@@ -251,6 +251,25 @@ void tlb_flush_by_mmuidx_all_cpus(CPUState *cpu, uint16_t idxmap);
* depend on when the guests translation ends the TB.
*/
void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap);
+
+/**
+ * tlb_flush_page_bits_by_mmuidx
+ * @cpu: CPU whose TLB should be flushed
+ * @addr: virtual address of page to be flushed
+ * @idxmap: bitmap of mmu indexes to flush
+ * @bits: number of significant bits in address
+ *
+ * Similar to tlb_flush_page_mask, but with a bitmap of indexes.
+ */
+void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
+ uint16_t idxmap, unsigned bits);
+
+/* Similarly, with broadcast and syncing. */
+void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu, target_ulong addr,
+ uint16_t idxmap, unsigned bits);
+void tlb_flush_page_bits_by_mmuidx_all_cpus_synced
+ (CPUState *cpu, target_ulong addr, uint16_t idxmap, unsigned bits);
+
/**
* tlb_set_page_with_attrs:
* @cpu: CPU to add this TLB entry for
@@ -337,6 +356,23 @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu,
uint16_t idxmap)
{
}
+static inline void tlb_flush_page_bits_by_mmuidx(CPUState *cpu,
+ target_ulong addr,
+ uint16_t idxmap,
+ unsigned bits)
+{
+}
+static inline void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *cpu,
+ target_ulong addr,
+ uint16_t idxmap,
+ unsigned bits)
+{
+}
+static inline void
+tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *cpu, target_ulong addr,
+ uint16_t idxmap, unsigned bits)
+{
+}
#endif
/**
* probe_access:
@@ -409,12 +409,21 @@ void tlb_flush_all_cpus_synced(CPUState *src_cpu)
tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, ALL_MMUIDX_BITS);
}
+static bool tlb_hit_page_mask_anyprot(CPUTLBEntry *tlb_entry,
+ target_ulong page, target_ulong mask)
+{
+ page &= mask;
+ mask &= TARGET_PAGE_MASK | TLB_INVALID_MASK;
+
+ return (page == (tlb_entry->addr_read & mask) ||
+ page == (tlb_addr_write(tlb_entry) & mask) ||
+ page == (tlb_entry->addr_code & mask));
+}
+
static inline bool tlb_hit_page_anyprot(CPUTLBEntry *tlb_entry,
target_ulong page)
{
- return tlb_hit_page(tlb_entry->addr_read, page) ||
- tlb_hit_page(tlb_addr_write(tlb_entry), page) ||
- tlb_hit_page(tlb_entry->addr_code, page);
+ return tlb_hit_page_mask_anyprot(tlb_entry, page, -1);
}
/**
@@ -427,31 +436,45 @@ static inline bool tlb_entry_is_empty(const CPUTLBEntry *te)
}
/* Called with tlb_c.lock held */
-static inline bool tlb_flush_entry_locked(CPUTLBEntry *tlb_entry,
- target_ulong page)
+static bool tlb_flush_entry_mask_locked(CPUTLBEntry *tlb_entry,
+ target_ulong page,
+ target_ulong mask)
{
- if (tlb_hit_page_anyprot(tlb_entry, page)) {
+ if (tlb_hit_page_mask_anyprot(tlb_entry, page, mask)) {
memset(tlb_entry, -1, sizeof(*tlb_entry));
return true;
}
return false;
}
+static inline bool tlb_flush_entry_locked(CPUTLBEntry *tlb_entry,
+ target_ulong page)
+{
+ return tlb_flush_entry_mask_locked(tlb_entry, page, -1);
+}
+
/* Called with tlb_c.lock held */
-static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
- target_ulong page)
+static void tlb_flush_vtlb_page_mask_locked(CPUArchState *env, int mmu_idx,
+ target_ulong page,
+ target_ulong mask)
{
CPUTLBDesc *d = &env_tlb(env)->d[mmu_idx];
int k;
assert_cpu_is_self(env_cpu(env));
for (k = 0; k < CPU_VTLB_SIZE; k++) {
- if (tlb_flush_entry_locked(&d->vtable[k], page)) {
+ if (tlb_flush_entry_mask_locked(&d->vtable[k], page, mask)) {
tlb_n_used_entries_dec(env, mmu_idx);
}
}
}
+static inline void tlb_flush_vtlb_page_locked(CPUArchState *env, int mmu_idx,
+ target_ulong page)
+{
+ tlb_flush_vtlb_page_mask_locked(env, mmu_idx, page, -1);
+}
+
static void tlb_flush_page_locked(CPUArchState *env, int midx,
target_ulong page)
{
@@ -666,6 +689,224 @@ void tlb_flush_page_all_cpus_synced(CPUState *src, target_ulong addr)
tlb_flush_page_by_mmuidx_all_cpus_synced(src, addr, ALL_MMUIDX_BITS);
}
+static void tlb_flush_page_bits_locked(CPUArchState *env, int midx,
+ target_ulong page, unsigned bits)
+{
+ CPUTLBDesc *d = &env_tlb(env)->d[midx];
+ CPUTLBDescFast *f = &env_tlb(env)->f[midx];
+ target_ulong mask = MAKE_64BIT_MASK(0, bits);
+
+ /*
+ * If @bits is smaller than the tlb size, there may be multiple entries
+ * within the TLB; otherwise all addresses that match under @mask hit
+ * the same TLB entry.
