mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-03 18:56:41 +07:00
1189be6508
This makes the kernel use 1TB segments for all kernel mappings and for user addresses of 1TB and above, on machines which support them (currently POWER5+, POWER6 and PA6T). We detect that the machine supports 1TB segments by looking at the ibm,processor-segment-sizes property in the device tree. We don't currently use 1TB segments for user addresses < 1T, since that would effectively prevent 32-bit processes from using huge pages unless we also had a way to revert to using 256MB segments. That would be possible but would involve extra complications (such as keeping track of which segment size was used when HPTEs were inserted) and is not addressed here. Parts of this patch were originally written by Ben Herrenschmidt. Signed-off-by: Paul Mackerras <paulus@samba.org>
271 lines
7.8 KiB
C
271 lines
7.8 KiB
C
/*
|
|
* PowerPC64 SLB support.
|
|
*
|
|
* Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
|
|
* Based on earlier code writteh by:
|
|
* Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
|
|
* Copyright (c) 2001 Dave Engebretsen
|
|
* Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
|
|
*
|
|
*
|
|
* 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; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#undef DEBUG
|
|
|
|
#include <asm/pgtable.h>
|
|
#include <asm/mmu.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/paca.h>
|
|
#include <asm/cputable.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/smp.h>
|
|
#include <asm/firmware.h>
|
|
#include <linux/compiler.h>
|
|
|
|
#ifdef DEBUG
|
|
#define DBG(fmt...) udbg_printf(fmt)
|
|
#else
|
|
#define DBG(fmt...)
|
|
#endif
|
|
|
|
extern void slb_allocate_realmode(unsigned long ea);
|
|
extern void slb_allocate_user(unsigned long ea);
|
|
|
|
static void slb_allocate(unsigned long ea)
|
|
{
|
|
/* Currently, we do real mode for all SLBs including user, but
|
|
* that will change if we bring back dynamic VSIDs
|
|
*/
|
|
slb_allocate_realmode(ea);
|
|
}
|
|
|
|
static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
|
|
unsigned long slot)
|
|
{
|
|
unsigned long mask;
|
|
|
|
mask = (ssize == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T;
|
|
return (ea & mask) | SLB_ESID_V | slot;
|
|
}
|
|
|
|
#define slb_vsid_shift(ssize) \
|
|
((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T)
|
|
|
|
static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
|
|
unsigned long flags)
|
|
{
|
|
return (get_kernel_vsid(ea, ssize) << slb_vsid_shift(ssize)) | flags |
|
|
((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
|
|
}
|
|
|
|
static inline void slb_shadow_update(unsigned long ea, int ssize,
|
|
unsigned long flags,
|
|
unsigned long entry)
|
|
{
|
|
/*
|
|
* Clear the ESID first so the entry is not valid while we are
|
|
* updating it. No write barriers are needed here, provided
|
|
* we only update the current CPU's SLB shadow buffer.
|
|
*/
|
|
get_slb_shadow()->save_area[entry].esid = 0;
|
|
get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, ssize, flags);
|
|
get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, ssize, entry);
|
|
}
|
|
|
|
static inline void slb_shadow_clear(unsigned long entry)
|
|
{
|
|
get_slb_shadow()->save_area[entry].esid = 0;
|
|
}
|
|
|
|
static inline void create_shadowed_slbe(unsigned long ea, int ssize,
|
|
unsigned long flags,
|
|
unsigned long entry)
|
|
{
|
|
/*
|
|
* Updating the shadow buffer before writing the SLB ensures
|
|
* we don't get a stale entry here if we get preempted by PHYP
|
|
* between these two statements.
|
|
*/
|
|
slb_shadow_update(ea, ssize, flags, entry);
|
|
|
|
asm volatile("slbmte %0,%1" :
|
|
: "r" (mk_vsid_data(ea, ssize, flags)),
|
|
"r" (mk_esid_data(ea, ssize, entry))
|
|
: "memory" );
|
|
}
|
|
|
|
void slb_flush_and_rebolt(void)
|
|
{
|
|
/* If you change this make sure you change SLB_NUM_BOLTED
|
|
* appropriately too. */
|
|
unsigned long linear_llp, vmalloc_llp, lflags, vflags;
|
|
unsigned long ksp_esid_data, ksp_vsid_data;
|
|
|
|
WARN_ON(!irqs_disabled());
|
|
|
|
linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
|
|
vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
|
|
lflags = SLB_VSID_KERNEL | linear_llp;
|
|
vflags = SLB_VSID_KERNEL | vmalloc_llp;
|
|
|
|
ksp_esid_data = mk_esid_data(get_paca()->kstack, mmu_kernel_ssize, 2);
|
|
if ((ksp_esid_data & ~0xfffffffUL) <= PAGE_OFFSET) {
|
|
ksp_esid_data &= ~SLB_ESID_V;
|
|
ksp_vsid_data = 0;
|
|
slb_shadow_clear(2);
|
|
} else {
|
|
/* Update stack entry; others don't change */
|
|
slb_shadow_update(get_paca()->kstack, mmu_kernel_ssize, lflags, 2);
