/*
- * linux/arch/ppc64/kernel/vdso.c
- *
* Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
* <benh@kernel.crashing.org>
*
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/config.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
-#include <linux/smp_lock.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/sections.h>
+#include <asm/firmware.h>
#include <asm/vdso.h>
#include <asm/vdso_datapage.h>
+#include "setup.h"
+
#undef DEBUG
#ifdef DEBUG
extern char vdso32_start, vdso32_end;
static void *vdso32_kbase = &vdso32_start;
-unsigned int vdso32_pages;
+static unsigned int vdso32_pages;
+static struct page **vdso32_pagelist;
unsigned long vdso32_sigtramp;
unsigned long vdso32_rt_sigtramp;
#ifdef CONFIG_PPC64
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
-unsigned int vdso64_pages;
+static unsigned int vdso64_pages;
+static struct page **vdso64_pagelist;
unsigned long vdso64_rt_sigtramp;
#endif /* CONFIG_PPC64 */
+static int vdso_ready;
+
/*
* The vdso data page (aka. systemcfg for old ppc64 fans) is here.
* Once the early boot kernel code no longer needs to muck around
struct page *pg = virt_to_page(vdso32_kbase +
i*PAGE_SIZE);
struct page *upg = (vma && vma->vm_mm) ?
- follow_page(vma->vm_mm, vma->vm_start +
- i*PAGE_SIZE, 0)
+ follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
: NULL;
dump_one_vdso_page(pg, upg);
}
struct page *pg = virt_to_page(vdso64_kbase +
i*PAGE_SIZE);
struct page *upg = (vma && vma->vm_mm) ?
- follow_page(vma->vm_mm, vma->vm_start +
- i*PAGE_SIZE, 0)
+ follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
: NULL;
dump_one_vdso_page(pg, upg);
}
#endif /* DEBUG */
/*
- * Keep a dummy vma_close for now, it will prevent VMA merging.
- */
-static void vdso_vma_close(struct vm_area_struct * vma)
-{
-}
-
-/*
- * Our nopage() function, maps in the actual vDSO kernel pages, they will
- * be mapped read-only by do_no_page(), and eventually COW'ed, either
- * right away for an initial write access, or by do_wp_page().
- */
-static struct page * vdso_vma_nopage(struct vm_area_struct * vma,
- unsigned long address, int *type)
-{
- unsigned long offset = address - vma->vm_start;
- struct page *pg;
-#ifdef CONFIG_PPC64
- void *vbase = test_thread_flag(TIF_32BIT) ?
- vdso32_kbase : vdso64_kbase;
-#else
- void *vbase = vdso32_kbase;
-#endif
-
- DBG("vdso_vma_nopage(current: %s, address: %016lx, off: %lx)\n",
- current->comm, address, offset);
-
- if (address < vma->vm_start || address > vma->vm_end)
- return NOPAGE_SIGBUS;
-
- /*
- * Last page is systemcfg.
- */
- if ((vma->vm_end - address) <= PAGE_SIZE)
- pg = virt_to_page(vdso_data);
- else
- pg = virt_to_page(vbase + offset);
-
- get_page(pg);
- DBG(" ->page count: %d\n", page_count(pg));
-
- return pg;
-}
-
-static struct vm_operations_struct vdso_vmops = {
- .close = vdso_vma_close,
- .nopage = vdso_vma_nopage,
-};
-
-/*
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
*/
int executable_stack)
{
struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
+ struct page **vdso_pagelist;
unsigned long vdso_pages;
unsigned long vdso_base;
+ int rc;
+
+ if (!vdso_ready)
+ return 0;
#ifdef CONFIG_PPC64
if (test_thread_flag(TIF_32BIT)) {
+ vdso_pagelist = vdso32_pagelist;
vdso_pages = vdso32_pages;
vdso_base = VDSO32_MBASE;
} else {
+ vdso_pagelist = vdso64_pagelist;
vdso_pages = vdso64_pages;
vdso_base = VDSO64_MBASE;
}
#else
+ vdso_pagelist = vdso32_pagelist;
vdso_pages = vdso32_pages;
vdso_base = VDSO32_MBASE;
#endif
- current->thread.vdso_base = 0;
+ current->mm->context.vdso_base = 0;
/* vDSO has a problem and was disabled, just don't "enable" it for the
* process
*/
if (vdso_pages == 0)
return 0;
-
- vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
- if (vma == NULL)
- return -ENOMEM;
-
- memset(vma, 0, sizeof(*vma));
-
/* Add a page to the vdso size for the data page */
vdso_pages ++;
* at vdso_base which is the "natural" base for it, but we might 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);
- if (vdso_base & ~PAGE_MASK) {
- kmem_cache_free(vm_area_cachep, vma);
- return (int)vdso_base;
+ if (IS_ERR_VALUE(vdso_base)) {
+ rc = vdso_base;
+ goto fail_mmapsem;
}
- current->thread.vdso_base = vdso_base;
-
- vma->vm_mm = mm;
- vma->vm_start = current->thread.vdso_base;
- vma->vm_end = vma->vm_start + (vdso_pages << PAGE_SHIFT);
-
/*
* our vma flags don't have VM_WRITE so by default, the process isn't
* allowed to write those pages.
