aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/vdso.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kernel/vdso.c')
-rw-r--r--arch/powerpc/kernel/vdso.c130
1 files changed, 95 insertions, 35 deletions
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d3437c4c4a6..ce74c335a6a 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -1,3 +1,4 @@
+
/*
* Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
* <benh@kernel.crashing.org>
@@ -8,7 +9,6 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/module.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
@@ -21,21 +21,20 @@
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
-#include <asm/lmb.h>
+#include <asm/prom.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"
+#include <asm/setup.h>
#undef DEBUG
@@ -48,6 +47,9 @@
/* Max supported size for symbol names */
#define MAX_SYMNAME 64
+/* The alignment of the vDSO */
+#define VDSO_ALIGNMENT (1 << 16)
+
extern char vdso32_start, vdso32_end;
static void *vdso32_kbase = &vdso32_start;
static unsigned int vdso32_pages;
@@ -73,7 +75,7 @@ static int vdso_ready;
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;
/* Format of the patch table */
@@ -110,6 +112,10 @@ static struct vdso_patch_def vdso_patches[] = {
CPU_FTR_USE_TB, 0,
"__kernel_get_tbfreq", NULL
},
+ {
+ CPU_FTR_USE_TB, 0,
+ "__kernel_time", NULL
+ },
};
/*
@@ -141,7 +147,7 @@ static void dump_one_vdso_page(struct page *pg, struct page *upg)
printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
page_count(pg),
pg->flags);
- if (upg/* && pg != upg*/) {
+ if (upg && !IS_ERR(upg) /* && pg != upg*/) {
printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
<< PAGE_SHIFT),
page_count(upg),
@@ -154,7 +160,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
{
int i;
- if (!vma || test_thread_flag(TIF_32BIT)) {
+ if (!vma || is_32bit_task()) {
printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
for (i=0; i<vdso32_pages; i++) {
struct page *pg = virt_to_page(vdso32_kbase +
@@ -165,7 +171,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
dump_one_vdso_page(pg, upg);
}
}
- if (!vma || !test_thread_flag(TIF_32BIT)) {
+ if (!vma || !is_32bit_task()) {
printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
for (i=0; i<vdso64_pages; i++) {
struct page *pg = virt_to_page(vdso64_kbase +
@@ -183,8 +189,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
* This is called from binfmt_elf, we create the special vma for the
* vDSO and insert it into the mm struct tree
*/
-int arch_setup_additional_pages(struct linux_binprm *bprm,
- int executable_stack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
struct page **vdso_pagelist;
@@ -196,14 +201,19 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
return 0;
#ifdef CONFIG_PPC64
- if (test_thread_flag(TIF_32BIT)) {
+ if (is_32bit_task()) {
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;
+ /*
+ * On 64bit we don't have a preferred map address. This
+ * allows get_unmapped_area to find an area near other mmaps
+ * and most likely share a SLB entry.
+ */
+ vdso_base = 0;
}
#else
vdso_pagelist = vdso32_pagelist;
@@ -225,15 +235,28 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
* pick a base address for the vDSO in process space. We try to put it
* at vdso_base which is the "natural" base for it, but we might fail
* and end up putting it elsewhere.
+ * Add enough to the size so that the result can be aligned.
*/
down_write(&mm->mmap_sem);
vdso_base = get_unmapped_area(NULL, vdso_base,
- vdso_pages << PAGE_SHIFT, 0, 0);
+ (vdso_pages << PAGE_SHIFT) +
+ ((VDSO_ALIGNMENT - 1) & PAGE_MASK),
+ 0, 0);
if (IS_ERR_VALUE(vdso_base)) {
rc = vdso_base;
goto fail_mmapsem;
}
+ /* Add required alignment. */
+ vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
+
+ /*
+ * 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.
@@ -242,23 +265,16 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
* 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)
+ if (rc) {
+ current->mm->context.vdso_base = 0;
goto fail_mmapsem;
-
- /* Put vDSO base into mm struct */
- current->mm->context.vdso_base = vdso_base;
+ }
up_write(&mm->mmap_sem);
return 0;
@@ -566,10 +582,20 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
do_feature_fixups(cur_cpu_spec->cpu_features,
start64, start64 + size64);
+ start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64);
+ if (start64)
+ do_feature_fixups(cur_cpu_spec->mmu_features,
+ start64, start64 + size64);
+
start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
if (start64)
do_feature_fixups(powerpc_firmware_features,
start64, start64 + size64);
+
+ start64 = find_section64(v64->hdr, "__lwsync_fixup", &size64);
+ if (start64)
+ do_lwsync_fixups(cur_cpu_spec->cpu_features,
+ start64, start64 + size64);
#endif /* CONFIG_PPC64 */
start32 = find_section32(v32->hdr, "__ftr_fixup", &size32);
@@ -577,6 +603,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
do_feature_fixups(cur_cpu_spec->cpu_features,
start32, start32 + size32);
+ start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32);
+ if (start32)
+ do_feature_fixups(cur_cpu_spec->mmu_features,
+ start32, start32 + size32);
+
#ifdef CONFIG_PPC64
start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
if (start32)
@@ -584,6 +615,11 @@ static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
start32, start32 + size32);
#endif /* CONFIG_PPC64 */
+ start32 = find_section32(v32->hdr, "__lwsync_fixup", &size32);
+ if (start32)
+ do_lwsync_fixups(cur_cpu_spec->cpu_features,
+ start32, start32 + size32);
+
return 0;
}
@@ -673,6 +709,32 @@ static void __init vdso_setup_syscall_map(void)
}
}
+#ifdef CONFIG_PPC64
+int vdso_getcpu_init(void)
+{
+ unsigned long cpu, node, val;
+
+ /*
+ * SPRG_VDSO contains the CPU in the bottom 16 bits and the NUMA node
+ * in the next 16 bits. The VDSO uses this to implement getcpu().
+ */
+ cpu = get_cpu();
+ WARN_ON_ONCE(cpu > 0xffff);
+
+ node = cpu_to_node(cpu);
+ WARN_ON_ONCE(node > 0xffff);
+
+ val = (cpu & 0xfff) | ((node & 0xffff) << 16);
+ mtspr(SPRN_SPRG_VDSO_WRITE, val);
+ get_paca()->sprg_vdso = val;
+
+ put_cpu();
+
+ return 0;
+}
+/* We need to call this before SMP init */
+early_initcall(vdso_getcpu_init);
+#endif
static int __init vdso_init(void)
{
@@ -680,20 +742,20 @@ static int __init vdso_init(void)
#ifdef CONFIG_PPC64
/*
- * Fill up the "systemcfg" stuff for backward compatiblity
+ * Fill up the "systemcfg" stuff for backward compatibility
*/
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);
/*
- * Fake the old platform number for pSeries and iSeries and add
+ * Fake the old platform number for pSeries and add
* in LPAR bit if necessary
*/
- vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100;
+ vdso_data->platform = 0x100;
if (firmware_has_feature(FW_FEATURE_LPAR))
vdso_data->platform |= 1;
- vdso_data->physicalMemorySize = lmb_phys_mem_size();
+ vdso_data->physicalMemorySize = memblock_phys_mem_size();
vdso_data->dcache_size = ppc64_caches.dsize;
vdso_data->dcache_line_size = ppc64_caches.dline_size;
vdso_data->icache_size = ppc64_caches.isize;
@@ -777,21 +839,19 @@ static int __init vdso_init(void)
return 0;
}
-#ifdef CONFIG_PPC_MERGE
arch_initcall(vdso_init);
-#endif
-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;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 02:03:39 +0000