diff options
Diffstat (limited to 'arch/x86/xen/mmu_pv.c')
-rw-r--r-- | arch/x86/xen/mmu_pv.c | 672 |
1 files changed, 191 insertions, 481 deletions
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index bbba8b17829a..ee29fb558f2e 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -41,7 +41,6 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ #include <linux/sched/mm.h> -#include <linux/highmem.h> #include <linux/debugfs.h> #include <linux/bug.h> #include <linux/vmalloc.h> @@ -51,13 +50,13 @@ #include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/crash_dump.h> +#include <linux/pgtable.h> #ifdef CONFIG_KEXEC_CORE #include <linux/kexec.h> #endif #include <trace/events/xen.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> #include <asm/mmu_context.h> @@ -81,24 +80,16 @@ #include <xen/interface/version.h> #include <xen/interface/memory.h> #include <xen/hvc-console.h> +#include <xen/swiotlb-xen.h> #include "multicalls.h" #include "mmu.h" #include "debugfs.h" -#ifdef CONFIG_X86_32 -/* - * Identity map, in addition to plain kernel map. This needs to be - * large enough to allocate page table pages to allocate the rest. - * Each page can map 2MB. - */ -#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4) -static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES); -#endif -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_VSYSCALL_EMULATION /* l3 pud for userspace vsyscall mapping */ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; -#endif /* CONFIG_X86_64 */ +#endif /* * Protects atomic reservation decrease/increase against concurrent increases. @@ -252,9 +243,11 @@ static void xen_set_pmd(pmd_t *ptr, pmd_t val) * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. */ -void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) +void __init set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags) { - set_pte_vaddr(vaddr, mfn_pte(mfn, flags)); + if (HYPERVISOR_update_va_mapping(vaddr, mfn_pte(mfn, flags), + UVMF_INVLPG)) + BUG(); } static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) @@ -280,10 +273,7 @@ static inline void __xen_set_pte(pte_t *ptep, pte_t pteval) if (!xen_batched_set_pte(ptep, pteval)) { /* * Could call native_set_pte() here and trap and - * emulate the PTE write but with 32-bit guests this - * needs two traps (one for each of the two 32-bit - * words in the PTE) so do one hypercall directly - * instead. + * emulate the PTE write, but a hypercall is much cheaper. */ struct mmu_update u; @@ -299,13 +289,6 @@ static void xen_set_pte(pte_t *ptep, pte_t pteval) __xen_set_pte(ptep, pteval); } -static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) -{ - trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval); - __xen_set_pte(ptep, pteval); -} - pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { @@ -439,26 +422,6 @@ static void xen_set_pud(pud_t *ptr, pud_t val) xen_set_pud_hyper(ptr, val); } -#ifdef CONFIG_X86_PAE -static void xen_set_pte_atomic(pte_t *ptep, pte_t pte) -{ - trace_xen_mmu_set_pte_atomic(ptep, pte); - __xen_set_pte(ptep, pte); -} - -static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - trace_xen_mmu_pte_clear(mm, addr, ptep); - __xen_set_pte(ptep, native_make_pte(0)); -} - -static void xen_pmd_clear(pmd_t *pmdp) -{ - trace_xen_mmu_pmd_clear(pmdp); - set_pmd(pmdp, __pmd(0)); -} -#endif /* CONFIG_X86_PAE */ - __visible pmd_t xen_make_pmd(pmdval_t pmd) { pmd = pte_pfn_to_mfn(pmd); @@ -466,7 +429,6 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); -#ifdef CONFIG_X86_64 __visible pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); @@ -571,27 +533,27 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d); #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ -#endif /* CONFIG_X86_64 */ -static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int i, nr, flush = 0; + int i, nr; nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD; for (i = 0; i < nr; i++) { if (!pmd_none(pmd[i])) - flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE); + (*func)(mm, pmd_page(pmd[i]), PT_PTE); } - return flush; } -static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_pud_walk(struct mm_struct *mm, pud_t *pud, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int i, nr, flush = 0; + int i, nr; nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD; for (i = 0; i < nr; i++) { @@ -602,29 +564,26 @@ static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, pmd = pmd_offset(&pud[i], 0); if (PTRS_PER_PMD > 1) - flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); - flush |= xen_pmd_walk(mm, pmd, func, - last && i == nr - 1, limit); + (*func)(mm, virt_to_page(pmd), PT_PMD); + xen_pmd_walk(mm, pmd, func, last && i == nr - 1, limit); } - return flush; } -static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int flush = 0; pud_t *pud; if (p4d_none(*p4d)) - return flush; + return; pud = pud_offset(p4d, 0); if (PTRS_PER_PUD > 1) - flush |= (*func)(mm, virt_to_page(pud), PT_PUD); - flush |= xen_pud_walk(mm, pud, func, last, limit); - return flush; + (*func)(mm, virt_to_page(pud), PT_PUD); + xen_pud_walk(mm, pud, func, last, limit); } /* @@ -636,32 +595,27 @@ static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, * will be STACK_TOP_MAX, but at boot we need to pin up to * FIXADDR_TOP. * - * For 32-bit the important bit is that we don't pin beyond there, - * because then we start getting into Xen's ptes. - * - * For 64-bit, we must skip the Xen hole in the middle of the address - * space, just after the big x86-64 virtual hole. + * We must skip the Xen hole in the middle of the address space, just after + * the big x86-64 virtual hole. */ -static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, - int (*func)(struct mm_struct *mm, struct page *, - enum pt_level), - unsigned long limit) +static void __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) { - int i, nr, flush = 0; + int i, nr; unsigned hole_low = 0, hole_high = 0; /* The limit is the last byte to be touched */ limit--; BUG_ON(limit >= FIXADDR_TOP); -#ifdef CONFIG_X86_64 /* * 64-bit has a great big hole in the middle of the address * space, which contains the Xen mappings. */ hole_low = pgd_index(GUARD_HOLE_BASE_ADDR); hole_high = pgd_index(GUARD_HOLE_END_ADDR); -#endif nr = pgd_index(limit) + 1; for (i = 0; i < nr; i++) { @@ -674,22 +628,20 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, continue; p4d = p4d_offset(&pgd[i], 0); - flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); + xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); } /* Do the top level last, so that the callbacks can use it as a cue to do final things like tlb flushes. */ - flush |= (*func)(mm, virt_to_page(pgd), PT_PGD); - - return flush; + (*func)(mm, virt_to_page(pgd), PT_PGD); } -static int xen_pgd_walk(struct mm_struct *mm, - int (*func)(struct mm_struct *mm, struct page *, - enum pt_level), - unsigned long limit) +static void xen_pgd_walk(struct mm_struct *mm, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) { - return __xen_pgd_walk(mm, mm->pgd, func, limit); + __xen_pgd_walk(mm, mm->pgd, func, limit); } /* If we're using split pte locks, then take the page's lock and @@ -722,26 +674,17 @@ static void xen_do_pin(unsigned level, unsigned long pfn) xen_extend_mmuext_op(&op); } -static int xen_pin_page(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void xen_pin_page(struct mm_struct *mm, struct page *page, + enum pt_level level) { unsigned pgfl = TestSetPagePinned(page); - int flush; - - if (pgfl) - flush = 0; /* already pinned */ - else if (PageHighMem(page)) - /* kmaps need flushing if we found an unpinned - highpage */ - flush = 1; - else { + + if (!pgfl) { void *pt = lowmem_page_address(page); unsigned long pfn = page_to_pfn(page); struct multicall_space mcs = __xen_mc_entry(0); spinlock_t *ptl; - flush = 0; - /* * We need to hold the pagetable lock between the time * we make the pagetable RO and when