xref: /linux/arch/x86/mm/tlb.c (revision 53597deca0e38c30e6cd4ba2114fa42d2bcd85bb)

// SPDX-License-Identifier: GPL-2.0-only
#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 <linux/debugfs.h>
#include <linux/sched/smt.h>
#include <linux/task_work.h>
#include <linux/mmu_notifier.h>
#include <linux/mmu_context.h>
#include <linux/kvm_types.h>

#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/nospec-branch.h>
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/apic.h>
#include <asm/msr.h>
#include <asm/perf_event.h>
#include <asm/tlb.h>

#include "mm_internal.h"

#ifdef CONFIG_PARAVIRT
# define STATIC_NOPV
#else
# define STATIC_NOPV			static
# define __flush_tlb_local		native_flush_tlb_local
# define __flush_tlb_global		native_flush_tlb_global
# define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
# define __flush_tlb_multi(msk, info)	native_flush_tlb_multi(msk, info)
#endif

/*
 *	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
 */

/*
 * Bits to mangle the TIF_SPEC_* state into the mm pointer which is
 * stored in cpu_tlb_state.last_user_mm_spec.
 */
#define LAST_USER_MM_IBPB	0x1UL
#define LAST_USER_MM_L1D_FLUSH	0x2UL
#define LAST_USER_MM_SPEC_MASK	(LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH)

/* Bits to set when tlbstate and flush is (re)initialized */
#define LAST_USER_MM_INIT	LAST_USER_MM_IBPB

/*
 * The x86 feature is called PCID (Process Context IDentifier). It is similar
 * to what is traditionally called ASID on the RISC processors.
 *
 * We don't use the traditional ASID implementation, where each process/mm gets
 * its own ASID and flush/restart when we run out of ASID space.
 *
 * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
 * that came by on this CPU, allowing cheaper switch_mm between processes on
 * this CPU.
 *
 * We end up with different spaces for different things. To avoid confusion we
 * use different names for each of them:
 *
 * ASID  - [0, TLB_NR_DYN_ASIDS-1]
 *         the canonical identifier for an mm, dynamically allocated on each CPU
 *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
 *         the canonical, global identifier for an mm, identical across all CPUs
 *
 * kPCID - [1, MAX_ASID_AVAILABLE]
 *         the value we write into the PCID part of CR3; corresponds to the
 *         ASID+1, because PCID 0 is special.
 *
 * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
 *         for KPTI each mm has two address spaces and thus needs two
 *         PCID values, but we can still do with a single ASID denomination
 *         for each mm. Corresponds to kPCID + 2048.
 *
 */

/*
 * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for
 * user/kernel switches
 */
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
# define PTI_CONSUMED_PCID_BITS	1
#else
# define PTI_CONSUMED_PCID_BITS	0
#endif

#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)

/*
 * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
 * for them being zero-based.  Another -1 is because PCID 0 is reserved for
 * use by non-PCID-aware users.
 */
#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)

/*
 * Given @asid, compute kPCID
 */
static inline u16 kern_pcid(u16 asid)
{
	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);

#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
	/*
	 * Make sure that the dynamic ASID space does not conflict with the
	 * bit we are using to switch between user and kernel ASIDs.
	 */
	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));

	/*
	 * The ASID being passed in here should have respected the
	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
	 */
	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
#endif
	/*
	 * The dynamically-assigned ASIDs that get passed in are small
	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
	 * so do not bother to clear it.
	 *
	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
	 * PCID bits.  This serves two purposes.  It prevents a nasty
	 * situation in which PCID-unaware code saves CR3, loads some other
	 * value (with PCID == 0), and then restores CR3, thus corrupting
	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
	 * that any bugs involving loading a PCID-enabled CR3 with
	 * CR4.PCIDE off will trigger deterministically.
	 */
	return asid + 1;
}

/*
 * Given @asid, compute uPCID
 */
static inline u16 user_pcid(u16 asid)
{
	u16 ret = kern_pcid(asid);
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
#endif
	return ret;
}

static inline unsigned long build_cr3(pgd_t *pgd, u16 asid, unsigned long lam)
{
	unsigned long cr3 = __sme_pa(pgd) | lam;

	if (static_cpu_has(X86_FEATURE_PCID)) {
		cr3 |= kern_pcid(asid);
	} else {
		VM_WARN_ON_ONCE(asid != 0);
	}

	return cr3;
}

static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid,
					      unsigned long lam)
{
	/*
	 * Use boot_cpu_has() instead of this_cpu_has() as this function
	 * might be called during early boot. This should work even after
	 * boot because all CPU's the have same capabilities:
	 */
	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
	return build_cr3(pgd, asid, lam) | CR3_NOFLUSH;
}

/*
 * 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.
 */
static 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);

struct new_asid {
	unsigned int asid	: 16;
	unsigned int need_flush : 1;
};

static struct new_asid choose_new_asid(struct mm_struct *next, u64 next_tlb_gen)
{
	struct new_asid ns;
	u16 asid;

	if (!static_cpu_has(X86_FEATURE_PCID)) {
		ns.asid = 0;
		ns.need_flush = 1;
		return ns;
	}

