diff options
Diffstat (limited to 'arch/x86/xen')
-rw-r--r-- | arch/x86/xen/enlighten.c | 22 | ||||
-rw-r--r-- | arch/x86/xen/mmu.c | 17 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 287 | ||||
-rw-r--r-- | arch/x86/xen/setup.c | 79 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 2 | ||||
-rw-r--r-- | arch/x86/xen/time.c | 22 | ||||
-rw-r--r-- | arch/x86/xen/xen-ops.h | 6 |
7 files changed, 100 insertions, 335 deletions
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 6bf3a13e3e0f..78a881b7fc41 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -40,6 +40,7 @@ #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> #include <xen/interface/memory.h> +#include <xen/interface/nmi.h> #include <xen/interface/xen-mca.h> #include <xen/features.h> #include <xen/page.h> @@ -66,6 +67,7 @@ #include <asm/reboot.h> #include <asm/stackprotector.h> #include <asm/hypervisor.h> +#include <asm/mach_traps.h> #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/pat.h> @@ -1351,6 +1353,21 @@ static const struct machine_ops xen_machine_ops __initconst = { .emergency_restart = xen_emergency_restart, }; +static unsigned char xen_get_nmi_reason(void) +{ + unsigned char reason = 0; + + /* Construct a value which looks like it came from port 0x61. */ + if (test_bit(_XEN_NMIREASON_io_error, + &HYPERVISOR_shared_info->arch.nmi_reason)) + reason |= NMI_REASON_IOCHK; + if (test_bit(_XEN_NMIREASON_pci_serr, + &HYPERVISOR_shared_info->arch.nmi_reason)) + reason |= NMI_REASON_SERR; + + return reason; +} + static void __init xen_boot_params_init_edd(void) { #if IS_ENABLED(CONFIG_EDD) @@ -1535,9 +1552,12 @@ asmlinkage __visible void __init xen_start_kernel(void) pv_info = xen_info; pv_init_ops = xen_init_ops; pv_apic_ops = xen_apic_ops; - if (!xen_pvh_domain()) + if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; + x86_platform.get_nmi_reason = xen_get_nmi_reason; + } + if (xen_feature(XENFEAT_auto_translated_physmap)) x86_init.resources.memory_setup = xen_auto_xlated_memory_setup; else diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5c1f9ace7ae7..adca9e2b6553 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1489,7 +1489,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) { struct mmuext_op op; op.cmd = cmd; @@ -1657,7 +1657,7 @@ void __init xen_reserve_top(void) * Like __va(), but returns address in the kernel mapping (which is * all we have until the physical memory mapping has been set up. */ -static void *__ka(phys_addr_t paddr) +static void * __init __ka(phys_addr_t paddr) { #ifdef CONFIG_X86_64 return (void *)(paddr + __START_KERNEL_map); @@ -1667,7 +1667,7 @@ static void *__ka(phys_addr_t paddr) } /* Convert a machine address to physical address */ -static unsigned long m2p(phys_addr_t maddr) +static unsigned long __init m2p(phys_addr_t maddr) { phys_addr_t paddr; @@ -1678,13 +1678,14 @@ static unsigned long m2p(phys_addr_t maddr) } /* Convert a machine address to kernel virtual */ -static void *m2v(phys_addr_t maddr) +static void * __init m2v(phys_addr_t maddr) { return __ka(m2p(maddr)); } /* Set the page permissions on an identity-mapped pages */ -static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) +static void __init set_page_prot_flags(void *addr, pgprot_t prot, + unsigned long flags) { unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); @@ -1696,7 +1697,7 @@ static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } -static void set_page_prot(void *addr, pgprot_t prot) +static void __init set_page_prot(void *addr, pgprot_t prot) { return set_page_prot_flags(addr, prot, UVMF_NONE); } @@ -1733,10 +1734,8 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; -#ifdef CONFIG_X86_32 if (pfn > max_pfn_mapped) max_pfn_mapped = pfn; -#endif if (!pte_none(pte_page[pteidx])) continue; @@ -1769,7 +1768,7 @@ void __init xen_setup_machphys_mapping(void) } #ifdef CONFIG_X86_64 -static void convert_pfn_mfn(void *v) +static void __init convert_pfn_mfn(void *v) { pte_t *pte = v; int i; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index edbc7a63fd73..f18fd1d411f6 