+ *
+ * TODO: Perhaps allow bits to be a few bits less than the size.
+ * For now, just flush the entire TLB.
+ */
+ if (mask < f->mask) {
+ tlb_debug("forcing full flush midx %d ("
+ TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
+ midx, page, mask);
+ tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
+ return;
+ }
+
+ /* Check if we need to flush due to large pages. */
+ if ((page & d->large_page_mask) == d->large_page_addr) {
+ tlb_debug("forcing full flush midx %d ("
+ TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
+ midx, d->large_page_addr, d->large_page_mask);
+ tlb_flush_one_mmuidx_locked(env, midx, get_clock_realtime());
+ return;
+ }
+
+ if (tlb_flush_entry_mask_locked(tlb_entry(env, midx, page), page, mask)) {
+ tlb_n_used_entries_dec(env, midx);
+ }
+ tlb_flush_vtlb_page_mask_locked(env, midx, page, mask);
+}
+
+static void tlb_flush_page_bits_by_mmuidx_async_0(CPUState *cpu,
+ target_ulong addr,
+ uint16_t idxmap,
+ unsigned bits)
+{
+ CPUArchState *env = cpu->env_ptr;
+ int mmu_idx;
+
+ assert_cpu_is_self(cpu);
+
+ tlb_debug("page addr:" TARGET_FMT_lx "/%u mmu_map:0x%x\n",
+ addr, bits, idxmap);
+
+ qemu_spin_lock(&env_tlb(env)->c.lock);
+ for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+ if ((idxmap >> mmu_idx) & 1) {
+ tlb_flush_page_bits_locked(env, mmu_idx, addr, bits);
+ }
+ }
+ qemu_spin_unlock(&env_tlb(env)->c.lock);
+
+ tb_flush_jmp_cache(cpu, addr);
+}
+
+static void tlb_flush_page_bits_by_mmuidx_async_1(CPUState *cpu,
+ run_on_cpu_data data)
+{
+ target_ulong addr_map_bits = (target_ulong) data.target_ptr;
+ target_ulong addr = addr_map_bits & TARGET_PAGE_MASK;
+ uint16_t idxmap = (addr_map_bits & ~TARGET_PAGE_MASK) >> 6;
+ unsigned bits = addr_map_bits & 0x3f;
+
+ tlb_flush_page_bits_by_mmuidx_async_0(cpu, addr, idxmap, bits);
+}
+
+typedef struct {
+ target_ulong addr;
+ uint16_t idxmap;
+ uint16_t bits;
+} TLBFlushPageBitsByMMUIdxData;
+
+static void tlb_flush_page_bits_by_mmuidx_async_2(CPUState *cpu,
+ run_on_cpu_data data)
+{
+ TLBFlushPageBitsByMMUIdxData *d = data.host_ptr;
+
+ tlb_flush_page_bits_by_mmuidx_async_0(cpu, d->addr, d->idxmap, d->bits);
+ g_free(d);
+}
+
+void tlb_flush_page_bits_by_mmuidx(CPUState *cpu, target_ulong addr,
+ uint16_t idxmap, unsigned bits)
+{
+ /* If all bits are significant, this devolves to tlb_flush_page. */
+ if (bits >= TARGET_LONG_BITS) {
+ tlb_flush_page_by_mmuidx(cpu, addr, idxmap);
+ return;
+ }
+ /* If no page bits are significant, this devolves to tlb_flush. */
+ if (bits < TARGET_PAGE_BITS) {
+ tlb_flush_by_mmuidx(cpu, idxmap);
+ return;
+ }
+
+ /* This should already be page aligned */
+ addr &= TARGET_PAGE_MASK;
+
+ if (qemu_cpu_is_self(cpu)) {
+ tlb_flush_page_bits_by_mmuidx_async_0(cpu, addr, idxmap, bits);
+ } else if (idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
+ run_on_cpu_data data
+ = RUN_ON_CPU_TARGET_PTR(addr | (idxmap << 6) | bits);
+ async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_1, data);
+ } else {
+ TLBFlushPageBitsByMMUIdxData *d
+ = g_new(TLBFlushPageBitsByMMUIdxData, 1);
+
+ /* Otherwise allocate a structure, freed by the worker. */
+ d->addr = addr;
+ d->idxmap = idxmap;
+ d->bits = bits;
+ async_run_on_cpu(cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+}
+
