linux_dsm_epyc7002/arch/arm64/kernel/process.c

390 lines
9.4 KiB
C
Raw Normal View History

/*
* Based on arch/arm/kernel/process.c
*
* Original Copyright (C) 1995 Linus Torvalds
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Copyright (C) 2012 ARM Ltd.
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdarg.h>
#include <linux/compat.h>
#include <linux/efi.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/user.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <linux/cpu.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/personality.h>
#include <linux/notifier.h>
#include <trace/events/power.h>
#include <asm/alternative.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
#include <asm/exec.h>
#include <asm/fpsimd.h>
#include <asm/mmu_context.h>
#include <asm/processor.h>
#include <asm/stacktrace.h>
#ifdef CONFIG_CC_STACKPROTECTOR
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
/*
* Function pointers to optional machine specific functions
*/
void (*pm_power_off)(void);
EXPORT_SYMBOL_GPL(pm_power_off);
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
/*
* This is our default idle handler.
*/
void arch_cpu_idle(void)
{
/*
* This should do all the clock switching and wait for interrupt
* tricks
*/
trace_cpu_idle_rcuidle(1, smp_processor_id());
cpu_do_idle();
local_irq_enable();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
#ifdef CONFIG_HOTPLUG_CPU
void arch_cpu_idle_dead(void)
{
cpu_die();
}
#endif
/*
* Called by kexec, immediately prior to machine_kexec().
*
* This must completely disable all secondary CPUs; simply causing those CPUs
* to execute e.g. a RAM-based pin loop is not sufficient. This allows the
* kexec'd kernel to use any and all RAM as it sees fit, without having to
* avoid any code or data used by any SW CPU pin loop. The CPU hotplug
* functionality embodied in disable_nonboot_cpus() to achieve this.
*/
void machine_shutdown(void)
{
disable_nonboot_cpus();
}
/*
* Halting simply requires that the secondary CPUs stop performing any
* activity (executing tasks, handling interrupts). smp_send_stop()
* achieves this.
*/
void machine_halt(void)
{
local_irq_disable();
smp_send_stop();
while (1);
}
/*
* Power-off simply requires that the secondary CPUs stop performing any
* activity (executing tasks, handling interrupts). smp_send_stop()
* achieves this. When the system power is turned off, it will take all CPUs
* with it.
*/
void machine_power_off(void)
{
local_irq_disable();
smp_send_stop();
if (pm_power_off)
pm_power_off();
}
/*
* Restart requires that the secondary CPUs stop performing any activity
* while the primary CPU resets the system. Systems with multiple CPUs must
* provide a HW restart implementation, to ensure that all CPUs reset at once.
* This is required so that any code running after reset on the primary CPU
* doesn't have to co-ordinate with other CPUs to ensure they aren't still
* executing pre-reset code, and using RAM that the primary CPU's code wishes
* to use. Implementing such co-ordination would be essentially impossible.
*/
void machine_restart(char *cmd)
{
/* Disable interrupts first */
local_irq_disable();
smp_send_stop();
/*
* UpdateCapsule() depends on the system being reset via
* ResetSystem().
*/
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_reboot(reboot_mode, NULL);
/* Now call the architecture specific reboot code. */
if (arm_pm_restart)
arm_pm_restart(reboot_mode, cmd);
else
do_kernel_restart(cmd);
/*
* Whoops - the architecture was unable to reboot.
