summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/mm')
-rw-r--r--arch/x86/mm/Makefile12
-rw-r--r--arch/x86/mm/amdtopology.c1
-rw-r--r--arch/x86/mm/fault.c12
-rw-r--r--arch/x86/mm/hugetlbpage.c1
-rw-r--r--arch/x86/mm/ident_map.c1
-rw-r--r--arch/x86/mm/kasan_init_64.c1
-rw-r--r--arch/x86/mm/kaslr.c1
-rw-r--r--arch/x86/mm/kmemcheck/error.c1
-rw-r--r--arch/x86/mm/kmemcheck/error.h1
-rw-r--r--arch/x86/mm/kmemcheck/opcode.c1
-rw-r--r--arch/x86/mm/kmemcheck/opcode.h1
-rw-r--r--arch/x86/mm/kmemcheck/pte.c1
-rw-r--r--arch/x86/mm/kmemcheck/pte.h1
-rw-r--r--arch/x86/mm/kmemcheck/selftest.c1
-rw-r--r--arch/x86/mm/kmemcheck/selftest.h1
-rw-r--r--arch/x86/mm/kmemcheck/shadow.h1
-rw-r--r--arch/x86/mm/kmmio.c1
-rw-r--r--arch/x86/mm/mm_internal.h1
-rw-r--r--arch/x86/mm/mpx.c1
-rw-r--r--arch/x86/mm/numa_64.c1
-rw-r--r--arch/x86/mm/numa_emulation.c1
-rw-r--r--arch/x86/mm/numa_internal.h1
-rw-r--r--arch/x86/mm/pageattr-test.c1
-rw-r--r--arch/x86/mm/pat_internal.h1
-rw-r--r--arch/x86/mm/pat_rbtree.c1
-rw-r--r--arch/x86/mm/pgtable.c1
-rw-r--r--arch/x86/mm/pgtable_32.c1
-rw-r--r--arch/x86/mm/physaddr.c1
-rw-r--r--arch/x86/mm/physaddr.h1
-rw-r--r--arch/x86/mm/setup_nx.c1
-rw-r--r--arch/x86/mm/srat.c1
-rw-r--r--arch/x86/mm/tlb.c122
32 files changed, 125 insertions, 50 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 72bf8c01c6e3..7ba7f3d7f477 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,13 @@
-# Kernel does not boot with instrumentation of tlb.c.
-KCOV_INSTRUMENT_tlb.o := n
+# SPDX-License-Identifier: GPL-2.0
+# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c
+KCOV_INSTRUMENT_tlb.o := n
+KCOV_INSTRUMENT_mem_encrypt.o := n
+
+KASAN_SANITIZE_mem_encrypt.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_mem_encrypt.o = -pg
+endif
obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
pat.o pgtable.o physaddr.o setup_nx.o tlb.o
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index 91f501b2da3b..048c761d97b0 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* AMD NUMA support.
* Discover the memory map and associated nodes.
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e2baeaa053a5..b0ff378650a9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
@@ -1440,7 +1441,17 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if
* we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
+ *
+ * Note that handle_userfault() may also release and reacquire mmap_sem
+ * (and not return with VM_FAULT_RETRY), when returning to userland to
+ * repeat the page fault later with a VM_FAULT_NOPAGE retval
+ * (potentially after handling any pending signal during the return to
+ * userland). The return to userland is identified whenever
+ * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
+ * Thus we have to be careful about not touching vma after handling the
+ * fault, so we read the pkey beforehand.
*/
+ pkey = vma_pkey(vma);
fault = handle_mm_fault(vma, address, flags);
major |= fault & VM_FAULT_MAJOR;
@@ -1467,7 +1478,6 @@ good_area:
return;
}
- pkey = vma_pkey(vma);
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, &pkey, fault);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 6d06cf33e3de..8ae0000cbdb3 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* IA-32 Huge TLB Page Support for Kernel.
*
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 31cea988fa36..ab33a32df2a8 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Helper routines for building identity mapping page tables. This is
* included by both the compressed kernel and the regular kernel.
