OpenCloudOS-Kernel/arch/arm/kernel/process.c

471 lines
11 KiB
C
Raw Normal View History

/*
* linux/arch/arm/kernel/process.c
*
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Original Copyright (C) 1995 Linus Torvalds
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <stdarg.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/elfcore.h>
#include <linux/pm.h>
#include <linux/tick.h>
#include <linux/utsname.h>
#include <linux/uaccess.h>
#include <linux/random.h>
#include <linux/hw_breakpoint.h>
#include <linux/leds.h>
#include <asm/processor.h>
#include <asm/thread_notify.h>
#include <asm/stacktrace.h>
#include <asm/system_misc.h>
#include <asm/mach/time.h>
#include <asm/tls.h>
#include <asm/vdso.h>
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
static const char *processor_modes[] __maybe_unused = {
"USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
"UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",
"USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "MON_32" , "ABT_32" ,
"UK8_32" , "UK9_32" , "HYP_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32"
};
static const char *isa_modes[] __maybe_unused = {
"ARM" , "Thumb" , "Jazelle", "ThumbEE"
};
/*
* This is our default idle handler.
*/
void (*arm_pm_idle)(void);
/*
* Called from the core idle loop.
*/
void arch_cpu_idle(void)
{
if (arm_pm_idle)
arm_pm_idle();
else
cpu_do_idle();
local_irq_enable();
}
void arch_cpu_idle_prepare(void)
{
local_fiq_enable();
}
void arch_cpu_idle_enter(void)
{
ledtrig_cpu(CPU_LED_IDLE_START);
#ifdef CONFIG_PL310_ERRATA_769419
wmb();
#endif
}
void arch_cpu_idle_exit(void)
{
ledtrig_cpu(CPU_LED_IDLE_END);
}
void __show_regs(struct pt_regs *regs)
{
unsigned long flags;
char buf[64];
#ifndef CONFIG_CPU_V7M
unsigned int domain, fs;
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
/*
* Get the domain register for the parent context. In user
* mode, we don't save the DACR, so lets use what it should
* be. For other modes, we place it after the pt_regs struct.
*/
if (user_mode(regs)) {
domain = DACR_UACCESS_ENABLE;
fs = get_fs();
} else {
domain = to_svc_pt_regs(regs)->dacr;
fs = to_svc_pt_regs(regs)->addr_limit;
}
#else
domain = get_domain();
fs = get_fs();
#endif
#endif
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
show_regs_print_info(KERN_DEFAULT);
printk("PC is at %pS\n", (void *)instruction_pointer(regs));
printk("LR is at %pS\n", (void *)regs->ARM_lr);
printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n",
regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr);
printk("sp : %08lx ip : %08lx fp : %08lx\n",
regs->ARM_sp, regs->ARM_ip, regs->ARM_fp);
printk("r10: %08lx r9 : %08lx r8 : %08lx\n",
regs->ARM_r10, regs->ARM_r9,
regs->ARM_r8);
printk("r7 : %08lx r6 : %08lx r5 : %08lx r4 : %08lx\n",
regs->ARM_r7, regs->ARM_r6,
regs->ARM_r5, regs->ARM_r4);
printk("r3 : %08lx r2 : %08lx r1 : %08lx r0 : %08lx\n",
regs->ARM_r3, regs->ARM_r2,
regs->ARM_r1, regs->ARM_r0);
flags = regs->ARM_cpsr;
buf[0] = flags & PSR_N_BIT ? 'N' : 'n';
buf[1] = flags & PSR_Z_BIT ? 'Z' : 'z';
buf[2] = flags & PSR_C_BIT ? 'C' : 'c';
buf[3] = flags & PSR_V_BIT ? 'V' : 'v';
buf[4] = '\0';
#ifndef CONFIG_CPU_V7M
{
const char *segment;
if ((domain & domain_mask(DOMAIN_USER)) ==
domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
segment = "none";
else if (fs == KERNEL_DS)
segment = "kernel";
else
segment = "user";
printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n",
buf, interrupts_enabled(regs) ? "n" : "ff",
fast_interrupts_enabled(regs) ? "n" : "ff",
processor_modes[processor_mode(regs)],
isa_modes[isa_mode(regs)], segment);
}
#else
printk("xPSR: %08lx\n", regs->ARM_cpsr);
#endif
#ifdef CONFIG_CPU_CP15
{
unsigned int ctrl;
buf[0] = '\0';
#ifdef CONFIG_CPU_CP15_MMU
{
unsigned int transbase;
asm("mrc p15, 0, %0, c2, c0\n\t"
: "=r" (transbase));
snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x",
transbase, domain);
}
#endif
asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl));
printk("Control: %08x%s\n", ctrl, buf);
}
#endif
}
void show_regs(struct pt_regs * regs)
{
__show_regs(regs);
dump_stack();
}
ATOMIC_NOTIFIER_HEAD(thread_notify_head);
EXPORT_SYMBOL_GPL(thread_notify_head);
/*
* Free current thread data structures etc..
