qemu/cputlb.c
Jan Kiszka 90260c6c09 exec: Resolve subpages in one step except for IOTLB fills
Except for the case of setting the IOTLB entry in TCG mode, we can avoid
the subpage dispatching handlers and do the resolution directly on
address_space_lookup_region. An IOTLB entry describes a full page, not
only the region that the first access to a sub-divided page may return.

This patch therefore introduces a special translation function,
address_space_translate_for_iotlb, that avoids the subpage resolutions.
In contrast, callers of the existing address_space_translate service
will now always receive the terminal memory region section. This will be
important for breaking the BQL and for enabling unaligned memory region.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2013-06-20 16:32:46 +02:00

363 lines
11 KiB
C

/*
* Common CPU TLB handling
*
* Copyright (c) 2003 Fabrice Bellard
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library 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. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "config.h"
#include "cpu.h"
#include "exec/exec-all.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "exec/cputlb.h"
#include "exec/memory-internal.h"
//#define DEBUG_TLB
//#define DEBUG_TLB_CHECK
/* statistics */
int tlb_flush_count;
static const CPUTLBEntry s_cputlb_empty_entry = {
.addr_read = -1,
.addr_write = -1,
.addr_code = -1,
.addend = -1,
};
/* NOTE:
* If flush_global is true (the usual case), flush all tlb entries.
* If flush_global is false, flush (at least) all tlb entries not
* marked global.
*
* Since QEMU doesn't currently implement a global/not-global flag
* for tlb entries, at the moment tlb_flush() will also flush all
* tlb entries in the flush_global == false case. This is OK because
* CPU architectures generally permit an implementation to drop
* entries from the TLB at any time, so flushing more entries than
* required is only an efficiency issue, not a correctness issue.
*/
void tlb_flush(CPUArchState *env, int flush_global)
{
CPUState *cpu = ENV_GET_CPU(env);
int i;
#if defined(DEBUG_TLB)
printf("tlb_flush:\n");
#endif
/* must reset current TB so that interrupts cannot modify the
links while we are modifying them */
cpu->current_tb = NULL;
for (i = 0; i < CPU_TLB_SIZE; i++) {
int mmu_idx;
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
env->tlb_table[mmu_idx][i] = s_cputlb_empty_entry;
}
}
memset(env->tb_jmp_cache, 0, TB_JMP_CACHE_SIZE * sizeof (void *));
env->tlb_flush_addr = -1;
env->tlb_flush_mask = 0;
tlb_flush_count++;
}
static inline void tlb_flush_entry(CPUTLBEntry *tlb_entry, target_ulong addr)
{
if (addr == (tlb_entry->addr_read &
(TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
addr == (tlb_entry->addr_write &
(TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
addr == (tlb_entry->addr_code &
(TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
*tlb_entry = s_cputlb_empty_entry;
}
}
void tlb_flush_page(CPUArchState *env, target_ulong addr)
{
CPUState *cpu = ENV_GET_CPU(env);
int i;
int mmu_idx;
#if defined(DEBUG_TLB)
printf("tlb_flush_page: " TARGET_FMT_lx "\n", addr);
#endif
/* Check if we need to flush due to large pages. */
if ((addr & env->tlb_flush_mask) == env->tlb_flush_addr) {
#if defined(DEBUG_TLB)
printf("tlb_flush_page: forced full flush ("
TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
env->tlb_flush_addr, env->tlb_flush_mask);
#endif
tlb_flush(env, 1);
return;
}
/* must reset current TB so that interrupts cannot modify the
links while we are modifying them */
cpu->current_tb = NULL;
addr &= TARGET_PAGE_MASK;
i = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
tlb_flush_entry(&env->tlb_table[mmu_idx][i], addr);
}
tb_flush_jmp_cache(env, addr);
}
/* update the TLBs so that writes to code in the virtual page 'addr'
can be detected */
void tlb_protect_code(ram_addr_t ram_addr)
{
cpu_physical_memory_reset_dirty(ram_addr,
ram_addr + TARGET_PAGE_SIZE,
CODE_DIRTY_FLAG);
}
/* update the TLB so that writes in physical page 'phys_addr' are no longer
tested for self modifying code */
void tlb_unprotect_code_phys(CPUArchState *env, ram_addr_t ram_addr,
target_ulong vaddr)
{
cpu_physical_memory_set_dirty_flags(ram_addr, CODE_DIRTY_FLAG);
}
static bool tlb_is_dirty_ram(CPUTLBEntry *tlbe)
{
return (tlbe->addr_write & (TLB_INVALID_MASK|TLB_MMIO|TLB_NOTDIRTY)) == 0;
}
void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start,
uintptr_t length)
{
uintptr_t addr;
if (tlb_is_dirty_ram(tlb_entry)) {
addr = (tlb_entry->addr_write & TARGET_PAGE_MASK) + tlb_entry->addend;
if ((addr - start) < length) {
tlb_entry->addr_write |= TLB_NOTDIRTY;
}
}
}
static inline void tlb_update_dirty(CPUTLBEntry *tlb_entry)
{
ram_addr_t ram_addr;
void *p;
if (tlb_is_dirty_ram(tlb_entry)) {
p = (void *)(uintptr_t)((tlb_entry->addr_write & TARGET_PAGE_MASK)
+ tlb_entry->addend);
ram_addr = qemu_ram_addr_from_host_nofail(p);
if (!cpu_physical_memory_is_dirty(ram_addr)) {