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index bc84b73684b7..8f5be3eb40dd 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
#include <linux/bootmem.h>
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index af599167fe3c..879ef930e2c2 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* This file implements KASLR memory randomization for x86_64. It randomizes
* the virtual address space of kernel memory regions (physical memory
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index dab41876cdd5..872ec4159a68 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/interrupt.h>
#include <linux/kdebug.h>
#include <linux/kmemcheck.h>
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
index 0efc2e8d0a20..39f80d7a874d 100644
--- a/arch/x86/mm/kmemcheck/error.h
+++ b/arch/x86/mm/kmemcheck/error.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H
#define ARCH__X86__MM__KMEMCHECK__ERROR_H
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index 324aa3f07237..df8109ddf7fe 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/types.h>
#include "opcode.h"
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
index 6956aad66b5b..51a1ce94c24a 100644
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ b/arch/x86/mm/kmemcheck/opcode.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H
#define ARCH__X86__MM__KMEMCHECK__OPCODE_H
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
index 4ead26eeaf96..8a03be90272a 100644
--- a/arch/x86/mm/kmemcheck/pte.c
+++ b/arch/x86/mm/kmemcheck/pte.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/mm.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
index 9f5966456492..b595612382c2 100644
--- a/arch/x86/mm/kmemcheck/pte.h
+++ b/arch/x86/mm/kmemcheck/pte.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH__X86__MM__KMEMCHECK__PTE_H
#define ARCH__X86__MM__KMEMCHECK__PTE_H
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
index aef7140c0063..7ce0be1f99eb 100644
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ b/arch/x86/mm/kmemcheck/selftest.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/bug.h>
#include <linux/kernel.h>
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
index 8fed4fe11f95..8d759aae453d 100644
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ b/arch/x86/mm/kmemcheck/selftest.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H
#define ARCH_X86_MM_KMEMCHECK_SELFTEST_H
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
index ff0b2f70fbcb..49768dc18664 100644
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ b/arch/x86/mm/kmemcheck/shadow.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H
#define ARCH__X86__MM__KMEMCHECK__SHADOW_H
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index afc47f5c9531..c21c2ed04612 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/* Support for MMIO probes.
* Benfit many code from kprobes
* (C) 2002 Louis Zhuang <louis.zhuang@intel.com>.
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 62474ba66c8e..4e1f6e1b8159 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __X86_MM_INTERNAL_H
#define __X86_MM_INTERNAL_H
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 9ceaa955d2ba..7eb06701a935 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* mpx.c - Memory Protection eXtensions
*
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9405ffc91502..066f3511d5f1 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Generic VM initialization for x86-64 NUMA setups.
* Copyright 2002,2003 Andi Kleen, SuSE Labs.
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index d805162e6045..34a2a3bfde9c 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* NUMA emulation
*/
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index ad86ec91e640..86860f279662 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __X86_MM_NUMA_INTERNAL_H
#define __X86_MM_NUMA_INTERNAL_H
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 5f169d5d76a8..a25588ad75ef 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* self test for change_page_attr.
*
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index a739bfc40690..eeb5caeb089b 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PAT_INTERNAL_H_
#define __PAT_INTERNAL_H_
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index d76485b22824..fa16036fa592 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Handle caching attributes in page tables (PAT)
*
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index b372f3442bbf..17ebc5a978cc 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/mm.h>
#include <linux/gfp.h>
#include <asm/pgalloc.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index b9bd5b8b14fa..6b9bf023a700 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c
index cfc3b9121ce4..7f9acb68324c 100644
--- a/arch/x86/mm/physaddr.c
+++ b/arch/x86/mm/physaddr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/bootmem.h>
#include <linux/mmdebug.h>
#include <linux/export.h>
diff --git a/arch/x86/mm/physaddr.h b/arch/x86/mm/physaddr.h
index a3cd5a0c97b3..9f6419cafc32 100644
--- a/arch/x86/mm/physaddr.h
+++ b/arch/x86/mm/physaddr.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#include <asm/processor.h>
static inline int phys_addr_valid(resource_size_t addr)
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index f65a33f505b6..adb3c5784dac 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/init.h>
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 3ea20d61b523..dac07e4f5834 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* ACPI 3.0 based NUMA setup
* Copyright 2004 Andi Kleen, SuSE Labs.
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 49d9778376d7..3118392cdf75 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,6 +30,7 @@
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+
static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
u16 *new_asid, bool *need_flush)
{
@@ -80,10 +81,11 @@ void leave_mm(int cpu)
return;
/* Warn if we're not lazy. */
- WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm)));
+ WARN_ON(!this_cpu_read(cpu_tlbstate.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)
@@ -142,45 +144,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
__flush_tlb_all();
}
#endif
+ this_cpu_write(cpu_tlbstate.is_lazy, false);
if (real_prev == next) {
- VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
- next->context.ctx_id);
-
- if (cpumask_test_cpu(cpu, mm_cpumask(next))) {
- /*
- * There's nothing to do: we weren't lazy, and we
- * aren't changing our mm. We don't need to flush
- * anything, nor do we need to update CR3, CR4, or
- * LDTR.
