sh: Initial vsyscall page support.

This implements initial support for the vsyscall page on SH.
At the moment we leave it configurable due to having nommu
to support from the same code base. We hook it up for the
signal trampoline return at present, with more to be added
later, once uClibc catches up.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This commit is contained in:
Paul Mundt 2006-09-27 18:33:49 +09:00
parent 8c12b5dc13
commit 19f9a34f87
19 changed files with 473 additions and 17 deletions

View File

@ -9,6 +9,7 @@ obj-y := process.o signal.o entry.o traps.o irq.o \
io.o io_generic.o sh_ksyms.o syscalls.o
obj-y += cpu/ timers/
obj-$(CONFIG_VSYSCALL) += vsyscall/
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_CF_ENABLER) += cf-enabler.o

View File

@ -355,7 +355,7 @@ struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *ne
else if (next->thread.ubc_pc && next->mm) {
int asid = 0;
#ifdef CONFIG_MMU
asid |= next->mm->context & MMU_CONTEXT_ASID_MASK;
asid |= next->mm->context.id & MMU_CONTEXT_ASID_MASK;
#endif
ubc_set_tracing(asid, next->thread.ubc_pc);
} else {

View File

@ -8,7 +8,6 @@
* SuperH version: Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
*
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
@ -21,6 +20,7 @@
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/tty.h>
#include <linux/elf.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
@ -29,8 +29,6 @@
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#undef DEBUG
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
/*
@ -312,6 +310,11 @@ get_sigframe(struct k_sigaction *ka, unsigned long sp, size_t frame_size)
return (void __user *)((sp - frame_size) & -8ul);
}
/* These symbols are defined with the addresses in the vsyscall page.
See vsyscall-trapa.S. */
extern void __user __kernel_sigreturn;
extern void __user __kernel_rt_sigreturn;
static int setup_frame(int sig, struct k_sigaction *ka,
sigset_t *set, struct pt_regs *regs)
{
@ -340,6 +343,10 @@ static int setup_frame(int sig, struct k_sigaction *ka,
already in userspace. */
if (ka->sa.sa_flags & SA_RESTORER) {
regs->pr = (unsigned long) ka->sa.sa_restorer;
#ifdef CONFIG_VSYSCALL
} else if (likely(current->mm->context.vdso)) {
regs->pr = VDSO_SYM(&__kernel_sigreturn);
#endif
} else {
/* Generate return code (system call to sigreturn) */
err |= __put_user(MOVW(7), &frame->retcode[0]);
@ -416,6 +423,10 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
already in userspace. */
if (ka->sa.sa_flags & SA_RESTORER) {
regs->pr = (unsigned long) ka->sa.sa_restorer;
#ifdef CONFIG_VSYSCALL
} else if (likely(current->mm->context.vdso)) {
regs->pr = VDSO_SYM(&__kernel_rt_sigreturn);
#endif
} else {
/* Generate return code (system call to rt_sigreturn) */
err |= __put_user(MOVW(7), &frame->retcode[0]);

View File

@ -0,0 +1,36 @@
obj-y += vsyscall.o vsyscall-syscall.o
$(obj)/vsyscall-syscall.o: \
$(foreach F,trapa,$(obj)/vsyscall-$F.so)
# Teach kbuild about targets
targets += $(foreach F,trapa,vsyscall-$F.o vsyscall-$F.so)
targets += vsyscall-note.o vsyscall.lds
# The DSO images are built using a special linker script
quiet_cmd_syscall = SYSCALL $@
cmd_syscall = $(CC) -nostdlib $(SYSCFLAGS_$(@F)) \
-Wl,-T,$(filter-out FORCE,$^) -o $@
export CPPFLAGS_vsyscall.lds += -P -C -Ush
vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \
$(call ld-option, -Wl$(comma)--hash-style=sysv)
SYSCFLAGS_vsyscall-trapa.so = $(vsyscall-flags)
$(obj)/vsyscall-trapa.so: \
$(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
$(call if_changed,syscall)
# We also create a special relocatable object that should mirror the symbol
# table and layout of the linked DSO. With ld -R we can then refer to
# these symbols in the kernel code rather than hand-coded addresses.
extra-y += vsyscall-syms.o
$(obj)/built-in.o: $(obj)/vsyscall-syms.o
$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o
SYSCFLAGS_vsyscall-syms.o = -r
$(obj)/vsyscall-syms.o: $(src)/vsyscall.lds \
$(obj)/vsyscall-trapa.o $(obj)/vsyscall-note.o FORCE
$(call if_changed,syscall)

