mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 21:56:40 +07:00
89cbc76768
__get_cpu_var() is used for multiple purposes in the kernel source. One of
them is address calculation via the form &__get_cpu_var(x). This calculates
the address for the instance of the percpu variable of the current processor
based on an offset.
Other use cases are for storing and retrieving data from the current
processors percpu area. __get_cpu_var() can be used as an lvalue when
writing data or on the right side of an assignment.
__get_cpu_var() is defined as :
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
__get_cpu_var() always only does an address determination. However, store
and retrieve operations could use a segment prefix (or global register on
other platforms) to avoid the address calculation.
this_cpu_write() and this_cpu_read() can directly take an offset into a
percpu area and use optimized assembly code to read and write per cpu
variables.
This patch converts __get_cpu_var into either an explicit address
calculation using this_cpu_ptr() or into a use of this_cpu operations that
use the offset. Thereby address calculations are avoided and less registers
are used when code is generated.
Transformations done to __get_cpu_var()
1. Determine the address of the percpu instance of the current processor.
DEFINE_PER_CPU(int, y);
int *x = &__get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(&y);
2. Same as #1 but this time an array structure is involved.
DEFINE_PER_CPU(int, y[20]);
int *x = __get_cpu_var(y);
Converts to
int *x = this_cpu_ptr(y);
3. Retrieve the content of the current processors instance of a per cpu
variable.
DEFINE_PER_CPU(int, y);
int x = __get_cpu_var(y)
Converts to
int x = __this_cpu_read(y);
4. Retrieve the content of a percpu struct
DEFINE_PER_CPU(struct mystruct, y);
struct mystruct x = __get_cpu_var(y);
Converts to
memcpy(&x, this_cpu_ptr(&y), sizeof(x));
5. Assignment to a per cpu variable
DEFINE_PER_CPU(int, y)
__get_cpu_var(y) = x;
Converts to
__this_cpu_write(y, x);
6. Increment/Decrement etc of a per cpu variable
DEFINE_PER_CPU(int, y);
__get_cpu_var(y)++
Converts to
__this_cpu_inc(y)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86@kernel.org
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
90 lines
2.5 KiB
C
90 lines
2.5 KiB
C
/*
|
|
* Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
|
|
*
|
|
* This file contains the lowest level x86_64-specific interrupt
|
|
* entry and irq statistics code. All the remaining irq logic is
|
|
* done by the generic kernel/irq/ code and in the
|
|
* x86_64-specific irq controller code. (e.g. i8259.c and
|
|
* io_apic.c.)
|
|
*/
|
|
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/module.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/smp.h>
|
|
#include <asm/io_apic.h>
|
|
#include <asm/idle.h>
|
|
#include <asm/apic.h>
|
|
|
|
DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
|
|
EXPORT_PER_CPU_SYMBOL(irq_stat);
|
|
|
|
DEFINE_PER_CPU(struct pt_regs *, irq_regs);
|
|
EXPORT_PER_CPU_SYMBOL(irq_regs);
|
|
|
|
int sysctl_panic_on_stackoverflow;
|
|
|
|
/*
|
|
* Probabilistic stack overflow check:
|
|
*
|
|
* Only check the stack in process context, because everything else
|
|
* runs on the big interrupt stacks. Checking reliably is too expensive,
|
|
* so we just check from interrupts.
|
|
*/
|
|
static inline void stack_overflow_check(struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_DEBUG_STACKOVERFLOW
|
|
#define STACK_TOP_MARGIN 128
|
|
struct orig_ist *oist;
|
|
u64 irq_stack_top, irq_stack_bottom;
|
|
u64 estack_top, estack_bottom;
|
|
u64 curbase = (u64)task_stack_page(current);
|
|
|
|
if (user_mode_vm(regs))
|
|
return;
|
|
|
|
if (regs->sp >= curbase + sizeof(struct thread_info) +
|
|
sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
|
|
regs->sp <= curbase + THREAD_SIZE)
|
|
return;
|
|
|
|
irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
|
|
STACK_TOP_MARGIN;
|
|
irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
|
|
if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
|
|
return;
|
|
|
|
oist = this_cpu_ptr(&orig_ist);
|
|
estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
|
|
estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
|
|
if (regs->sp >= estack_top && regs->sp <= estack_bottom)
|
|
return;
|
|
|
|
WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
|
|
current->comm, curbase, regs->sp,
|
|
irq_stack_top, irq_stack_bottom,
|
|
estack_top, estack_bottom);
|
|
|
|
if (sysctl_panic_on_stackoverflow)
|
|
panic("low stack detected by irq handler - check messages\n");
|
|
#endif
|
|
}
|
|
|
|
bool handle_irq(unsigned irq, struct pt_regs *regs)
|
|
{
|
|
struct irq_desc *desc;
|
|
|
|
stack_overflow_check(regs);
|
|
|
|
desc = irq_to_desc(irq);
|
|
if (unlikely(!desc))
|
|
return false;
|
|
|
|
generic_handle_irq_desc(irq, desc);
|
|
return true;
|
|
}
|