summaryrefslogtreecommitdiff
path: root/arch/s390/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/mm')
-rw-r--r--arch/s390/mm/fault.c5
-rw-r--r--arch/s390/mm/gmap.c167
-rw-r--r--arch/s390/mm/hugetlbpage.c21
-rw-r--r--arch/s390/mm/init.c30
-rw-r--r--arch/s390/mm/mmap.c9
-rw-r--r--arch/s390/mm/vmem.c5
6 files changed, 171 insertions, 66 deletions
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index c421dd44ffbe..65747f15dbec 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -75,7 +75,7 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_PGSTE))
return KERNEL_FAULT;
gmap = (struct gmap *)S390_lowcore.gmap;
- if (regs->cr1 == gmap->asce)
+ if (gmap && gmap->asce == regs->cr1)
return GMAP_FAULT;
return KERNEL_FAULT;
}
@@ -325,7 +325,8 @@ static void do_exception(struct pt_regs *regs, int access)
goto lock_mmap;
if (!(vma->vm_flags & access)) {
vma_end_read(vma);
- goto lock_mmap;
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return handle_fault_error_nolock(regs, SEGV_ACCERR);
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 094b43b121cd..474a25ca5c48 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2550,41 +2550,6 @@ static inline void thp_split_mm(struct mm_struct *mm)
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * Remove all empty zero pages from the mapping for lazy refaulting
- * - This must be called after mm->context.has_pgste is set, to avoid
- * future creation of zero pages
- * - This must be called after THP was disabled.
- *
- * mm contracts with s390, that even if mm were to remove a page table,
- * racing with the loop below and so causing pte_offset_map_lock() to fail,
- * it will never insert a page table containing empty zero pages once
- * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
- */
-static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
- unsigned long end, struct mm_walk *walk)
-{
- unsigned long addr;
-
- for (addr = start; addr != end; addr += PAGE_SIZE) {
- pte_t *ptep;
- spinlock_t *ptl;
-
- ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
- if (!ptep)
- break;
- if (is_zero_pfn(pte_pfn(*ptep)))
- ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
- pte_unmap_unlock(ptep, ptl);
- }
- return 0;
-}
-
-static const struct mm_walk_ops zap_zero_walk_ops = {
- .pmd_entry = __zap_zero_pages,
- .walk_lock = PGWALK_WRLOCK,
-};
-
-/*
* switch on pgstes for its userspace process (for kvm)
*/
int s390_enable_sie(void)
@@ -2601,22 +2566,142 @@ int s390_enable_sie(void)
mm->context.has_pgste = 1;
/* split thp mappings and disable thp for future mappings */
thp_split_mm(mm);
- walk_page_range(mm, 0, TASK_SIZE, &zap_zero_walk_ops, NULL);
mmap_write_unlock(mm);
return 0;
}
EXPORT_SYMBOL_GPL(s390_enable_sie);
-int gmap_mark_unmergeable(void)
+static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ unsigned long *found_addr = walk->private;
+
+ /* Return 1 of the page is a zeropage. */
+ if (is_zero_pfn(pte_pfn(*pte))) {
+ /*
+ * Shared zeropage in e.g., a FS DAX mapping? We cannot do the
+ * right thing and likely don't care: FAULT_FLAG_UNSHARE
+ * currently only works in COW mappings, which is also where
+ * mm_forbids_zeropage() is checked.
+ */
+ if (!is_cow_mapping(walk->vma->vm_flags))
+ return -EFAULT;
+
+ *found_addr = addr;
+ return 1;
+ }
+ return 0;
+}
+
+static const struct mm_walk_ops find_zeropage_ops = {
+ .pte_entry = find_zeropage_pte_entry,
+ .walk_lock = PGWALK_WRLOCK,
+};
+
+/*
+ * Unshare all shared zeropages, replacing them by anonymous pages. Note that
+ * we cannot simply zap all shared zeropages, because this could later
+ * trigger unexpected userfaultfd missing events.
+ *
+ * This must be called after mm->context.allow_cow_sharing was
+ * set to 0, to avoid future mappings of shared zeropages.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * and racing with walk_page_range_vma() calling pte_offset_map_lock()
+ * would fail, it will never insert a page table containing empty zero
+ * pages once mm_forbids_zeropage(mm) i.e.
+ * mm->context.allow_cow_sharing is set to 0.
+ */
+static int __s390_unshare_zeropages(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, mm, 0);
+ unsigned long addr;
+ vm_fault_t fault;
+ int rc;
+
+ for_each_vma(vmi, vma) {
+ /*
+ * We could only look at COW mappings, but it's more future
+ * proof to catch unexpected zeropages in other mappings and
+ * fail.
