phys_to_machine_multi(unsigned long pfn, p2m_entry->mfn = mfn; write_lock_irqsave(&p2m_lock, irqflags); - if ((rc = xen_add_phys_to_mach_entry(p2m_entry) < 0) || - (rc = xen_add_mach_to_phys_entry(p2m_entry) < 0)) { + if ((rc = xen_add_phys_to_mach_entry(p2m_entry)) < 0) { write_unlock_irqrestore(&p2m_lock, irqflags); return false; } -- cgit v1.2.3