	/*
	 * TLB consistency for global ASIDs is maintained with hardware assisted
	 * remote TLB flushing. Global ASIDs are always up to date.
	 */
	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
		u16 global_asid = mm_global_asid(next);

		if (global_asid) {
			ns.asid = global_asid;
			ns.need_flush = 0;
			return ns;
		}
	}

	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;

		ns.asid = asid;
		ns.need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < next_tlb_gen);
		return ns;
	}

	/*
	 * We don't currently own an ASID slot on this CPU.
	 * Allocate a slot.
	 */
	ns.asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
	if (ns.asid >= TLB_NR_DYN_ASIDS) {
		ns.asid = 0;
		this_cpu_write(cpu_tlbstate.next_asid, 1);
	}
	ns.need_flush = true;

	return ns;
}

/*
 * Global ASIDs are allocated for multi-threaded processes that are
 * active on multiple CPUs simultaneously, giving each of those
 * processes the same PCID on every CPU, for use with hardware-assisted
 * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
 *
 * These global ASIDs are held for the lifetime of the process.
 */
static DEFINE_RAW_SPINLOCK(global_asid_lock);
static u16 last_global_asid = MAX_ASID_AVAILABLE;
static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;

/*
 * When the search for a free ASID in the global ASID space reaches
 * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
 * freed global ASIDs are safe to re-use.
 *
 * This way the global flush only needs to happen at ASID rollover
 * time, and not at ASID allocation time.
 */
static void reset_global_asid_space(void)
{
	lockdep_assert_held(&global_asid_lock);

	invlpgb_flush_all_nonglobals();

	/*
	 * The TLB flush above makes it safe to re-use the previously
	 * freed global ASIDs.
	 */
	bitmap_andnot(global_asid_used, global_asid_used,
			global_asid_freed, MAX_ASID_AVAILABLE);
	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);

	/* Restart the search from the start of global ASID space. */
	last_global_asid = TLB_NR_DYN_ASIDS;
}

static u16 allocate_global_asid(void)
{
	u16 asid;

	lockdep_assert_held(&global_asid_lock);

	/* The previous allocation hit the edge of available address space */
	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
		reset_global_asid_space();

	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);

	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
		/* This should never happen. */
		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
				global_asid_available);
		return 0;
	}

	/* Claim this global ASID. */
	__set_bit(asid, global_asid_used);
	last_global_asid = asid;
	global_asid_available--;
	return asid;
}

/*
 * Check whether a process is currently active on more than @threshold CPUs.
 * This is a cheap estimation on whether or not it may make sense to assign
 * a global ASID to this process, and use broadcast TLB invalidation.
 */
static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
{
	int count = 0;
	int cpu;

	/* This quick check should eliminate most single threaded programs. */
	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
		return false;

	/* Slower check to make sure. */
	for_each_cpu(cpu, mm_cpumask(mm)) {
		/* Skip the CPUs that aren't really running this process. */
		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
			continue;

		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
			continue;

		if (++count > threshold)
			return true;
	}
	return false;
}

/*
 * Assign a global ASID to the current process, protecting against
 * races between multiple threads in the process.
 */
static void use_global_asid(struct mm_struct *mm)
{
	u16 asid;

	guard(raw_spinlock_irqsave)(&global_asid_lock);

	/* This process is already using broadcast TLB invalidation. */
	if (mm_global_asid(mm))
		return;

	/*
	 * The last global ASID was consumed while waiting for the lock.
	 *
	 * If this fires, a more aggressive ASID reuse scheme might be
	 * needed.
	 */
	if (!global_asid_available) {
		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
		return;
	}

	asid = allocate_global_asid();
	if (!asid)
		return;

	mm_assign_global_asid(mm, asid);
}

#ifdef CONFIG_BROADCAST_TLB_FLUSH
void mm_free_global_asid(struct mm_struct *mm)
{
	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
		return;

	if (!mm_global_asid(mm))
		return;

	guard(raw_spinlock_irqsave)(&global_asid_lock);

	/* The global ASID can be re-used only after flush at wrap-around. */
	__set_bit(mm->context.global_asid, global_asid_freed);

	mm->context.global_asid = 0;
	global_asid_available++;
}
#endif

/*
 * Is the mm transitioning from a CPU-local ASID to a global ASID?
 */
static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
{
	u16 global_asid = mm_global_asid(mm);

	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
		return false;

	/* Process is transitioning to a global ASID */
	if (global_asid && asid != global_asid)
		return true;

	return false;
}

/*
 * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
 * systems have over 8k CPUs. Because of this potential ASID shortage,
 * global ASIDs are handed out to processes that have frequent TLB
 * flushes and are active on 4 or more CPUs simultaneously.
 */
static void consider_global_asid(struct mm_struct *mm)
{
	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
		return;

	/* Check every once in a while. */
	if ((current->pid & 0x1f) != (jiffies & 0x1f))
		return;

