diff options
Diffstat (limited to 'arch/x86/xen')
-rw-r--r-- | arch/x86/xen/Kconfig | 11 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 1 | ||||
-rw-r--r-- | arch/x86/xen/mmu.c | 52 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 128 | ||||
-rw-r--r-- | arch/x86/xen/setup.c | 284 |
5 files changed, 234 insertions, 242 deletions
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 5cc821cb2e09..26c731a106af 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -25,8 +25,7 @@ config XEN_PRIVILEGED_GUEST config XEN_PVHVM def_bool y - depends on XEN - depends on X86_LOCAL_APIC + depends on XEN && PCI && X86_LOCAL_APIC config XEN_MAX_DOMAIN_MEMORY int @@ -49,11 +48,3 @@ config XEN_DEBUG_FS help Enable statistics output and various tuning options in debugfs. Enabling this option may incur a significant performance overhead. - -config XEN_DEBUG - bool "Enable Xen debug checks" - depends on XEN - default n - help - Enable various WARN_ON checks in the Xen MMU code. - Enabling this option WILL incur a significant performance overhead. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2d69617950f7..da8afd576a6b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void) ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ ax = 1; + cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); xsave_mask = diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3dd53f997b11..87f6673b1207 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -495,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); -#ifdef CONFIG_XEN_DEBUG -pte_t xen_make_pte_debug(pteval_t pte) -{ - phys_addr_t addr = (pte & PTE_PFN_MASK); - phys_addr_t other_addr; - bool io_page = false; - pte_t _pte; - - if (pte & _PAGE_IOMAP) - io_page = true; - - _pte = xen_make_pte(pte); - - if (!addr) - return _pte; - - if (io_page && - (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { - other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; - WARN_ONCE(addr != other_addr, - "0x%lx is using VM_IO, but it is 0x%lx!\n", - (unsigned long)addr, (unsigned long)other_addr); - } else { - pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; - other_addr = (_pte.pte & PTE_PFN_MASK); - WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), - "0x%lx is missing VM_IO (and wasn't fixed)!\n", - (unsigned long)addr); - } - - return _pte; -} -PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); -#endif - static pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); @@ -1992,9 +1957,6 @@ void __init xen_ident_map_ISA(void) static void __init xen_post_allocator_init(void) { -#ifdef CONFIG_XEN_DEBUG - pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug); -#endif pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2404,17 +2366,3 @@ out: return err; } EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); - -#ifdef CONFIG_XEN_DEBUG_FS -static int p2m_dump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, p2m_dump_show, NULL); -} - -static const struct file_operations p2m_dump_fops = { - .open = p2m_dump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58efeb9d5440..1b267e75158d 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -161,7 +161,9 @@ #include <asm/xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/grant_table.h> +#include "multicalls.h" #include "xen-ops.h" static void __init m2p_override_init(void); @@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn) } /* Add an MFN override for a particular page */ -int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) +int m2p_add_override(unsigned long mfn, struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long pfn; @@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } - - page->private = mfn; + WARN_ON(PagePrivate(page)); + SetPagePrivate(page); + set_page_private(page, mfn); page->index = pfn_to_mfn(pfn); if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) return -ENOMEM; - if (clear_pte && !PageHighMem(page)) - /* Just zap old mapping for now */ - pte_clear(&init_mm, address, ptep); + if (kmap_op != NULL) { + if (!PageHighMem(page)) { + struct multicall_space mcs = + xen_mc_entry(sizeof(*kmap_op)); + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_map_grant_ref, kmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + } + /* let's use dev_bus_addr to record the old mfn instead */ + kmap_op->dev_bus_addr = page->index; + page->index = (unsigned long) kmap_op; + } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); @@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte) spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); - set_phys_to_machine(pfn, page->index); + WARN_ON(!PagePrivate(page)); + ClearPagePrivate(page); - if (clear_pte && !PageHighMem(page)) - set_pte_at(&init_mm, address, ptep, - pfn_pte(pfn, PAGE_KERNEL)); - /* No tlb flush necessary because the caller already - * left the pte unmapped. */ + if (clear_pte) { + struct gnttab_map_grant_ref *map_op = + (struct gnttab_map_grant_ref *) page->index; + set_phys_to_machine(pfn, map_op->dev_bus_addr); + if (!PageHighMem(page)) { + struct multicall_space mcs; + struct gnttab_unmap_grant_ref *unmap_op; + + /* + * It might be that we queued all the m2p grant table + * hypercalls in a multicall, then m2p_remove_override + * get called before the multicall has actually been + * issued. In this case handle is going to -1 because + * it hasn't been modified yet. + */ + if (map_op->handle == -1) + xen_mc_flush(); + /* + * Now if map_op->handle is negative it means that the + * hypercall actually returned an error. + */ + if (map_op->handle == GNTST_general_error) { + printk(KERN_WARNING "m2p_remove_override: " + "pfn %lx mfn %lx, failed to modify kernel mappings", + pfn, mfn); + return -1; + } + + mcs = xen_mc_entry( + sizeof(struct gnttab_unmap_grant_ref)); + unmap_op = mcs.args; + unmap_op->host_addr = map_op->host_addr; + unmap_op->handle = map_op->handle; + unmap_op->dev_bus_addr = 0; + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_unmap_grant_ref, unmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + + set_pte_at(&init_mm, address, ptep, + pfn_pte(pfn, PAGE_KERNEL)); + __flush_tlb_single(address); + map_op->host_addr = 0; + } + } else + set_phys_to_machine(pfn, page->index); return 0; } @@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn) spin_lock_irqsave(&m2p_override_lock, flags); list_for_each_entry(p, bucket, lru) { - if (p->private == mfn) { + if (page_private(p) == mfn) { ret = p; break; } @@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) EXPORT_SYMBOL_GPL(m2p_find_override_pfn); #ifdef CONFIG_XEN_DEBUG_FS - -int p2m_dump_show(struct seq_file *m, void *v) +#include <linux/debugfs.h> +#include "debugfs.h" +static int p2m_dump_show(struct seq_file *m, void *v) { static const char * const level_name[] = { "top", "middle", - "entry", "abnormal" }; - static const char * const type_name[] = { "identity", "missing", - "pfn", "abnormal"}; + "entry", "abnormal", "error"}; #define TYPE_IDENTITY 0 #define TYPE_MISSING 1 #define TYPE_PFN 2 #define TYPE_UNKNOWN 3 + static const char * const type_name[] = { + [TYPE_IDENTITY] = "identity", + [TYPE_MISSING] = "missing", + [TYPE_PFN] = "pfn", + [TYPE_UNKNOWN] = "abnormal"}; unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; unsigned int uninitialized_var(prev_level); unsigned int uninitialized_var(prev_type); @@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v) #undef TYPE_PFN #undef TYPE_UNKNOWN } -#endif + +static int p2m_dump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, p2m_dump_show, NULL); +} + +static const struct file_operations p2m_dump_fops = { + .open = p2m_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *d_mmu_debug; + +static int __init xen_p2m_debugfs(void) +{ + struct dentry *d_xen = xen_init_debugfs(); + + if (d_xen == NULL) + return -ENOMEM; + + d_mmu_debug = debugfs_create_dir("mmu", d_xen); + + debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); + return 0; +} +fs_initcall(xen_p2m_debugfs); +#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 46d6d21dbdbe..38d0af4fefec 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -37,7 +37,10 @@ extern void xen_syscall_target(void); extern void xen_syscall32_target(void); /* Amount of extra memory space we add to the e820 ranges */ -phys_addr_t xen_extra_mem_start, xen_extra_mem_size; +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +/* Number of pages released from the initial allocation. */ +unsigned long xen_released_pages; /* * The maximum amount of extra memory compared to the base size. The @@ -51,48 +54,47 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(unsigned long pages) +static void __init xen_add_extra_mem(u64 start, u64 size) { unsigned long pfn; + int i; - u64 size = (u64)pages * PAGE_SIZE; - u64 extra_start = xen_extra_mem_start + xen_extra_mem_size; - - if (!pages) - return; - - e820_add_region(extra_start, size, E820_RAM); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - - memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA"); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].size == 0) { + xen_extra_mem[i].start = start; + xen_extra_mem[i].size = size; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) { + xen_extra_mem[i].size += size; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - xen_extra_mem_size += size; + memblock_x86_reserve_range(start, start + size, "XEN EXTRA"); - xen_max_p2m_pfn = PFN_DOWN(extra_start + size); + xen_max_p2m_pfn = PFN_DOWN(start + size); - for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++) + for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } -static unsigned long __init xen_release_chunk(phys_addr_t start_addr, - phys_addr_t end_addr) +static unsigned long __init xen_release_chunk(unsigned long start, + unsigned long end) { struct xen_memory_reservation reservation = { .address_bits = 0, .extent_order = 0, .domid = DOMID_SELF }; - unsigned long start, end; unsigned long len = 0; unsigned long pfn; int ret; - start = PFN_UP(start_addr); - end = PFN_DOWN(end_addr); - - if (end <= start) - return 0; - for(pfn = start; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -117,72 +119,52 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr, return len; } -static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, - const struct e820map *e820) +static unsigned long __init xen_set_identity_and_release( + const struct e820entry *list, size_t map_size, unsigned long nr_pages) { - phys_addr_t max_addr = PFN_PHYS(max_pfn); - phys_addr_t last_end = ISA_END_ADDRESS; + phys_addr_t start = 0; unsigned long released = 0; - int i; - - /* Free any unused memory above the low 1Mbyte. */ - for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { - phys_addr_t end = e820->map[i].addr; - end = min(max_addr, end); - - if (last_end < end) - released += xen_release_chunk(last_end, end); - last_end = max(last_end, e820->map[i].addr + e820->map[i].size); - } - - if (last_end < max_addr) - released += xen_release_chunk(last_end, max_addr); - - printk(KERN_INFO "released %lu pages of unused memory\n", released); - return released; -} - -static unsigned long __init xen_set_identity(const struct e820entry *list, - ssize_t map_size) -{ - phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS; - phys_addr_t start_pci = last; - const struct e820entry *entry; unsigned long identity = 0; + const struct e820entry *entry; int i; + /* + * Combine non-RAM regions and gaps until a RAM region (or the + * end of the map) is reached, then set the 1:1 map and + * release the pages (if available) in those non-RAM regions. + * + * The combined non-RAM regions are rounded to a whole number + * of pages so any partial pages are accessible via the 1:1 + * mapping. This is needed for some BIOSes that put (for + * example) the DMI tables in a reserved region that begins on + * a non-page boundary. + */ for (i = 0, entry = list; i < map_size; i++, entry++) { - phys_addr_t start = entry->addr; - phys_addr_t end = start + entry->size; + phys_addr_t end = entry->addr + entry->size; - if (start < last) - start = last; + if (entry->type == E820_RAM || i == map_size - 1) { + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); - if (end <= start) - continue; + if (entry->type == E820_RAM) + end_pfn = PFN_UP(entry->addr); - /* Skip over the 1MB region. */ - if (last > end) - continue; + if (start_pfn < end_pfn) { + if (start_pfn < nr_pages) + released += xen_release_chunk( + start_pfn, min(end_pfn, nr_pages)); - if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) { - if (start > start_pci) identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(start)); - - /* Without saving 'last' we would gooble RAM too - * at the end of the loop. */ - last = end; - start_pci = end; - continue; + start_pfn, end_pfn); + } + start = end; } - start_pci = min(start, start_pci); - last = end; } - if (last > start_pci) - identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(last)); - return identity; + + printk(KERN_INFO "Released %lu pages of unused memory\n", released); + printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity); + + return released; } static unsigned long __init xen_get_max_pages(void) @@ -197,21 +179,32 @@ static unsigned long __init xen_get_max_pages(void) return min(max_pages, MAX_DOMAIN_PAGES); } +static void xen_align_and_add_e820_region(u64 start, u64 size, int type) +{ + u64 end = start + size; + + /* Align RAM regions to page boundaries. */ + if (type == E820_RAM) { + start = PAGE_ALIGN(start); + end &= ~((u64)PAGE_SIZE - 1); + } + + e820_add_region(start, end - start, type); +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { static struct e820entry map[E820MAX] __initdata; - static struct e820entry map_raw[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; unsigned long long mem_end; int rc; struct xen_memory_map memmap; + unsigned long max_pages; unsigned long extra_pages = 0; - unsigned long extra_limit; - unsigned long identity_pages = 0; int i; int