*/
exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Jonas Bonn <jonas@southpole.se> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:20 +08:00
void exit_thread(struct task_struct *tsk)
{
exit_thread: accept a task parameter to be exited We need to call exit_thread from copy_process in a fail path. So make it accept task_struct as a parameter. [v2] * s390: exit_thread_runtime_instr doesn't make sense to be called for non-current tasks. * arm: fix the comment in vfp_thread_copy * change 'me' to 'tsk' for task_struct * now we can change only archs that actually have exit_thread [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Jiri Slaby <jslaby@suse.cz> Cc: "David S. Miller" <davem@davemloft.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Chris Zankel <chris@zankel.net> Cc: David Howells <dhowells@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Jonas Bonn <jonas@southpole.se> Cc: Koichi Yasutake <yasutake.koichi@jp.panasonic.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mikael Starvik <starvik@axis.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <linux@arm.linux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:20 +08:00
thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk));
}
void flush_thread(void)
{
struct thread_info *thread = current_thread_info();
struct task_struct *tsk = current;
flush_ptrace_hw_breakpoint(tsk);
memset(thread->used_cp, 0, sizeof(thread->used_cp));
memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
memset(&thread->fpstate, 0, sizeof(union fp_state));
flush_tls();
thread_notify(THREAD_NOTIFY_FLUSH, thread);
}
void release_thread(struct task_struct *dead_task)
{
}
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
int
copy_thread(unsigned long clone_flags, unsigned long stack_start,
unsigned long stk_sz, struct task_struct *p)
{
struct thread_info *thread = task_thread_info(p);
struct pt_regs *childregs = task_pt_regs(p);
memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
#ifdef CONFIG_CPU_USE_DOMAINS
/*
* Copy the initial value of the domain access control register
* from the current thread: thread->addr_limit will have been
* copied from the current thread via setup_thread_stack() in
* kernel/fork.c
*/
thread->cpu_domain = get_domain();
#endif
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->ARM_r0 = 0;
if (stack_start)
childregs->ARM_sp = stack_start;
} else {
memset(childregs, 0, sizeof(struct pt_regs));
thread->cpu_context.r4 = stk_sz;
thread->cpu_context.r5 = stack_start;
childregs->ARM_cpsr = SVC_MODE;
}
thread->cpu_context.pc = (unsigned long)ret_from_fork;
thread->cpu_context.sp = (unsigned long)childregs;
clear_ptrace_hw_breakpoint(p);
if (clone_flags & CLONE_SETTLS)
thread->tp_value[0] = childregs->ARM_r3;
thread->tp_value[1] = get_tpuser();
thread_notify(THREAD_NOTIFY_COPY, thread);
#ifdef CONFIG_STACKPROTECTOR_PER_TASK
thread->stack_canary = p->stack_canary;
#endif
return 0;
}
/*
* Fill in the task's elfregs structure for a core dump.
*/
int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs)
{
elf_core_copy_regs(elfregs, task_pt_regs(t));
return 1;
}
/*
* fill in the fpe structure for a core dump...