- */
- return;
- }
-
- /* Resume remote flushes and then read tlb_gen. */
- cpumask_set_cpu(cpu, mm_cpumask(next));
- next_tlb_gen = atomic64_read(&next->context.tlb_gen);
-
- if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) <
- next_tlb_gen) {
- /*
- * Ideally, we'd have a flush_tlb() variant that
- * takes the known CR3 value as input. This would
- * be faster on Xen PV and on hypothetical CPUs
- * on which INVPCID is fast.
- */
- this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
- next_tlb_gen);
- write_cr3(build_cr3(next, prev_asid));
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
- TLB_FLUSH_ALL);
- }
+ VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+ next->context.ctx_id);
/*
- * We just exited lazy mode, which means that CR4 and/or LDTR
- * may be stale. (Changes to the required CR4 and LDTR states
- * are not reflected in tlb_gen.)
+ * We don't currently support having a real mm loaded without
+ * our cpu set in mm_cpumask(). We have all the bookkeeping
+ * in place to figure out whether we would need to flush
+ * if our cpu were cleared in mm_cpumask(), but we don't
+ * currently use it.
*/
+ if (WARN_ON_ONCE(real_prev != &init_mm &&
+ !cpumask_test_cpu(cpu, mm_cpumask(next))))
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+
+ return;
} else {
u16 new_asid;
bool need_flush;
@@ -199,10 +180,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
}
/* Stop remote flushes for the previous mm */
- if (cpumask_test_cpu(cpu, mm_cpumask(real_prev)))
- cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
-
- VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+ VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
+ real_prev != &init_mm);
+ cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
/*
* Start remote flushes and then read tlb_gen.
@@ -216,12 +196,22 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
write_cr3(build_cr3(next, new_asid));
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
- TLB_FLUSH_ALL);
+
+ /*
+ * NB: This gets called via leave_mm() in the idle path
+ * where RCU functions differently. Tracing normally
+ * uses RCU, so we need to use the _rcuidle variant.
+ *
+ * (There is no good reason for this. The idle code should
+ * be rearranged to call this before rcu_idle_enter().)
+ */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
write_cr3(build_cr3_noflush(next, new_asid));
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
+
+ /* See above wrt _rcuidle. */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
this_cpu_write(cpu_tlbstate.loaded_mm, next);
@@ -233,6 +223,40 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
}
/*
+ * Please ignore the name of this function. It should be called
+ * switch_to_kernel_thread().
+ *
+ * enter_lazy_tlb() is a hint from the scheduler that we are entering a
+ * kernel thread or other context without an mm. Acceptable implementations
+ * include doing nothing whatsoever, switching to init_mm, or various clever
+ * lazy tricks to try to minimize TLB flushes.
+ *
+ * The scheduler reserves the right to call enter_lazy_tlb() several times
+ * in a row. It will notify us that we're going back to a real mm by
+ * calling switch_mm_irqs_off().
+ */
+void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+ if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
+ return;
+
+ if (tlb_defer_switch_to_init_mm()) {
+ /*
+ * There's a significant optimization that may be possible
+ * here. We have accurate enough TLB flush tracking that we
+ * don't need to maintain coherence of TLB per se when we're
+ * lazy. We do, however, need to maintain coherence of
+ * paging-structure caches. We could, in principle, leave our
+ * old mm loaded and only switch to init_mm when
+ * tlb_remove_page() happens.
+ */
+ this_cpu_write(cpu_tlbstate.is_lazy, true);
+ } else {
+ switch_mm(NULL, &init_mm, NULL);
+ }
+}
+
+/*
* Call this when reinitializing a CPU. It fixes the following potential
* problems:
*
@@ -303,16 +327,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
/* This code cannot presently handle being reentered. */
VM_WARN_ON(!irqs_disabled());
+ if (unlikely(loaded_mm == &init_mm))
+ return;
+
VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
loaded_mm->context.ctx_id);
- if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) {
+ if (this_cpu_read(cpu_tlbstate.is_lazy)) {
/*
- * We're in lazy mode -- don't flush. We can get here on
- * remote flushes due to races and on local flushes if a
- * kernel thread coincidentally flushes the mm it's lazily
- * still using.
+ * 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.
*/
+ switch_mm_irqs_off(NULL, &init_mm, NULL);
return;
}