mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
e59a1bb2fd
lpage allocator aliases a PMD page for each cpu and returns whatever is unused to the page allocator. When the pageattr of the recycled pages are changed, this makes the two aliases point to the overlapping regions with different attributes which isn't allowed and known to cause subtle data corruption in certain cases. This can be handled in simliar manner to the x86_64 highmap alias. pageattr code should detect if the target pages have PMD alias and split the PMD alias and synchronize the attributes. pcpur allocator is updated to keep the allocated PMD pages map sorted in ascending address order and provide pcpu_lpage_remapped() function which binary searches the array to determine whether the given address is aliased and if so to which address. pageattr is updated to use pcpu_lpage_remapped() to detect the PMD alias and split it up as necessary from cpa_process_alias(). Jan Beulich spotted the original problem and incorrect usage of vaddr instead of laddr for lookup. With this, lpage percpu allocator should work correctly. Re-enable it. [ Impact: fix subtle lpage pageattr bug and re-enable lpage ] Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jan Beulich <JBeulich@novell.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu>
216 lines
5.6 KiB
C
216 lines
5.6 KiB
C
#ifndef _ASM_X86_PERCPU_H
|
|
#define _ASM_X86_PERCPU_H
|
|
|
|
#ifdef CONFIG_X86_64
|
|
#define __percpu_seg gs
|
|
#define __percpu_mov_op movq
|
|
#else
|
|
#define __percpu_seg fs
|
|
#define __percpu_mov_op movl
|
|
#endif
|
|
|
|
#ifdef __ASSEMBLY__
|
|
|
|
/*
|
|
* PER_CPU finds an address of a per-cpu variable.
|
|
*
|
|
* Args:
|
|
* var - variable name
|
|
* reg - 32bit register
|
|
*
|
|
* The resulting address is stored in the "reg" argument.
|
|
*
|
|
* Example:
|
|
* PER_CPU(cpu_gdt_descr, %ebx)
|
|
*/
|
|
#ifdef CONFIG_SMP
|
|
#define PER_CPU(var, reg) \
|
|
__percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg; \
|
|
lea per_cpu__##var(reg), reg
|
|
#define PER_CPU_VAR(var) %__percpu_seg:per_cpu__##var
|
|
#else /* ! SMP */
|
|
#define PER_CPU(var, reg) \
|
|
__percpu_mov_op $per_cpu__##var, reg
|
|
#define PER_CPU_VAR(var) per_cpu__##var
|
|
#endif /* SMP */
|
|
|
|
#ifdef CONFIG_X86_64_SMP
|
|
#define INIT_PER_CPU_VAR(var) init_per_cpu__##var
|
|
#else
|
|
#define INIT_PER_CPU_VAR(var) per_cpu__##var
|
|
#endif
|
|
|
|
#else /* ...!ASSEMBLY */
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/stringify.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
|
|
#define __my_cpu_offset percpu_read(this_cpu_off)
|
|
#else
|
|
#define __percpu_arg(x) "%" #x
|
|
#endif
|
|
|
|
/*
|
|
* Initialized pointers to per-cpu variables needed for the boot
|
|
* processor need to use these macros to get the proper address
|
|
* offset from __per_cpu_load on SMP.
