diff options
Diffstat (limited to 'arch/s390/kernel/vdso.c')
| -rw-r--r-- | arch/s390/kernel/vdso.c | 163 |
1 files changed, 131 insertions, 32 deletions
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 10a6ccef441..61364909678 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -22,17 +22,15 @@ #include <linux/elf.h> #include <linux/security.h> #include <linux/bootmem.h> - +#include <linux/compat.h> +#include <asm/asm-offsets.h> #include <asm/pgtable.h> -#include <asm/system.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mmu_context.h> #include <asm/sections.h> #include <asm/vdso.h> - -/* Max supported size for symbol names */ -#define MAX_SYMNAME 64 +#include <asm/facility.h> #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) extern char vdso32_start, vdso32_end; @@ -56,8 +54,19 @@ unsigned int __read_mostly vdso_enabled = 1; static int __init vdso_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); - return 1; + unsigned long val; + int rc; + + rc = 0; + if (strncmp(s, "on", 3) == 0) + vdso_enabled = 1; + else if (strncmp(s, "off", 4) == 0) + vdso_enabled = 0; + else { + rc = kstrtoul(s, 0, &val); + vdso_enabled = rc ? 0 : !!val; + } + return !rc; } __setup("vdso=", vdso_setup); @@ -67,10 +76,102 @@ __setup("vdso=", vdso_setup); static union { struct vdso_data data; u8 page[PAGE_SIZE]; -} vdso_data_store __attribute__((__section__(".data.page_aligned"))); +} vdso_data_store __page_aligned_data; struct vdso_data *vdso_data = &vdso_data_store.data; /* + * Setup vdso data page. + */ +static void vdso_init_data(struct vdso_data *vd) +{ + vd->ectg_available = test_facility(31); +} + +#ifdef CONFIG_64BIT +/* + * Allocate/free per cpu vdso data. + */ +#define SEGMENT_ORDER 2 + +int vdso_alloc_per_cpu(struct _lowcore *lowcore) +{ + unsigned long segment_table, page_table, page_frame; + u32 *psal, *aste; + int i; + + lowcore->vdso_per_cpu_data = __LC_PASTE; + + if (!vdso_enabled) + return 0; + + segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER); + page_table = get_zeroed_page(GFP_KERNEL | GFP_DMA); + page_frame = get_zeroed_page(GFP_KERNEL); + if (!segment_table || !page_table || !page_frame) + goto out; + + clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY, + PAGE_SIZE << SEGMENT_ORDER); + clear_table((unsigned long *) page_table, _PAGE_INVALID, + 256*sizeof(unsigned long)); + + *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table; + *(unsigned long *) page_table = _PAGE_PROTECT + page_frame; + + psal = (u32 *) (page_table + 256*sizeof(unsigned long)); + aste = psal + 32; + + for (i = 4; i < 32; i += 4) + psal[i] = 0x80000000; + + lowcore->paste[4] = (u32)(addr_t) psal; + psal[0] = 0x02000000; + psal[2] = (u32)(addr_t) aste; + *(unsigned long *) (aste + 2) = segment_table + + _ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT; + aste[4] = (u32)(addr_t) psal; + lowcore->vdso_per_cpu_data = page_frame; + + return 0; + +out: + free_page(page_frame); + free_page(page_table); + free_pages(segment_table, SEGMENT_ORDER); + return -ENOMEM; +} + +void vdso_free_per_cpu(struct _lowcore *lowcore) +{ + unsigned long segment_table, page_table, page_frame; + u32 *psal, *aste; + + if (!vdso_enabled) + return; + + psal = (u32 *)(addr_t) lowcore->paste[4]; + aste = (u32 *)(addr_t) psal[2]; + segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK; + page_table = *(unsigned long *) segment_table; + page_frame = *(unsigned long *) page_table; + + free_page(page_frame); + free_page(page_table); + free_pages(segment_table, SEGMENT_ORDER); +} + +static void vdso_init_cr5(void) +{ + unsigned long cr5; + + if (!vdso_enabled) + return; + cr5 = offsetof(struct _lowcore, paste); + __ctl_load(cr5, 5, 5); +} +#endif /* CONFIG_64BIT */ + +/* * This is called from binfmt_elf, we create the special vma for the * vDSO and insert it into the mm struct tree */ @@ -90,12 +191,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!uses_interp) return 0; - vdso_base = mm->mmap_base; #ifdef CONFIG_64BIT vdso_pagelist = vdso64_pagelist; vdso_pages = vdso64_pages; #ifdef CONFIG_COMPAT - if (test_thread_flag(TIF_31BIT)) { + if (is_compat_task()) { vdso_pagelist = vdso32_pagelist; vdso_pages = vdso32_pages; } @@ -120,14 +220,20 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * fail and end up putting it elsewhere. */ down_write(&mm->mmap_sem); - vdso_base = get_unmapped_area(NULL, vdso_base, - vdso_pages << PAGE_SHIFT, 0, 0); + vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0); if (IS_ERR_VALUE(vdso_base)) { rc = vdso_base; goto out_up; } /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + current->mm->context.vdso_base = vdso_base; + + /* * our vma flags don't have VM_WRITE so by default, the process * isn't allowed to write those pages. * gdb can break that with ptrace interface, and thus trigger COW @@ -135,27 +241,14 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * on the "data" page of the vDSO or you'll stop getting kernel * updates and your nice userland gettimeofday will be totally dead. * It's fine to use that for setting breakpoints in the vDSO code - * pages though - * - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. + * pages though. */ rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| - VM_ALWAYSDUMP, + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, vdso_pagelist); if (rc) - goto out_up; - - /* Put vDSO base into mm struct */ - current->mm->context.vdso_base = vdso_base; - - up_write(&mm->mmap_sem); - return 0; - + current->mm->context.vdso_base = 0; out_up: up_write(&mm->mmap_sem); return rc; @@ -172,6 +265,9 @@ static int __init vdso_init(void) { int i; + if (!vdso_enabled) + return 0; + vdso_init_data(vdso_data); #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) /* Calculate the size of the 32 bit vDSO */ vdso32_pages = ((&vdso32_end - &vdso32_start @@ -208,6 +304,9 @@ static int __init vdso_init(void) } vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data); vdso64_pagelist[vdso64_pages] = NULL; + if (vdso_alloc_per_cpu(&S390_lowcore)) + BUG(); + vdso_init_cr5(); #endif /* CONFIG_64BIT */ get_page(virt_to_page(vdso_data)); @@ -216,19 +315,19 @@ static int __init vdso_init(void) return 0; } -arch_initcall(vdso_init); +early_initcall(vdso_init); -int in_gate_area_no_task(unsigned long addr) +int in_gate_area_no_mm(unsigned long addr) { return 0; } -int in_gate_area(struct task_struct *task, unsigned long addr) +int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } |