kernel_optimize_test/arch/sh/kernel/process_32.c

237 lines
5.6 KiB
C
Raw Normal View History

/*
* arch/sh/kernel/process.c
*
* This file handles the architecture-dependent parts of process handling..
*
* Copyright (C) 1995 Linus Torvalds
*
* SuperH version: Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
* Copyright (C) 2006 Lineo Solutions Inc. support SH4A UBC
* Copyright (C) 2002 - 2008 Paul Mundt
*
* 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/module.h>
#include <linux/mm.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/elfcore.h>
#include <linux/kallsyms.h>
#include <linux/fs.h>
#include <linux/ftrace.h>
#include <linux/hw_breakpoint.h>
#include <linux/prefetch.h>
#include <linux/stackprotector.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/fpu.h>
#include <asm/syscalls.h>
#include <asm/switch_to.h>
void show_regs(struct pt_regs * regs)
{
printk("\n");
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);
print_symbol("PC is at %s\n", instruction_pointer(regs));
print_symbol("PR is at %s\n", regs->pr);
printk("PC : %08lx SP : %08lx SR : %08lx ",
regs->pc, regs->regs[15], regs->sr);
#ifdef CONFIG_MMU
printk("TEA : %08x\n", __raw_readl(MMU_TEA));
#else
printk("\n");
#endif
printk("R0 : %08lx R1 : %08lx R2 : %08lx R3 : %08lx\n",
regs->regs[0],regs->regs[1],
regs->regs[2],regs->regs[3]);
printk("R4 : %08lx R5 : %08lx R6 : %08lx R7 : %08lx\n",
regs->regs[4],regs->regs[5],
regs->regs[6],regs->regs[7]);
printk("R8 : %08lx R9 : %08lx R10 : %08lx R11 : %08lx\n",
regs->regs[8],regs->regs[9],
regs->regs[10],regs->regs[11]);
printk("R12 : %08lx R13 : %08lx R14 : %08lx\n",
regs->regs[12],regs->regs[13],
regs->regs[14]);
printk("MACH: %08lx MACL: %08lx GBR : %08lx PR : %08lx\n",
regs->mach, regs->macl, regs->gbr, regs->pr);
show_trace(NULL, (unsigned long *)regs->regs[15], regs);
show_code(regs);
}
void start_thread(struct pt_regs *regs, unsigned long new_pc,
unsigned long new_sp)
{
regs->pr = 0;
regs->sr = SR_FD;
regs->pc = new_pc;
regs->regs[15] = new_sp;
free_thread_xstate(current);
}
EXPORT_SYMBOL(start_thread);
/*
* Free current thread data structures etc..
*/
void exit_thread(void)
{
}
void flush_thread(void)
{
struct task_struct *tsk = current;
flush_ptrace_hw_breakpoint(tsk);
#if defined(CONFIG_SH_FPU)
/* Forget lazy FPU state */
clear_fpu(tsk, task_pt_regs(tsk));
clear_used_math();
#endif
}
void release_thread(struct task_struct *dead_task)
{
/* do nothing */
}
/* Fill in the fpu structure for a core dump.. */
int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
{
int fpvalid = 0;
#if defined(CONFIG_SH_FPU)
struct task_struct *tsk = current;
fpvalid = !!tsk_used_math(tsk);
if (fpvalid)
fpvalid = !fpregs_get(tsk, NULL, 0,
sizeof(struct user_fpu_struct),
fpu, NULL);
#endif
return fpvalid;
}
EXPORT_SYMBOL(dump_fpu);
asmlinkage void ret_from_fork(void);
asmlinkage void ret_from_kernel_thread(void);
int copy_thread(unsigned long clone_flags, unsigned long usp,
unsigned long arg, struct task_struct *p)
{
struct thread_info *ti = task_thread_info(p);
struct pt_regs *childregs;
#if defined(CONFIG_SH_DSP)
struct task_struct *tsk = current;
if (is_dsp_enabled(tsk)) {
/* We can use the __save_dsp or just copy the struct:
* __save_dsp(p);
* p->thread.dsp_status.status |= SR_DSP
*/
p->thread.dsp_status = tsk->thread.dsp_status;
}
#endif
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
childregs = task_pt_regs(p);
p->thread.sp = (unsigned long) childregs;
if (unlikely(p->flags & PF_KTHREAD)) {
memset(childregs, 0, sizeof(struct pt_regs));
p->thread.pc = (unsigned long) ret_from_kernel_thread;
childregs->regs[4] = arg;
childregs->regs[5] = usp;
childregs->sr = SR_MD;
#if defined(CONFIG_SH_FPU)
childregs->sr |= SR_FD;
#endif
ti->addr_limit = KERNEL_DS;
ti->status &= ~TS_USEDFPU;
p->fpu_counter = 0;
return 0;
}
*childregs = *current_pt_regs();
if (usp)
childregs->regs[15] = usp;
ti->addr_limit = USER_DS;
if (clone_flags & CLONE_SETTLS)
childregs->gbr = childregs->regs[0];
childregs->regs[0] = 0; /* Set return value for child */
p->thread.pc = (unsigned long) ret_from_fork;
return 0;
}
/*
* switch_to(x,y) should switch tasks from x to y.
*
*/
__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev, struct task_struct *next)
{
struct thread_struct *next_t = &next->thread;
#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
__stack_chk_guard = next->stack_canary;
#endif
unlazy_fpu(prev, task_pt_regs(prev));
/* we're going to use this soon, after a few expensive things */
if (next->fpu_counter > 5)
prefetch(next_t->xstate);
#ifdef CONFIG_MMU
/*
* Restore the kernel mode register
* k7 (r7_bank1)
*/
asm volatile("ldc %0, r7_bank"
: /* no output */
: "r" (task_thread_info(next)));
#endif
/*
* If the task has used fpu the last 5 timeslices, just do a full
* restore of the math state immediately to avoid the trap; the
* chances of needing FPU soon are obviously high now
*/
if (next->fpu_counter > 5)
__fpu_state_restore();
return prev;
}
unsigned long get_wchan(struct task_struct *p)
{
unsigned long pc;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
/*
* The same comment as on the Alpha applies here, too ...
*/
pc = thread_saved_pc(p);
#ifdef CONFIG_FRAME_POINTER
if (in_sched_functions(pc)) {
unsigned long schedule_frame = (unsigned long)p->thread.sp;
return ((unsigned long *)schedule_frame)[21];
}
#endif
return pc;
}