blob: a1561957dccbb82d188d8209d76f7eddb780519a [file] [log] [blame]
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/cpu.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/cache.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
#include <linux/debugfs.h>
/*
* TLB flushing, formerly SMP-only
* c/o Linus Torvalds.
*
* These mean you can really definitely utterly forget about
* writing to user space from interrupts. (Its not allowed anyway).
*
* Optimizations Manfred Spraul <manfred@colorfullife.com>
*
* More scalable flush, from Andi Kleen
*
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/
/*
* We get here when we do something requiring a TLB invalidation
* but could not go invalidate all of the contexts. We do the
* necessary invalidation by clearing out the 'ctx_id' which
* forces a TLB flush when the context is loaded.
*/
void clear_asid_other(void)
{
u16 asid;
/*
* This is only expected to be set if we have disabled
* kernel _PAGE_GLOBAL pages.
*/
if (!static_cpu_has(X86_FEATURE_PTI)) {
WARN_ON_ONCE(1);
return;
}
for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
/* Do not need to flush the current asid */
if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
continue;
/*
* Make sure the next time we go to switch to
* this asid, we do a flush:
*/
this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
}
this_cpu_write(cpu_tlbstate.invalidate_other, false);
}
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
u16 *new_asid, bool *need_flush)
{
u16 asid;
if (!static_cpu_has(X86_FEATURE_PCID)) {
*new_asid = 0;
*need_flush = true;
return;
}
if (this_cpu_read(cpu_tlbstate.invalidate_other))
clear_asid_other();
for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
next->context.ctx_id)
continue;
*new_asid = asid;
*need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) <
next_tlb_gen);
return;
}
/*
* We don't currently own an ASID slot on this CPU.
* Allocate a slot.
*/
*new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
if (*new_asid >= TLB_NR_DYN_ASIDS) {
*new_asid = 0;
this_cpu_write(cpu_tlbstate.next_asid, 1);
}
*need_flush = true;
}
static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
{
unsigned long new_mm_cr3;
if (need_flush) {
invalidate_user_asid(new_asid);
new_mm_cr3 = build_cr3(pgdir, new_asid);
} else {
new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
}
/*
* Caution: many callers of this function expect
* that load_cr3() is serializing and orders TLB
* fills with respect to the mm_cpumask writes.
*/
write_cr3(new_mm_cr3);
}
void leave_mm(int cpu)
{
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
/*
* It's plausible that we're in lazy TLB mode while our mm is init_mm.
* If so, our callers still expect us to flush the TLB, but there
* aren't any user TLB entries in init_mm to worry about.
*
* This needs to happen before any other sanity checks due to
* intel_idle's shenanigans.
*/
if (loaded_mm == &init_mm)
return;
/* Warn if we're not lazy. */
WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy));
switch_mm(NULL, &init_mm, NULL);
}
EXPORT_SYMBOL_GPL(leave_mm);
void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
unsigned long flags;
local_irq_save(flags);
switch_mm_irqs_off(prev, next, tsk);
local_irq_restore(flags);
}
void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
unsigned cpu = smp_processor_id();
u64 next_tlb_gen;
/*
* NB: The scheduler will call us with prev == next when switching
* from lazy TLB mode to normal mode if active_mm isn't changing.
* When this happens, we don't assume that CR3 (and hence
* cpu_tlbstate.loaded_mm) matches next.
*
* NB: leave_mm() calls us with prev == NULL and tsk == NULL.
*/
/* We don't want flush_tlb_func_* to run concurrently with us. */
if (IS_ENABLED(CONFIG_PROVE_LOCKING))
WARN_ON_ONCE(!irqs_disabled());
/*
* Verify that CR3 is what we think it is. This will catch
* hypothetical buggy code that directly switches to swapper_pg_dir
* without going through leave_mm() / switch_mm_irqs_off() or that
* does something like write_cr3(read_cr3_pa()).
*
* Only do this check if CONFIG_DEBUG_VM=y because __read_cr3()
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
/*
* If we were to BUG here, we'd be very likely to kill
* the system so hard that we don't see the call trace.
