summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig7
-rw-r--r--arch/x86/include/asm/io.h5
-rw-r--r--arch/x86/include/asm/pgtable.h28
-rw-r--r--arch/x86/include/asm/tlbflush.h24
-rw-r--r--arch/x86/mm/fault.c7
-rw-r--r--arch/x86/mm/pgtable.c47
-rw-r--r--arch/x86/mm/tlb.c2
-rw-r--r--arch/x86/xen/mmu_pv.c2
8 files changed, 72 insertions, 50 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8d9e4b362572..ad3a53e28aac 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -102,6 +102,7 @@ config X86
select ARCH_HAS_DEBUG_WX
select ARCH_HAS_ZONE_DMA_SET if EXPERT
select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
@@ -128,7 +129,8 @@ config X86
select ARCH_WANT_GENERAL_HUGETLB
select ARCH_WANT_HUGE_PMD_SHARE
select ARCH_WANT_LD_ORPHAN_WARN
- select ARCH_WANT_OPTIMIZE_VMEMMAP if X86_64
+ select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64
+ select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64
select ARCH_WANTS_THP_SWAP if X86_64
select ARCH_HAS_PARANOID_L1D_FLUSH
select BUILDTIME_TABLE_SORT
@@ -2599,9 +2601,6 @@ config ARCH_HAS_ADD_PAGES
def_bool y
depends on ARCH_ENABLE_MEMORY_HOTPLUG
-config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
- def_bool y
-
menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e9025640f634..76238842406a 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -35,9 +35,6 @@
* - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*/
-#define ARCH_HAS_IOREMAP_WC
-#define ARCH_HAS_IOREMAP_WT
-
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/cc_platform.h>
@@ -212,8 +209,6 @@ void memset_io(volatile void __iomem *, int, size_t);
#define memcpy_toio memcpy_toio
#define memset_io memset_io
-#include <asm-generic/iomap.h>
-
/*
* ISA space is 'always mapped' on a typical x86 system, no need to
* explicitly ioremap() it. The fact that the ISA IO space is mapped
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5700bb337987..dbf8af70b7c2 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -185,6 +185,8 @@ static inline int pte_special(pte_t pte)
static inline u64 protnone_mask(u64 val);
+#define PFN_PTE_SHIFT PAGE_SHIFT
+
static inline unsigned long pte_pfn(pte_t pte)
{
phys_addr_t pfn = pte_val(pte);
@@ -1020,24 +1022,17 @@ static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp)
return res;
}
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
-{
- page_table_check_pte_set(mm, addr, ptep, pte);
- set_pte(ptep, pte);
-}
-
static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp, pmd_t pmd)
{
- page_table_check_pmd_set(mm, addr, pmdp, pmd);
+ page_table_check_pmd_set(mm, pmdp, pmd);
set_pmd(pmdp, pmd);
}
static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
pud_t *pudp, pud_t pud)
{
- page_table_check_pud_set(mm, addr, pudp, pud);
+ page_table_check_pud_set(mm, pudp, pud);
native_set_pud(pudp, pud);
}
@@ -1068,7 +1063,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
pte_t pte = native_ptep_get_and_clear(ptep);
- page_table_check_pte_clear(mm, addr, pte);
+ page_table_check_pte_clear(mm, pte);
return pte;
}
@@ -1084,7 +1079,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
* care about updates and native needs no locking
*/
pte = native_local_ptep_get_and_clear(ptep);
- page_table_check_pte_clear(mm, addr, pte);
+ page_table_check_pte_clear(mm, pte);
} else {
pte = ptep_get_and_clear(mm, addr, ptep);
}
@@ -1133,7 +1128,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long
{
pmd_t pmd = native_pmdp_get_and_clear(pmdp);
- page_table_check_pmd_clear(mm, addr, pmd);
+ page_table_check_pmd_clear(mm, pmd);
return pmd;
}
@@ -1144,7 +1139,7 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
{
pud_t pud = native_pudp_get_and_clear(pudp);
- page_table_check_pud_clear(mm, addr, pud);
+ page_table_check_pud_clear(mm, pud);
return pud;
}
@@ -1167,7 +1162,7 @@ static inline int pud_write(pud_t pud)
static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
- page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
+ page_table_check_pmd_set(vma->vm_mm, pmdp, pmd);
if (IS_ENABLED(CONFIG_SMP)) {
return xchg(pmdp, pmd);
} else {
@@ -1292,6 +1287,11 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
}
+static inline void update_mmu_cache_range(struct vm_fault *vmf,
+ struct vm_area_struct *vma, unsigned long addr,
+ pte_t *ptep, unsigned int nr)
+{
+}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd)
{
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 80450e1d5385..6ab42caaa67a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -3,6 +3,7 @@
#define _ASM_X86_TLBFLUSH_H
#include <linux/mm_types.h>
+#include <linux/mmu_notifier.h>
#include <linux/sched.h>
#include <asm/processor.h>
@@ -253,6 +254,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
}
+static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+ bool should_defer = false;
+
+ /* If remote CPUs need to be flushed then defer batch the flush */
+ if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids)
+ should_defer = true;
+ put_cpu();
+
+ return should_defer;
+}
+
static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
{
/*
@@ -264,11 +277,18 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
return atomic64_inc_return(&mm->context.tlb_gen);
}
-static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
- struct mm_struct *mm)