View File

@ -0,0 +1,25 @@
/*
* This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
* Here we can supply some information useful to userland.
*/
#include <linux/uts.h>
#include <linux/version.h>
#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \
.section name, flags; \
.balign 4; \
.long 1f - 0f; /* name length */ \
.long 3f - 2f; /* data length */ \
.long type; /* note type */ \
0: .asciz vendor; /* vendor name */ \
1: .balign 4; \
2:
#define ASM_ELF_NOTE_END \
3: .balign 4; /* pad out section */ \
.previous
ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
.long LINUX_VERSION_CODE
ASM_ELF_NOTE_END

View File

@ -0,0 +1,39 @@
#include <asm/unistd.h>
.text
.balign 32
.globl __kernel_sigreturn
.type __kernel_sigreturn,@function
__kernel_sigreturn:
.LSTART_sigreturn:
mov.w 1f, r3
trapa #0x10
or r0, r0
or r0, r0
or r0, r0
or r0, r0
or r0, r0
1: .short __NR_sigreturn
.LEND_sigreturn:
.size __kernel_sigreturn,.-.LSTART_sigreturn
.balign 32
.globl __kernel_rt_sigreturn
.type __kernel_rt_sigreturn,@function
__kernel_rt_sigreturn:
.LSTART_rt_sigreturn:
mov.w 1f, r3
trapa #0x10
or r0, r0
or r0, r0
or r0, r0
or r0, r0
or r0, r0
1: .short __NR_rt_sigreturn
.LEND_rt_sigreturn:
.size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
.section .eh_frame,"a",@progbits
.previous

View File

@ -0,0 +1,10 @@
#include <linux/init.h>
__INITDATA
.globl vsyscall_trapa_start, vsyscall_trapa_end
vsyscall_trapa_start:
.incbin "arch/sh/kernel/vsyscall/vsyscall-trapa.so"
vsyscall_trapa_end:
__FINIT

View File

@ -0,0 +1,42 @@
.text
.globl __kernel_vsyscall
.type __kernel_vsyscall,@function
__kernel_vsyscall:
.LSTART_vsyscall:
/* XXX: We'll have to do something here once we opt to use the vDSO
* page for something other than the signal trampoline.. as well as
* fill out .eh_frame -- PFM. */
.LEND_vsyscall:
.size __kernel_vsyscall,.-.LSTART_vsyscall
.previous
.section .eh_frame,"a",@progbits
.LCIE:
.ualong .LCIE_end - .LCIE_start
.LCIE_start:
.ualong 0 /* CIE ID */
.byte 0x1 /* Version number */
.string "zRS" /* NUL-terminated augmentation string */
.uleb128 0x1 /* Code alignment factor */
.sleb128 -4 /* Data alignment factor */
.byte 0x11 /* Return address register column */
/* Augmentation length and data (none) */
.byte 0xc /* DW_CFA_def_cfa */
.uleb128 0xf /* r15 */
.uleb128 0x0 /* offset 0 */
.align 2
.LCIE_end:
.ualong .LFDE_end-.LFDE_start /* Length FDE */
.LFDE_start:
.ualong .LCIE /* CIE pointer */
.ualong .LSTART_vsyscall-. /* start address */
.ualong .LEND_vsyscall-.LSTART_vsyscall
.uleb128 0
.align 2
.LFDE_end:
.previous
/* Get the common code for the sigreturn entry points */
#include "vsyscall-sigreturn.S"