* Try to recover instead by ignoring the error and doing
* a global flush to minimize the chance of corruption.
*
* (This is far from being a fully correct recovery.
* Architecturally, the CPU could prefetch something
* back into an incorrect ASID slot and leave it there
* to cause trouble down the road. It's better than
* nothing, though.)
*/
__flush_tlb_all();
}
#endif
this_cpu_write(cpu_tlbstate.is_lazy, false);
if (real_prev == next) {
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
next->context.ctx_id);
/*
* 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));
return;
} else {
u16 new_asid;
bool need_flush;
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
/*
* If our current stack is in vmalloc space and isn't
* mapped in the new pgd, we'll double-fault. Forcibly
* map it.
*/
unsigned int index = pgd_index(current_stack_pointer);
pgd_t *pgd = next->pgd + index;
if (unlikely(pgd_none(*pgd)))
set_pgd(pgd, init_mm.pgd[index]);
}
/* Stop remote flushes for the previous mm */
VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
real_prev != &init_mm);
cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
/*
* Start remote flushes and then read tlb_gen.
*/
cpumask_set_cpu(cpu, mm_cpumask(next));
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
load_new_mm_cr3(next->pgd, new_asid, true);
/*
* NB: This gets called via leave_mm() in the idle path
* where RCU functions differently. Tracing normally
* uses RCU, so we need to use the _rcuidle variant.
*
* (There is no good reason for this. The idle code should
* be rearranged to call this before rcu_idle_enter().)
*/
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
load_new_mm_cr3(next->pgd, new_asid, false);
/* See above wrt _rcuidle. */
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
this_cpu_write(cpu_tlbstate.loaded_mm, next);
this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
}
load_mm_cr4(next);
switch_ldt(real_prev, next);
}
/*
* Please ignore the name of this function. It should be called
* switch_to_kernel_thread().
*
* enter_lazy_tlb() is a hint from the scheduler that we are entering a
* kernel thread or other context without an mm. Acceptable implementations
* include doing nothing whatsoever, switching to init_mm, or various clever
* lazy tricks to try to minimize TLB flushes.
*
* The scheduler reserves the right to call enter_lazy_tlb() several times
* in a row. It will notify us that we're going back to a real mm by
* calling switch_mm_irqs_off().
*/
void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
return;
if (tlb_defer_switch_to_init_mm()) {
/*
* There's a significant optimization that may be possible
* here. We have accurate enough TLB flush tracking that we
* don't need to maintain coherence of TLB per se when we're
* lazy. We do, however, need to maintain coherence of
* paging-structure caches. We could, in principle, leave our
* old mm loaded and only switch to init_mm when
* tlb_remove_page() happens.
*/
this_cpu_write(cpu_tlbstate.is_lazy, true);
} else {
switch_mm(NULL, &init_mm, NULL);
}
}
/*
* Call this when reinitializing a CPU. It fixes the following potential
* problems:
*
* - The ASID changed from what cpu_tlbstate thinks it is (most likely
* because the CPU was taken down and came back up with CR3's PCID
* bits clear. CPU hotplug can do this.
*
* - The TLB contains junk in slots corresponding to inactive ASIDs.
*
* - The CPU went so far out to lunch that it may have missed a TLB
* flush.
*/
void initialize_tlbstate_and_flush(void)
{
int i;
struct mm_struct *mm = this_cpu_read(cpu_tlbstate.loaded_mm);
u64 tlb_gen = atomic64_read(&init_mm.context.tlb_gen);
unsigned long cr3 = __read_cr3();
/* Assert that CR3 already references the right mm. */
WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
/*
* Assert that CR4.PCIDE is set if needed. (CR4.PCIDE initialization
* doesn't work like other CR4 bits because it can only be set from
* long mode.)