op; @@ -237,58 +230,65 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); - memcpy(map_raw, map, sizeof(map)); - e820.nr_map = 0; - xen_extra_mem_start = mem_end; - for (i = 0; i < memmap.nr_entries; i++) { - unsigned long long end; - - /* Guard against non-page aligned E820 entries. */ - if (map[i].type == E820_RAM) - map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE; - - end = map[i].addr + map[i].size; - if (map[i].type == E820_RAM && end > mem_end) { - /* RAM off the end - may be partially included */ - u64 delta = min(map[i].size, end - mem_end); - - map[i].size -= delta; - end -= delta; - - extra_pages += PFN_DOWN(delta); - /* - * Set RAM below 4GB that is not for us to be unusable. - * This prevents "System RAM" address space from being - * used as potential resource for I/O address (happens - * when 'allocate_resource' is called). - */ - if (delta && - (xen_initial_domain() && end < 0x100000000ULL)) - e820_add_region(end, delta, E820_UNUSABLE); + /* Make sure the Xen-supplied memory map is well-ordered. */ + sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); + + max_pages = xen_get_max_pages(); + if (max_pages > max_pfn) + extra_pages += max_pages - max_pfn; + + /* + * Set P2M for all non-RAM pages and E820 gaps to be identity + * type PFNs. Any RAM pages that would be made inaccesible by + * this are first released. + */ + xen_released_pages = xen_set_identity_and_release( + map, memmap.nr_entries, max_pfn); + extra_pages += xen_released_pages; + + /* + * Clamp the amount of extra memory to a EXTRA_MEM_RATIO + * factor the base size. On non-highmem systems, the base + * size is the full initial memory allocation; on highmem it + * is limited to the max size of lowmem, so that it doesn't + * get completely filled. + * + * In principle there could be a problem in lowmem systems if + * the initial memory is also very large with respect to + * lowmem, but we won't try to deal with that here. + */ + extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages); + + i = 0; + while (i < memmap.nr_entries) { + u64 addr = map[i].addr; + u64 size = map[i].size; + u32 type = map[i].type; + + if (type == E820_RAM) { + if (addr < mem_end) { + size = min(size, mem_end - addr); + } else if (extra_pages) { + size = min(size, (u64)extra_pages * PAGE_SIZE); + extra_pages -= size / PAGE_SIZE; + xen_add_extra_mem(addr, size); + } else + type = E820_UNUSABLE; } - if (map[i].size > 0 && end > xen_extra_mem_start) - xen_extra_mem_start = end; + xen_align_and_add_e820_region(addr, size, type); - /* Add region if any remains */ - if (map[i].size > 0) - e820_add_region(map[i].addr, map[i].size, map[i].type); + map[i].addr += size; + map[i].size -= size; + if (map[i].size == 0) + i++; } - /* Align the balloon area so that max_low_pfn does not get set - * to be at the _end_ of the PCI gap at the far end (fee01000). - * Note that xen_extra_mem_start gets set in the loop above to be - * past the last E820 region. */ - if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) - xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we * reserve ISA memory anyway because too many things poke * about in there. - * - * In Dom0, the host E820 information can leave gaps in the - * ISA range, which would cause us to release those pages. To - * avoid this, we unconditionally reserve them here. */ e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); @@ -305,44 +305,6 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - extra_limit = xen_get_max_pages(); - if (max_pfn + extra_pages > extra_limit) { - if (extra_limit > max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - } - - extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820); - - /* - * Clamp the amount of extra memory to a EXTRA_MEM_RATIO - * factor the base size. On non-highmem systems, the base - * size is the full initial memory allocation; on highmem it - * is limited to the max size of lowmem, so that it doesn't - * get completely filled. - * - * In principle there could be a problem in lowmem systems if - * the initial memory is also very large with respect to - * lowmem, but we won't try to deal with that here. - */ - extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - max_pfn + extra_pages); - - if (extra_limit >= max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - - xen_add_extra_mem(extra_pages); - - /* - * Set P2M for all non-RAM pages and E820 gaps to be identity - * type PFNs. We supply it with the non-sanitized version - * of the E820. - */ - identity_pages = xen_set_identity(map_raw, memmap.nr_entries); - printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages); return "Xen"; } |