|
|
*
|
|
* There also must be an entry in vmlinux_64.lds.S
|
|
*/
|
|
#define DECLARE_INIT_PER_CPU(var) \
|
|
extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
|
|
|
|
#ifdef CONFIG_X86_64_SMP
|
|
#define init_per_cpu_var(var) init_per_cpu__##var
|
|
#else
|
|
#define init_per_cpu_var(var) per_cpu_var(var)
|
|
#endif
|
|
|
|
/* For arch-specific code, we can use direct single-insn ops (they
|
|
* don't give an lvalue though). */
|
|
extern void __bad_percpu_size(void);
|
|
|
|
#define percpu_to_op(op, var, val) \
|
|
do { \
|
|
typedef typeof(var) T__; \
|
|
if (0) { \
|
|
T__ tmp__; \
|
|
tmp__ = (val); \
|
|
} \
|
|
switch (sizeof(var)) { \
|
|
case 1: \
|
|
asm(op "b %1,"__percpu_arg(0) \
|
|
: "+m" (var) \
|
|
: "qi" ((T__)(val))); \
|
|
break; \
|
|
case 2: \
|
|
asm(op "w %1,"__percpu_arg(0) \
|
|
: "+m" (var) \
|
|
: "ri" ((T__)(val))); \
|
|
break; \
|
|
case 4: \
|
|
asm(op "l %1,"__percpu_arg(0) \
|
|
: "+m" (var) \
|
|
: "ri" ((T__)(val))); \
|
|
break; \
|
|
case 8: \
|
|
asm(op "q %1,"__percpu_arg(0) \
|
|
: "+m" (var) \
|
|
: "re" ((T__)(val))); \
|
|
break; \
|
|
default: __bad_percpu_size(); \
|
|
} \
|
|
} while (0)
|
|
|
|
#define percpu_from_op(op, var) \
|
|
({ \
|
|
typeof(var) ret__; \
|
|
switch (sizeof(var)) { \
|
|
case 1: \
|
|
asm(op "b "__percpu_arg(1)",%0" \
|
|
: "=q" (ret__) \
|
|
: "m" (var)); \
|
|
break; \
|
|
case 2: \
|
|
asm(op "w "__percpu_arg(1)",%0" \
|
|
: "=r" (ret__) \
|
|
: "m" (var)); \
|
|
break; \
|
|
case 4: \
|
|
asm(op "l "__percpu_arg(1)",%0" \
|
|
: "=r" (ret__) \
|
|
: "m" (var)); \
|
|
break; \
|
|
case 8: \
|
|
asm(op "q "__percpu_arg(1)",%0" \
|
|
: "=r" (ret__) \
|
|
: "m" (var)); \
|
|
break; \
|
|
default: __bad_percpu_size(); \
|
|
} \
|
|
ret__; \
|
|
})
|
|
|
|
#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
|
|
#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
|
|
#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
|
|
#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
|
|
#define percpu_and(var, val) percpu_to_op("and", per_cpu__##var, val)
|
|
#define percpu_or(var, val) percpu_to_op("or", per_cpu__##var, val)
|
|
#define percpu_xor(var, val) percpu_to_op("xor", per_cpu__##var, val)
|
|
|
|
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
|
|
#define x86_test_and_clear_bit_percpu(bit, var) \
|
|
({ \
|
|
int old__; \
|
|
asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0" \
|
|
: "=r" (old__), "+m" (per_cpu__##var) \
|
|
: "dIr" (bit)); \
|
|
old__; \
|
|
})
|
|
|
|
#include <asm-generic/percpu.h>
|
|
|
|
/* We can use this directly for local CPU (faster). */
|
|
DECLARE_PER_CPU(unsigned long, this_cpu_off);
|
|
|
|
#ifdef CONFIG_NEED_MULTIPLE_NODES
|
|
void *pcpu_lpage_remapped(void *kaddr);
|
|
#else
|
|
static inline void *pcpu_lpage_remapped(void *kaddr)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
* Define the "EARLY_PER_CPU" macros. These are used for some per_cpu
|
|
* variables that are initialized and accessed before there are per_cpu
|
|
* areas allocated.
|
|
*/
|
|
|
|
#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
|
|
DEFINE_PER_CPU(_type, _name) = _initvalue; \
|
|
__typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \
|
|
{ [0 ... NR_CPUS-1] = _initvalue }; \
|
|
__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
|
|
|
|
#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
|
|
EXPORT_PER_CPU_SYMBOL(_name)
|
|
|
|
#define DECLARE_EARLY_PER_CPU(_type, _name) \
|
|
DECLARE_PER_CPU(_type, _name); \
|
|
extern __typeof__(_type) *_name##_early_ptr; \
|
|
extern __typeof__(_type) _name##_early_map[]
|
|
|
|
#define early_per_cpu_ptr(_name) (_name##_early_ptr)
|
|
#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
|
|
#define early_per_cpu(_name, _cpu) \
|
|
*(early_per_cpu_ptr(_name) ? \
|
|
&early_per_cpu_ptr(_name)[_cpu] : \
|
|
&per_cpu(_name, _cpu))
|
|
|
|
#else /* !CONFIG_SMP */
|
|
#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
|
|
DEFINE_PER_CPU(_type, _name) = _initvalue
|
|
|
|
#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
|
|
EXPORT_PER_CPU_SYMBOL(_name)
|
|
|
|
#define DECLARE_EARLY_PER_CPU(_type, _name) \
|
|
DECLARE_PER_CPU(_type, _name)
|
|
|
|
#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
|
|
#define early_per_cpu_ptr(_name) NULL
|
|
/* no early_per_cpu_map() */
|
|
|
|
#endif /* !CONFIG_SMP */
|
|
|
|
#endif /* _ASM_X86_PERCPU_H */
|