tlb_entry->addr_write |= TLB_NOTDIRTY;
}
}
}
void cpu_tlb_reset_dirty_all(ram_addr_t start1, ram_addr_t length)
{
CPUArchState *env;
for (env = first_cpu; env != NULL; env = env->next_cpu) {
int mmu_idx;
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
unsigned int i;
for (i = 0; i < CPU_TLB_SIZE; i++) {
tlb_reset_dirty_range(&env->tlb_table[mmu_idx][i],
start1, length);
}
}
}
}
static inline void tlb_set_dirty1(CPUTLBEntry *tlb_entry, target_ulong vaddr)
{
if (tlb_entry->addr_write == (vaddr | TLB_NOTDIRTY)) {
tlb_entry->addr_write = vaddr;
}
}
/* update the TLB corresponding to virtual page vaddr
so that it is no longer dirty */
void tlb_set_dirty(CPUArchState *env, target_ulong vaddr)
{
int i;
int mmu_idx;
vaddr &= TARGET_PAGE_MASK;
i = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
tlb_set_dirty1(&env->tlb_table[mmu_idx][i], vaddr);
}
}
/* Our TLB does not support large pages, so remember the area covered by
large pages and trigger a full TLB flush if these are invalidated. */
static void tlb_add_large_page(CPUArchState *env, target_ulong vaddr,
target_ulong size)
{
target_ulong mask = ~(size - 1);
if (env->tlb_flush_addr == (target_ulong)-1) {
env->tlb_flush_addr = vaddr & mask;
env->tlb_flush_mask = mask;
return;
}
/* Extend the existing region to include the new page.
This is a compromise between unnecessary flushes and the cost
of maintaining a full variable size TLB. */
mask &= env->tlb_flush_mask;
while (((env->tlb_flush_addr ^ vaddr) & mask) != 0) {
mask <<= 1;
}
env->tlb_flush_addr &= mask;
env->tlb_flush_mask = mask;
}
/* Add a new TLB entry. At most one entry for a given virtual address
is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the
supplied size is only used by tlb_flush_page. */
void tlb_set_page(CPUArchState *env, target_ulong vaddr,
hwaddr paddr, int prot,
int mmu_idx, target_ulong size)
{
MemoryRegionSection *section;
unsigned int index;
target_ulong address;
target_ulong code_address;
uintptr_t addend;
CPUTLBEntry *te;
hwaddr iotlb, xlat, sz;
assert(size >= TARGET_PAGE_SIZE);
if (size != TARGET_PAGE_SIZE) {
tlb_add_large_page(env, vaddr, size);
}
sz = size;
section = address_space_translate_for_iotlb(&address_space_memory, paddr,
&xlat, &sz);
assert(sz >= TARGET_PAGE_SIZE);
#if defined(DEBUG_TLB)
printf("tlb_set_page: vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
" prot=%x idx=%d\n",
vaddr, paddr, prot, mmu_idx);
#endif
address = vaddr;
if (!memory_region_is_ram(section->mr) && !memory_region_is_romd(section->mr)) {
/* IO memory case */
address |= TLB_MMIO;
addend = 0;
} else {
/* TLB_MMIO for rom/romd handled below */
addend = (uintptr_t)memory_region_get_ram_ptr(section->mr) + xlat;
}
code_address = address;
iotlb = memory_region_section_get_iotlb(env, section, vaddr, paddr, xlat,
prot, &address);
index = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
env->iotlb[mmu_idx][index] = iotlb - vaddr;
te = &env->tlb_table[mmu_idx][index];
te->addend = addend - vaddr;
if (prot & PAGE_READ) {
te->addr_read = address;
} else {
te->addr_read = -1;
}
if (prot & PAGE_EXEC) {
te->addr_code = code_address;
} else {
te->addr_code = -1;
}
if (prot & PAGE_WRITE) {
if ((memory_region_is_ram(section->mr) && section->readonly)
|| memory_region_is_romd(section->mr)) {
/* Write access calls the I/O callback. */
te->addr_write = address | TLB_MMIO;
} else if (memory_region_is_ram(section->mr)
&& !cpu_physical_memory_is_dirty(section->mr->ram_addr + xlat)) {
te->addr_write = address | TLB_NOTDIRTY;
} else {
te->addr_write = address;
}
} else {
te->addr_write = -1;
}
}
/* NOTE: this function can trigger an exception */
/* NOTE2: the returned address is not exactly the physical address: it
* is actually a ram_addr_t (in system mode; the user mode emulation
* version of this function returns a guest virtual address).
*/
tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
{
int mmu_idx, page_index, pd;
void *p;
MemoryRegion *mr;
page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
mmu_idx = cpu_mmu_index(env1);
if (unlikely(env1->tlb_table[mmu_idx][page_index].addr_code !=
(addr & TARGET_PAGE_MASK))) {
cpu_ldub_code(env1, addr);
}
pd = env1->iotlb[mmu_idx][page_index] & ~TARGET_PAGE_MASK;
mr = iotlb_to_region(pd);
if (memory_region_is_unassigned(mr)) {
#if defined(TARGET_ALPHA) || defined(TARGET_MIPS) || defined(TARGET_SPARC)
cpu_unassigned_access(env1, addr, 0, 1, 0, 4);
#else
cpu_abort(env1, "Trying to execute code outside RAM or ROM at 0x"
TARGET_FMT_lx "\n", addr);
#endif
}
p = (void *)((uintptr_t)addr + env1->tlb_table[mmu_idx][page_index].addend);
return qemu_ram_addr_from_host_nofail(p);
}
#define MMUSUFFIX _cmmu
#undef GETPC
#define GETPC() ((uintptr_t)0)
#define SOFTMMU_CODE_ACCESS
#define SHIFT 0
#include "exec/softmmu_template.h"
#define SHIFT 1
#include "exec/softmmu_template.h"
#define SHIFT 2
#include "exec/softmmu_template.h"
#define SHIFT 3
#include "exec/softmmu_template.h"
#undef env