76c567fbba
The Tilera architecture traditionally supports 64KB page sizes to improve TLB utilization and improve performance when the hardware is being used primarily to run a single application. For more generic server scenarios, it can be beneficial to run with 4KB page sizes, so this commit allows that to be specified (by modifying the arch/tile/include/hv/pagesize.h header). As part of this change, we also re-worked the PTE management slightly so that PTE writes all go through a __set_pte() function where we can do some additional validation. The set_pte_order() function was eliminated since the "order" argument wasn't being used. One bug uncovered was in the PCI DMA code, which wasn't properly flushing the specified range. This was benign with 64KB pages, but with 4KB pages we were getting some larger flushes wrong. The per-cpu memory reservation code also needed updating to conform with the newer percpu stuff; before it always chose 64KB, and that was always correct, but with 4KB granularity we now have to pay closer attention and reserve the amount of memory that will be requested when the percpu code starts allocating. Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
212 lines
4.4 KiB
ArmAsm
212 lines
4.4 KiB
ArmAsm
/*
|
|
* Copyright 2010 Tilera Corporation. All Rights Reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation, version 2.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* This routine is a helper for migrating the home of a set of pages to
|
|
* a new cpu. See the documentation in homecache.c for more information.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <linux/threads.h>
|
|
#include <asm/page.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/types.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <hv/hypervisor.h>
|
|
|
|
.text
|
|
|
|
/*
|
|
* First, some definitions that apply to all the code in the file.
|
|
*/
|
|
|
|
/* Locals (caller-save) */
|
|
#define r_tmp r10
|
|
#define r_save_sp r11
|
|
|
|
/* What we save where in the stack frame; must include all callee-saves. */
|
|
#define FRAME_SP 4
|
|
#define FRAME_R30 8
|
|
#define FRAME_R31 12
|
|
#define FRAME_R32 16
|
|
#define FRAME_R33 20
|
|
#define FRAME_R34 24
|
|
#define FRAME_R35 28
|
|
#define FRAME_SIZE 32
|
|
|
|
|
|
|
|
|
|
/*
|
|
* On entry:
|
|
*
|
|
* r0 low word of the new context PA to install (moved to r_context_lo)
|
|
* r1 high word of the new context PA to install (moved to r_context_hi)
|
|
* r2 low word of PTE to use for context access (moved to r_access_lo)
|
|
* r3 high word of PTE to use for context access (moved to r_access_lo)
|
|
* r4 ASID to use for new context (moved to r_asid)
|
|
* r5 pointer to cpumask with just this cpu set in it (r_my_cpumask)
|
|
*/
|
|
|
|
/* Arguments (caller-save) */
|
|
#define r_context_lo_in r0
|
|
#define r_context_hi_in r1
|
|
#define r_access_lo_in r2
|
|
#define r_access_hi_in r3
|
|
#define r_asid_in r4
|
|
#define r_my_cpumask r5
|
|
|
|
/* Locals (callee-save); must not be more than FRAME_xxx above. */
|
|
#define r_save_ics r30
|
|
#define r_context_lo r31
|
|
#define r_context_hi r32
|
|
#define r_access_lo r33
|
|
#define r_access_hi r34
|
|
#define r_asid r35
|
|
|
|
STD_ENTRY(flush_and_install_context)
|
|
/*
|
|
* Create a stack frame; we can't touch it once we flush the
|
|
* cache until we install the new page table and flush the TLB.
