105 lines
2.7 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* TLB shootdown specifics for powerpc
*
* Copyright (C) 2002 Anton Blanchard, IBM Corp.
* Copyright (C) 2002 Paul Mackerras, IBM Corp.
*/
#ifndef _ASM_POWERPC_TLB_H
#define _ASM_POWERPC_TLB_H
#ifdef __KERNEL__
#ifndef __powerpc64__
#include <asm/pgtable.h>
#endif
#include <asm/pgalloc.h>
#ifndef __powerpc64__
#include <asm/page.h>
#include <asm/mmu.h>
#endif
#include <linux/pagemap.h>
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
#define tlb_flush tlb_flush
extern void tlb_flush(struct mmu_gather *tlb);
mm/mmu_gather: invalidate TLB correctly on batch allocation failure and flush Architectures for which we have hardware walkers of Linux page table should flush TLB on mmu gather batch allocation failures and batch flush. Some architectures like POWER supports multiple translation modes (hash and radix) and in the case of POWER only radix translation mode needs the above TLBI. This is because for hash translation mode kernel wants to avoid this extra flush since there are no hardware walkers of linux page table. With radix translation, the hardware also walks linux page table and with that, kernel needs to make sure to TLB invalidate page walk cache before page table pages are freed. More details in commit d86564a2f085 ("mm/tlb, x86/mm: Support invalidating TLB caches for RCU_TABLE_FREE") The changes to sparc are to make sure we keep the old behavior since we are now removing HAVE_RCU_TABLE_NO_INVALIDATE. The default value for tlb_needs_table_invalidate is to always force an invalidate and sparc can avoid the table invalidate. Hence we define tlb_needs_table_invalidate to false for sparc architecture. Link: http://lkml.kernel.org/r/20200116064531.483522-3-aneesh.kumar@linux.ibm.com Fixes: a46cc7a90fd8 ("powerpc/mm/radix: Improve TLB/PWC flushes") Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Cc: <stable@vger.kernel.org> [4.14+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-03 17:36:49 -08:00
/*
* book3s:
* Hash does not use the linux page-tables, so we can avoid
* the TLB invalidate for page-table freeing, Radix otoh does use the
* page-tables and needs the TLBI.
*
* nohash:
* We still do TLB invalidate in the __pte_free_tlb routine before we
* add the page table pages to mmu gather table batch.
*/
#define tlb_needs_table_invalidate() radix_enabled()
/* Get the generic bits... */
#include <asm-generic/tlb.h>
extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
unsigned long address);
static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
unsigned long address)
{
#ifdef CONFIG_PPC_BOOK3S_32
if (pte_val(*ptep) & _PAGE_HASHPTE)
flush_hash_entry(tlb->mm, ptep, address);
#endif
}
#ifdef CONFIG_SMP
static inline int mm_is_core_local(struct mm_struct *mm)
{
return cpumask_subset(mm_cpumask(mm),
topology_sibling_cpumask(smp_processor_id()));
}
#ifdef CONFIG_PPC_BOOK3S_64
static inline int mm_is_thread_local(struct mm_struct *mm)
{
if (atomic_read(&mm->context.active_cpus) > 1)
return false;
return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm));
}
powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask When a single-threaded process has a non-local mm_cpumask, try to use that point to flush the TLBs out of other CPUs in the cpumask. An IPI is used for clearing remote CPUs for a few reasons: - An IPI can end lazy TLB use of the mm, which is required to prevent TLB entries being created on the remote CPU. The alternative is to drop lazy TLB switching completely, which costs 7.5% in a context switch ping-pong test betwee a process and kernel idle thread. - An IPI can have remote CPUs flush the entire PID, but the local CPU can flush a specific VA. tlbie would require over-flushing of the local CPU (where the process is running). - A single threaded process that is migrated to a different CPU is likely to have a relatively small mm_cpumask, so IPI is reasonable. No other thread can concurrently switch to this mm, because it must have been given a reference to mm_users by the current thread before it can use_mm. mm_users can be asynchronously incremented (by mm_activate or mmget_not_zero), but those users must use remote mm access and can't use_mm or access user address space. Existing code makes the this assumption already, for example sparc64 has reset mm_cpumask using this condition since the start of history, see arch/sparc/kernel/smp_64.c. This reduces tlbies for a kernel compile workload from 0.90M to 0.12M, tlbiels are increased significantly due to the PID flushing for the cleaning up remote CPUs, and increased local flushes (PID flushes take 128 tlbiels vs 1 tlbie). Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2018-06-01 20:01:21 +10:00
static inline void mm_reset_thread_local(struct mm_struct *mm)
{
WARN_ON(atomic_read(&mm->context.copros) > 0);
/*
* It's possible for mm_access to take a reference on mm_users to
* access the remote mm from another thread, but it's not allowed
* to set mm_cpumask, so mm_users may be > 1 here.
*/
WARN_ON(current->mm != mm);
atomic_set(&mm->context.active_cpus, 1);
cpumask_clear(mm_cpumask(mm));
cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
}
#else /* CONFIG_PPC_BOOK3S_64 */
static inline int mm_is_thread_local(struct mm_struct *mm)
{
return cpumask_equal(mm_cpumask(mm),
cpumask_of(smp_processor_id()));
}
#endif /* !CONFIG_PPC_BOOK3S_64 */
#else /* CONFIG_SMP */
static inline int mm_is_core_local(struct mm_struct *mm)
{
return 1;
}
static inline int mm_is_thread_local(struct mm_struct *mm)
{
return 1;
}
#endif
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_TLB_H */