we actually pin @@ -778,8 +721,6 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page, xen_mc_callback(xen_pte_unlock, ptl); } } - - return flush; } /* This is called just after a mm has been created, but it has not @@ -787,39 +728,22 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page, read-only, and can be pinned. */ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd) { + pgd_t *user_pgd = xen_get_user_pgd(pgd); + trace_xen_mmu_pgd_pin(mm, pgd); xen_mc_batch(); - if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) { - /* re-enable interrupts for flushing */ - xen_mc_issue(0); + __xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT); - kmap_flush_unused(); + xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd))); - xen_mc_batch(); + if (user_pgd) { + xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD); + xen_do_pin(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa(user_pgd))); } -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd))); - - if (user_pgd) { - xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD); - xen_do_pin(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa(user_pgd))); - } - } -#else /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_PAE - /* Need to make sure unshared kernel PMD is pinnable */ - xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]), - PT_PMD); -#endif - xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd))); -#endif /* CONFIG_X86_64 */ xen_mc_issue(0); } @@ -854,11 +778,10 @@ void xen_mm_pin_all(void) spin_unlock(&pgd_lock); } -static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, + enum pt_level level) { SetPagePinned(page); - return 0; } /* @@ -870,18 +793,18 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, static void __init xen_after_bootmem(void) { static_branch_enable(&xen_struct_pages_ready); -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_VSYSCALL_EMULATION SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } -static int xen_unpin_page(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void xen_unpin_page(struct mm_struct *mm, struct page *page, + enum pt_level level) { unsigned pgfl = TestClearPagePinned(page); - if (pgfl && !PageHighMem(page)) { + if (pgfl) { void *pt = lowmem_page_address(page); unsigned long pfn = page_to_pfn(page); spinlock_t *ptl = NULL; @@ -912,36 +835,24 @@ static int xen_unpin_page(struct mm_struct *mm, struct page *page, xen_mc_callback(xen_pte_unlock, ptl); } } - - return 0; /* never need to flush on unpin */ } /* Release a pagetables pages back as normal RW */ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd) { + pgd_t *user_pgd = xen_get_user_pgd(pgd); + trace_xen_mmu_pgd_unpin(mm, pgd); xen_mc_batch(); xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - if (user_pgd) { - xen_do_pin(MMUEXT_UNPIN_TABLE, - PFN_DOWN(__pa(user_pgd))); - xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD); - } + if (user_pgd) { + xen_do_pin(MMUEXT_UNPIN_TABLE, + PFN_DOWN(__pa(user_pgd))); + xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD); } -#endif - -#ifdef CONFIG_X86_PAE - /* Need to make sure unshared kernel PMD is unpinned */ - xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]), - PT_PMD); -#endif __xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT); @@ -1089,7 +1000,6 @@ static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) BUG(); } -#ifdef CONFIG_X86_64 static void __init xen_cleanhighmap(unsigned long vaddr, unsigned long vaddr_end) { @@ -1121,7 +1031,7 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) make_lowmem_page_readwrite(vaddr); - memblock_free(paddr, size); + memblock_phys_free(paddr, size); } static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) @@ -1238,7 +1148,7 @@ static void __init xen_pagetable_p2m_free(void) * We could be in __ka space. * We roundup to the PMD, which means that if anybody at this stage is * using the __ka address of xen_start_info or - * xen_start_info->shared_info