*/
int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
{
struct thread_info *thread = current_thread_info();
int used_math = thread->used_cp[1] | thread->used_cp[2];
if (used_math)
memcpy(fp, &thread->fpstate.soft, sizeof (*fp));
return used_math != 0;
}
EXPORT_SYMBOL(dump_fpu);
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
frame.lr = 0; /* recovered from the stack */
frame.pc = thread_saved_pc(p);
stack_page = (unsigned long)task_stack_page(p);
do {
if (frame.sp < stack_page ||
frame.sp >= stack_page + THREAD_SIZE ||
unwind_frame(&frame) < 0)
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
} while (count ++ < 16);
return 0;
}
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
return randomize_page(mm->brk, 0x02000000);
}
#ifdef CONFIG_MMU
#ifdef CONFIG_KUSER_HELPERS
/*
* The vectors page is always readable from user space for the
* atomic helpers. Insert it into the gate_vma so that it is visible
* through ptrace and /proc/<pid>/mem.
*/
static struct vm_area_struct gate_vma;
static int __init gate_vma_init(void)
{
vma_init(&gate_vma, NULL);
gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
gate_vma.vm_start = 0xffff0000;
gate_vma.vm_end = 0xffff0000 + PAGE_SIZE;
gate_vma.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC;
return 0;
}
arch_initcall(gate_vma_init);
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
return &gate_vma;
}
int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
}
int in_gate_area_no_mm(unsigned long addr)
{
return in_gate_area(NULL, addr);
}
#define is_gate_vma(vma) ((vma) == &gate_vma)
#else
#define is_gate_vma(vma) 0
#endif
const char *arch_vma_name(struct vm_area_struct *vma)
{
return is_gate_vma(vma) ? "[vectors]" : NULL;
}
/* If possible, provide a placement hint at a random offset from the
ARM: 8331/1: VDSO initialization, mapping, and synchronization Initialize the VDSO page list at boot, install the VDSO mapping at exec time, and update the data page during timer ticks. This code is not built if CONFIG_VDSO is not enabled. Account for the VDSO length when randomizing the offset from the stack. The [vdso] and [vvar] pages are placed immediately following the sigpage with separate _install_special_mapping calls. We want to "penalize" systems lacking the arch timer as little as possible. Previous versions of this code installed the VDSO unconditionally and unmodified, making it a measurably slower way for glibc to invoke the real syscalls on such systems. E.g. calling gettimeofday via glibc goes from ~560ns to ~630ns on i.MX6Q. If we can indicate to glibc that the time-related APIs in the VDSO are not accelerated, glibc can continue to invoke the syscalls directly instead of dispatching through the VDSO only to fall back to the slow path. Thus, if the architected timer is unusable for whatever reason, patch the VDSO at boot time so that symbol lookups for gettimeofday and clock_gettime return NULL. (This is similar to what powerpc does and borrows code from there.) This allows glibc to perform the syscall directly instead of passing control to the VDSO, which minimizes the penalty. In my measurements the time taken for a gettimeofday call via glibc goes from ~560ns to ~580ns (again on i.MX6Q), and this is solely due to adding a test and branch to glibc's gettimeofday syscall wrapper. An alternative to patching the VDSO at boot would be to not install the VDSO at all when the arch timer isn't usable. Another alternative is to include a separate "dummy" vdso.so without gettimeofday and clock_gettime, which would be selected at boot time. Either of these would get cumbersome if the VDSO were to gain support for an API such as getcpu which is unrelated to arch timer support. Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-03-26 02:15:08 +08:00
* stack for the sigpage and vdso pages.