* 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.
*/
- vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE |
- VM_MAYEXEC | VM_RESERVED;
- vma->vm_flags |= mm->def_flags;
- vma->vm_page_prot = protection_map[vma->vm_flags & 0x7];
- vma->vm_ops = &vdso_vmops;
+ rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+ VM_ALWAYSDUMP,
+ vdso_pagelist);
+ if (rc)
+ goto fail_mmapsem;
- down_write(&mm->mmap_sem);
- if (insert_vm_struct(mm, vma)) {
- up_write(&mm->mmap_sem);
- kmem_cache_free(vm_area_cachep, vma);
- return -ENOMEM;
- }
- mm->total_vm += (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
- up_write(&mm->mmap_sem);
+ /* Put vDSO base into mm struct */
+ current->mm->context.vdso_base = vdso_base;
+ up_write(&mm->mmap_sem);
return 0;
+
+ fail_mmapsem:
+ up_write(&mm->mmap_sem);
+ return rc;
}
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+ if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
+ return "[vdso]";
+ return NULL;
+}
+
+
+
static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname,
unsigned long *size)
{
return 0;
}
+
+static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
+ struct lib64_elfinfo *v64)
+{
+ void *start32;
+ unsigned long size32;
+
+#ifdef CONFIG_PPC64
+ void *start64;
+ unsigned long size64;
+
+ start64 = find_section64(v64->hdr, "__ftr_fixup", &size64);
+ if (start64)
+ do_feature_fixups(cur_cpu_spec->cpu_features,
+ start64, start64 + size64);
+
+ start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
+ if (start64)
+ do_feature_fixups(powerpc_firmware_features,
+ start64, start64 + size64);
+#endif /* CONFIG_PPC64 */
+
+ start32 = find_section32(v32->hdr, "__ftr_fixup", &size32);
+ if (start32)
+ do_feature_fixups(cur_cpu_spec->cpu_features,
+ start32, start32 + size32);
+
+#ifdef CONFIG_PPC64
+ start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
+ if (start32)
+ do_feature_fixups(powerpc_firmware_features,
+ start32, start32 + size32);
+#endif /* CONFIG_PPC64 */
+
+ return 0;
+}
+
static __init int vdso_fixup_alt_funcs(struct lib32_elfinfo *v32,
struct lib64_elfinfo *v64)
{
if (vdso_fixup_datapage(&v32, &v64))
return -1;
+ if (vdso_fixup_features(&v32, &v64))
+ return -1;
+
if (vdso_fixup_alt_funcs(&v32, &v64))
return -1;
}
-void __init vdso_init(void)
+static int __init vdso_init(void)
{
int i;
/*
* Fill up the "systemcfg" stuff for backward compatiblity
*/
- strcpy(vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
+ strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
vdso_data->version.major = SYSTEMCFG_MAJOR;
vdso_data->version.minor = SYSTEMCFG_MINOR;
vdso_data->processor = mfspr(SPRN_PVR);
- vdso_data->platform = _machine;
+ /*
+ * Fake the old platform number for pSeries and iSeries and add
+ * in LPAR bit if necessary
+ */
+ vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100;
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ vdso_data->platform |= 1;
vdso_data->physicalMemorySize = lmb_phys_mem_size();
vdso_data->dcache_size = ppc64_caches.dsize;
vdso_data->dcache_line_size = ppc64_caches.dline_size;
* Setup the syscall map in the vDOS
*/
vdso_setup_syscall_map();
+
/*
* Initialize the vDSO images in memory, that is do necessary
* fixups of vDSO symbols, locate trampolines, etc...
#ifdef CONFIG_PPC64
vdso64_pages = 0;
#endif
- return;
+ return 0;
}
/* Make sure pages are in the correct state */
+ vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 2),
+ GFP_KERNEL);
+ BUG_ON(vdso32_pagelist == NULL);
for (i = 0; i < vdso32_pages; i++) {
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
-
+ vdso32_pagelist[i] = pg;
}
+ vdso32_pagelist[i++] = virt_to_page(vdso_data);
+ vdso32_pagelist[i] = NULL;
+
#ifdef CONFIG_PPC64
+ vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 2),
+ GFP_KERNEL);
+ BUG_ON(vdso64_pagelist == NULL);
for (i = 0; i < vdso64_pages; i++) {
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
+ vdso64_pagelist[i] = pg;
}
+ vdso64_pagelist[i++] = virt_to_page(vdso_data);
+ vdso64_pagelist[i] = NULL;
#endif /* CONFIG_PPC64 */
get_page(virt_to_page(vdso_data));
+
+ smp_wmb();
+ vdso_ready = 1;
+
+ return 0;
}
+arch_initcall(vdso_init);
int in_gate_area_no_task(unsigned long addr)
{