blob: d89bb22589f660fb34a5786a243167245d0f4754 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/mm/context.c
*
* Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/bitops.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <asm/cpufeature.h>
#include <asm/mmu_context.h>
#include <asm/smp.h>
#include <asm/tlbflush.h>
static u32 asid_bits;
static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
static atomic64_t asid_generation;
static unsigned long *asid_map;
static DEFINE_PER_CPU(atomic64_t, active_asids);
static DEFINE_PER_CPU(u64, reserved_asids);
static cpumask_t tlb_flush_pending;
#define ASID_MASK (~GENMASK(asid_bits - 1, 0))
#define ASID_FIRST_VERSION (1UL << asid_bits)
#define NUM_USER_ASIDS ASID_FIRST_VERSION
#define asid2idx(asid) ((asid) & ~ASID_MASK)
#define idx2asid(idx) asid2idx(idx)
/* Get the ASIDBits supported by the current CPU */
static u32 get_cpu_asid_bits(void)
{
u32 asid;
int fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64MMFR0_EL1),
ID_AA64MMFR0_ASID_SHIFT);
switch (fld) {
default:
pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
smp_processor_id(), fld);
/* Fallthrough */
case 0:
asid = 8;
break;
case 2:
asid = 16;
}
return asid;
}
/* Check if the current cpu's ASIDBits is compatible with asid_bits */
void verify_cpu_asid_bits(void)
{
u32 asid = get_cpu_asid_bits();
if (asid < asid_bits) {
/*
* We cannot decrease the ASID size at runtime, so panic if we support
* fewer ASID bits than the boot CPU.
*/
pr_crit("CPU%d: smaller ASID size(%u) than boot CPU (%u)\n",
smp_processor_id(), asid, asid_bits);
cpu_panic_kernel();
}
}
static void set_kpti_asid_bits(void)
{
unsigned int len = BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(unsigned long);
/*
* In case of KPTI kernel/user ASIDs are allocated in
* pairs, the bottom bit distinguishes the two: if it
* is set, then the ASID will map only userspace. Thus
* mark even as reserved for kernel.
*/
memset(asid_map, 0xaa, len);
}
static void set_reserved_asid_bits(void)
{
if (arm64_kernel_unmapped_at_el0())
set_kpti_asid_bits();
else
bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
}
static void flush_context(void)
{
int i;
u64 asid;
/* Update the list of reserved ASIDs and the ASID bitmap. */
set_reserved_asid_bits();
for_each_possible_cpu(i) {
asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0);
/*
* If this CPU has already been through a
* rollover, but hasn't run another task in
* the meantime, we must preserve its reserved
* ASID, as this is the only trace we have of
* the process it is still running.
*/
if (asid == 0)
asid = per_cpu(reserved_asids, i);
__set_bit(asid2idx(asid), asid_map);
per_cpu(reserved_asids, i) = asid;
}
/*
* Queue a TLB invalidation for each CPU to perform on next
* context-switch
*/
cpumask_setall(&tlb_flush_pending);
}
static bool check_update_reserved_asid(u64 asid, u64 newasid)
{
int cpu;
bool hit = false;
/*
* Iterate over the set of reserved ASIDs looking for a match.
* If we find one, then we can update our mm to use newasid
* (i.e. the same ASID in the current generation) but we can't
* exit the loop early, since we need to ensure that all copies
* of the old ASID are updated to reflect the mm. Failure to do
* so could result in us missing the reserved ASID in a future
* generation.
*/
for_each_possible_cpu(cpu) {
if (per_cpu(reserved_asids, cpu) == asid) {
hit = true;
per_cpu(reserved_asids, cpu) = newasid;
}
}
return hit;
}
static u64 new_context(struct mm_struct *mm)
{
static u32 cur_idx = 1;
u64 asid = atomic64_read(&mm->context.id);
u64 generation = atomic64_read(&asid_generation);
if (asid != 0) {
u64 newasid = generation | (asid & ~ASID_MASK);
/*
* If our current ASID was active during a rollover, we
* can continue to use it and this was just a false alarm.