*/
static unsigned long sigpage_addr(const struct mm_struct *mm,
unsigned int npages)
{
unsigned long offset;
unsigned long first;
unsigned long last;
unsigned long addr;
unsigned int slots;
first = PAGE_ALIGN(mm->start_stack);
last = TASK_SIZE - (npages << PAGE_SHIFT);
/* No room after stack? */
if (first > last)
return 0;
/* Just enough room? */
if (first == last)
return first;
slots = ((last - first) >> PAGE_SHIFT) + 1;
offset = get_random_int() % slots;
addr = first + (offset << PAGE_SHIFT);
return addr;
}
static struct page *signal_page;
extern struct page *get_signal_page(void);
static int sigpage_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
current->mm->context.sigpage = new_vma->vm_start;
return 0;
}
static const struct vm_special_mapping sigpage_mapping = {
.name = "[sigpage]",
.pages = &signal_page,
.mremap = sigpage_mremap,
};
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
ARM: 8331/1: VDSO initialization, mapping, and synchronization Initialize the VDSO page list at boot, install the VDSO mapping at exec time, and update the data page during timer ticks. This code is not built if CONFIG_VDSO is not enabled. Account for the VDSO length when randomizing the offset from the stack. The [vdso] and [vvar] pages are placed immediately following the sigpage with separate _install_special_mapping calls. We want to "penalize" systems lacking the arch timer as little as possible. Previous versions of this code installed the VDSO unconditionally and unmodified, making it a measurably slower way for glibc to invoke the real syscalls on such systems. E.g. calling gettimeofday via glibc goes from ~560ns to ~630ns on i.MX6Q. If we can indicate to glibc that the time-related APIs in the VDSO are not accelerated, glibc can continue to invoke the syscalls directly instead of dispatching through the VDSO only to fall back to the slow path. Thus, if the architected timer is unusable for whatever reason, patch the VDSO at boot time so that symbol lookups for gettimeofday and clock_gettime return NULL. (This is similar to what powerpc does and borrows code from there.) This allows glibc to perform the syscall directly instead of passing control to the VDSO, which minimizes the penalty. In my measurements the time taken for a gettimeofday call via glibc goes from ~560ns to ~580ns (again on i.MX6Q), and this is solely due to adding a test and branch to glibc's gettimeofday syscall wrapper. An alternative to patching the VDSO at boot would be to not install the VDSO at all when the arch timer isn't usable. Another alternative is to include a separate "dummy" vdso.so without gettimeofday and clock_gettime, which would be selected at boot time. Either of these would get cumbersome if the VDSO were to gain support for an API such as getcpu which is unrelated to arch timer support. Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-03-26 02:15:08 +08:00
unsigned long npages;
unsigned long addr;
unsigned long hint;
int ret = 0;
if (!signal_page)
signal_page = get_signal_page();
if (!signal_page)
return -ENOMEM;
ARM: 8331/1: VDSO initialization, mapping, and synchronization Initialize the VDSO page list at boot, install the VDSO mapping at exec time, and update the data page during timer ticks. This code is not built if CONFIG_VDSO is not enabled. Account for the VDSO length when randomizing the offset from the stack. The [vdso] and [vvar] pages are placed immediately following the sigpage with separate _install_special_mapping calls. We want to "penalize" systems lacking the arch timer as little as possible. Previous versions of this code installed the VDSO unconditionally and unmodified, making it a measurably slower way for glibc to invoke the real syscalls on such systems. E.g. calling gettimeofday via glibc goes from ~560ns to ~630ns on i.MX6Q. If we can indicate to glibc that the time-related APIs in the VDSO are not accelerated, glibc can continue to invoke the syscalls directly instead of dispatching through the VDSO only to fall back to the slow path. Thus, if the architected timer is unusable for whatever reason, patch the VDSO at boot time so that symbol lookups for gettimeofday and clock_gettime return NULL. (This is similar to what powerpc does and borrows code from there.) This allows glibc to perform the syscall directly instead of passing control to the VDSO, which minimizes the penalty. In my measurements the time taken for a gettimeofday call via glibc goes from ~560ns to ~580ns (again on i.MX6Q), and this is solely due to adding a test and branch to glibc's gettimeofday syscall wrapper. An alternative to patching the VDSO at boot would be to not install the VDSO at all when the arch timer isn't usable. Another alternative is to include a separate "dummy" vdso.so without gettimeofday and clock_gettime, which would be selected at boot time. Either of these would get cumbersome if the VDSO were to gain support for an API such as getcpu which is unrelated to arch timer support. Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-03-26 02:15:08 +08:00