|
|
*/
|
|
{
|
|
move r_save_sp, sp
|
|
sw sp, lr
|
|
addi sp, sp, -FRAME_SIZE
|
|
}
|
|
addi r_tmp, sp, FRAME_SP
|
|
{
|
|
sw r_tmp, r_save_sp
|
|
addi r_tmp, sp, FRAME_R30
|
|
}
|
|
{
|
|
sw r_tmp, r30
|
|
addi r_tmp, sp, FRAME_R31
|
|
}
|
|
{
|
|
sw r_tmp, r31
|
|
addi r_tmp, sp, FRAME_R32
|
|
}
|
|
{
|
|
sw r_tmp, r32
|
|
addi r_tmp, sp, FRAME_R33
|
|
}
|
|
{
|
|
sw r_tmp, r33
|
|
addi r_tmp, sp, FRAME_R34
|
|
}
|
|
{
|
|
sw r_tmp, r34
|
|
addi r_tmp, sp, FRAME_R35
|
|
}
|
|
sw r_tmp, r35
|
|
|
|
/* Move some arguments to callee-save registers. */
|
|
{
|
|
move r_context_lo, r_context_lo_in
|
|
move r_context_hi, r_context_hi_in
|
|
}
|
|
{
|
|
move r_access_lo, r_access_lo_in
|
|
move r_access_hi, r_access_hi_in
|
|
}
|
|
move r_asid, r_asid_in
|
|
|
|
/* Disable interrupts, since we can't use our stack. */
|
|
{
|
|
mfspr r_save_ics, INTERRUPT_CRITICAL_SECTION
|
|
movei r_tmp, 1
|
|
}
|
|
mtspr INTERRUPT_CRITICAL_SECTION, r_tmp
|
|
|
|
/* First, flush our L2 cache. */
|
|
{
|
|
move r0, zero /* cache_pa */
|
|
move r1, zero
|
|
}
|
|
{
|
|
auli r2, zero, ha16(HV_FLUSH_EVICT_L2) /* cache_control */
|
|
move r3, r_my_cpumask /* cache_cpumask */
|
|
}
|
|
{
|
|
move r4, zero /* tlb_va */
|
|
move r5, zero /* tlb_length */
|
|
}
|
|
{
|
|
move r6, zero /* tlb_pgsize */
|
|
move r7, zero /* tlb_cpumask */
|
|
}
|
|
{
|
|
move r8, zero /* asids */
|
|
move r9, zero /* asidcount */
|
|
}
|
|
jal hv_flush_remote
|
|
bnz r0, .Ldone
|
|
|
|
/* Now install the new page table. */
|
|
{
|
|
move r0, r_context_lo
|
|
move r1, r_context_hi
|
|
}
|
|
{
|
|
move r2, r_access_lo
|
|
move r3, r_access_hi
|
|
}
|
|
{
|
|
move r4, r_asid
|
|
movei r5, HV_CTX_DIRECTIO
|
|
}
|
|
jal hv_install_context
|
|
bnz r0, .Ldone
|
|
|
|
/* Finally, flush the TLB. */
|
|
{
|
|
movei r0, 0 /* preserve_global */
|
|
jal hv_flush_all
|
|
}
|
|
|
|
.Ldone:
|
|
/* Reset interrupts back how they were before. */
|
|
mtspr INTERRUPT_CRITICAL_SECTION, r_save_ics
|
|
|
|
/* Restore the callee-saved registers and return. */
|
|
addli lr, sp, FRAME_SIZE
|
|
{
|
|
lw lr, lr
|
|
addli r_tmp, sp, FRAME_R30
|
|
}
|
|
{
|
|
lw r30, r_tmp
|
|
addli r_tmp, sp, FRAME_R31
|
|
}
|
|
{
|
|
lw r31, r_tmp
|
|
addli r_tmp, sp, FRAME_R32
|
|
}
|
|
{
|
|
lw r32, r_tmp
|
|
addli r_tmp, sp, FRAME_R33
|
|
}
|
|
{
|
|
lw r33, r_tmp
|
|
addli r_tmp, sp, FRAME_R34
|
|
}
|
|
{
|
|
lw r34, r_tmp
|
|
addli r_tmp, sp, FRAME_R35
|
|
}
|
|
{
|
|
lw r35, r_tmp
|
|
addi sp, sp, FRAME_SIZE
|
|
}
|
|
jrp lr
|
|
STD_ENDPROC(flush_and_install_context)
|