+void tlb_flush_page_bits_by_mmuidx_all_cpus(CPUState *src_cpu,
+ target_ulong addr,
+ uint16_t idxmap,
+ unsigned bits)
+{
+ /* If all bits are significant, this devolves to tlb_flush_page. */
+ if (bits >= TARGET_LONG_BITS) {
+ tlb_flush_page_by_mmuidx_all_cpus(src_cpu, addr, idxmap);
+ return;
+ }
+ /* If no page bits are significant, this devolves to tlb_flush. */
+ if (bits < TARGET_PAGE_BITS) {
+ tlb_flush_by_mmuidx_all_cpus(src_cpu, idxmap);
+ return;
+ }
+
+ /* This should already be page aligned */
+ addr &= TARGET_PAGE_MASK;
+
+ if (idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
+ run_on_cpu_data data
+ = RUN_ON_CPU_TARGET_PTR(addr | (idxmap << 6) | bits);
+ flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, data);
+ } else {
+ CPUState *dst_cpu;
+ TLBFlushPageBitsByMMUIdxData *d;
+
+ /* Allocate a separate data block for each destination cpu. */
+ CPU_FOREACH(dst_cpu) {
+ if (dst_cpu != src_cpu) {
+ d = g_new(TLBFlushPageBitsByMMUIdxData, 1);
+ d->addr = addr;
+ d->idxmap = idxmap;
+ d->bits = bits;
+ async_run_on_cpu(dst_cpu,
+ tlb_flush_page_bits_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+ }
+ }
+
+ tlb_flush_page_bits_by_mmuidx_async_0(src_cpu, addr, idxmap, bits);
+}
+
+void tlb_flush_page_bits_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
+ target_ulong addr,
+ uint16_t idxmap,
+ unsigned bits)
+{
+ /* If all bits are significant, this devolves to tlb_flush_page. */
+ if (bits >= TARGET_LONG_BITS) {
+ tlb_flush_page_by_mmuidx_all_cpus_synced(src_cpu, addr, idxmap);
+ return;
+ }
+ /* If no page bits are significant, this devolves to tlb_flush. */
+ if (bits < TARGET_PAGE_BITS) {
+ tlb_flush_by_mmuidx_all_cpus_synced(src_cpu, idxmap);
+ return;
+ }
+
+ /* This should already be page aligned */
+ addr &= TARGET_PAGE_MASK;
+
+ if (idxmap <= MAKE_64BIT_MASK(0, TARGET_PAGE_BITS - 6)) {
+ run_on_cpu_data data
+ = RUN_ON_CPU_TARGET_PTR(addr | (idxmap << 6) | bits);
+ flush_all_helper(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1, data);
+ async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_1,
+ data);
+ } else {
+ CPUState *dst_cpu;
+ TLBFlushPageBitsByMMUIdxData *d;
+
+ /* Allocate a separate data block for each destination cpu. */
+ CPU_FOREACH(dst_cpu) {
+ if (dst_cpu != src_cpu) {
+ d = g_new(TLBFlushPageBitsByMMUIdxData, 1);
+ d->addr = addr;
+ d->idxmap = idxmap;
+ d->bits = bits;
+ async_run_on_cpu(dst_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+ }
+
+ d = g_new(TLBFlushPageBitsByMMUIdxData, 1);
+ d->addr = addr;
+ d->idxmap = idxmap;
+ d->bits = bits;
+ async_safe_run_on_cpu(src_cpu, tlb_flush_page_bits_by_mmuidx_async_2,
+ RUN_ON_CPU_HOST_PTR(d));
+ }
+}
+
/* 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)
On ARM, the Top Byte Ignore feature means that only 56 bits of the address are significant in the virtual address. We are required to give the entire 64-bit address to FAR_ELx on fault, which means that we do not "clean" the top byte early in TCG. This new interface allows us to flush all 256 possible aliases for a given page, currently missed by tlb_flush_page*. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- include/exec/exec-all.h | 36 ++++++ accel/tcg/cputlb.c | 259 ++++++++++++++++++++++++++++++++++++++-- 2 files changed, 286 insertions(+), 9 deletions(-)