linux_dsm_epyc7002/arch/arm/kernel/armksyms.c
Russell King e26a9e00af ARM: Better virt_to_page() handling
virt_to_page() is incredibly inefficient when virt-to-phys patching is
enabled.  This is because we end up with this calculation:

  page = &mem_map[asm virt_to_phys(addr) >> 12 - __pv_phys_offset >> 12]

in assembly.  The asm virt_to_phys() is equivalent this this operation:

  addr - PAGE_OFFSET + __pv_phys_offset

and we can see that because this is assembly, the compiler has no chance
to optimise some of that away.  This should reduce down to:

  page = &mem_map[(addr - PAGE_OFFSET) >> 12]

for the common cases.  Permit the compiler to make this optimisation by
giving it more of the information it needs - do this by providing a
virt_to_pfn() macro.

Another issue which makes this more complex is that __pv_phys_offset is
a 64-bit type on all platforms.  This is needlessly wasteful - if we
store the physical offset as a PFN, we can save a lot of work having
to deal with 64-bit values, which sometimes ends up producing incredibly
horrid code:

     a4c:       e3009000        movw    r9, #0
                        a4c: R_ARM_MOVW_ABS_NC  __pv_phys_offset
     a50:       e3409000        movt    r9, #0          ; r9 = &__pv_phys_offset
                        a50: R_ARM_MOVT_ABS     __pv_phys_offset
     a54:       e3002000        movw    r2, #0
                        a54: R_ARM_MOVW_ABS_NC  __pv_phys_offset
     a58:       e3402000        movt    r2, #0          ; r2 = &__pv_phys_offset
                        a58: R_ARM_MOVT_ABS     __pv_phys_offset
     a5c:       e5999004        ldr     r9, [r9, #4]    ; r9 = high word of __pv_phys_offset
     a60:       e3001000        movw    r1, #0
                        a60: R_ARM_MOVW_ABS_NC  mem_map
     a64:       e592c000        ldr     ip, [r2]        ; ip = low word of __pv_phys_offset

Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2014-04-03 22:46:34 +01:00

164 lines
3.9 KiB
C

/*
* linux/arch/arm/kernel/armksyms.c
*
* Copyright (C) 2000 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/cryptohash.h>
#include <linux/delay.h>
#include <linux/in6.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <asm/checksum.h>
#include <asm/ftrace.h>
/*
* libgcc functions - functions that are used internally by the
* compiler... (prototypes are not correct though, but that
* doesn't really matter since they're not versioned).
*/
extern void __ashldi3(void);
extern void __ashrdi3(void);
extern void __divsi3(void);
extern void __lshrdi3(void);
extern void __modsi3(void);
extern void __muldi3(void);
extern void __ucmpdi2(void);
extern void __udivsi3(void);
extern void __umodsi3(void);
extern void __do_div64(void);
extern void __bswapsi2(void);
extern void __bswapdi2(void);
extern void __aeabi_idiv(void);
extern void __aeabi_idivmod(void);
extern void __aeabi_lasr(void);
extern void __aeabi_llsl(void);
extern void __aeabi_llsr(void);
extern void __aeabi_lmul(void);
extern void __aeabi_uidiv(void);
extern void __aeabi_uidivmod(void);
extern void __aeabi_ulcmp(void);
extern void fpundefinstr(void);
/* platform dependent support */
EXPORT_SYMBOL(arm_delay_ops);
/* networking */
EXPORT_SYMBOL(csum_partial);
EXPORT_SYMBOL(csum_partial_copy_from_user);
EXPORT_SYMBOL(csum_partial_copy_nocheck);
EXPORT_SYMBOL(__csum_ipv6_magic);
/* io */
#ifndef __raw_readsb
EXPORT_SYMBOL(__raw_readsb);
#endif
#ifndef __raw_readsw
EXPORT_SYMBOL(__raw_readsw);
#endif
#ifndef __raw_readsl
EXPORT_SYMBOL(__raw_readsl);
#endif
#ifndef __raw_writesb
EXPORT_SYMBOL(__raw_writesb);
#endif
#ifndef __raw_writesw
EXPORT_SYMBOL(__raw_writesw);
#endif
#ifndef __raw_writesl
EXPORT_SYMBOL(__raw_writesl);
#endif
/* string / mem functions */
EXPORT_SYMBOL(strchr);
EXPORT_SYMBOL(strrchr);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(memchr);
EXPORT_SYMBOL(__memzero);
#ifdef CONFIG_MMU
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(__copy_from_user);
EXPORT_SYMBOL(__copy_to_user);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
EXPORT_SYMBOL(__get_user_4);
EXPORT_SYMBOL(__put_user_1);
EXPORT_SYMBOL(__put_user_2);
EXPORT_SYMBOL(__put_user_4);
EXPORT_SYMBOL(__put_user_8);
#endif
/* gcc lib functions */
EXPORT_SYMBOL(__ashldi3);
EXPORT_SYMBOL(__ashrdi3);
EXPORT_SYMBOL(__divsi3);
EXPORT_SYMBOL(__lshrdi3);
EXPORT_SYMBOL(__modsi3);
EXPORT_SYMBOL(__muldi3);
EXPORT_SYMBOL(__ucmpdi2);
EXPORT_SYMBOL(__udivsi3);
EXPORT_SYMBOL(__umodsi3);
EXPORT_SYMBOL(__do_div64);
EXPORT_SYMBOL(__bswapsi2);
EXPORT_SYMBOL(__bswapdi2);
#ifdef CONFIG_AEABI
EXPORT_SYMBOL(__aeabi_idiv);
EXPORT_SYMBOL(__aeabi_idivmod);
EXPORT_SYMBOL(__aeabi_lasr);
EXPORT_SYMBOL(__aeabi_llsl);
EXPORT_SYMBOL(__aeabi_llsr);
EXPORT_SYMBOL(__aeabi_lmul);
EXPORT_SYMBOL(__aeabi_uidiv);
EXPORT_SYMBOL(__aeabi_uidivmod);
EXPORT_SYMBOL(__aeabi_ulcmp);
#endif
/* bitops */
EXPORT_SYMBOL(_set_bit);
EXPORT_SYMBOL(_test_and_set_bit);
EXPORT_SYMBOL(_clear_bit);
EXPORT_SYMBOL(_test_and_clear_bit);
EXPORT_SYMBOL(_change_bit);
EXPORT_SYMBOL(_test_and_change_bit);
EXPORT_SYMBOL(_find_first_zero_bit_le);
EXPORT_SYMBOL(_find_next_zero_bit_le);
EXPORT_SYMBOL(_find_first_bit_le);
EXPORT_SYMBOL(_find_next_bit_le);
#ifdef __ARMEB__
EXPORT_SYMBOL(_find_first_zero_bit_be);
EXPORT_SYMBOL(_find_next_zero_bit_be);
EXPORT_SYMBOL(_find_first_bit_be);
EXPORT_SYMBOL(_find_next_bit_be);
#endif
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_OLD_MCOUNT
EXPORT_SYMBOL(mcount);
#endif
EXPORT_SYMBOL(__gnu_mcount_nc);
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
EXPORT_SYMBOL(__pv_phys_pfn_offset);
EXPORT_SYMBOL(__pv_offset);
#endif