*/
printk("Reboot failed -- System halted\n");
while (1);
}
void __show_regs(struct pt_regs *regs)
{
int i, top_reg;
u64 lr, sp;
if (compat_user_mode(regs)) {
lr = regs->compat_lr;
sp = regs->compat_sp;
top_reg = 12;
} else {
lr = regs->regs[30];
sp = regs->sp;
top_reg = 29;
}
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 05:27:17 +07:00
show_regs_print_info(KERN_DEFAULT);
print_symbol("PC is at %s\n", instruction_pointer(regs));
print_symbol("LR is at %s\n", lr);
printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
regs->pc, lr, regs->pstate);
printk("sp : %016llx\n", sp);
arm64: fix show_regs fallout from KERN_CONT changes Recently in commit 4bcc595ccd80decb ("printk: reinstate KERN_CONT for printing continuation lines"), the behaviour of printk changed w.r.t. KERN_CONT. Now, KERN_CONT is mandatory to continue existing lines. Without this, prefixes are inserted, making output illegible, e.g. [ 1007.069010] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 1007.076329] sp : ffff000008d53ec0 [ 1007.079606] x29: ffff000008d53ec0 [ 1007.082797] x28: 0000000080c50018 [ 1007.086160] [ 1007.087630] x27: ffff000008e0c7f8 [ 1007.090820] x26: ffff80097631ca00 [ 1007.094183] [ 1007.095653] x25: 0000000000000001 [ 1007.098843] x24: 000000ea68b61cac [ 1007.102206] ... or when dumped with the userpace dmesg tool, which has slightly different implicit newline behaviour. e.g. [ 1007.069010] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 1007.076329] sp : ffff000008d53ec0 [ 1007.079606] x29: ffff000008d53ec0 [ 1007.082797] x28: 0000000080c50018 [ 1007.086160] [ 1007.087630] x27: ffff000008e0c7f8 [ 1007.090820] x26: ffff80097631ca00 [ 1007.094183] [ 1007.095653] x25: 0000000000000001 [ 1007.098843] x24: 000000ea68b61cac [ 1007.102206] We can't simply always use KERN_CONT for lines which may or may not be continuations. That causes line prefixes (e.g. timestamps) to be supressed, and the alignment of all but the first line will be broken. For even more fun, we can't simply insert some dummy empty-string printk calls, as GCC warns for an empty printk string, and even if we pass KERN_DEFAULT explcitly to silence the warning, the prefix gets swallowed unless there is an additional part to the string. Instead, we must manually iterate over pairs of registers, which gives us the legible output we want in either case, e.g. [ 169.771790] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 169.779109] sp : ffff000008d53ec0 [ 169.782386] x29: ffff000008d53ec0 x28: 0000000080c50018 [ 169.787650] x27: ffff000008e0c7f8 x26: ffff80097631de00 [ 169.792913] x25: 0000000000000001 x24: 00000027827b2cf4 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-10-20 18:23:16 +07:00
i = top_reg;
while (i >= 0) {
printk("x%-2d: %016llx ", i, regs->regs[i]);
arm64: fix show_regs fallout from KERN_CONT changes Recently in commit 4bcc595ccd80decb ("printk: reinstate KERN_CONT for printing continuation lines"), the behaviour of printk changed w.r.t. KERN_CONT. Now, KERN_CONT is mandatory to continue existing lines. Without this, prefixes are inserted, making output illegible, e.g. [ 1007.069010] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 1007.076329] sp : ffff000008d53ec0 [ 1007.079606] x29: ffff000008d53ec0 [ 1007.082797] x28: 0000000080c50018 [ 1007.086160] [ 1007.087630] x27: ffff000008e0c7f8 [ 1007.090820] x26: ffff80097631ca00 [ 1007.094183] [ 1007.095653] x25: 0000000000000001 [ 1007.098843] x24: 000000ea68b61cac [ 1007.102206] ... or when dumped with the userpace dmesg tool, which has slightly different implicit newline behaviour. e.g. [ 1007.069010] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 1007.076329] sp : ffff000008d53ec0 [ 1007.079606] x29: ffff000008d53ec0 [ 1007.082797] x28: 0000000080c50018 [ 1007.086160] [ 1007.087630] x27: ffff000008e0c7f8 [ 1007.090820] x26: ffff80097631ca00 [ 1007.094183] [ 1007.095653] x25: 0000000000000001 [ 1007.098843] x24: 000000ea68b61cac [ 1007.102206] We can't simply always use KERN_CONT for lines which may or may not be continuations. That causes line prefixes (e.g. timestamps) to be supressed, and the alignment of all but the first line will be broken. For even more fun, we can't simply insert some dummy empty-string printk calls, as GCC warns for an empty printk string, and even if we pass KERN_DEFAULT explcitly to silence the warning, the prefix gets swallowed unless there is an additional part to the string. Instead, we must manually iterate over pairs of registers, which gives us the legible output we want in either case, e.g. [ 169.771790] pc : [<ffff00000871898c>] lr : [<ffff000008718948>] pstate: 40000145 [ 169.779109] sp : ffff000008d53ec0 [ 169.782386] x29: ffff000008d53ec0 x28: 0000000080c50018 [ 169.787650] x27: ffff000008e0c7f8 x26: ffff80097631de00 [ 169.792913] x25: 0000000000000001 x24: 00000027827b2cf4 Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2016-10-20 18:23:16 +07:00
i--;
if (i % 2 == 0) {
pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
i--;
}
pr_cont("\n");
}
printk("\n");
}
void show_regs(struct pt_regs * regs)
{
printk("\n");
__show_regs(regs);
}
static void tls_thread_flush(void)
{
write_sysreg(0, tpidr_el0);
if (is_compat_task()) {
current->thread.tp_value = 0;
/*
* We need to ensure ordering between the shadow state and the
* hardware state, so that we don't corrupt the hardware state
* with a stale shadow state during context switch.