	/*
	 * Assign a global ASID if the process is active on
	 * 4 or more CPUs simultaneously.
	 */
	if (mm_active_cpus_exceeds(mm, 3))
		use_global_asid(mm);
}

static void finish_asid_transition(struct flush_tlb_info *info)
{
	struct mm_struct *mm = info->mm;
	int bc_asid = mm_global_asid(mm);
	int cpu;

	if (!mm_in_asid_transition(mm))
		return;

	for_each_cpu(cpu, mm_cpumask(mm)) {
		/*
		 * The remote CPU is context switching. Wait for that to
		 * finish, to catch the unlikely case of it switching to
		 * the target mm with an out of date ASID.
		 */
		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
			cpu_relax();

		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
			continue;

		/*
		 * If at least one CPU is not using the global ASID yet,
		 * send a TLB flush IPI. The IPI should cause stragglers
		 * to transition soon.
		 *
		 * This can race with the CPU switching to another task;
		 * that results in a (harmless) extra IPI.
		 */
		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
			flush_tlb_multi(mm_cpumask(info->mm), info);
			return;
		}
	}

	/* All the CPUs running this process are using the global ASID. */
	mm_clear_asid_transition(mm);
}

static void broadcast_tlb_flush(struct flush_tlb_info *info)
{
	bool pmd = info->stride_shift == PMD_SHIFT;
	unsigned long asid = mm_global_asid(info->mm);
	unsigned long addr = info->start;

	/*
	 * TLB flushes with INVLPGB are kicked off asynchronously.
	 * The inc_mm_tlb_gen() guarantees page table updates are done
	 * before these TLB flushes happen.
	 */
	if (info->end == TLB_FLUSH_ALL) {
		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
		/* Do any CPUs supporting INVLPGB need PTI? */
		if (cpu_feature_enabled(X86_FEATURE_PTI))
			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
	} else do {
		unsigned long nr = 1;

		if (info->stride_shift <= PMD_SHIFT) {
			nr = (info->end - addr) >> info->stride_shift;
			nr = clamp_val(nr, 1, invlpgb_count_max);
		}

		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
		if (cpu_feature_enabled(X86_FEATURE_PTI))
			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);

		addr += nr << info->stride_shift;
	} while (addr < info->end);

	finish_asid_transition(info);

	/* Wait for the INVLPGBs kicked off above to finish. */
	__tlbsync();
}

/*
 * Given an ASID, flush the corresponding user ASID.  We can delay this
 * until the next time we switch to it.
 *
 * See SWITCH_TO_USER_CR3.
 */
static inline void invalidate_user_asid(u16 asid)
{
	/* There is no user ASID if address space separation is off */
	if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
		return;

	/*
	 * We only have a single ASID if PCID is off and the CR3
	 * write will have flushed it.
	 */
	if (!cpu_feature_enabled(X86_FEATURE_PCID))
		return;

	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	__set_bit(kern_pcid(asid),
		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
}

static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam,
			    bool need_flush)
{
	unsigned long new_mm_cr3;

	if (need_flush) {
		invalidate_user_asid(new_asid);
		new_mm_cr3 = build_cr3(pgdir, new_asid, lam);
	} else {
		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid, lam);
	}

	/*
	 * 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(void)
{
	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_shared.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(NULL, next, tsk);
	local_irq_restore(flags);
}

/*
 * Invoked from return to user/guest by a task that opted-in to L1D
 * flushing but ended up running on an SMT enabled core due to wrong
 * affinity settings or CPU hotplug. This is part of the paranoid L1D flush
 * contract which this task requested.
 */
static void l1d_flush_force_sigbus(struct callback_head *ch)
{
	force_sig(SIGBUS);
}

static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
				struct task_struct *next)
{
	/* Flush L1D if the outgoing task requests it */
	if (prev_mm & LAST_USER_MM_L1D_FLUSH)
		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);

	/* Check whether the incoming task opted in for L1D flush */
	if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
		return;

	/*
	 * Validate that it is not running on an SMT sibling as this would
	 * make the exercise pointless because the siblings share L1D. If
	 * it runs on a SMT sibling, notify it with SIGBUS on return to
	 * user/guest
	 */
	if (this_cpu_read(cpu_info.smt_active)) {
		clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH);
		next->l1d_flush_kill.func = l1d_flush_force_sigbus;
		task_work_add(next, &next->l1d_flush_kill, TWA_RESUME);
	}
}

static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next)
{
	unsigned long next_tif = read_task_thread_flags(next);
	unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK;

	/*
	 * Ensure that the bit shift above works as expected and the two flags
	 * end up in bit 0 and 1.
	 */
	BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1);

	return (unsigned long)next->mm | spec_bits;
}

static void cond_mitigation(struct task_struct *next)
{
	unsigned long prev_mm, next_mm;

	if (!next || !next->mm)
		return;

	next_mm = mm_mangle_tif_spec_bits(next);
	prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);