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -84,8 +84,6 @@ #define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE) -static void __init m2p_override_init(void); - unsigned long *xen_p2m_addr __read_mostly; EXPORT_SYMBOL_GPL(xen_p2m_addr); unsigned long xen_p2m_size __read_mostly; @@ -167,10 +165,13 @@ static void * __ref alloc_p2m_page(void) return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); } -/* Only to be called in case of a race for a page just allocated! */ -static void free_p2m_page(void *p) +static void __ref free_p2m_page(void *p) { - BUG_ON(!slab_is_available()); + if (unlikely(!slab_is_available())) { + free_bootmem((unsigned long)p, PAGE_SIZE); + return; + } + free_page((unsigned long)p); } @@ -375,7 +376,7 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m) p2m_missing_pte : p2m_identity_pte; for (i = 0; i < PMDS_PER_MID_PAGE; i++) { pmdp = populate_extra_pmd( - (unsigned long)(p2m + pfn + i * PTRS_PER_PTE)); + (unsigned long)(p2m + pfn) + i * PMD_SIZE); set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE)); } } @@ -399,8 +400,6 @@ void __init xen_vmalloc_p2m_tree(void) xen_p2m_size = xen_max_p2m_pfn; xen_inv_extra_mem(); - - m2p_override_init(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -436,10 +435,9 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine); * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual * pmd. In case of PAE/x86-32 there are multiple pmds to allocate! */ -static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) +static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) { pte_t *ptechk; - pte_t *pteret = ptep; pte_t *pte_newpg[PMDS_PER_MID_PAGE]; pmd_t *pmdp; unsigned int level; @@ -473,8 +471,6 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) if (ptechk == pte_pg) { set_pmd(pmdp, __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE)); - if (vaddr == (addr & ~(PMD_SIZE - 1))) - pteret = pte_offset_kernel(pmdp, addr); pte_newpg[i] = NULL; } @@ -488,7 +484,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg) vaddr += PMD_SIZE; } - return pteret; + return lookup_address(addr, &level); } /* @@ -517,7 +513,7 @@ static bool alloc_p2m(unsigned long pfn) if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) { /* PMD level is missing, allocate a new one */ - ptep = alloc_p2m_pmd(addr, ptep, pte_pg); + ptep = alloc_p2m_pmd(addr, pte_pg); if (!ptep) return false; } @@ -652,100 +648,21 @@ bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } -#define M2P_OVERRIDE_HASH_SHIFT 10 -#define M2P_OVERRIDE_HASH (1 << M2P_OVERRIDE_HASH_SHIFT) - -static struct list_head *m2p_overrides; -static DEFINE_SPINLOCK(m2p_override_lock); - -static void __init m2p_override_init(void) -{ - unsigned i; - - m2p_overrides = alloc_bootmem_align( - sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH, - sizeof(unsigned long)); - - for (i = 0; i < M2P_OVERRIDE_HASH; i++) - INIT_LIST_HEAD(&m2p_overrides[i]); -} - -static unsigned long mfn_hash(unsigned long mfn) -{ - return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT); -} - -/* Add an MFN override for a particular page */ -static int m2p_add_override(unsigned long mfn, struct page *page, - struct gnttab_map_grant_ref *kmap_op) -{ - unsigned long flags; - unsigned long pfn; - unsigned long uninitialized_var(address); - unsigned level; - pte_t *ptep = NULL; - - pfn = page_to_pfn(page); - if (!PageHighMem(page)) { - address = (unsigned long)__va(pfn << PAGE_SHIFT); - ptep = lookup_address(address, &level); - if (WARN(ptep == NULL || level != PG_LEVEL_4K, - "m2p_add_override: pfn %lx not mapped", pfn)) - return -EINVAL; - } - - 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); - } - } - spin_lock_irqsave(&m2p_override_lock, flags); - list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); - spin_unlock_irqrestore(&m2p_override_lock, flags); - - /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in - * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other - * pfn so that the following mfn_to_pfn(mfn) calls will return the - * pfn from the m2p_override (the backend