1 files changed, 327 insertions, 0 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
new file mode 100644
index 00000000000..dd8dda167a2
--- /dev/null
+++ b/arch/x86/mm/tlb.c
@@ -0,0 +1,327 @@
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/module.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>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
+			= { &init_mm, 0, };
+
+/*
+ *	Smarter SMP flushing macros.
+ *		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
+ */
+
+struct flush_tlb_info {
+	struct mm_struct *flush_mm;
+	unsigned long flush_start;
+	unsigned long flush_end;
+};
+
+/*
+ * We cannot call mmdrop() because we are in interrupt context,
+ * instead update mm->cpu_vm_mask.
+ */
+void leave_mm(int cpu)
+{
+	struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
+	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		BUG();
+	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
+		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
+		load_cr3(swapper_pg_dir);
+	}
+}
+EXPORT_SYMBOL_GPL(leave_mm);
+
+/*
+ * The flush IPI assumes that a thread switch happens in this order:
+ * [cpu0: the cpu that switches]
+ * 1) switch_mm() either 1a) or 1b)
+ * 1a) thread switch to a different mm
+ * 1a1) set cpu_tlbstate to TLBSTATE_OK
+ *	Now the tlb flush NMI handler flush_tlb_func won't call leave_mm
+ *	if cpu0 was in lazy tlb mode.
+ * 1a2) update cpu active_mm
+ *	Now cpu0 accepts tlb flushes for the new mm.
+ * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask);
+ *	Now the other cpus will send tlb flush ipis.
+ * 1a4) change cr3.
+ * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask);
+ *	Stop ipi delivery for the old mm. This is not synchronized with
+ *	the other cpus, but flush_tlb_func ignore flush ipis for the wrong
+ *	mm, and in the worst case we perform a superfluous tlb flush.
+ * 1b) thread switch without mm change
+ *	cpu active_mm is correct, cpu0 already handles flush ipis.
+ * 1b1) set cpu_tlbstate to TLBSTATE_OK
+ * 1b2) test_and_set the cpu bit in cpu_vm_mask.
+ *	Atomically set the bit [other cpus will start sending flush ipis],
+ *	and test the bit.
+ * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
+ * 2) switch %%esp, ie current
+ *
+ * The interrupt must handle 2 special cases:
+ * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
+ * - the cpu performs speculative tlb reads, i.e. even if the cpu only
+ *   runs in kernel space, the cpu could load tlb entries for user space
+ *   pages.
+ *
+ * The good news is that cpu_tlbstate is local to each cpu, no
+ * write/read ordering problems.
+ */
+
+/*
+ * TLB flush funcation:
+ * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
+ * 2) Leave the mm if we are in the lazy tlb mode.
+ */
+static void flush_tlb_func(void *info)
+{
+	struct flush_tlb_info *f = info;
+
+	inc_irq_stat(irq_tlb_count);
+
+	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+		return;
+
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
+		if (f->flush_end == TLB_FLUSH_ALL)
+			local_flush_tlb();
+		else if (!f->flush_end)
+			__flush_tlb_single(f->flush_start);
+		else {
+			unsigned long addr;
+			addr = f->flush_start;
+			while (addr < f->flush_end) {
+				__flush_tlb_single(addr);
+				addr += PAGE_SIZE;
+			}
+		}
+	} else
+		leave_mm(smp_processor_id());
+
+}
+
+void native_flush_tlb_others(const struct cpumask *cpumask,
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long end)
+{
+	struct flush_tlb_info info;
+	info.flush_mm = mm;
+	info.flush_start = start;
+	info.flush_end = end;
+
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
+	if (is_uv_system()) {
+		unsigned int cpu;
+
+		cpu = smp_processor_id();
+		cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu);
+		if (cpumask)
+			smp_call_function_many(cpumask, flush_tlb_func,
+								&info, 1);
+		return;
+	}
+	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
+}
+
+void flush_tlb_current_task(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	preempt_disable();
+
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+	local_flush_tlb();
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
+	preempt_enable();
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned long vmflag)
+{
+	unsigned long addr;
+	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
+
+	preempt_disable();
+	if (current->active_mm != mm)
+		goto flush_all;
+
+	if (!current->mm) {
+		leave_mm(smp_processor_id());
+		goto flush_all;
+	}
+
+	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
+					|| vmflag & VM_HUGETLB) {
+		local_flush_tlb();
+		goto flush_all;
+	}
+
+	/* In modern CPU, last level tlb used for both data/ins */
+	if (vmflag & VM_EXEC)
+		tlb_entries = tlb_lli_4k[ENTRIES];
+	else
+		tlb_entries = tlb_lld_4k[ENTRIES];
+
+	/* Assume all of TLB entries was occupied by this task */
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
+
+	/* tlb_flushall_shift is on balance point, details in commit log */
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+		local_flush_tlb();
+	} else {
+		/* flush range by one by one 'invlpg' */
+		for (addr = start; addr < end;	addr += PAGE_SIZE) {
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
+			__flush_tlb_single(addr);
+		}
+
+		if (cpumask_any_but(mm_cpumask(mm),
+				smp_processor_id()) < nr_cpu_ids)
+			flush_tlb_others(mm_cpumask(mm), mm, start, end);
+		preempt_enable();
+		return;
+	}
+
+flush_all:
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
+	preempt_enable();
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	preempt_disable();
+
+	if (current->active_mm == mm) {
+		if (current->mm)
+			__flush_tlb_one(start);
+		else
+			leave_mm(smp_processor_id());
+	}
+
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+
+	preempt_enable();
+}
+
+static void do_flush_tlb_all(void *info)
+{
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	__flush_tlb_all();
+	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
+		leave_mm(smp_processor_id());
+}
+
+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->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
+		__flush_tlb_single(addr);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned act_entries;
+	struct flush_tlb_info info;
+
+	/* In modern CPU, last level tlb used for both data/ins */
+	act_entries = tlb_lld_4k[ENTRIES];
+
+	/* Balance as user space task's flush, a bit conservative */
+	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 ||
+		(end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+	else {
+		info.flush_start = start;
+		info.flush_end = end;
+		on_each_cpu(do_kernel_range_flush, &info, 1);
+	}
+}
+
+#ifdef CONFIG_DEBUG_TLBFLUSH
+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, "%hd\n", tlb_flushall_shift);
+	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;
+	s8 shift;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	buf[len] = '\0';
+	if (kstrtos8(buf, 0, &shift))
+		return -EINVAL;
+
+	if (shift < -1 || shift >= BITS_PER_LONG)
+		return -EINVAL;
+
+	tlb_flushall_shift = shift;
+	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_flushall_shift(void)
+{
+	debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
+			    arch_debugfs_dir, NULL, &fops_tlbflush);
+	return 0;
+}
+late_initcall(create_tlb_flushall_shift);
+#endif