|
|
ksp_vsid_data = get_slb_shadow()->save_area[2].vsid;
|
|
}
|
|
|
|
/* We need to do this all in asm, so we're sure we don't touch
|
|
* the stack between the slbia and rebolting it. */
|
|
asm volatile("isync\n"
|
|
"slbia\n"
|
|
/* Slot 1 - first VMALLOC segment */
|
|
"slbmte %0,%1\n"
|
|
/* Slot 2 - kernel stack */
|
|
"slbmte %2,%3\n"
|
|
"isync"
|
|
:: "r"(mk_vsid_data(VMALLOC_START, mmu_kernel_ssize, vflags)),
|
|
"r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, 1)),
|
|
"r"(ksp_vsid_data),
|
|
"r"(ksp_esid_data)
|
|
: "memory");
|
|
}
|
|
|
|
void slb_vmalloc_update(void)
|
|
{
|
|
unsigned long vflags;
|
|
|
|
vflags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmalloc_psize].sllp;
|
|
slb_shadow_update(VMALLOC_START, mmu_kernel_ssize, vflags, 1);
|
|
slb_flush_and_rebolt();
|
|
}
|
|
|
|
/* Flush all user entries from the segment table of the current processor. */
|
|
void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
|
|
{
|
|
unsigned long offset = get_paca()->slb_cache_ptr;
|
|
unsigned long slbie_data = 0;
|
|
unsigned long pc = KSTK_EIP(tsk);
|
|
unsigned long stack = KSTK_ESP(tsk);
|
|
unsigned long unmapped_base;
|
|
|
|
if (offset <= SLB_CACHE_ENTRIES) {
|
|
int i;
|
|
asm volatile("isync" : : : "memory");
|
|
for (i = 0; i < offset; i++) {
|
|
slbie_data = (unsigned long)get_paca()->slb_cache[i]
|
|
<< SID_SHIFT; /* EA */
|
|
slbie_data |= user_segment_size(slbie_data)
|
|
<< SLBIE_SSIZE_SHIFT;
|
|
slbie_data |= SLBIE_C; /* C set for user addresses */
|
|
asm volatile("slbie %0" : : "r" (slbie_data));
|
|
}
|
|
asm volatile("isync" : : : "memory");
|
|
} else {
|
|
slb_flush_and_rebolt();
|
|
}
|
|
|
|
/* Workaround POWER5 < DD2.1 issue */
|
|
if (offset == 1 || offset > SLB_CACHE_ENTRIES)
|
|
asm volatile("slbie %0" : : "r" (slbie_data));
|
|
|
|
get_paca()->slb_cache_ptr = 0;
|
|
get_paca()->context = mm->context;
|
|
|
|
/*
|
|
* preload some userspace segments into the SLB.
|
|
*/
|
|
if (test_tsk_thread_flag(tsk, TIF_32BIT))
|
|
unmapped_base = TASK_UNMAPPED_BASE_USER32;
|
|
else
|
|
unmapped_base = TASK_UNMAPPED_BASE_USER64;
|
|
|
|
if (is_kernel_addr(pc))
|
|
return;
|
|
slb_allocate(pc);
|
|
|
|
if (GET_ESID(pc) == GET_ESID(stack))
|
|
return;
|
|
|
|
if (is_kernel_addr(stack))
|
|
return;
|
|
slb_allocate(stack);
|
|
|
|
if ((GET_ESID(pc) == GET_ESID(unmapped_base))
|
|
|| (GET_ESID(stack) == GET_ESID(unmapped_base)))
|
|
return;
|
|
|
|
if (is_kernel_addr(unmapped_base))
|
|
return;
|
|
slb_allocate(unmapped_base);
|
|
}
|
|
|
|
static inline void patch_slb_encoding(unsigned int *insn_addr,
|
|
unsigned int immed)
|
|
{
|
|
/* Assume the instruction had a "0" immediate value, just
|
|
* "or" in the new value
|
|
*/
|
|
*insn_addr |= immed;
|
|
flush_icache_range((unsigned long)insn_addr, 4+
|
|
(unsigned long)insn_addr);
|
|
}
|
|
|
|
void slb_initialize(void)
|
|
{
|
|
unsigned long linear_llp, vmalloc_llp, io_llp;
|
|
unsigned long lflags, vflags;
|
|
static int slb_encoding_inited;
|
|
extern unsigned int *slb_miss_kernel_load_linear;
|
|
extern unsigned int *slb_miss_kernel_load_io;
|
|
|
|
/* Prepare our SLB miss handler based on our page size */
|
|
linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
|
|
io_llp = mmu_psize_defs[mmu_io_psize].sllp;
|
|
vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
|
|
get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
|
|
|
|
if (!slb_encoding_inited) {
|
|
slb_encoding_inited = 1;
|
|
patch_slb_encoding(slb_miss_kernel_load_linear,
|
|
SLB_VSID_KERNEL | linear_llp);
|
|
patch_slb_encoding(slb_miss_kernel_load_io,
|
|
SLB_VSID_KERNEL | io_llp);
|
|
|
|
DBG("SLB: linear LLP = %04x\n", linear_llp);
|
|
DBG("SLB: io LLP = %04x\n", io_llp);
|
|
}
|
|
|
|
get_paca()->stab_rr = SLB_NUM_BOLTED;
|
|
|
|
/* On iSeries the bolted entries have already been set up by
|
|
* the hypervisor from the lparMap data in head.S */
|
|
if (firmware_has_feature(FW_FEATURE_ISERIES))
|
|
return;
|
|
|
|
lflags = SLB_VSID_KERNEL | linear_llp;
|
|
vflags = SLB_VSID_KERNEL | vmalloc_llp;
|
|
|
|
/* Invalidate the entire SLB (even slot 0) & all the ERATS */
|
|
asm volatile("isync":::"memory");
|
|
asm volatile("slbmte %0,%0"::"r" (0) : "memory");
|
|
asm volatile("isync; slbia; isync":::"memory");
|
|
create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, 0);
|
|
|
|
create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1);
|
|
|
|
/* We don't bolt the stack for the time being - we're in boot,
|
|
* so the stack is in the bolted segment. By the time it goes
|
|
* elsewhere, we'll call _switch() which will bolt in the new
|
|
* one. */
|
|
asm volatile("isync":::"memory");
|
|
}
|