	/*
	 * Avoid user->user BTB/RSB poisoning by flushing them when switching
	 * between processes. This stops one process from doing Spectre-v2
	 * attacks on another.
	 *
	 * Both, the conditional and the always IBPB mode use the mm
	 * pointer to avoid the IBPB when switching between tasks of the
	 * same process. Using the mm pointer instead of mm->context.ctx_id
	 * opens a hypothetical hole vs. mm_struct reuse, which is more or
	 * less impossible to control by an attacker. Aside of that it
	 * would only affect the first schedule so the theoretically
	 * exposed data is not really interesting.
	 */
	if (static_branch_likely(&switch_mm_cond_ibpb)) {
		/*
		 * This is a bit more complex than the always mode because
		 * it has to handle two cases:
		 *
		 * 1) Switch from a user space task (potential attacker)
		 *    which has TIF_SPEC_IB set to a user space task
		 *    (potential victim) which has TIF_SPEC_IB not set.
		 *
		 * 2) Switch from a user space task (potential attacker)
		 *    which has TIF_SPEC_IB not set to a user space task
		 *    (potential victim) which has TIF_SPEC_IB set.
		 *
		 * This could be done by unconditionally issuing IBPB when
		 * a task which has TIF_SPEC_IB set is either scheduled in
		 * or out. Though that results in two flushes when:
		 *
		 * - the same user space task is scheduled out and later
		 *   scheduled in again and only a kernel thread ran in
		 *   between.
		 *
		 * - a user space task belonging to the same process is
		 *   scheduled in after a kernel thread ran in between
		 *
		 * - a user space task belonging to the same process is
		 *   scheduled in immediately.
		 *
		 * Optimize this with reasonably small overhead for the
		 * above cases. Mangle the TIF_SPEC_IB bit into the mm
		 * pointer of the incoming task which is stored in
		 * cpu_tlbstate.last_user_mm_spec for comparison.
		 *
		 * Issue IBPB only if the mm's are different and one or
		 * both have the IBPB bit set.
		 */
		if (next_mm != prev_mm &&
		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
			indirect_branch_prediction_barrier();
	}

	if (static_branch_unlikely(&switch_mm_always_ibpb)) {
		/*
		 * Only flush when switching to a user space task with a
		 * different context than the user space task which ran
		 * last on this CPU.
		 */
		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm)
			indirect_branch_prediction_barrier();
	}

	if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) {
		/*
		 * Flush L1D when the outgoing task requested it and/or
		 * check whether the incoming task requested L1D flushing
		 * and ended up on an SMT sibling.
		 */
		if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH))
			l1d_flush_evaluate(prev_mm, next_mm, next);
	}

	this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm);
}

#ifdef CONFIG_PERF_EVENTS
static inline void cr4_update_pce_mm(struct mm_struct *mm)
{
	if (static_branch_unlikely(&rdpmc_always_available_key) ||
	    (!static_branch_unlikely(&rdpmc_never_available_key) &&
	     atomic_read(&mm->context.perf_rdpmc_allowed))) {
		/*
		 * Clear the existing dirty counters to
		 * prevent the leak for an RDPMC task.
		 */
		perf_clear_dirty_counters();
		cr4_set_bits_irqsoff(X86_CR4_PCE);
	} else
		cr4_clear_bits_irqsoff(X86_CR4_PCE);
}

void cr4_update_pce(void *ignored)
{
	cr4_update_pce_mm(this_cpu_read(cpu_tlbstate.loaded_mm));
}

#else
static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
#endif

/*
 * This optimizes when not actually switching mm's.  Some architectures use the
 * 'unused' argument for this optimization, but x86 must use
 * 'cpu_tlbstate.loaded_mm' instead because it does not always keep
 * 'current->active_mm' up to date.
 */
void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
			struct task_struct *tsk)
{
	struct mm_struct *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_shared.is_lazy);
	unsigned cpu = smp_processor_id();
	unsigned long new_lam;
	struct new_asid ns;
	u64 next_tlb_gen;


	/* 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(prev->pgd, prev_asid,
						   tlbstate_lam_cr3_mask()))) {
		/*
		 * 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
	if (was_lazy)
		this_cpu_write(cpu_tlbstate_shared.is_lazy, false);

	/*
	 * The membarrier system call requires a full memory barrier and
	 * core serialization before returning to user-space, after
	 * storing to rq->curr, when changing mm.  This is because
	 * membarrier() sends IPIs to all CPUs that are in the target mm
	 * to make them issue memory barriers.  However, if another CPU
	 * switches to/from the target mm concurrently with
	 * membarrier(), it can cause that CPU not to receive an IPI
	 * when it really should issue a memory barrier.  Writing to CR3
	 * provides that full memory barrier and core serializing
	 * instruction.
	 */
	if (prev == next) {
		/* Not actually switching mm's */
		VM_WARN_ON(is_dyn_asid(prev_asid) &&
			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
			   next->context.ctx_id);

		/*
		 * If this races with another thread that enables lam, 'new_lam'
		 * might not match tlbstate_lam_cr3_mask().
		 */

