#include <linux/export.h>
#include <linux/cpu.h>
#include <linux/debugfs.h>
-#include <linux/gfp.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
{
struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
- bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
unsigned cpu = smp_processor_id();
u64 next_tlb_gen;
bool need_flush;
next->context.ctx_id);
/*
- * Even in lazy TLB mode, the CPU should stay set in the
- * mm_cpumask. The TLB shootdown code can figure out from
- * from cpu_tlbstate.is_lazy whether or not to send an IPI.
+ * We don't currently support having a real mm loaded without
+ * our cpu set in mm_cpumask(). We have all the bookkeeping
+ * in place to figure out whether we would need to flush
+ * if our cpu were cleared in mm_cpumask(), but we don't
+ * currently use it.
*/
if (WARN_ON_ONCE(real_prev != &init_mm &&
!cpumask_test_cpu(cpu, mm_cpumask(next))))
cpumask_set_cpu(cpu, mm_cpumask(next));
- /*
- * If the CPU is not in lazy TLB mode, we are just switching
- * from one thread in a process to another thread in the same
- * process. No TLB flush required.
- */
- if (!was_lazy)
- return;
-
- /*
- * Read the tlb_gen to check whether a flush is needed.
- * If the TLB is up to date, just use it.
- * The barrier synchronizes with the tlb_gen increment in
- * the TLB shootdown code.
- */
- smp_mb();
- next_tlb_gen = atomic64_read(&next->context.tlb_gen);
- if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
- next_tlb_gen)
- return;
-
- /*
- * TLB contents went out of date while we were in lazy
- * mode. Fall through to the TLB switching code below.
- */
- new_asid = prev_asid;
- need_flush = true;
+ return;
} else {
u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+
+ /* Let nmi_uaccess_okay() know that we're changing CR3. */
+ this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+ barrier();
}
if (need_flush) {
if (next != &init_mm)
this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+ /* Make sure we write CR3 before loaded_mm. */
+ barrier();
+
this_cpu_write(cpu_tlbstate.loaded_mm, next);
this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
* paging-structure cache to avoid speculatively reading
* garbage into our TLB. Since switching to init_mm is barely
* slower than a minimal flush, just switch to init_mm.
- *
- * This should be rare, with native_flush_tlb_others skipping
- * IPIs to lazy TLB mode CPUs.
*/
switch_mm_irqs_off(NULL, &init_mm, NULL);
return;
f->new_tlb_gen == local_tlb_gen + 1 &&
f->new_tlb_gen == mm_tlb_gen) {
/* Partial flush */
- unsigned long addr;
- unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT;
+ unsigned long nr_invalidate = (f->end - f->start) >> f->stride_shift;
+ unsigned long addr = f->start;
- addr = f->start;
while (addr < f->end) {
__flush_tlb_one_user(addr);
- addr += PAGE_SIZE;
+ addr += 1UL << f->stride_shift;
}
if (local)
- count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages);
- trace_tlb_flush(reason, nr_pages);
+ count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
+ trace_tlb_flush(reason, nr_invalidate);
} else {
/* Full flush. */
local_flush_tlb();
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
- cpumask_var_t lazymask;
- unsigned int cpu;
-
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
if (info->end == TLB_FLUSH_ALL)
trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
* that UV should be updated so that smp_call_function_many(),
* etc, are optimal on UV.
*/
+ unsigned int cpu;
+
cpu = smp_processor_id();
cpumask = uv_flush_tlb_others(cpumask, info);
if (cpumask)
(void *)info, 1);
return;
}
-
- /*
- * A temporary cpumask is used in order to skip sending IPIs
- * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm).
- * If the allocation fails, simply IPI every CPU in mm_cpumask.
- */
- if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) {
- smp_call_function_many(cpumask, flush_tlb_func_remote,
+ smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
- return;
- }
-
- cpumask_copy(lazymask, cpumask);
-
- for_each_cpu(cpu, lazymask) {
- if (per_cpu(cpu_tlbstate.is_lazy, cpu))
- cpumask_clear_cpu(cpu, lazymask);
- }
-
- smp_call_function_many(lazymask, flush_tlb_func_remote,
- (void *)info, 1);
-
- free_cpumask_var(lazymask);
}
/*
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
- unsigned long end, unsigned long vmflag)
+ unsigned long end, unsigned int stride_shift,
+ bool freed_tables)
{
int cpu;
struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
.mm = mm,
+ .stride_shift = stride_shift,
+ .freed_tables = freed_tables,
};
cpu = get_cpu();
/* Should we flush just the requested range? */
if ((end != TLB_FLUSH_ALL) &&
- !(vmflag & VM_HUGETLB) &&
- ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) {
+ ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) {
info.start = start;
info.end = end;
} else {
put_cpu();
}
-void tlb_flush_remove_tables_local(void *arg)
-{
- struct mm_struct *mm = arg;
-
- if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm &&
- this_cpu_read(cpu_tlbstate.is_lazy)) {
- /*
- * We're in lazy mode. We need to at least flush our
- * paging-structure cache to avoid speculatively reading
- * garbage into our TLB. Since switching to init_mm is barely
- * slower than a minimal flush, just switch to init_mm.
- */
- switch_mm_irqs_off(NULL, &init_mm, NULL);
- }
-}
-
-static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
- struct cpumask *lazy_cpus)
-{
- int cpu;
-
- for_each_cpu(cpu, mm_cpumask(mm)) {
- if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
- cpumask_set_cpu(cpu, lazy_cpus);
- }
-}
-
-void tlb_flush_remove_tables(struct mm_struct *mm)
-{
- int cpu = get_cpu();
- cpumask_var_t lazy_cpus;
-
- if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) {
- put_cpu();
- return;
- }
-
- if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
- /*
- * If the cpumask allocation fails, do a brute force flush
- * on all the CPUs that have this mm loaded.
- */
- smp_call_function_many(mm_cpumask(mm),
- tlb_flush_remove_tables_local, (void *)mm, 1);
- put_cpu();
- return;
- }
-
- /*
- * CPUs with !is_lazy either received a TLB flush IPI while the user
- * pages in this address range were unmapped, or have context switched
- * and reloaded %CR3 since then.
- *
- * Shootdown IPIs at page table freeing time only need to be sent to
- * CPUs that may have out of date TLB contents.
- */
- mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
- smp_call_function_many(lazy_cpus,
- tlb_flush_remove_tables_local, (void *)mm, 1);
- free_cpumask_var(lazy_cpus);
- put_cpu();
-}
static void do_flush_tlb_all(void *info)
{