mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 16:36:47 +07:00
b3ca1c10d7
The kernel has never been audited to ensure that this_cpu operations are
consistently used throughout the kernel. The code generated in many
places can be improved through the use of this_cpu operations (which
uses a segment register for relocation of per cpu offsets instead of
performing address calculations).
The patch set also addresses various consistency issues in general with
the per cpu macros.
A. The semantics of __this_cpu_ptr() differs from this_cpu_ptr only
because checks are skipped. This is typically shown through a raw_
prefix. So this patch set changes the places where __this_cpu_ptr()
is used to raw_cpu_ptr().
B. There has been the long term wish by some that __this_cpu operations
would check for preemption. However, there are cases where preemption
checks need to be skipped. This patch set adds raw_cpu operations that
do not check for preemption and then adds preemption checks to the
__this_cpu operations.
C. The use of __get_cpu_var is always a reference to a percpu variable
that can also be handled via a this_cpu operation. This patch set
replaces all uses of __get_cpu_var with this_cpu operations.
D. We can then use this_cpu RMW operations in various places replacing
sequences of instructions by a single one.
E. The use of this_cpu operations throughout will allow other arches than
x86 to implement optimized references and RMV operations to work with
per cpu local data.
F. The use of this_cpu operations opens up the possibility to
further optimize code that relies on synchronization through
per cpu data.
The patch set works in a couple of stages:
I. Patch 1 adds the additional raw_cpu operations and raw_cpu_ptr().
Also converts the existing __this_cpu_xx_# primitive in the x86
code to raw_cpu_xx_#.
II. Patch 2-4 use the raw_cpu operations in places that would give
us false positives once they are enabled.
III. Patch 5 adds preemption checks to __this_cpu operations to allow
checking if preemption is properly disabled when these functions
are used.
IV. Patches 6-20 are patches that simply replace uses of __get_cpu_var
with this_cpu_ptr. They do not depend on any changes to the percpu
code. No preemption tests are skipped if they are applied.
V. Patches 21-46 are conversion patches that use this_cpu operations
in various kernel subsystems/drivers or arch code.
VI. Patches 47/48 (not included in this series) remove no longer used
functions (__this_cpu_ptr and __get_cpu_var). These should only be
applied after all the conversion patches have made it and after we
have done additional passes through the kernel to ensure that none of
the uses of these functions remain.
This patch (of 46):
The patches following this one will add preemption checks to __this_cpu
ops so we need to have an alternative way to use this_cpu operations
without preemption checks.
raw_cpu_ops will be the basis for all other ops since these will be the
operations that do not implement any checks.
Primitive operations are renamed by this patch from __this_cpu_xxx to
raw_cpu_xxxx.
Also change the uses of the x86 percpu primitives in preempt.h.
These depend directly on asm/percpu.h (header #include nesting issue).
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Alex Shi <alex.shi@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bryan Wu <cooloney@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: David Daney <david.daney@cavium.com>
Cc: David Miller <davem@davemloft.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Hedi Berriche <hedi@sgi.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Mike Travis <travis@sgi.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Robert Richter <rric@kernel.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
129 lines
3.2 KiB
C
129 lines
3.2 KiB
C
#ifndef _ASM_GENERIC_PERCPU_H_
|
|
#define _ASM_GENERIC_PERCPU_H_
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/percpu-defs.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
* per_cpu_offset() is the offset that has to be added to a
|
|
* percpu variable to get to the instance for a certain processor.
|
|
*
|
|
* Most arches use the __per_cpu_offset array for those offsets but
|
|
* some arches have their own ways of determining the offset (x86_64, s390).
|
|
*/
|
|
#ifndef __per_cpu_offset
|
|
extern unsigned long __per_cpu_offset[NR_CPUS];
|
|
|
|
#define per_cpu_offset(x) (__per_cpu_offset[x])
|
|
#endif
|
|
|
|
/*
|
|
* Determine the offset for the currently active processor.
|
|
* An arch may define __my_cpu_offset to provide a more effective
|
|
* means of obtaining the offset to the per cpu variables of the
|
|
* current processor.
|
|
*/
|
|
#ifndef __my_cpu_offset
|
|
#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
#define my_cpu_offset per_cpu_offset(smp_processor_id())
|
|
#else
|
|
#define my_cpu_offset __my_cpu_offset
|
|
#endif
|
|
|
|
/*
|
|
* Add a offset to a pointer but keep the pointer as is.
|
|
*
|
|
* Only S390 provides its own means of moving the pointer.
|
|
*/
|
|
#ifndef SHIFT_PERCPU_PTR
|
|
/* Weird cast keeps both GCC and sparse happy. */
|
|
#define SHIFT_PERCPU_PTR(__p, __offset) ({ \
|
|
__verify_pcpu_ptr((__p)); \
|
|
RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)); \
|
|
})
|
|
#endif
|
|
|
|
/*
|
|
* A percpu variable may point to a discarded regions. The following are
|
|
* established ways to produce a usable pointer from the percpu variable
|
|
* offset.
|
|
*/
|
|
#define per_cpu(var, cpu) \
|
|
(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
|
|
|
|
#ifndef raw_cpu_ptr
|
|
#define raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
|
|
#endif
|
|
#ifdef CONFIG_DEBUG_PREEMPT
|
|
#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
|
|
#else
|
|
#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
|
|
#endif
|
|
|
|
#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
|
|
#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var)))
|
|
|
|
#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
|
|
extern void setup_per_cpu_areas(void);
|
|
#endif
|
|
|
|
#else /* ! SMP */
|
|
|
|
#define VERIFY_PERCPU_PTR(__p) ({ \
|
|
__verify_pcpu_ptr((__p)); \
|
|
(typeof(*(__p)) __kernel __force *)(__p); \
|
|
})
|
|
|
|
#define per_cpu(var, cpu) (*((void)(cpu), VERIFY_PERCPU_PTR(&(var))))
|
|
#define __get_cpu_var(var) (*VERIFY_PERCPU_PTR(&(var)))
|
|
#define __raw_get_cpu_var(var) (*VERIFY_PERCPU_PTR(&(var)))
|
|
#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
|
|
#define raw_cpu_ptr(ptr) this_cpu_ptr(ptr)
|
|
|
|
#endif /* SMP */
|
|
|
|
#ifndef PER_CPU_BASE_SECTION
|
|
#ifdef CONFIG_SMP
|
|
#define PER_CPU_BASE_SECTION ".data..percpu"
|
|
#else
|
|
#define PER_CPU_BASE_SECTION ".data"
|
|
#endif
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
#ifdef MODULE
|
|
#define PER_CPU_SHARED_ALIGNED_SECTION ""
|
|
#define PER_CPU_ALIGNED_SECTION ""
|
|
#else
|
|
#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
|
|
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
|
|
#endif
|
|
#define PER_CPU_FIRST_SECTION "..first"
|
|
|
|
#else
|
|
|
|
#define PER_CPU_SHARED_ALIGNED_SECTION ""
|
|
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
|
|
#define PER_CPU_FIRST_SECTION ""
|
|
|
|
#endif
|
|
|
|
#ifndef PER_CPU_ATTRIBUTES
|
|
#define PER_CPU_ATTRIBUTES
|
|
#endif
|
|
|
|
#ifndef PER_CPU_DEF_ATTRIBUTES
|
|
#define PER_CPU_DEF_ATTRIBUTES
|
|
#endif
|
|
|
|
/* Keep until we have removed all uses of __this_cpu_ptr */
|
|
#define __this_cpu_ptr raw_cpu_ptr
|
|
|
|
#endif /* _ASM_GENERIC_PERCPU_H_ */
|