		/*
		 * Even in lazy TLB mode, the CPU should stay set in the
		 * mm_cpumask. The TLB shootdown code can figure out from
		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
		 */
		if (IS_ENABLED(CONFIG_DEBUG_VM) &&
		    WARN_ON_ONCE(prev != &init_mm && !is_notrack_mm(prev) &&
				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
			cpumask_set_cpu(cpu, mm_cpumask(next));

		/* Check if the current mm is transitioning to a global ASID */
		if (mm_needs_global_asid(next, prev_asid)) {
			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
			ns = choose_new_asid(next, next_tlb_gen);
			goto reload_tlb;
		}

		/*
		 * Broadcast TLB invalidation keeps this ASID up to date
		 * all the time.
		 */
		if (is_global_asid(prev_asid))
			return;

		/*
		 * 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.
		 */
		ns.asid = prev_asid;
		ns.need_flush = true;
	} else {
		/*
		 * Apply process to process speculation vulnerability
		 * mitigations if applicable.
		 */
		cond_mitigation(tsk);

		/*
		 * Indicate that CR3 is about to change. nmi_uaccess_okay()
		 * and others are sensitive to the window where mm_cpumask(),
		 * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
		 */
		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);

		/*
		 * Make sure this CPU is set in mm_cpumask() such that we'll
		 * receive invalidation IPIs.
		 *
		 * Rely on the smp_mb() implied by cpumask_set_cpu()'s atomic
		 * operation, or explicitly provide one. Such that:
		 *
		 * switch_mm_irqs_off()				flush_tlb_mm_range()
		 *   smp_store_release(loaded_mm, SWITCHING);     atomic64_inc_return(tlb_gen)
		 *   smp_mb(); // here                            // smp_mb() implied
		 *   atomic64_read(tlb_gen);                      this_cpu_read(loaded_mm);
		 *
		 * we properly order against flush_tlb_mm_range(), where the
		 * loaded_mm load can happen in mative_flush_tlb_multi() ->
		 * should_flush_tlb().
		 *
		 * This way switch_mm() must see the new tlb_gen or
		 * flush_tlb_mm_range() must see the new loaded_mm, or both.
		 */
		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
			cpumask_set_cpu(cpu, mm_cpumask(next));
		else
			smp_mb();

		next_tlb_gen = atomic64_read(&next->context.tlb_gen);

		ns = choose_new_asid(next, next_tlb_gen);
	}

reload_tlb:
	new_lam = mm_lam_cr3_mask(next);
	if (ns.need_flush) {
		VM_WARN_ON_ONCE(is_global_asid(ns.asid));
		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].ctx_id, next->context.ctx_id);
		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].tlb_gen, next_tlb_gen);
		load_new_mm_cr3(next->pgd, ns.asid, new_lam, true);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
	} else {
		/* The new ASID is already up to date. */
		load_new_mm_cr3(next->pgd, ns.asid, new_lam, false);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
	}

	/* 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, ns.asid);
	cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next));

	if (next != prev) {
		cr4_update_pce_mm(next);
		switch_ldt(prev, next);
	}
}

/*
 * Using a temporary mm allows to set temporary mappings that are not accessible
 * by other CPUs. Such mappings are needed to perform sensitive memory writes
 * that override the kernel memory protections (e.g., W^X), without exposing the
 * temporary page-table mappings that are required for these write operations to
 * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
 * mapping is torn down.  Temporary mms can also be used for EFI runtime service
 * calls or similar functionality.
 *
 * It is illegal to schedule while using a temporary mm -- the context switch
 * code is unaware of the temporary mm and does not know how to context switch.
 * Use a real (non-temporary) mm in a kernel thread if you need to sleep.
 *
 * Note: For sensitive memory writes, the temporary mm needs to be used
 *       exclusively by a single core, and IRQs should be disabled while the
 *       temporary mm is loaded, thereby preventing interrupt handler bugs from
 *       overriding the kernel memory protection.
 */
struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm)
{
	struct mm_struct *prev_mm;

	lockdep_assert_preemption_disabled();
	guard(irqsave)();

	/*
	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
	 * with a stale address space WITHOUT being in lazy mode after
	 * restoring the previous mm.
	 */
	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
		leave_mm();

	prev_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	switch_mm_irqs_off(NULL, temp_mm, current);

	/*
	 * If breakpoints are enabled, disable them while the temporary mm is
	 * used. Userspace might set up watchpoints on addresses that are used
	 * in the temporary mm, which would lead to wrong signals being sent or
	 * crashes.
	 *
	 * Note that breakpoints are not disabled selectively, which also causes
	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
	 * undesirable, but still seems reasonable as the code that runs in the
	 * temporary mm should be short.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_disable();

	return prev_mm;
}

void unuse_temporary_mm(struct mm_struct *prev_mm)
{
	lockdep_assert_preemption_disabled();
	guard(irqsave)();

	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
	cpumask_clear_cpu(smp_processor_id(), mm_cpumask(this_cpu_read(cpu_tlbstate.loaded_mm)));

	switch_mm_irqs_off(NULL, prev_mm, current);

	/*
	 * Restore the breakpoints if they were disabled before the temporary mm
	 * was loaded.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_restore();
}