they are in going to crash. Fortunatly + * xen_start_info->shared_info they are in going to crash. Fortunately * we have already revectored in xen_setup_kernel_pagetable. */ size = roundup(size, PMD_SIZE); @@ -1247,7 +1157,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(addr), size); + memblock_free((void *)addr, size); } else { xen_cleanmfnmap(addr); } @@ -1273,23 +1183,28 @@ static void __init xen_pagetable_cleanhighmap(void) xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); } -#endif static void __init xen_pagetable_p2m_setup(void) { xen_vmalloc_p2m_tree(); -#ifdef CONFIG_X86_64 xen_pagetable_p2m_free(); xen_pagetable_cleanhighmap(); -#endif + /* And revector! Bye bye old array */ xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; } static void __init xen_pagetable_init(void) { + /* + * The majority of further PTE writes is to pagetables already + * announced as such to Xen. Hence it is more efficient to use + * hypercalls for these updates. + */ + pv_ops.mmu.set_pte = __xen_set_pte; + paging_init(); xen_post_allocator_init(); @@ -1302,7 +1217,8 @@ static void __init xen_pagetable_init(void) xen_remap_memory(); xen_setup_mfn_list_list(); } -static void xen_write_cr2(unsigned long cr2) + +static noinstr void xen_write_cr2(unsigned long cr2) { this_cpu_read(xen_vcpu)->arch.cr2 = cr2; } @@ -1345,8 +1261,8 @@ static void xen_flush_tlb_one_user(unsigned long addr) preempt_enable(); } -static void xen_flush_tlb_others(const struct cpumask *cpus, - const struct flush_tlb_info *info) +static void xen_flush_tlb_multi(const struct cpumask *cpus, + const struct flush_tlb_info *info) { struct { struct mmuext_op op; @@ -1356,7 +1272,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, const size_t mc_entry_size = sizeof(args->op) + sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus()); - trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); + trace_xen_mmu_flush_tlb_multi(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ @@ -1365,9 +1281,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, args = mcs.args; args->op.arg2.vcpumask = to_cpumask(args->mask); - /* Remove us, and any offline CPUS. */ + /* Remove any offline CPUs */ cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask); - cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; if (info->end != TLB_FLUSH_ALL && @@ -1420,6 +1335,8 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3) } static void xen_write_cr3(unsigned long cr3) { + pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); + BUG_ON(preemptible()); xen_mc_batch(); /* disables interrupts */ @@ -1430,20 +1347,14 @@ static void xen_write_cr3(unsigned long cr3) __xen_write_cr3(true, cr3); -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); - if (user_pgd) - __xen_write_cr3(false, __pa(user_pgd)); - else - __xen_write_cr3(false, 0); - } -#endif + if (user_pgd) + __xen_write_cr3(false, __pa(user_pgd)); + else + __xen_write_cr3(false, 0); xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ } -#ifdef CONFIG_X86_64 /* * At the start of the day - when Xen launches a guest, it has already * built pagetables for the guest. We diligently look over them @@ -1478,49 +1389,39 @@ static void __init xen_write_cr3_init(unsigned long cr3) xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ } -#endif static int xen_pgd_alloc(struct mm_struct *mm) { pgd_t *pgd = mm->pgd; - int ret = 0; + struct page *page = virt_to_page(pgd); + pgd_t *user_pgd; + int ret = -ENOMEM; BUG_ON(PagePinned(virt_to_page(pgd))); + BUG_ON(page->private != 0); -#ifdef CONFIG_X86_64 - { - struct page *page = virt_to_page(pgd); - pgd_t *user_pgd; - - BUG_ON(page->private != 0); - - ret = -ENOMEM; + user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + page->private = (unsigned long)user_pgd; - user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - page->private = (unsigned long)user_pgd; - - if (user_pgd != NULL) { + if (user_pgd != NULL) { #ifdef CONFIG_X86_VSYSCALL_EMULATION - user_pgd[pgd_index(VSYSCALL_ADDR)] = - __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); + user_pgd[pgd_index(VSYSCALL_ADDR)] = + __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); #endif - ret = 0; - } - - BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); + ret = 0; } -#endif + + BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); + return ret; } static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) { -#ifdef CONFIG_X86_64 pgd_t *user_pgd = xen_get_user_pgd(pgd); if (user_pgd) free_page((unsigned long)user_pgd); -#endif } /* @@ -1533,13 +1434,20 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) * * Many of these PTE updates are done on unpinned and writable pages * and doing a hypercall for these is unnecessary and expensive. At - * this point it is not possible to tell if a page is pinned or not, - * so always write the PTE directly and rely on Xen trapping and + * this point it is rarely possible to tell if a page is pinned, so + * mostly write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ +static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +{ + if (unlikely(is_early_ioremap_ptep(ptep))) + __xen_set_pte(ptep, pte); + else + native_set_pte(ptep, pte); +} + __visible pte_t xen_make_pte_init(pteval_t pte) { -#ifdef CONFIG_X86_64 unsigned long pfn; /* @@ -1553,24 +1461,12 @@ __visible pte_t xen_make_pte_init(pteval_t pte) pfn >= xen_start_info->first_p2m_pfn && pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) pte &= ~_PAGE_RW; -#endif + pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); -static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) -{ -#ifdef CONFIG_X86_32 - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_mfn(pte) != INVALID_P2M_ENTRY - && pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); -#endif - __xen_set_pte(ptep, pte); -} - /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1639,23 +1535,20 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (pinned) { struct page *page = pfn_to_page(pfn); - if (static_branch_likely(&xen_struct_pages_ready)) + pinned = false; + if (static_branch_likely(&xen_struct_pages_ready)) { + pinned = PagePinned(page); SetPagePinned(page); + } - if (!PageHighMem(page)) { - xen_mc_batch(); + xen_mc_batch(); - __set_pfn_prot(pfn, PAGE_KERNEL_RO); + __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) - __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) + __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); - xen_mc_issue(PARAVIRT_LAZY_MMU); - } else { - /* make sure there are no stray mappings of - this page */ - kmap_flush_unused(); - } + xen_mc_issue(PARAVIRT_LAZY_MMU); } } @@ -1678,16 +1571,15 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) trace_xen_mmu_release_ptpage(pfn, level, pinned); if (pinned) { - if (!PageHighMem(page)) { - xen_mc_batch(); + xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) - __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); - __set_pfn_prot(pfn, PAGE_KERNEL); + __set_pfn_prot(pfn, PAGE_KERNEL); + + xen_mc_issue(PARAVIRT_LAZY_MMU); - xen_mc_issue(PARAVIRT_LAZY_MMU); - } ClearPagePinned(page); } } @@ -1702,7 +1594,6 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#ifdef CONFIG_X86_64 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -1712,20 +1603,6 @@ static void xen_release_pud(unsigned long pfn) { xen_release_ptpage(pfn, PT_PUD); } -#endif - -void __init xen_reserve_top(void) -{ -#ifdef CONFIG_X86_32 - unsigned long top = HYPERVISOR_VIRT_START; - struct xen_platform_parameters pp; - - if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0) - top = pp.virt_start; - - reserve_top_address(-top); -#endif /* CONFIG_X86_32 */ -} /* * Like __va(), but returns address in the kernel mapping (which is @@ -1733,11 +1610,7 @@ void __init xen_reserve_top(void) */ static void * __init __ka(phys_addr_t paddr) { -#ifdef CONFIG_X86_64 return (void *)(paddr + __START_KERNEL_map); -#else - return __va(paddr); -#endif } /* Convert a machine address to physical address */ @@ -1771,56 +1644,7 @@ static void __init set_page_prot(void *addr, pgprot_t prot) { return set_page_prot_flags(addr, prot, UVMF_NONE); } -#ifdef CONFIG_X86_32 -static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) -{ - unsigned pmdidx, pteidx; - unsigned ident_pte; - unsigned long pfn; - - level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES, - PAGE_SIZE); - - ident_pte = 0; - pfn = 0; - for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) { - pte_t *pte_page; - - /* Reuse or allocate a page of ptes */ - if (pmd_present(pmd[pmdidx])) - pte_page = m2v(pmd[pmdidx].pmd); - else { - /* Check for free pte pages */ - if (ident_pte == LEVEL1_IDENT_ENTRIES) - break; - - pte_page = &level1_ident_pgt[ident_pte]; - ident_pte += PTRS_PER_PTE; - - pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE); - } - - /* Install mappings */ - for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { - pte_t pte; - if (pfn > max_pfn_mapped) - max_pfn_mapped = pfn; - - if (!pte_none(pte_page[pteidx])) - continue; - - pte = pfn_pte(pfn, PAGE_KERNEL_EXEC); - pte_page[pteidx] = pte; - } - } - - for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE) - set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO); - - set_page_prot(pmd, PAGE_KERNEL_RO); -} -#endif void __init xen_setup_machphys_mapping(void) { struct xen_machphys_mapping mapping; @@ -1831,13 +1655,8 @@ void __init xen_setup_machphys_mapping(void) } else { machine_to_phys_nr = MACH2PHYS_NR_ENTRIES; } -#ifdef CONFIG_X86_32 - WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1)) - < machine_to_phys_mapping); -#endif } -#ifdef CONFIG_X86_64 static void __init convert_pfn_mfn(void *v) { pte_t *pte = v; @@ -1947,7 +1766,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(init_top_pgt, PAGE_KERNEL_RO); set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); @@ -1964,6 +1782,13 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Unpin Xen-provided one */ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); +#ifdef CONFIG_X86_VSYSCALL_EMULATION + /* Pin user vsyscall L3 */ + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, + PFN_DOWN(__pa_symbol(level3_user_vsyscall))); +#endif + /* * At this stage there can be no user pgd, and no page structure to * attach it to, so make sure we just set kernel pgd. @@ -2153,7 +1978,7 @@ void __init xen_relocate_p2m(void) pfn_end = p2m_pfn_end; } - memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); while (pfn < pfn_end) { if (pfn == p2m_pfn) { pfn = p2m_pfn_end; @@ -2168,105 +1993,6 @@ void __init xen_relocate_p2m(void) xen_start_info->nr_p2m_frames = n_frames; } -#else /* !CONFIG_X86_64 */ -static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); -static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); -RESERVE_BRK(fixup_kernel_pmd, PAGE_SIZE); -RESERVE_BRK(fixup_kernel_pte, PAGE_SIZE); - -static void __init xen_write_cr3_init(unsigned long cr3) -{ - unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); - - BUG_ON(read_cr3_pa() != __pa(initial_page_table)); - BUG_ON(cr3 != __pa(swapper_pg_dir)); - - /* - * We are switching to swapper_pg_dir for the first time (from - * initial_page_table) and therefore need to mark that page - * read-only and then pin it. - * - * Xen disallows sharing of kernel PMDs for PAE - * guests. Therefore we must copy the kernel PMD from - * initial_page_table into a new kernel PMD to be used in - * swapper_pg_dir. - */ - swapper_kernel_pmd = - extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - copy_page(swapper_kernel_pmd, initial_kernel_pmd); - swapper_pg_dir[KERNEL_PGD_BOUNDARY] = - __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT); - set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO); - - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); - xen_write_cr3(cr3); - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, - PFN_DOWN(__pa(initial_page_table))); - set_page_prot(initial_page_table, PAGE_KERNEL); - set_page_prot(initial_kernel_pmd, PAGE_KERNEL); - - pv_ops.mmu.write_cr3 = &xen_write_cr3; -} - -/* - * For 32 bit domains xen_start_info->pt_base is the pgd address which might be - * not the first page table in the page table pool. - * Iterate through the initial page tables to find the real page table base. - */ -static phys_addr_t __init xen_find_pt_base(pmd_t *pmd) -{ - phys_addr_t pt_base, paddr; - unsigned pmdidx; - - pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd)); - - for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) - if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) { - paddr = m2p(pmd[pmdidx].pmd); - pt_base = min(pt_base, paddr); - } - - return pt_base; -} - -void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) -{ - pmd_t *kernel_pmd; - - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - - xen_pt_base = xen_find_pt_base(kernel_pmd); - xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE; - - initial_kernel_pmd = - extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - - max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024); - - copy_page(initial_kernel_pmd, kernel_pmd); - - xen_map_identity_early(initial_kernel_pmd, max_pfn); - - copy_page(initial_page_table, pgd); - initial_page_table[KERNEL_PGD_BOUNDARY] = - __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT); - - set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO); - set_page_prot(initial_page_table, PAGE_KERNEL_RO); - set_page_prot(empty_zero_page, PAGE_KERNEL_RO); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, - PFN_DOWN(__pa(initial_page_table))); - xen_write_cr3(__pa(initial_page_table)); - - memblock_reserve(xen_pt_base, xen_pt_size); -} -#endif /* CONFIG_X86_64 */ - void __init xen_reserve_special_pages(void) { phys_addr_t paddr; @@ -2295,17 +2021,13 @@ static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) { pte_t pte; + unsigned long vaddr; phys >>= PAGE_SHIFT; switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_32 - case FIX_WP_TEST: -# ifdef CONFIG_HIGHMEM - case FIX_KMAP_BEGIN ... FIX_KMAP_END: -# endif -#elif defined(CONFIG_X86_VSYSCALL_EMULATION) +#ifdef CONFIG_X86_VSYSCALL_EMULATION case VSYSCALL_PAGE: #endif /* All local page mappings */ @@ -2340,15 +2062,15 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) break; } - __native_set_fixmap(idx, pte); + vaddr = __fix_to_virt(idx); + if (HYPERVISOR_update_va_mapping(vaddr, pte, UVMF_INVLPG)) + BUG(); #ifdef CONFIG_X86_VSYSCALL_EMULATION /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ - if (idx == VSYSCALL_PAGE) { - unsigned long vaddr = __fix_to_virt(idx); + if (idx == VSYSCALL_PAGE) set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); - } #endif } @@ -2357,9 +2079,7 @@ static void __init xen_post_allocator_init(void) pv_ops.mmu.set_pte = xen_set_pte; pv_ops.mmu.set_pmd = xen_set_pmd; pv_ops.mmu.set_pud = xen_set_pud; -#ifdef CONFIG_X86_64 pv_ops.mmu.set_p4d = xen_set_p4d; -#endif /* This will work as long as patching hasn't happened yet (which it hasn't) */ @@ -2367,15 +2087,11 @@ static void __init xen_post_allocator_init(void) pv_ops.mmu.alloc_pmd = xen_alloc_pmd; pv_ops.mmu.release_pte = xen_release_pte; pv_ops.mmu.release_pmd = xen_release_pmd; -#ifdef CONFIG_X86_64 pv_ops.mmu.alloc_pud = xen_alloc_pud; pv_ops.mmu.release_pud = xen_release_pud; -#endif pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte); -#ifdef CONFIG_X86_64 pv_ops.mmu.write_cr3 = &xen_write_cr3; -#endif } static void xen_leave_lazy_mmu(void) @@ -2386,75 +2102,69 @@ static void xen_leave_lazy_mmu(void) preempt_enable(); } -static const struct pv_mmu_ops xen_mmu_ops __initconst = { - .