mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 13:46:47 +07:00
69111bac42
This still has not been merged and now powerpc is the only arch that does
not have this change. Sorry about missing linuxppc-dev before.
V2->V2
- Fix up to work against 3.18-rc1
__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 :
__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.
At the end of the patch set all uses of __get_cpu_var have been removed so
the macro is removed too.
The patch set includes passes over all arches as well. Once these operations
are used throughout then specialized macros can be defined in non -x86
arches as well in order to optimize per cpu access by f.e. using a global
register that may be set to the per cpu base.
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: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
[mpe: Fix build errors caused by set/or_softirq_pending(), and rework
assignment in __set_breakpoint() to use memcpy().]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
85 lines
1.5 KiB
C
85 lines
1.5 KiB
C
#include <linux/percpu.h>
|
|
#include <linux/jump_label.h>
|
|
#include <asm/trace.h>
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
struct static_key opal_tracepoint_key = STATIC_KEY_INIT;
|
|
|
|
void opal_tracepoint_regfunc(void)
|
|
{
|
|
static_key_slow_inc(&opal_tracepoint_key);
|
|
}
|
|
|
|
void opal_tracepoint_unregfunc(void)
|
|
{
|
|
static_key_slow_dec(&opal_tracepoint_key);
|
|
}
|
|
#else
|
|
/*
|
|
* We optimise OPAL calls by placing opal_tracepoint_refcount
|
|
* directly in the TOC so we can check if the opal tracepoints are
|
|
* enabled via a single load.
|
|
*/
|
|
|
|
/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
|
|
extern long opal_tracepoint_refcount;
|
|
|
|
void opal_tracepoint_regfunc(void)
|
|
{
|
|
opal_tracepoint_refcount++;
|
|
}
|
|
|
|
void opal_tracepoint_unregfunc(void)
|
|
{
|
|
opal_tracepoint_refcount--;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Since the tracing code might execute OPAL calls we need to guard against
|
|
* recursion.
|
|
*/
|
|
static DEFINE_PER_CPU(unsigned int, opal_trace_depth);
|
|
|
|
void __trace_opal_entry(unsigned long opcode, unsigned long *args)
|
|
{
|
|
unsigned long flags;
|
|
unsigned int *depth;
|
|
|
|
local_irq_save(flags);
|
|
|
|
depth = this_cpu_ptr(&opal_trace_depth);
|
|
|
|
if (*depth)
|
|
goto out;
|
|
|
|
(*depth)++;
|
|
preempt_disable();
|
|
trace_opal_entry(opcode, args);
|
|
(*depth)--;
|
|
|
|
out:
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
void __trace_opal_exit(long opcode, unsigned long retval)
|
|
{
|
|
unsigned long flags;
|
|
unsigned int *depth;
|
|
|
|
local_irq_save(flags);
|
|
|
|
depth = this_cpu_ptr(&opal_trace_depth);
|
|
|
|
if (*depth)
|
|
goto out;
|
|
|
|
(*depth)++;
|
|
trace_opal_exit(opcode, retval);
|
|
preempt_enable();
|
|
(*depth)--;
|
|
|
|
out:
|
|
local_irq_restore(flags);
|
|
}
|