View File

@ -0,0 +1,150 @@
/*
* arch/sh/kernel/vsyscall.c
*
* Copyright (C) 2006 Paul Mundt
*
* vDSO randomization
* Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/gfp.h>
#include <linux/module.h>
#include <linux/elf.h>
/*
* Should the kernel map a VDSO page into processes and pass its
* address down to glibc upon exec()?
*/
unsigned int __read_mostly vdso_enabled = 1;
EXPORT_SYMBOL_GPL(vdso_enabled);
static int __init vdso_setup(char *s)
{
vdso_enabled = simple_strtoul(s, NULL, 0);
return 1;
}
__setup("vdso=", vdso_setup);
/*
* These symbols are defined by vsyscall.o to mark the bounds
* of the ELF DSO images included therein.
*/
extern const char vsyscall_trapa_start, vsyscall_trapa_end;
static void *syscall_page;
int __init vsyscall_init(void)
{
syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
/*
* XXX: Map this page to a fixmap entry if we get around
* to adding the page to ELF core dumps
*/
memcpy(syscall_page,
&vsyscall_trapa_start,
&vsyscall_trapa_end - &vsyscall_trapa_start);
return 0;
}
static struct page *syscall_vma_nopage(struct vm_area_struct *vma,
unsigned long address, int *type)
{
unsigned long offset = address - vma->vm_start;
struct page *page;
if (address < vma->vm_start || address > vma->vm_end)
return NOPAGE_SIGBUS;
page = virt_to_page(syscall_page + offset);
get_page(page);
return page;
}
/* Prevent VMA merging */
static void syscall_vma_close(struct vm_area_struct *vma)
{
}
static struct vm_operations_struct syscall_vm_ops = {
.nopage = syscall_vma_nopage,
.close = syscall_vma_close,
};
/* Setup a VMA at program startup for the vsyscall page */
int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr;
int ret;
down_write(&mm->mmap_sem);
addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
vma = kmem_cache_zalloc(vm_area_cachep, SLAB_KERNEL);
if (!vma) {
ret = -ENOMEM;
goto up_fail;
}
vma->vm_start = addr;
vma->vm_end = addr + PAGE_SIZE;
/* MAYWRITE to allow gdb to COW and set breakpoints */
vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE;
vma->vm_flags |= mm->def_flags;
vma->vm_page_prot = protection_map[vma->vm_flags & 7];
vma->vm_ops = &syscall_vm_ops;
vma->vm_mm = mm;
ret = insert_vm_struct(mm, vma);
if (unlikely(ret)) {
kmem_cache_free(vm_area_cachep, vma);
goto up_fail;
}
current->mm->context.vdso = (void *)addr;
mm->total_vm++;
up_fail:
up_write(&mm->mmap_sem);
return ret;
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
return "[vdso]";
return NULL;
}
struct vm_area_struct *get_gate_vma(struct task_struct *task)
{
return NULL;
}
int in_gate_area(struct task_struct *task, unsigned long address)
{
return 0;
}
int in_gate_area_no_task(unsigned long address)
{
return 0;
}

