include/asm/mmu_context.h

#ifndef _ASM_X86_MMU_CONTEXT_H
#define _ASM_X86_MMU_CONTEXT_H

#include <asm/desc.h>
#include <linux/atomic.h>
#include <linux/mm_types.h>

#include <trace/events/tlb.h>

#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#include <asm/mpx.h>
#ifndef CONFIG_PARAVIRT
static inline void paravirt_activate_mm(struct mm_struct *prev,
					struct mm_struct *next)
{
}
#endif	/* !CONFIG_PARAVIRT */

#ifdef CONFIG_PERF_EVENTS
extern struct static_key rdpmc_always_available;

static inline void load_mm_cr4(struct mm_struct *mm)
{
	if (static_key_false(&rdpmc_always_available) ||
	    atomic_read(&mm->context.perf_rdpmc_allowed))
		cr4_set_bits(X86_CR4_PCE);
	else
		cr4_clear_bits(X86_CR4_PCE);
}
#else
static inline void load_mm_cr4(struct mm_struct *mm) {}
#endif

/*
 * ldt_structs can be allocated, used, and freed, but they are never
 * modified while live.
 */
struct ldt_struct {
	/*
	 * Xen requires page-aligned LDTs with special permissions.  This is
	 * needed to prevent us from installing evil descriptors such as
	 * call gates.  On native, we could merge the ldt_struct and LDT
	 * allocations, but it's not worth trying to optimize.
	 */
	struct desc_struct *entries;
	int size;
};

static inline void load_mm_ldt(struct mm_struct *mm)
{
	struct ldt_struct *ldt;

	/* lockless_dereference synchronizes with smp_store_release */
	ldt = lockless_dereference(mm->context.ldt);

	/*
	 * Any change to mm->context.ldt is followed by an IPI to all
	 * CPUs with the mm active.  The LDT will not be freed until
	 * after the IPI is handled by all such CPUs.  This means that,
	 * if the ldt_struct changes before we return, the values we see
	 * will be safe, and the new values will be loaded before we run
	 * any user code.
	 *
	 * NB: don't try to convert this to use RCU without extreme care.
	 * We would still need IRQs off, because we don't want to change
	 * the local LDT after an IPI loaded a newer value than the one
	 * that we can see.
	 */

	if (unlikely(ldt))
		set_ldt(ldt->entries, ldt->size);
	else
		clear_LDT();

	DEBUG_LOCKS_WARN_ON(preemptible());
}

/*
 * Used for LDT copy/destruction.
 */
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context(struct mm_struct *mm);


static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
#ifdef CONFIG_SMP
	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
#endif
}

static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
			     struct task_struct *tsk)
{
	unsigned cpu = smp_processor_id();

	if (likely(prev != next)) {
#ifdef CONFIG_SMP
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
		cpumask_set_cpu(cpu, mm_cpumask(next));

		/*
		 * Re-load page tables.
		 *
		 * This logic has an ordering constraint:
		 *
		 *  CPU 0: Write to a PTE for 'next'
		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
		 *  CPU 1: set bit 1 in next's mm_cpumask
		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
		 *
		 * We need to prevent an outcome in which CPU 1 observes
		 * the new PTE value and CPU 0 observes bit 1 clear in
		 * mm_cpumask.  (If that occurs, then the IPI will never
		 * be sent, and CPU 0's TLB will contain a stale entry.)
		 *
		 * The bad outcome can occur if either CPU's load is
		 * reordered before that CPU's store, so both CPUs must
		 * execute full barriers to prevent this from happening.
		 *
		 * Thus, switch_mm needs a full barrier between the
		 * store to mm_cpumask and any operation that could load
		 * from next->pgd.  TLB fills are special and can happen
		 * due to instruction fetches or for no reason at all,
		 * and neither LOCK nor MFENCE orders them.
		 * Fortunately, load_cr3() is serializing and gives the
		 * ordering guarantee we need.
		 *
		 */
		load_cr3(next->pgd);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);

		/* Stop flush ipis for the previous mm */
		cpumask_clear_cpu(cpu, mm_cpumask(prev));

		/* Load per-mm CR4 state */
		load_mm_cr4(next);

		/*
		 * Load the LDT, if the LDT is different.
		 *
		 * It's possible that prev->context.ldt doesn't match
		 * the LDT register.  This can happen if leave_mm(prev)
		 * was called and then modify_ldt changed
		 * prev->context.ldt but suppressed an IPI to this CPU.
		 * In this case, prev->context.ldt != NULL, because we
		 * never set context.ldt to NULL while the mm still
		 * exists.  That means that next->context.ldt !=
		 * prev->context.ldt, because mms never share an LDT.
		 */
		if (unlikely(prev->context.ldt != next->context.ldt))
			load_mm_ldt(next);
	}
#ifdef CONFIG_SMP
	  else {
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);

		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
			/*
			 * On established mms, the mm_cpumask is only changed
			 * from irq context, from ptep_clear_flush() while in
			 * lazy tlb mode, and here. Irqs are blocked during
			 * schedule, protecting us from simultaneous changes.
			 */
			cpumask_set_cpu(cpu, mm_cpumask(next));

			/*
			 * We were in lazy tlb mode and leave_mm disabled
			 * tlb flush IPI delivery. We must reload CR3
			 * to make sure to use no freed page tables.
			 *
			 * As above, load_cr3() is serializing and orders TLB
			 * fills with respect to the mm_cpumask write.
			 */
			load_cr3(next->pgd);
			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
			load_mm_cr4(next);
			load_mm_ldt(next);
		}
	}
#endif
}

#define activate_mm(prev, next)			\
do {						\
	paravirt_activate_mm((prev), (next));	\
	switch_mm((prev), (next), NULL);	\
} while (0);

#ifdef CONFIG_X86_32
#define deactivate_mm(tsk, mm)			\
do {						\
	lazy_load_gs(0);			\
} while (0)
#else
#define deactivate_mm(tsk, mm)			\
do {						\
	load_gs_index(0);			\
	loadsegment(fs, 0);			\
} while (0)
#endif

static inline void arch_dup_mmap(struct mm_struct *oldmm,
				 struct mm_struct *mm)
{
	paravirt_arch_dup_mmap(oldmm, mm);
}

static inline void arch_exit_mmap(struct mm_struct *mm)
{
	paravirt_arch_exit_mmap(mm);
}

static inline void arch_bprm_mm_init(struct mm_struct *mm,
		struct vm_area_struct *vma)
{
	mpx_mm_init(mm);
}

static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
			      unsigned long start, unsigned long end)
{
	/*
	 * mpx_notify_unmap() goes and reads a rarely-hot
	 * cacheline in the mm_struct.  That can be expensive
	 * enough to be seen in profiles.
	 *
	 * The mpx_notify_unmap() call and its contents have been
	 * observed to affect munmap() performance on hardware
	 * where MPX is not present.
	 *
	 * The unlikely() optimizes for the fast case: no MPX
	 * in the CPU, or no MPX use in the process.  Even if
	 * we get this wrong (in the unlikely event that MPX
	 * is widely enabled on some system) the overhead of
	 * MPX itself (reading bounds tables) is expected to
	 * overwhelm the overhead of getting this unlikely()
	 * consistently wrong.
	 */
	if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
		mpx_notify_unmap(mm, vma, start, end);
}

#endif /* _ASM_X86_MMU_CONTEXT_H */