/*
 * 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 lam = mm_lam_cr3_mask(mm);
	unsigned long cr3 = __read_cr3();

	/* Assert that CR3 already references the right mm. */
	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));

	/* LAM expected to be disabled */
	WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
	WARN_ON(lam);

	/*
	 * 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));

	/* Disable LAM, force ASID 0 and force a TLB flush. */
	write_cr3(build_cr3(mm->pgd, 0, 0));

	/* Reinitialize tlbstate. */
	this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
	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);
	cpu_tlbstate_update_lam(lam, mm_untag_mask(mm));

	for (i = 1; i < TLB_NR_DYN_ASIDS; i++)
		this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0);
}

/*
 * flush_tlb_func()'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(void *info)
{
	/*
	 * 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.
	 */
	const struct flush_tlb_info *f = info;
	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 local_tlb_gen;
	bool local = smp_processor_id() == f->initiating_cpu;
	unsigned long nr_invalidate = 0;
	u64 mm_tlb_gen;

	/* This code cannot presently handle being reentered. */
	VM_WARN_ON(!irqs_disabled());

	if (!local) {
		inc_irq_stat(irq_tlb_count);
		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
	}

	/* The CPU was left in the mm_cpumask of the target mm. Clear it. */
	if (f->mm && f->mm != loaded_mm) {
		cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
		trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
		return;
	}

	if (unlikely(loaded_mm == &init_mm))
		return;

	/* Reload the ASID if transitioning into or out of a global ASID */
	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
		switch_mm_irqs_off(NULL, loaded_mm, NULL);
		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
	}

	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
	if (is_global_asid(loaded_mm_asid))
		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_shared.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.
		 *
		 * This should be rare, with native_flush_tlb_multi() skipping
		 * IPIs to lazy TLB mode CPUs.
		 */
		switch_mm_irqs_off(NULL, &init_mm, NULL);
		return;
	}

	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);

	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
		     f->new_tlb_gen <= local_tlb_gen)) {
		/*
		 * The TLB is already up to date in respect to f->new_tlb_gen.
		 * While the core might be still behind mm_tlb_gen, checking
		 * mm_tlb_gen unnecessarily would have negative caching effects
		 * so avoid it.
		 */
		return;
	}

	/*
	 * Defer mm_tlb_gen reading as long as possible to avoid cache
	 * contention.
	 */
	mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);

	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.
		 */
		goto done;
	}

	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_one_user() 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 optimization.
	 *    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 = f->start;

		/* Partial flush cannot have invalid generations */
		VM_WARN_ON(f->new_tlb_gen == TLB_GENERATION_INVALID);

		/* Partial flush must have valid mm */
		VM_WARN_ON(f->mm == NULL);

		nr_invalidate = (f->end - f->start) >> f->stride_shift;

		while (addr < f->end) {
			flush_tlb_one_user(addr);
			addr += 1UL << f->stride_shift;
		}
		if (local)
			count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
	} else {
		/* Full flush. */
		nr_invalidate = TLB_FLUSH_ALL;

		flush_tlb_local();
		if (local)
			count_vm_tlb_event(NR_TLB_LOCAL_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);

	/* Tracing is done in a unified manner to reduce the code size */
done:
	trace_tlb_flush(!local ? TLB_REMOTE_SHOOTDOWN :
				(f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN :
						  TLB_LOCAL_MM_SHOOTDOWN,
			nr_invalidate);
}

static bool should_flush_tlb(int cpu, void *data)
{
	struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
	struct flush_tlb_info *info = data;

	/*
	 * Order the 'loaded_mm' and 'is_lazy' against their
	 * write ordering in switch_mm_irqs_off(). Ensure
	 * 'is_lazy' is at least as new as 'loaded_mm'.
	 */
	smp_rmb();

	/* Lazy TLB will get flushed at the next context switch. */
	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
		return false;

	/* No mm means kernel memory flush. */
	if (!info->mm)
		return true;

	/*
	 * While switching, the remote CPU could have state from
	 * either the prev or next mm. Assume the worst and flush.
	 */
	if (loaded_mm == LOADED_MM_SWITCHING)
		return true;

	/* The target mm is loaded, and the CPU is not lazy. */
	if (loaded_mm == info->mm)
		return true;

	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
	if (info->trim_cpumask)
		return true;

	return false;
}

static bool should_trim_cpumask(struct mm_struct *mm)
{
	if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) {
		WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ);
		return true;
	}
	return false;
}

DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);

STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
					 const struct flush_tlb_info *info)
{
	/*
	 * Do accounting and tracing. Note that there are (and have always been)
	 * cases in which a remote TLB flush will be traced, but eventually
	 * would not happen.
	 */
	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 no page tables were freed, we can skip sending IPIs to
	 * CPUs in lazy TLB mode. They will flush the CPU themselves
	 * at the next context switch.
	 *
	 * However, if page tables are getting freed, we need to send the
	 * IPI everywhere, to prevent CPUs in lazy TLB mode from tripping
	 * up on the new contents of what used to be page tables, while
	 * doing a speculative memory access.
	 */
	if (info->freed_tables || mm_in_asid_transition(info->mm))
		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
	else
		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
				(void *)info, 1, cpumask);
}

void flush_tlb_multi(const struct cpumask *cpumask,
		      const struct flush_tlb_info *info)
{
	__flush_tlb_multi(cpumask, info);
}

