summaryrefslogtreecommitdiffstats
path: root/arch/x86/include
diff options
context:
space:
mode:
authorLinus Torvalds2018-08-23 23:55:01 +0200
committerLinus Torvalds2018-08-23 23:55:01 +0200
commit706a1ea65e6faaf853427a0e931f59d604dd45e3 (patch)
tree2c0ca7652ac5398c05f389bdd7d5b5377d43fee7 /arch/x86/include
parentMerge tag 'for-linus-4.19b-rc1b-tag' of git://git.kernel.org/pub/scm/linux/ke... (diff)
parentx86/mm: Only use tlb_remove_table() for paravirt (diff)
downloadkernel-qcow2-linux-706a1ea65e6faaf853427a0e931f59d604dd45e3.tar.gz
kernel-qcow2-linux-706a1ea65e6faaf853427a0e931f59d604dd45e3.tar.xz
kernel-qcow2-linux-706a1ea65e6faaf853427a0e931f59d604dd45e3.zip
Merge branch 'tlb-fixes'
Merge fixes for missing TLB shootdowns. This fixes a couple of cases that involved us possibly freeing page table structures before the required TLB shootdown had been done. There are a few cleanup patches to make the code easier to follow, and to avoid some of the more problematic cases entirely when not necessary. To make this easier for backports, it undoes the recent lazy TLB patches, because the cleanups and fixes are more important, and Rik is ok with re-doing them later when things have calmed down. The missing TLB flush was only delayed, and the wrong ordering only happened under memory pressure (and in theory under a couple of other fairly theoretical situations), so this may have been all very unlikely to have hit people in practice. But getting the TLB shootdown wrong is _so_ hard to debug and see that I consider this a crticial fix. Many thanks to Jann Horn for having debugged this. * tlb-fixes: x86/mm: Only use tlb_remove_table() for paravirt mm: mmu_notifier fix for tlb_end_vma mm/tlb, x86/mm: Support invalidating TLB caches for RCU_TABLE_FREE mm/tlb: Remove tlb_remove_table() non-concurrent condition mm: move tlb_table_flush to tlb_flush_mmu_free x86/mm/tlb: Revert the recent lazy TLB patches
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/paravirt.h5
-rw-r--r--arch/x86/include/asm/paravirt_types.h3
-rw-r--r--arch/x86/include/asm/tlbflush.h24
3 files changed, 27 insertions, 5 deletions
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index d49bbf4bb5c8..e375d4266b53 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -309,6 +309,11 @@ static inline void flush_tlb_others(const struct cpumask *cpumask,
PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info);
}
+static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+ PVOP_VCALL2(pv_mmu_ops.tlb_remove_table, tlb, table);
+}
+
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
{
return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 180bc0bff0fb..4b75acc23b30 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -54,6 +54,7 @@ struct desc_struct;
struct task_struct;
struct cpumask;
struct flush_tlb_info;
+struct mmu_gather;
/*
* Wrapper type for pointers to code which uses the non-standard
@@ -222,6 +223,8 @@ struct pv_mmu_ops {
void (*flush_tlb_others)(const struct cpumask *cpus,
const struct flush_tlb_info *info);
+ void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
+
/* Hooks for allocating and freeing a pagetable top-level */
int (*pgd_alloc)(struct mm_struct *mm);
void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 511bf5fae8b8..29c9da6c62fc 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -148,6 +148,22 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
#endif
+static inline bool tlb_defer_switch_to_init_mm(void)
+{
+ /*
+ * If we have PCID, then switching to init_mm is reasonably
+ * fast. If we don't have PCID, then switching to init_mm is
+ * quite slow, so we try to defer it in the hopes that we can
+ * avoid it entirely. The latter approach runs the risk of
+ * receiving otherwise unnecessary IPIs.
+ *
+ * This choice is just a heuristic. The tlb code can handle this
+ * function returning true or false regardless of whether we have
+ * PCID.
+ */
+ return !static_cpu_has(X86_FEATURE_PCID);
+}
+
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -536,11 +552,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, info) \
native_flush_tlb_others(mask, info)
-#endif
-extern void tlb_flush_remove_tables(struct mm_struct *mm);
-extern void tlb_flush_remove_tables_local(void *arg);
-
-#define HAVE_TLB_FLUSH_REMOVE_TABLES
+#define paravirt_tlb_remove_table(tlb, page) \
+ tlb_remove_page(tlb, (void *)(page))
+#endif
#endif /* _ASM_X86_TLBFLUSH_H */