View File

@ -0,0 +1,74 @@
/*
* Linker script for vsyscall DSO. The vsyscall page is an ELF shared
* object prelinked to its virtual address, and with only one read-only
* segment (that fits in one page). This script controls its layout.
*/
#include <asm/asm-offsets.h>
#ifdef CONFIG_CPU_LITTLE_ENDIAN
OUTPUT_FORMAT("elf32-sh-linux", "elf32-sh-linux", "elf32-sh-linux")
#else
OUTPUT_FORMAT("elf32-shbig-linux", "elf32-shbig-linux", "elf32-shbig-linux")
#endif
OUTPUT_ARCH(sh)
/* The ELF entry point can be used to set the AT_SYSINFO value. */
ENTRY(__kernel_vsyscall);
SECTIONS
{
. = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
.dynsym : { *(.dynsym) }
.dynstr : { *(.dynstr) }
.gnu.version : { *(.gnu.version) }
.gnu.version_d : { *(.gnu.version_d) }
.gnu.version_r : { *(.gnu.version_r) }
/* This linker script is used both with -r and with -shared.
For the layouts to match, we need to skip more than enough
space for the dynamic symbol table et al. If this amount
is insufficient, ld -shared will barf. Just increase it here. */
. = 0x400;
.text : { *(.text) } :text =0x90909090
.note : { *(.note.*) } :text :note
.eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
.eh_frame : { KEEP (*(.eh_frame)) } :text
.dynamic : { *(.dynamic) } :text :dynamic
.useless : {
*(.got.plt) *(.got)
*(.data .data.* .gnu.linkonce.d.*)
*(.dynbss)
*(.bss .bss.* .gnu.linkonce.b.*)
} :text
}
/*
* We must supply the ELF program headers explicitly to get just one
* PT_LOAD segment, and set the flags explicitly to make segments read-only.
*/
PHDRS
{
text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
note PT_NOTE FLAGS(4); /* PF_R */
eh_frame_hdr 0x6474e550; /* PT_GNU_EH_FRAME, but ld doesn't match the name */
}
/*
* This controls what symbols we export from the DSO.
*/
VERSION
{
LINUX_2.6 {
global:
__kernel_vsyscall;
__kernel_sigreturn;
__kernel_rt_sigreturn;
local: *;
};
}

View File

@ -223,6 +223,19 @@ config 32BIT
32-bits through the SH-4A PMB. If this is not set, legacy
29-bit physical addressing will be used.
config VSYSCALL
bool "Support vsyscall page"
depends on MMU
default y
help
This will enable support for the kernel mapping a vDSO page
in process space, and subsequently handing down the entry point
to the libc through the ELF auxiliary vector.
From the kernel side this is used for the signal trampoline.
For systems with an MMU that can afford to give up a page,
(the default value) say Y.
choice
prompt "HugeTLB page size"
depends on HUGETLB_PAGE && CPU_SH4 && MMU

View File

@ -286,6 +286,9 @@ void __init mem_init(void)
initsize >> 10);
p3_cache_init();
/* Initialize the vDSO */
vsyscall_init();
}
void free_initmem(void)

View File

@ -14,12 +14,12 @@
void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
{
if (vma->vm_mm && vma->vm_mm->context != NO_CONTEXT) {
if (vma->vm_mm && vma->vm_mm->context.id != NO_CONTEXT) {
unsigned long flags;
unsigned long asid;
unsigned long saved_asid = MMU_NO_ASID;
asid = vma->vm_mm->context & MMU_CONTEXT_ASID_MASK;
asid = vma->vm_mm->context.id & MMU_CONTEXT_ASID_MASK;
page &= PAGE_MASK;
local_irq_save(flags);
@ -39,20 +39,21 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
{
struct mm_struct *mm = vma->vm_mm;
if (mm->context != NO_CONTEXT) {
if (mm->context.id != NO_CONTEXT) {
unsigned long flags;
int size;
local_irq_save(flags);
size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
if (size > (MMU_NTLB_ENTRIES/4)) { /* Too many TLB to flush */
mm->context = NO_CONTEXT;
mm->context.id = NO_CONTEXT;
if (mm == current->mm)
activate_context(mm);
} else {
unsigned long asid = mm->context&MMU_CONTEXT_ASID_MASK;
unsigned long asid;
unsigned long saved_asid = MMU_NO_ASID;
asid = mm->context.id & MMU_CONTEXT_ASID_MASK;
start &= PAGE_MASK;
end += (PAGE_SIZE - 1);
end &= PAGE_MASK;
@ -81,9 +82,10 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
if (size > (MMU_NTLB_ENTRIES/4)) { /* Too many TLB to flush */
flush_tlb_all();
} else {
unsigned long asid = init_mm.context&MMU_CONTEXT_ASID_MASK;
unsigned long asid;
unsigned long saved_asid = get_asid();
asid = init_mm.context.id & MMU_CONTEXT_ASID_MASK;
start &= PAGE_MASK;
end += (PAGE_SIZE - 1);
end &= PAGE_MASK;
@ -101,11 +103,11 @@ void flush_tlb_mm(struct mm_struct *mm)
{
/* Invalidate all TLB of this process. */
/* Instead of invalidating each TLB, we get new MMU context. */
if (mm->context != NO_CONTEXT) {
if (mm->context.id != NO_CONTEXT) {
unsigned long flags;
local_irq_save(flags);
mm->context = NO_CONTEXT;
mm->context.id = NO_CONTEXT;
if (mm == current->mm)
activate_context(mm);
local_irq_restore(flags);