*/
WARN_ON(boot_cpu_has(X86_FEATURE_PCID) &&
!(cr4_read_shadow() & X86_CR4_PCIDE));
/* Force ASID 0 and force a TLB flush. */
write_cr3(build_cr3(mm->pgd, 0));
/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
this_cpu_write(cpu_tlbstate.next_asid, 1);
this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen);
for (i = 1; i < TLB_NR_DYN_ASIDS; i++)
this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0);
}
/*
* flush_tlb_func_common()'s memory ordering requirement is that any
* TLB fills that happen after we flush the TLB are ordered after we
* read active_mm's tlb_gen. We don't need any explicit barriers
* because all x86 flush operations are serializing and the
* atomic64_read operation won't be reordered by the compiler.
*/
static void flush_tlb_func_common(const struct flush_tlb_info *f,
bool local, enum tlb_flush_reason reason)
{
/*
* We have three different tlb_gen values in here. They are:
*
* - mm_tlb_gen: the latest generation.
* - local_tlb_gen: the generation that this CPU has already caught
* up to.
* - f->new_tlb_gen: the generation that the requester of the flush
* wants us to catch up to.
*/
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
/* This code cannot presently handle being reentered. */
VM_WARN_ON(!irqs_disabled());
if (unlikely(loaded_mm == &init_mm))
return;
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
loaded_mm->context.ctx_id);
if (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);
return;
}
if (unlikely(local_tlb_gen == mm_tlb_gen)) {
/*
* There's nothing to do: we're already up to date. This can
* happen if two concurrent flushes happen -- the first flush to
* be handled can catch us all the way up, leaving no work for
* the second flush.
*/
trace_tlb_flush(reason, 0);
return;
}
WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen);
WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen);
/*
* If we get to this point, we know that our TLB is out of date.
* This does not strictly imply that we need to flush (it's
* possible that f->new_tlb_gen <= local_tlb_gen), but we're
* going to need to flush in the very near future, so we might
* as well get it over with.
*
* The only question is whether to do a full or partial flush.
*
* We do a partial flush if requested and two extra conditions
* are met:
*
* 1. f->new_tlb_gen == local_tlb_gen + 1. We have an invariant that
* we've always done all needed flushes to catch up to
* local_tlb_gen. If, for example, local_tlb_gen == 2 and
* f->new_tlb_gen == 3, then we know that the flush needed to bring
* us up to date for tlb_gen 3 is the partial flush we're
* processing.
*
* As an example of why this check is needed, suppose that there
* are two concurrent flushes. The first is a full flush that
* changes context.tlb_gen from 1 to 2. The second is a partial
* flush that changes context.tlb_gen from 2 to 3. If they get
* processed on this CPU in reverse order, we'll see
* local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL.
* If we were to use __flush_tlb_single() and set local_tlb_gen to
* 3, we'd be break the invariant: we'd update local_tlb_gen above
* 1 without the full flush that's needed for tlb_gen 2.
*
* 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation.
* Partial TLB flushes are not all that much cheaper than full TLB
* flushes, so it seems unlikely that it would be a performance win
* to do a partial flush if that won't bring our TLB fully up to
* date. By doing a full flush instead, we can increase
* local_tlb_gen all the way to mm_tlb_gen and we can probably
* avoid another flush in the very near future.
*/
if (f->end != TLB_FLUSH_ALL &&
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;
addr = f->start;
while (addr < f->end) {
__flush_tlb_single(addr);
addr += PAGE_SIZE;
}
if (local)
count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages);
trace_tlb_flush(reason, nr_pages);
} else {
/* Full flush. */
local_flush_tlb();
if (local)
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
trace_tlb_flush(reason, TLB_FLUSH_ALL);
}
/* Both paths above update our state to mm_tlb_gen. */
this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
}
static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason)
{
const struct flush_tlb_info *f = info;
flush_tlb_func_common(f, true, reason);
}
static void flush_tlb_func_remote(void *info)
{
const struct flush_tlb_info *f = info;
inc_irq_stat(irq_tlb_count);
if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm))
return;
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
}
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info)
{
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
if (info->end == TLB_FLUSH_ALL)
trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
else
trace_tlb_flush(TLB_REMOTE_SEND_IPI,
(info->end - info->start) >> PAGE_SHIFT);
if (is_uv_system()) {
/*
* This whole special case is confused. UV has a "Broadcast
* Assist Unit", which seems to be a fancy way to send IPIs.