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), - .write_cr2 = xen_write_cr2, +static const typeof(pv_ops) xen_mmu_ops __initconst = { + .mmu = { + .read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2), + .write_cr2 = xen_write_cr2, - .read_cr3 = xen_read_cr3, - .write_cr3 = xen_write_cr3_init, + .read_cr3 = xen_read_cr3, + .write_cr3 = xen_write_cr3_init, - .flush_tlb_user = xen_flush_tlb, - .flush_tlb_kernel = xen_flush_tlb, - .flush_tlb_one_user = xen_flush_tlb_one_user, - .flush_tlb_others = xen_flush_tlb_others, - .tlb_remove_table = tlb_remove_table, + .flush_tlb_user = xen_flush_tlb, + .flush_tlb_kernel = xen_flush_tlb, + .flush_tlb_one_user = xen_flush_tlb_one_user, + .flush_tlb_multi = xen_flush_tlb_multi, + .tlb_remove_table = tlb_remove_table, - .pgd_alloc = xen_pgd_alloc, - .pgd_free = xen_pgd_free, + .pgd_alloc = xen_pgd_alloc, + .pgd_free = xen_pgd_free, - .alloc_pte = xen_alloc_pte_init, - .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pmd_init, - .release_pmd = xen_release_pmd_init, + .alloc_pte = xen_alloc_pte_init, + .release_pte = xen_release_pte_init, + .alloc_pmd = xen_alloc_pmd_init, + .release_pmd = xen_release_pmd_init, - .set_pte = xen_set_pte_init, - .set_pte_at = xen_set_pte_at, - .set_pmd = xen_set_pmd_hyper, + .set_pte = xen_set_pte_init, + .set_pmd = xen_set_pmd_hyper, - .ptep_modify_prot_start = __ptep_modify_prot_start, - .ptep_modify_prot_commit = __ptep_modify_prot_commit, + .ptep_modify_prot_start = xen_ptep_modify_prot_start, + .ptep_modify_prot_commit = xen_ptep_modify_prot_commit, - .pte_val = PV_CALLEE_SAVE(xen_pte_val), - .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), + .pte_val = PV_CALLEE_SAVE(xen_pte_val), + .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), - .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), + .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), -#ifdef CONFIG_X86_PAE - .set_pte_atomic = xen_set_pte_atomic, - .pte_clear = xen_pte_clear, - .pmd_clear = xen_pmd_clear, -#endif /* CONFIG_X86_PAE */ - .set_pud = xen_set_pud_hyper, + .set_pud = xen_set_pud_hyper, - .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), - .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), + .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), + .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#ifdef CONFIG_X86_64 - .pud_val = PV_CALLEE_SAVE(xen_pud_val), - .make_pud = PV_CALLEE_SAVE(xen_make_pud), - .set_p4d = xen_set_p4d_hyper, + .pud_val = PV_CALLEE_SAVE(xen_pud_val), + .make_pud = PV_CALLEE_SAVE(xen_make_pud), + .set_p4d = xen_set_p4d_hyper, - .alloc_pud = xen_alloc_pmd_init, - .release_pud = xen_release_pmd_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #if CONFIG_PGTABLE_LEVELS >= 5 - .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), - .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), + .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), + .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), #endif -#endif /* CONFIG_X86_64 */ - .activate_mm = xen_activate_mm, - .dup_mmap = xen_dup_mmap, - .exit_mmap = xen_exit_mmap, + .activate_mm = xen_activate_mm, + .dup_mmap = xen_dup_mmap, + .exit_mmap = xen_exit_mmap, - .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, - .leave = xen_leave_lazy_mmu, - .flush = paravirt_flush_lazy_mmu, - }, + .lazy_mode = { + .enter = paravirt_enter_lazy_mmu, + .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, + }, - .set_fixmap = xen_set_fixmap, + .set_fixmap = xen_set_fixmap, + }, }; void __init xen_init_mmu_ops(void) @@ -2462,7 +2172,7 @@ void __init xen_init_mmu_ops(void) x86_init.paging.pagetable_init = xen_pagetable_init; x86_init.hyper.init_after_bootmem = xen_after_bootmem; - pv_ops.mmu = xen_mmu_ops; + pv_ops.mmu = xen_mmu_ops.mmu; memset(dummy_mapping, 0xff, PAGE_SIZE); } @@ -2714,7 +2424,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; @@ -2728,7 +2438,7 @@ int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, rmd.prot = prot; /* * We use the err_ptr to indicate if there we are doing a contiguous - * mapping or a discontigious mapping. + * mapping or a discontiguous mapping. */ rmd.contiguous = !err_ptr; rmd.no_translate = no_translate; |