*/
barrier();
write_sysreg(0, tpidrro_el0);
}
}
void flush_thread(void)
{
fpsimd_flush_thread();
tls_thread_flush();
flush_ptrace_hw_breakpoint(current);
}
void release_thread(struct task_struct *dead_task)
{
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
if (current->mm)
fpsimd_preserve_current_state();
*dst = *src;
return 0;
}
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 pt_regs *childregs = task_pt_regs(p);
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
/*
* Read the current TLS pointer from tpidr_el0 as it may be
* out-of-sync with the saved value.
*/
*task_user_tls(p) = read_sysreg(tpidr_el0);
if (stack_start) {
if (is_compat_thread(task_thread_info(p)))
childregs->compat_sp = stack_start;
else
childregs->sp = stack_start;
}
/*
* If a TLS pointer was passed to clone (4th argument), use it
* for the new thread.
*/
if (clone_flags & CLONE_SETTLS)
p->thread.tp_value = childregs->regs[3];
} else {
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h;
if (IS_ENABLED(CONFIG_ARM64_UAO) &&
cpus_have_cap(ARM64_HAS_UAO))
childregs->pstate |= PSR_UAO_BIT;
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
ptrace_hw_copy_thread(p);
return 0;
}
static void tls_thread_switch(struct task_struct *next)
{
unsigned long tpidr, tpidrro;
tpidr = read_sysreg(tpidr_el0);
*task_user_tls(current) = tpidr;
tpidr = *task_user_tls(next);
tpidrro = is_compat_thread(task_thread_info(next)) ?
next->thread.tp_value : 0;
write_sysreg(tpidr, tpidr_el0);
write_sysreg(tpidrro, tpidrro_el0);
}
/* Restore the UAO state depending on next's addr_limit */
void uao_thread_switch(struct task_struct *next)
{
if (IS_ENABLED(CONFIG_ARM64_UAO)) {
if (task_thread_info(next)->addr_limit == KERNEL_DS)
asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO));
else
asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO));
}
}
/*
* Thread switching.
*/
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next)
{
struct task_struct *last;
fpsimd_thread_switch(next);
tls_thread_switch(next);
hw_breakpoint_thread_switch(next);
contextidr_thread_switch(next);
uao_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
* the thread migrates to a different CPU.
*/
dsb(ish);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
return last;
}
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.pc = thread_saved_pc(p);
arm64: ftrace: fix a stack tracer's output under function graph tracer Function graph tracer modifies a return address (LR) in a stack frame to hook a function return. This will result in many useless entries (return_to_handler) showing up in a) a stack tracer's output b) perf call graph (with perf record -g) c) dump_backtrace (at panic et al.) For example, in case of a), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo 1 > /proc/sys/kernel/stack_trace_enabled $ cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (54 entries) ----- ---- -------- 0) 4504 16 gic_raise_softirq+0x28/0x150 1) 4488 80 smp_cross_call+0x38/0xb8 2) 4408 48 return_to_handler+0x0/0x40 3) 4360 32 return_to_handler+0x0/0x40 ... In case of b), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ perf record -e mem:XXX:x -ag -- sleep 10 $ perf report ... | | |--0.22%-- 0x550f8 | | | 0x10888 | | | el0_svc_naked | | | sys_openat | | | return_to_handler | | | return_to_handler ... In case of c), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo c > /proc/sysrq-trigger ... Call trace: [<ffffffc00044d3ac>] sysrq_handle_crash+0x24/0x30 [<ffffffc000092250>] return_to_handler+0x0/0x40 [<ffffffc000092250>] return_to_handler+0x0/0x40 ... This patch replaces such entries with real addresses preserved in current->ret_stack[] at unwind_frame(). This way, we can cover all the cases. Reviewed-by: Jungseok Lee <jungseoklee85@gmail.com> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> [will: fixed minor context changes conflicting with irq stack bits] Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-12-15 15:33:41 +07:00
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = p->curr_ret_stack;
#endif
stack_page = (unsigned long)task_stack_page(p);
do {
if (frame.sp < stack_page ||
frame.sp >= stack_page + THREAD_SIZE ||
unwind_frame(p, &frame))
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
} while (count ++ < 16);
return 0;
}
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
sp -= get_random_int() & ~PAGE_MASK;
return sp & ~0xf;
}
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
if (is_compat_task())
return randomize_page(mm->brk, 0x02000000);
else
return randomize_page(mm->brk, 0x40000000);
}