npages = 1; /* for sigpage */
npages += vdso_total_pages;
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
ARM: 8331/1: VDSO initialization, mapping, and synchronization Initialize the VDSO page list at boot, install the VDSO mapping at exec time, and update the data page during timer ticks. This code is not built if CONFIG_VDSO is not enabled. Account for the VDSO length when randomizing the offset from the stack. The [vdso] and [vvar] pages are placed immediately following the sigpage with separate _install_special_mapping calls. We want to "penalize" systems lacking the arch timer as little as possible. Previous versions of this code installed the VDSO unconditionally and unmodified, making it a measurably slower way for glibc to invoke the real syscalls on such systems. E.g. calling gettimeofday via glibc goes from ~560ns to ~630ns on i.MX6Q. If we can indicate to glibc that the time-related APIs in the VDSO are not accelerated, glibc can continue to invoke the syscalls directly instead of dispatching through the VDSO only to fall back to the slow path. Thus, if the architected timer is unusable for whatever reason, patch the VDSO at boot time so that symbol lookups for gettimeofday and clock_gettime return NULL. (This is similar to what powerpc does and borrows code from there.) This allows glibc to perform the syscall directly instead of passing control to the VDSO, which minimizes the penalty. In my measurements the time taken for a gettimeofday call via glibc goes from ~560ns to ~580ns (again on i.MX6Q), and this is solely due to adding a test and branch to glibc's gettimeofday syscall wrapper. An alternative to patching the VDSO at boot would be to not install the VDSO at all when the arch timer isn't usable. Another alternative is to include a separate "dummy" vdso.so without gettimeofday and clock_gettime, which would be selected at boot time. Either of these would get cumbersome if the VDSO were to gain support for an API such as getcpu which is unrelated to arch timer support. Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-03-26 02:15:08 +08:00
hint = sigpage_addr(mm, npages);
addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
vma = _install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
&sigpage_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto up_fail;
}
mm->context.sigpage = addr;
ARM: 8331/1: VDSO initialization, mapping, and synchronization Initialize the VDSO page list at boot, install the VDSO mapping at exec time, and update the data page during timer ticks. This code is not built if CONFIG_VDSO is not enabled. Account for the VDSO length when randomizing the offset from the stack. The [vdso] and [vvar] pages are placed immediately following the sigpage with separate _install_special_mapping calls. We want to "penalize" systems lacking the arch timer as little as possible. Previous versions of this code installed the VDSO unconditionally and unmodified, making it a measurably slower way for glibc to invoke the real syscalls on such systems. E.g. calling gettimeofday via glibc goes from ~560ns to ~630ns on i.MX6Q. If we can indicate to glibc that the time-related APIs in the VDSO are not accelerated, glibc can continue to invoke the syscalls directly instead of dispatching through the VDSO only to fall back to the slow path. Thus, if the architected timer is unusable for whatever reason, patch the VDSO at boot time so that symbol lookups for gettimeofday and clock_gettime return NULL. (This is similar to what powerpc does and borrows code from there.) This allows glibc to perform the syscall directly instead of passing control to the VDSO, which minimizes the penalty. In my measurements the time taken for a gettimeofday call via glibc goes from ~560ns to ~580ns (again on i.MX6Q), and this is solely due to adding a test and branch to glibc's gettimeofday syscall wrapper. An alternative to patching the VDSO at boot would be to not install the VDSO at all when the arch timer isn't usable. Another alternative is to include a separate "dummy" vdso.so without gettimeofday and clock_gettime, which would be selected at boot time. Either of these would get cumbersome if the VDSO were to gain support for an API such as getcpu which is unrelated to arch timer support. Signed-off-by: Nathan Lynch <nathan_lynch@mentor.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2015-03-26 02:15:08 +08:00
/* Unlike the sigpage, failure to install the vdso is unlikely
* to be fatal to the process, so no error check needed
* here.
*/
arm_install_vdso(mm, addr + PAGE_SIZE);
up_fail:
up_write(&mm->mmap_sem);
return ret;
}
#endif