kernel_optimize_test/arch/powerpc/perf/callchain.c
Mike Rapoport e31cf2f4ca mm: don't include asm/pgtable.h if linux/mm.h is already included
Patch series "mm: consolidate definitions of page table accessors", v2.

The low level page table accessors (pXY_index(), pXY_offset()) are
duplicated across all architectures and sometimes more than once.  For
instance, we have 31 definition of pgd_offset() for 25 supported
architectures.

Most of these definitions are actually identical and typically it boils
down to, e.g.

static inline unsigned long pmd_index(unsigned long address)
{
        return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}

static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
        return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
}

These definitions can be shared among 90% of the arches provided
XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined.

For architectures that really need a custom version there is always
possibility to override the generic version with the usual ifdefs magic.

These patches introduce include/linux/pgtable.h that replaces
include/asm-generic/pgtable.h and add the definitions of the page table
accessors to the new header.

This patch (of 12):

The linux/mm.h header includes <asm/pgtable.h> to allow inlining of the
functions involving page table manipulations, e.g.  pte_alloc() and
pmd_alloc().  So, there is no point to explicitly include <asm/pgtable.h>
in the files that include <linux/mm.h>.

The include statements in such cases are remove with a simple loop:

	for f in $(git grep -l "include <linux/mm.h>") ; do
		sed -i -e '/include <asm\/pgtable.h>/ d' $f
	done

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: Guo Ren <guoren@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ley Foon Tan <ley.foon.tan@intel.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nick Hu <nickhu@andestech.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org
Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 09:39:13 -07:00

110 lines
2.7 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Performance counter callchain support - powerpc architecture code
*
* Copyright © 2009 Paul Mackerras, IBM Corporation.
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/perf_event.h>
#include <linux/percpu.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
#include <asm/ptrace.h>
#include <asm/sigcontext.h>
#include <asm/ucontext.h>
#include <asm/vdso.h>
#include <asm/pte-walk.h>
#include "callchain.h"
/*
* Is sp valid as the address of the next kernel stack frame after prev_sp?
* The next frame may be in a different stack area but should not go
* back down in the same stack area.
*/
static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
{
if (sp & 0xf)
return 0; /* must be 16-byte aligned */
if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
return 0;
if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
return 1;
/*
* sp could decrease when we jump off an interrupt stack
* back to the regular process stack.
*/
if ((sp & ~(THREAD_SIZE - 1)) != (prev_sp & ~(THREAD_SIZE - 1)))
return 1;
return 0;
}
void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
unsigned long sp, next_sp;
unsigned long next_ip;
unsigned long lr;
long level = 0;
unsigned long *fp;
lr = regs->link;
sp = regs->gpr[1];
perf_callchain_store(entry, perf_instruction_pointer(regs));
if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
return;
for (;;) {
fp = (unsigned long *) sp;
next_sp = fp[0];
if (next_sp == sp + STACK_INT_FRAME_SIZE &&
fp[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
/*
* This looks like an interrupt frame for an
* interrupt that occurred in the kernel
*/
regs = (struct pt_regs *)(sp + STACK_FRAME_OVERHEAD);
next_ip = regs->nip;
lr = regs->link;
level = 0;
perf_callchain_store_context(entry, PERF_CONTEXT_KERNEL);
} else {
if (level == 0)
next_ip = lr;
else
next_ip = fp[STACK_FRAME_LR_SAVE];
/*
* We can't tell which of the first two addresses
* we get are valid, but we can filter out the
* obviously bogus ones here. We replace them
* with 0 rather than removing them entirely so
* that userspace can tell which is which.
*/
if ((level == 1 && next_ip == lr) ||
(level <= 1 && !kernel_text_address(next_ip)))
next_ip = 0;
++level;
}
perf_callchain_store(entry, next_ip);
if (!valid_next_sp(next_sp, sp))
return;
sp = next_sp;
}
}
void
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
if (!is_32bit_task())
perf_callchain_user_64(entry, regs);
else
perf_callchain_user_32(entry, regs);
}