* Back when x86 used an explicit TLB flush IPI, UV was
* optimized to use its own mechanism. These days, x86 uses
* smp_call_function_many(), but UV still uses a manual IPI,
* and that IPI's action is out of date -- it does a manual
* flush instead of calling flush_tlb_func_remote(). This
* means that the percpu tlb_gen variables won't be updated
* and we'll do pointless flushes on future context switches.
*
* Rather than hooking native_flush_tlb_others() here, I think
* 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)
smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
return;
}
smp_call_function_many(cpumask, flush_tlb_func_remote,
(void *)info, 1);
}
/*
* See Documentation/x86/tlb.txt for details. We choose 33
* because it is large enough to cover the vast majority (at
* least 95%) of allocations, and is small enough that we are
* confident it will not cause too much overhead. Each single
* flush is about 100 ns, so this caps the maximum overhead at
* _about_ 3,000 ns.
*
* This is in units of pages.
*/
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)
{
int cpu;
struct flush_tlb_info info = {
.mm = mm,
};
cpu = get_cpu();
/* This is also a barrier that synchronizes with switch_mm(). */
info.new_tlb_gen = inc_mm_tlb_gen(mm);
/* Should we flush just the requested range? */
if ((end != TLB_FLUSH_ALL) &&
!(vmflag & VM_HUGETLB) &&
((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) {
info.start = start;
info.end = end;
} else {
info.start = 0UL;
info.end = TLB_FLUSH_ALL;
}
if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
VM_WARN_ON(irqs_disabled());
local_irq_disable();
flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
local_irq_enable();
}
if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
flush_tlb_others(mm_cpumask(mm), &info);
put_cpu();
}
static void do_flush_tlb_all(void *info)
{
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
__flush_tlb_all();
}
void flush_tlb_all(void)
{
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
on_each_cpu(do_flush_tlb_all, NULL, 1);
}
static void do_kernel_range_flush(void *info)
{
struct flush_tlb_info *f = info;
unsigned long addr;
/* flush range by one by one 'invlpg' */
for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
__flush_tlb_one(addr);
}
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
/* Balance as user space task's flush, a bit conservative */
if (end == TLB_FLUSH_ALL ||
(end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
on_each_cpu(do_flush_tlb_all, NULL, 1);
} else {
struct flush_tlb_info info;
info.start = start;
info.end = end;
on_each_cpu(do_kernel_range_flush, &info, 1);
}
}
void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
struct flush_tlb_info info = {
.mm = NULL,
.start = 0UL,
.end = TLB_FLUSH_ALL,
};
int cpu = get_cpu();
if (cpumask_test_cpu(cpu, &batch->cpumask)) {
VM_WARN_ON(irqs_disabled());
local_irq_disable();
flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN);
local_irq_enable();
}
if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
flush_tlb_others(&batch->cpumask, &info);
cpumask_clear(&batch->cpumask);
put_cpu();
}
static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
char buf[32];
unsigned int len;
len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling);
return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}
static ssize_t tlbflush_write_file(struct file *file,
const char __user *user_buf, size_t count, loff_t *ppos)
{
char buf[32];
ssize_t len;
int ceiling;
len = min(count, sizeof(buf) - 1);
if (copy_from_user(buf, user_buf, len))
return -EFAULT;
buf[len] = '\0';
if (kstrtoint(buf, 0, &ceiling))
return -EINVAL;
if (ceiling < 0)
return -EINVAL;
tlb_single_page_flush_ceiling = ceiling;
return count;
}
static const struct file_operations fops_tlbflush = {
.read = tlbflush_read_file,
.write = tlbflush_write_file,
.llseek = default_llseek,
};
static int __init create_tlb_single_page_flush_ceiling(void)
{
debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR,
arch_debugfs_dir, NULL, &fops_tlbflush);
return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);