*/
if (check_update_reserved_asid(asid, newasid))
return newasid;
/*
* We had a valid ASID in a previous life, so try to re-use
* it if possible.
*/
if (!__test_and_set_bit(asid2idx(asid), asid_map))
return newasid;
}
/*
* Allocate a free ASID. If we can't find one, take a note of the
* currently active ASIDs and mark the TLBs as requiring flushes. We
* always count from ASID #2 (index 1), as we use ASID #0 when setting
* a reserved TTBR0 for the init_mm and we allocate ASIDs in even/odd
* pairs.
*/
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
if (asid != NUM_USER_ASIDS)
goto set_asid;
/* We're out of ASIDs, so increment the global generation count */
generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
&asid_generation);
flush_context();
/* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
set_asid:
__set_bit(asid, asid_map);
cur_idx = asid;
return idx2asid(asid) | generation;
}
void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
{
unsigned long flags;
u64 asid, old_active_asid;
if (system_supports_cnp())
cpu_set_reserved_ttbr0();
asid = atomic64_read(&mm->context.id);
/*
* The memory ordering here is subtle.
* If our active_asids is non-zero and the ASID matches the current
* generation, then we update the active_asids entry with a relaxed
* cmpxchg. Racing with a concurrent rollover means that either:
*
* - We get a zero back from the cmpxchg and end up waiting on the
* lock. Taking the lock synchronises with the rollover and so
* we are forced to see the updated generation.
*
* - We get a valid ASID back from the cmpxchg, which means the
* relaxed xchg in flush_context will treat us as reserved
* because atomic RmWs are totally ordered for a given location.
*/
old_active_asid = atomic64_read(&per_cpu(active_asids, cpu));
if (old_active_asid &&
!((asid ^ atomic64_read(&asid_generation)) >> asid_bits) &&
atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu),
old_active_asid, asid))
goto switch_mm_fastpath;
raw_spin_lock_irqsave(&cpu_asid_lock, flags);
/* Check that our ASID belongs to the current generation. */
asid = atomic64_read(&mm->context.id);
if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
asid = new_context(mm);
atomic64_set(&mm->context.id, asid);
}
if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
local_flush_tlb_all();
atomic64_set(&per_cpu(active_asids, cpu), asid);
raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
switch_mm_fastpath:
arm64_apply_bp_hardening();
/*
* Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
* emulating PAN.
*/
if (!system_uses_ttbr0_pan())
cpu_switch_mm(mm->pgd, mm);
}
/* Errata workaround post TTBRx_EL1 update. */
asmlinkage void post_ttbr_update_workaround(void)
{
asm(ALTERNATIVE("nop; nop; nop",
"ic iallu; dsb nsh; isb",
ARM64_WORKAROUND_CAVIUM_27456,
CONFIG_CAVIUM_ERRATUM_27456));
}
static int asids_update_limit(void)
{
unsigned long num_available_asids = NUM_USER_ASIDS;
if (arm64_kernel_unmapped_at_el0())
num_available_asids /= 2;
/*
* Expect allocation after rollover to fail if we don't have at least
* one more ASID than CPUs. ASID #0 is reserved for init_mm.
*/
WARN_ON(num_available_asids - 1 <= num_possible_cpus());
pr_info("ASID allocator initialised with %lu entries\n",
num_available_asids);
return 0;
}
arch_initcall(asids_update_limit);
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
atomic64_set(&asid_generation, ASID_FIRST_VERSION);
asid_map = kcalloc(BITS_TO_LONGS(NUM_USER_ASIDS), sizeof(*asid_map),
GFP_KERNEL);
if (!asid_map)
panic("Failed to allocate bitmap for %lu ASIDs\n",
NUM_USER_ASIDS);
/*
* We cannot call set_reserved_asid_bits() here because CPU
* caps are not finalized yet, so it is safer to assume KPTI
* and reserve kernel ASID's from beginning.
*/
if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0))
set_kpti_asid_bits();
return 0;
}
early_initcall(asids_init);