pfn) instead. - * We need to do this because the pages shared by the frontend - * (xen-blkfront) can be already locked (lock_page, called by - * do_read_cache_page); when the userspace backend tries to use them - * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so - * do_blockdev_direct_IO is going to try to lock the same pages - * again resulting in a deadlock. - * As a side effect get_user_pages_fast might not be safe on the - * frontend pages while they are being shared with the backend, - * because mfn_to_pfn (that ends up being called by GUPF) will - * return the backend pfn rather than the frontend pfn. */ - pfn = mfn_to_pfn_no_overrides(mfn); - if (__pfn_to_mfn(pfn) == mfn) - set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); - - return 0; -} - 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) { int i, ret = 0; - bool lazy = false; pte_t *pte; if (xen_feature(XENFEAT_auto_translated_physmap)) return 0; - if (kmap_ops && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; + if (kmap_ops) { + ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, + kmap_ops, count); + if (ret) + goto out; } for (i = 0; i < count; i++) { @@ -764,170 +681,28 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, } pfn = page_to_pfn(pages[i]); - WARN_ON(PagePrivate(pages[i])); - SetPagePrivate(pages[i]); - set_page_private(pages[i], mfn); - pages[i]->index = pfn_to_mfn(pfn); + WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned"); if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { ret = -ENOMEM; goto out; } - - if (kmap_ops) { - ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]); - if (ret) - goto out; - } } out: - if (lazy) - arch_leave_lazy_mmu_mode(); - return ret; } EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping); -static struct page *m2p_find_override(unsigned long mfn) -{ - unsigned long flags; - struct list_head *bucket; - struct page *p, *ret; - - if (unlikely(!m2p_overrides)) - return NULL; - - ret = NULL; - bucket = &m2p_overrides[mfn_hash(mfn)]; - - spin_lock_irqsave(&m2p_override_lock, flags); - - list_for_each_entry(p, bucket, lru) { - if (page_private(p) == mfn) { - ret = p; - break; - } - } - - spin_unlock_irqrestore(&m2p_override_lock, flags); - - return ret; -} - -static int m2p_remove_override(struct page *page, - struct gnttab_map_grant_ref *kmap_op, - unsigned long mfn) -{ - unsigned long flags; - unsigned long pfn; - unsigned long uninitialized_var(address); - unsigned level; - pte_t *ptep = NULL; - - pfn = page_to_pfn(page); - - if (!PageHighMem(page)) { - address = (unsigned long)__va(pfn << PAGE_SHIFT); - ptep = lookup_address(address, &level); - - if (WARN(ptep == NULL || level != PG_LEVEL_4K, - "m2p_remove_override: pfn %lx not mapped", pfn)) - return -EINVAL; - } - - spin_lock_irqsave(&m2p_override_lock, flags); - list_del(&page->lru); - spin_unlock_irqrestore(&m2p_override_lock, flags); - - if (kmap_op != NULL) { - if (!PageHighMem(page)) { - struct multicall_space mcs; - struct gnttab_unmap_and_replace *unmap_op; - struct page *scratch_page = get_balloon_scratch_page(); - unsigned long scratch_page_address = (unsigned long) - __va(page_to_pfn(scratch_page) << PAGE_SHIFT); - - /* - * 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 (kmap_op->handle == -1) - xen_mc_flush(); - /* - * Now if kmap_op->handle is negative it means that the - * hypercall actually returned an error. - */ - if (kmap_op->handle == GNTST_general_error) { - pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings", - pfn, mfn); - put_balloon_scratch_page(); - return -1; - } - - xen_mc_batch(); - - mcs = __xen_mc_entry( - sizeof(struct gnttab_unmap_and_replace)); - unmap_op = mcs.args; - unmap_op->host_addr = kmap_op->host_addr; - unmap_op->new_addr = scratch_page_address; - unmap_op->handle = kmap_op->handle; - - MULTI_grant_table_op(mcs.mc, - GNTTABOP_unmap_and_replace, unmap_op, 1); - - mcs = __xen_mc_entry(0); - MULTI_update_va_mapping(mcs.mc, scratch_page_address, - pfn_pte(page_to_pfn(scratch_page), - PAGE_KERNEL_RO), 0); - - xen_mc_issue(PARAVIRT_LAZY_MMU); - - kmap_op->host_addr = 0; - put_balloon_scratch_page(); - } - } - - /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present - * somewhere in this domain, even before being added to the - * m2p_override (see comment above in m2p_add_override). - * If there are no other entries in the m2p_override corresponding - * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for - * the original pfn (the one shared by the frontend): the backend - * cannot do any IO on this page anymore because it has been - * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of - * the original pfn causes mfn_to_pfn(mfn) to return the frontend - * pfn again. */ - mfn &= ~FOREIGN_FRAME_BIT; - pfn = mfn_to_pfn_no_overrides(mfn); - if (__pfn_to_mfn(pfn) == FOREIGN_FRAME(mfn) && - m2p_find_override(mfn) == NULL) - set_phys_to_machine(pfn, mfn); - - return 0; -} - int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_map_grant_ref *kmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, struct page **pages, unsigned int count) { int i, ret = 0; - bool lazy = false; if (xen_feature(XENFEAT_auto_translated_physmap)) return 0; - if (kmap_ops && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); @@ -937,36 +712,16 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, goto out; } - set_page_private(pages[i], INVALID_P2M_ENTRY); - WARN_ON(!PagePrivate(pages[i])); - ClearPagePrivate(pages[i]); - set_phys_to_machine(pfn, pages[i]->index); - - if (kmap_ops) - ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn); - if (ret) - goto out; + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } - + if (kunmap_ops) + ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, + kunmap_ops, count); out: - if (lazy) - arch_leave_lazy_mmu_mode(); return ret; } EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping); -unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) -{ - struct page *p = m2p_find_override(mfn); - unsigned long ret = pfn; - - if (p) - ret = page_to_pfn(p); - - return ret; -} -EXPORT_SYMBOL_GPL(m2p_find_override_pfn); - #ifdef CONFIG_XEN_DEBUG_FS #include <linux/debugfs.h> #include "debugfs.h" diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index dfd77dec8e2b..55f388ef481a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -32,16 +32,6 @@ #include "p2m.h" #include "mmu.h" -/* These are code, but not functions. Defined in entry.S */ -extern const char xen_hypervisor_callback[]; -extern const char xen_failsafe_callback[]; -#ifdef CONFIG_X86_64 -extern asmlinkage void nmi(void); -#endif -extern void xen_sysenter_target(void); -extern void xen_syscall_target(void); -extern void xen_syscall32_target(void); - /* Amount of extra memory space we add to the e820 ranges */ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; @@ -74,7 +64,7 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(u64 start, u64 size) +static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size) { int i; @@ -97,10 +87,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); } -static void __init xen_del_extra_mem(u64 start, u64 size) +static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) { int i; - u64 start_r, size_r; + phys_addr_t start_r, size_r; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { start_r = xen_extra_mem[i].start; @@ -140,7 +130,7 @@ static void __init xen_del_extra_mem(u64 start, u64 size) unsigned long __ref xen_chk_extra_mem(unsigned long pfn) { int i; - unsigned long addr = PFN_PHYS(pfn); + phys_addr_t addr = PFN_PHYS(pfn); for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { if (addr >= xen_extra_mem[i].start && @@ -160,6 +150,8 @@ void __init xen_inv_extra_mem(void) int i; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + if (!xen_extra_mem[i].size) + continue; pfn_s = PFN_DOWN(xen_extra_mem[i].start); pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size); for (pfn = pfn_s; pfn < pfn_e; pfn++) @@ -229,15 +221,14 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity, - unsigned long *released) + unsigned long end_pfn, unsigned long nr_pages, unsigned long *released) { - unsigned long len = 0; unsigned long pfn, end; int ret; WARN_ON(start_pfn > end_pfn); + /* Release pages first. */ end = min(end_pfn, nr_pages); for (pfn = start_pfn; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -250,16 +241,14 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret); if (ret == 1) { + (*released)++; if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY)) break; - len++; } else break; } - /* Need to release pages first */ - *released += len; - *identity += set_phys_range_identity(start_pfn, end_pfn); + set_phys_range_identity(start_pfn, end_pfn); } /* @@ -268,7 +257,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) { struct mmu_update update = { - .ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE, + .ptr = ((uint64_t)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE, .val = pfn }; @@ -287,7 +276,7 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn) } /* Update kernel mapping, but not for highmem. */ - if ((pfn << PAGE_SHIFT) >= __pa(high_memory)) + if (pfn >= PFN_UP(__pa(high_memory - 1))) return; if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT), @@ -318,7 +307,6 @@ static void __init xen_do_set_identity_and_remap_chunk( unsigned long ident_pfn_iter, remap_pfn_iter; unsigned long ident_end_pfn = start_pfn + size; unsigned long left = size; - unsigned long ident_cnt = 0; unsigned int i, chunk; WARN_ON(size == 0); @@ -347,8 +335,7 @@ static void __init xen_do_set_identity_and_remap_chunk( xen_remap_mfn = mfn; /* Set identity map */ - ident_cnt += set_phys_range_identity(ident_pfn_iter, - ident_pfn_iter + chunk); + set_phys_range_identity(ident_pfn_iter, ident_pfn_iter + chunk); left -= chunk; } @@ -371,7 +358,7 @@ static void __init xen_do_set_identity_and_remap_chunk( static unsigned long __init xen_set_identity_and_remap_chunk( const struct e820entry *list, size_t map_size, unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn, - unsigned long *identity, unsigned long *released) + unsigned long *released, unsigned long *remapped) { unsigned long pfn; unsigned long i = 0; @@ -386,8 +373,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Do not remap pages beyond the current allocation */ if (cur_pfn >= nr_pages) { /* Identity map remaining pages */ - *identity += set_phys_range_identity(cur_pfn, - cur_pfn + size); + set_phys_range_identity(cur_pfn, cur_pfn + size); break; } if (cur_pfn + size > nr_pages) @@ -398,7 +384,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( if (!remap_range_size) { pr_warning("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages, identity, released); + cur_pfn + left, nr_pages, released); break; } /* Adjust size to fit in current e820 RAM region */ @@ -410,7 +396,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Update variables to reflect new mappings. */ i += size; remap_pfn += size; - *identity += size; + *remapped += size; } /* @@ -427,13 +413,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk( static void __init xen_set_identity_and_remap( const struct e820entry *list, size_t map_size, unsigned long nr_pages, - unsigned long *released) + unsigned long *released, unsigned long *remapped) { phys_addr_t start = 0; - unsigned long identity = 0; unsigned long last_pfn = nr_pages; const struct e820entry *entry; unsigned long num_released = 0; + unsigned long num_remapped = 0; int i; /* @@ -460,14 +446,14 @@ static void __init xen_set_identity_and_remap( last_pfn = xen_set_identity_and_remap_chunk( list, map_size, start_pfn, end_pfn, nr_pages, last_pfn, - &identity, &num_released); + &num_released, &num_remapped); start = end; } } *released = num_released; + *remapped = num_remapped; - pr_info("Set %ld page(s) to 1-1 mapping\n", identity); pr_info("Released %ld page(s)\n", num_released); } @@ -549,20 +535,21 @@ 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) +static void __init xen_align_and_add_e820_region(phys_addr_t start, + phys_addr_t size, int type) { - u64 end = start + size; + phys_addr_t end = start + size; /* Align RAM regions to page boundaries. */ if (type == E820_RAM) { start = PAGE_ALIGN(start); - end &= ~((u64)PAGE_SIZE - 1); + end &= ~((phys_addr_t)PAGE_SIZE - 1); } e820_add_region(start, end - start, type); } -void xen_ignore_unusable(struct e820entry *list, size_t map_size) +static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size) { struct e820entry *entry; unsigned int i; @@ -581,11 +568,12 @@ char * __init xen_memory_setup(void) static struct e820entry map[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; - unsigned long long mem_end; + phys_addr_t mem_end; int rc; struct xen_memory_map memmap; unsigned long max_pages; unsigned long extra_pages = 0; + unsigned long remapped_pages; int i; int op; @@ -635,9 +623,10 @@ char * __init xen_memory_setup(void) * underlying RAM. */ xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn, - &xen_released_pages); + &xen_released_pages, &remapped_pages); extra_pages += xen_released_pages; + extra_pages += remapped_pages; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO @@ -654,16 +643,16 @@ char * __init xen_memory_setup(void) extra_pages); i = 0; while (i < memmap.nr_entries) { - u64 addr = map[i].addr; - u64 size = map[i].size; + phys_addr_t addr = map[i].addr; + phys_addr_t 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; + size = min(size, PFN_PHYS(extra_pages)); + extra_pages -= PFN_DOWN(size); xen_add_extra_mem(addr, size); xen_max_p2m_pfn = PFN_DOWN(addr + size); } else diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 4c071aeb8417..08e8489c47f1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -507,7 +507,7 @@ static int xen_cpu_disable(void) static void xen_cpu_die(unsigned int cpu) { while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { - current->state = TASK_UNINTERRUPTIBLE; + __set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(HZ/10); } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index f473d268d387..55da33b1d51c 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -391,7 +391,7 @@ static const struct clock_event_device *xen_clockevent = struct xen_clock_event_device { struct clock_event_device evt; - char *name; + char name[16]; }; static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 }; @@ -420,46 +420,38 @@ void xen_teardown_timer(int cpu) if (evt->irq >= 0) { unbind_from_irqhandler(evt->irq, NULL); evt->irq = -1; - kfree(per_cpu(xen_clock_events, cpu).name); - per_cpu(xen_clock_events, cpu).name = NULL; } } void xen_setup_timer(int cpu) { - char *name; - struct clock_event_device *evt; + struct xen_clock_event_device *xevt = &per_cpu(xen_clock_events, cpu); + struct clock_event_device *evt = &xevt->evt; int irq; - evt = &per_cpu(xen_clock_events, cpu).evt; WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); if (evt->irq >= 0) xen_teardown_timer(cpu); printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); - name = kasprintf(GFP_KERNEL, "timer%d", cpu); - if (!name) - name = "<timer kasprintf failed>"; + snprintf(xevt->name, sizeof(xevt->name), "timer%d", cpu); irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, - name, NULL); + xevt->name, NULL); (void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX); memcpy(evt, xen_clockevent, sizeof(*evt)); evt->cpumask = cpumask_of(cpu); evt->irq = irq; - per_cpu(xen_clock_events, cpu).name = name; } void xen_setup_cpu_clockevents(void) { - BUG_ON(preemptible()); - clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt)); } @@ -487,6 +479,10 @@ static void __init xen_time_init(void) int cpu = smp_processor_id(); struct timespec tp; + /* As Dom0 is never moved, no penalty on using TSC there */ + if (xen_initial_domain()) + xen_clocksource.rating = 275; + clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC); if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 5686bd9d58cc..9e195c683549 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -10,6 +10,12 @@ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +void xen_sysenter_target(void); +#ifdef CONFIG_X86_64 +void xen_syscall_target(void); +void xen_syscall32_target(void); +#endif + extern void *xen_initial_gdt; struct trap_info; |