/*
 * See Documentation/arch/x86/tlb.rst 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.
 */
unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;

static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);

#ifdef CONFIG_DEBUG_VM
static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
#endif

static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
			unsigned long start, unsigned long end,
			unsigned int stride_shift, bool freed_tables,
			u64 new_tlb_gen)
{
	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);

#ifdef CONFIG_DEBUG_VM
	/*
	 * Ensure that the following code is non-reentrant and flush_tlb_info
	 * is not overwritten. This means no TLB flushing is initiated by
	 * interrupt handlers and machine-check exception handlers.
	 */
	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
#endif

	/*
	 * If the number of flushes is so large that a full flush
	 * would be faster, do a full flush.
	 */
	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
		start = 0;
		end = TLB_FLUSH_ALL;
	}

	info->start		= start;
	info->end		= end;
	info->mm		= mm;
	info->stride_shift	= stride_shift;
	info->freed_tables	= freed_tables;
	info->new_tlb_gen	= new_tlb_gen;
	info->initiating_cpu	= smp_processor_id();
	info->trim_cpumask	= 0;

	return info;
}

static void put_flush_tlb_info(void)
{
#ifdef CONFIG_DEBUG_VM
	/* Complete reentrancy prevention checks */
	barrier();
	this_cpu_dec(flush_tlb_info_idx);
#endif
}

void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, unsigned int stride_shift,
				bool freed_tables)
{
	struct flush_tlb_info *info;
	int cpu = get_cpu();
	u64 new_tlb_gen;

	/* This is also a barrier that synchronizes with switch_mm(). */
	new_tlb_gen = inc_mm_tlb_gen(mm);

	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
				  new_tlb_gen);

	/*
	 * flush_tlb_multi() is not optimized for the common case in which only
	 * a local TLB flush is needed. Optimize this use-case by calling
	 * flush_tlb_func_local() directly in this case.
	 */
	if (mm_global_asid(mm)) {
		broadcast_tlb_flush(info);
	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
		info->trim_cpumask = should_trim_cpumask(mm);
		flush_tlb_multi(mm_cpumask(mm), info);
		consider_global_asid(mm);
	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
		lockdep_assert_irqs_enabled();
		local_irq_disable();
		flush_tlb_func(info);
		local_irq_enable();
	}

	put_flush_tlb_info();
	put_cpu();
	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
}

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);

	/* First try (faster) hardware-assisted TLB invalidation. */
	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
		invlpgb_flush_all();
	else
		/* Fall back to the IPI-based invalidation. */
		on_each_cpu(do_flush_tlb_all, NULL, 1);
}

/* Flush an arbitrarily large range of memory with INVLPGB. */
static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
{
	unsigned long addr, nr;

	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
		nr = (info->end - addr) >> PAGE_SHIFT;

		/*
		 * INVLPGB has a limit on the size of ranges it can
		 * flush. Break up large flushes.
		 */
		nr = clamp_val(nr, 1, invlpgb_count_max);

		invlpgb_flush_addr_nosync(addr, nr);
	}
	__tlbsync();
}

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_kernel(addr);
}

static void kernel_tlb_flush_all(struct flush_tlb_info *info)
{
	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
		invlpgb_flush_all();
	else
		on_each_cpu(do_flush_tlb_all, NULL, 1);
}

static void kernel_tlb_flush_range(struct flush_tlb_info *info)
{
	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
		invlpgb_kernel_range_flush(info);
	else
		on_each_cpu(do_kernel_range_flush, info, 1);
}

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	struct flush_tlb_info *info;

	guard(preempt)();

	info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false,
				  TLB_GENERATION_INVALID);

	if (info->end == TLB_FLUSH_ALL)
		kernel_tlb_flush_all(info);
	else
		kernel_tlb_flush_range(info);

	put_flush_tlb_info();
}

/*
 * This can be used from process context to figure out what the value of
 * CR3 is without needing to do a (slow) __read_cr3().
 *
 * It's intended to be used for code like KVM that sneakily changes CR3
 * and needs to restore it.  It needs to be used very carefully.
 */
unsigned long __get_current_cr3_fast(void)
{
	unsigned long cr3 =
		build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
			  this_cpu_read(cpu_tlbstate.loaded_mm_asid),
			  tlbstate_lam_cr3_mask());

	/* For now, be very restrictive about when this can be called. */
	VM_WARN_ON(in_nmi() || preemptible());

	VM_BUG_ON(cr3 != __read_cr3());
	return cr3;
}
EXPORT_SYMBOL_FOR_KVM(__get_current_cr3_fast);

/*
 * Flush one page in the kernel mapping
 */
void flush_tlb_one_kernel(unsigned long addr)
{
	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);