View File

@ -1,4 +1,18 @@
#ifndef __ASM_SH_AUXVEC_H
#define __ASM_SH_AUXVEC_H
/*
* Architecture-neutral AT_ values in 0-17, leave some room
* for more of them.
*/
#ifdef CONFIG_VSYSCALL
/*
* Only define this in the vsyscall case, the entry point to
* the vsyscall page gets placed here. The kernel will attempt
* to build a gate VMA we don't care about otherwise..
*/
#define AT_SYSINFO_EHDR 33
#endif
#endif /* __ASM_SH_AUXVEC_H */

View File

@ -121,4 +121,24 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
#endif
#ifdef CONFIG_VSYSCALL
/* vDSO has arch_setup_additional_pages */
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack);
extern unsigned int vdso_enabled;
extern void __kernel_vsyscall;
#define VDSO_BASE ((unsigned long)current->mm->context.vdso)
#define VDSO_SYM(x) (VDSO_BASE + (unsigned long)(x))
#define ARCH_DLINFO \
do { \
if (vdso_enabled) \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \
} while (0)
#endif /* CONFIG_VSYSCALL */
#endif /* __ASM_SH_ELF_H */

View File

@ -11,7 +11,12 @@ typedef struct {
#else
/* Default "unsigned long" context */
typedef unsigned long mm_context_t;
typedef unsigned long mm_context_id_t;
typedef struct {
mm_context_id_t id;
void *vdso;
} mm_context_t;
#endif /* CONFIG_MMU */

View File

@ -49,7 +49,7 @@ get_mmu_context(struct mm_struct *mm)
unsigned long mc = mmu_context_cache;
/* Check if we have old version of context. */
if (((mm->context ^ mc) & MMU_CONTEXT_VERSION_MASK) == 0)
if (((mm->context.id ^ mc) & MMU_CONTEXT_VERSION_MASK) == 0)
/* It's up to date, do nothing */
return;
@ -68,7 +68,7 @@ get_mmu_context(struct mm_struct *mm)
if (!mc)
mmu_context_cache = mc = MMU_CONTEXT_FIRST_VERSION;
}
mm->context = mc;
mm->context.id = mc;
}
/*
@ -78,7 +78,7 @@ get_mmu_context(struct mm_struct *mm)
static __inline__ int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
mm->context = NO_CONTEXT;
mm->context.id = NO_CONTEXT;
return 0;
}
@ -123,7 +123,7 @@ static __inline__ unsigned long get_asid(void)
static __inline__ void activate_context(struct mm_struct *mm)
{
get_mmu_context(mm);
set_asid(mm->context & MMU_CONTEXT_ASID_MASK);
set_asid(mm->context.id & MMU_CONTEXT_ASID_MASK);
}
/* MMU_TTB can be used for optimizing the fault handling.

View File

@ -117,5 +117,10 @@ typedef struct { unsigned long pgprot; } pgprot_t;
#include <asm-generic/memory_model.h>
#include <asm-generic/page.h>
/* vDSO support */
#ifdef CONFIG_VSYSCALL
#define __HAVE_ARCH_GATE_AREA
#endif
#endif /* __KERNEL__ */
#endif /* __ASM_SH_PAGE_H */

View File

@ -276,5 +276,11 @@ static inline void prefetch(void *x)
#define prefetchw(x) prefetch(x)
#endif
#ifdef CONFIG_VSYSCALL
extern int vsyscall_init(void);
#else
#define vsyscall_init() do { } while (0)
#endif
#endif /* __KERNEL__ */
#endif /* __ASM_SH_PROCESSOR_H */