+static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm,
+ unsigned long uaddr)
{
inc_mm_tlb_gen(mm);
cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+ mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
+}
+
+static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
+{
+ flush_tlb_mm(mm);
}
extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e8711b2cafaf..2e861b9360c7 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1328,7 +1328,6 @@ void do_user_addr_fault(struct pt_regs *regs,
}
#endif
-#ifdef CONFIG_PER_VMA_LOCK
if (!(flags & FAULT_FLAG_USER))
goto lock_mmap;
@@ -1341,7 +1340,8 @@ void do_user_addr_fault(struct pt_regs *regs,
goto lock_mmap;
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
- vma_end_read(vma);
+ if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+ vma_end_read(vma);
if (!(fault & VM_FAULT_RETRY)) {
count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
@@ -1358,7 +1358,6 @@ void do_user_addr_fault(struct pt_regs *regs,
return;
}
lock_mmap:
-#endif /* CONFIG_PER_VMA_LOCK */
retry:
vma = lock_mm_and_find_vma(mm, address, regs);
@@ -1418,9 +1417,7 @@ retry:
}
mmap_read_unlock(mm);
-#ifdef CONFIG_PER_VMA_LOCK
done:
-#endif
if (likely(!(fault & VM_FAULT_ERROR)))
return;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 15a8009a4480..d3a93e8766ee 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -52,7 +52,7 @@ early_param("userpte", setup_userpte);
void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
{
- pgtable_pte_page_dtor(pte);
+ pagetable_pte_dtor(page_ptdesc(pte));
paravirt_release_pte(page_to_pfn(pte));
paravirt_tlb_remove_table(tlb, pte);
}
@@ -60,7 +60,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
#if CONFIG_PGTABLE_LEVELS > 2
void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
{
- struct page *page = virt_to_page(pmd);
+ struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
/*
* NOTE! For PAE, any changes to the top page-directory-pointer-table
@@ -69,8 +69,8 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
#ifdef CONFIG_X86_PAE
tlb->need_flush_all = 1;
#endif
- pgtable_pmd_page_dtor(page);
- paravirt_tlb_remove_table(tlb, page);
+ pagetable_pmd_dtor(ptdesc);
+ paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc));
}
#if CONFIG_PGTABLE_LEVELS > 3
@@ -92,16 +92,16 @@ void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
static inline void pgd_list_add(pgd_t *pgd)
{
- struct page *page = virt_to_page(pgd);
+ struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
- list_add(&page->lru, &pgd_list);
+ list_add(&ptdesc->pt_list, &pgd_list);
}
static inline void pgd_list_del(pgd_t *pgd)
{
- struct page *page = virt_to_page(pgd);
+ struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
- list_del(&page->lru);
+ list_del(&ptdesc->pt_list);
}
#define UNSHARED_PTRS_PER_PGD \
@@ -112,12 +112,12 @@ static inline void pgd_list_del(pgd_t *pgd)
static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
{
- virt_to_page(pgd)->pt_mm = mm;
+ virt_to_ptdesc(pgd)->pt_mm = mm;
}
struct mm_struct *pgd_page_get_mm(struct page *page)
{
- return page->pt_mm;
+ return page_ptdesc(page)->pt_mm;
}
static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
@@ -213,11 +213,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
{
int i;
+ struct ptdesc *ptdesc;
for (i = 0; i < count; i++)
if (pmds[i]) {
- pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
- free_page((unsigned long)pmds[i]);
+ ptdesc = virt_to_ptdesc(pmds[i]);
+
+ pagetable_pmd_dtor(ptdesc);
+ pagetable_free(ptdesc);
mm_dec_nr_pmds(mm);
}
}
@@ -230,18 +233,24 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
if (mm == &init_mm)
gfp &= ~__GFP_ACCOUNT;
+ gfp &= ~__GFP_HIGHMEM;
for (i = 0; i < count; i++) {
- pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
- if (!pmd)
+ pmd_t *pmd = NULL;
+ struct ptdesc *ptdesc = pagetable_alloc(gfp, 0);
+
+ if (!ptdesc)
failed = true;
- if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) {
- free_page((unsigned long)pmd);
- pmd = NULL;
+ if (ptdesc && !pagetable_pmd_ctor(ptdesc)) {
+ pagetable_free(ptdesc);
+ ptdesc = NULL;
failed = true;
}
- if (pmd)
+ if (ptdesc) {
mm_inc_nr_pmds(mm);
+ pmd = ptdesc_address(ptdesc);
+ }
+
pmds[i] = pmd;
}
@@ -830,7 +839,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
free_page((unsigned long)pmd_sv);
- pgtable_pmd_page_dtor(virt_to_page(pmd));
+ pagetable_pmd_dtor(virt_to_ptdesc(pmd));
free_page((unsigned long)pmd);
return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 267acf27480a..2d253919b3e8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -10,6 +10,7 @@
#include <linux/debugfs.h>
#include <linux/sched/smt.h>
#include <linux/task_work.h>
+#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
@@ -1036,6 +1037,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
put_flush_tlb_info();
put_cpu();
+ mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
}
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index eb3bac0b22a1..1b5cba70c236 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -667,7 +667,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
spinlock_t *ptl = NULL;
#if USE_SPLIT_PTE_PTLOCKS
- ptl = ptlock_ptr(page);
+ ptl = ptlock_ptr(page_ptdesc(page));
spin_lock_nest_lock(ptl, &mm->page_table_lock);
#endif
generated by cgit v1.2.3 (git 2.39.0) at 2024-08-19 14:58:20 +0300