	/*
	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
	 * use PCID if we also use global PTEs for the kernel mapping, and
	 * INVLPG flushes global translations across all address spaces.
	 *
	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
	 * __flush_tlb_one_user() will flush the given address for the current
	 * kernel address space and for its usermode counterpart, but it does
	 * not flush it for other address spaces.
	 */
	flush_tlb_one_user(addr);

	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	/*
	 * See above.  We need to propagate the flush to all other address
	 * spaces.  In principle, we only need to propagate it to kernelmode
	 * address spaces, but the extra bookkeeping we would need is not
	 * worth it.
	 */
	this_cpu_write(cpu_tlbstate.invalidate_other, true);
}

/*
 * Flush one page in the user mapping
 */
STATIC_NOPV void native_flush_tlb_one_user(unsigned long addr)
{
	u32 loaded_mm_asid;
	bool cpu_pcide;

	/* Flush 'addr' from the kernel PCID: */
	invlpg(addr);

	/* If PTI is off there is no user PCID and nothing to flush. */
	if (!static_cpu_has(X86_FEATURE_PTI))
		return;

	loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
	cpu_pcide      = this_cpu_read(cpu_tlbstate.cr4) & X86_CR4_PCIDE;

	/*
	 * invpcid_flush_one(pcid>0) will #GP if CR4.PCIDE==0.  Check
	 * 'cpu_pcide' to ensure that *this* CPU will not trigger those
	 * #GP's even if called before CR4.PCIDE has been initialized.
	 */
	if (boot_cpu_has(X86_FEATURE_INVPCID) && cpu_pcide)
		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
	else
		invalidate_user_asid(loaded_mm_asid);
}

void flush_tlb_one_user(unsigned long addr)
{
	__flush_tlb_one_user(addr);
}

/*
 * Flush everything
 */
STATIC_NOPV void native_flush_tlb_global(void)
{
	unsigned long flags;

	if (static_cpu_has(X86_FEATURE_INVPCID)) {
		/*
		 * Using INVPCID is considerably faster than a pair of writes
		 * to CR4 sandwiched inside an IRQ flag save/restore.
		 *
		 * Note, this works with CR4.PCIDE=0 or 1.
		 */
		invpcid_flush_all();
		return;
	}

	/*
	 * Read-modify-write to CR4 - protect it from preemption and
	 * from interrupts. (Use the raw variant because this code can
	 * be called from deep inside debugging code.)
	 */
	raw_local_irq_save(flags);

	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));

	raw_local_irq_restore(flags);
}

/*
 * Flush the entire current user mapping
 */
STATIC_NOPV void native_flush_tlb_local(void)
{
	/*
	 * Preemption or interrupts must be disabled to protect the access
	 * to the per CPU variable and to prevent being preempted between
	 * read_cr3() and write_cr3().
	 */
	WARN_ON_ONCE(preemptible());

	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));

	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
	native_write_cr3(__native_read_cr3());
}

void flush_tlb_local(void)
{
	__flush_tlb_local();
}

/*
 * Flush everything
 */
void __flush_tlb_all(void)
{
	/*
	 * This is to catch users with enabled preemption and the PGE feature
	 * and don't trigger the warning in __native_flush_tlb().
	 */
	VM_WARN_ON_ONCE(preemptible());

	if (cpu_feature_enabled(X86_FEATURE_PGE)) {
		__flush_tlb_global();
	} else {
		/*
		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
		 */
		flush_tlb_local();
	}
}
EXPORT_SYMBOL_FOR_KVM(__flush_tlb_all);

void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
	struct flush_tlb_info *info;

	int cpu = get_cpu();

	info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false,
				  TLB_GENERATION_INVALID);
	/*
	 * flush_tlb_multi() is not optimized for the common case in which only
	 * a local TLB flush is needed. Optimize this use-case by calling
	 * flush_tlb_func_local() directly in this case.
	 */
	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
		invlpgb_flush_all_nonglobals();
		batch->unmapped_pages = false;
	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
		flush_tlb_multi(&batch->cpumask, info);
	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
		lockdep_assert_irqs_enabled();
		local_irq_disable();
		flush_tlb_func(info);
		local_irq_enable();
	}

	cpumask_clear(&batch->cpumask);

	put_flush_tlb_info();
	put_cpu();
}

/*
 * Blindly accessing user memory from NMI context can be dangerous
 * if we're in the middle of switching the current user task or
 * switching the loaded mm.  It can also be dangerous if we
 * interrupted some kernel code that was temporarily using a
 * different mm.
 */
bool nmi_uaccess_okay(void)
{
	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	struct mm_struct *current_mm = current->mm;

	VM_WARN_ON_ONCE(!loaded_mm);

	/*
	 * The condition we want to check is
	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
	 * is supposed to be reasonably fast.
	 *
	 * Instead, we check the almost equivalent but somewhat conservative
	 * condition below, and we rely on the fact that switch_mm_irqs_off()
	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
	 */
	if (loaded_mm != current_mm)
		return false;

	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());

	return true;
}

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);