+ */
+ if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma))
+ continue;
+ addr = vma->vm_start;
+
+retry:
+ rc = walk_page_range_vma(vma, addr, vma->vm_end,
+ &find_zeropage_ops, &addr);
+ if (rc < 0)
+ return rc;
+ else if (!rc)
+ continue;
+
+ /* addr was updated by find_zeropage_pte_entry() */
+ fault = handle_mm_fault(vma, addr,
+ FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
+ NULL);
+ if (fault & VM_FAULT_OOM)
+ return -ENOMEM;
+ /*
+ * See break_ksm(): even after handle_mm_fault() returned 0, we
+ * must start the lookup from the current address, because
+ * handle_mm_fault() may back out if there's any difficulty.
+ *
+ * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but
+ * maybe they could trigger in the future on concurrent
+ * truncation. In that case, the shared zeropage would be gone
+ * and we can simply retry and make progress.
+ */
+ cond_resched();
+ goto retry;
+ }
+
+ return 0;
+}
+
+static int __s390_disable_cow_sharing(struct mm_struct *mm)
{
+ int rc;
+
+ if (!mm->context.allow_cow_sharing)
+ return 0;
+
+ mm->context.allow_cow_sharing = 0;
+
+ /* Replace all shared zeropages by anonymous pages. */
+ rc = __s390_unshare_zeropages(mm);
/*
* Make sure to disable KSM (if enabled for the whole process or
* individual VMAs). Note that nothing currently hinders user space
* from re-enabling it.
*/
- return ksm_disable(current->mm);
+ if (!rc)
+ rc = ksm_disable(mm);
+ if (rc)
+ mm->context.allow_cow_sharing = 1;
+ return rc;
+}
+
+/*
+ * Disable most COW-sharing of memory pages for the whole process:
+ * (1) Disable KSM and unmerge/unshare any KSM pages.
+ * (2) Disallow shared zeropages and unshare any zerpages that are mapped.
+ *
+ * Not that we currently don't bother with COW-shared pages that are shared
+ * with parent/child processes due to fork().
+ */
+int s390_disable_cow_sharing(void)
+{
+ int rc;
+
+ mmap_write_lock(current->mm);
+ rc = __s390_disable_cow_sharing(current->mm);
+ mmap_write_unlock(current->mm);
+ return rc;
}
-EXPORT_SYMBOL_GPL(gmap_mark_unmergeable);
+EXPORT_SYMBOL_GPL(s390_disable_cow_sharing);
/*
* Enable storage key handling from now on and initialize the storage
@@ -2661,7 +2746,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
return 0;
start = pmd_val(*pmd) & HPAGE_MASK;
- end = start + HPAGE_SIZE - 1;
+ end = start + HPAGE_SIZE;
__storage_key_init_range(start, end);
set_bit(PG_arch_1, &page->flags);
cond_resched();
@@ -2685,7 +2770,7 @@ int s390_enable_skey(void)
goto out_up;
mm->context.uses_skeys = 1;
- rc = gmap_mark_unmergeable();
+ rc = __s390_disable_cow_sharing(mm);
if (rc) {
mm->context.uses_skeys = 0;
goto out_up;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index c2e8242bd15d..2675aab4acc7 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
}
if (!test_and_set_bit(PG_arch_1, &page->flags))
- __storage_key_init_range(paddr, paddr + size - 1);
+ __storage_key_init_range(paddr, paddr + size);
}
void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -233,16 +233,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return (pte_t *) pmdp;
}
-int pmd_huge(pmd_t pmd)
-{
- return pmd_leaf(pmd);
-}
-
-int pud_huge(pud_t pud)
-{
- return pud_leaf(pud);
-}
-
bool __init arch_hugetlb_valid_size(unsigned long size)
{
if (MACHINE_HAS_EDAT1 && size == PMD_SIZE)
@@ -258,14 +248,12 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
- info.flags = 0;
info.length = len;
info.low_limit = current->mm->mmap_base;
info.high_limit = TASK_SIZE;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
return vm_unmapped_area(&info);
}
@@ -274,7 +262,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
unsigned long addr;
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
@@ -282,7 +270,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
info.low_limit = PAGE_SIZE;
info.high_limit = current->mm->mmap_base;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
addr = vm_unmapped_area(&info);
/*
@@ -328,7 +315,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
goto check_asce_limit;
}
- if (mm->get_unmapped_area == arch_get_unmapped_area)
+ if (!test_bit(MMF_TOPDOWN, &mm->flags))
addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
else
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f6391442c0c2..e769d2726f4e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,7 @@
#include <asm/uv.h>
#include <linux/virtio_anchor.h>
#include <linux/virtio_config.h>
+#include <linux/execmem.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
@@ -302,3 +303,32 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long module_load_offset = 0;
+ unsigned long start;
+
+ if (kaslr_enabled())
+ module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + module_load_offset;
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index b14fc0887654..206756946589 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -86,7 +86,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
@@ -102,7 +102,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
goto check_asce_limit;
}
- info.flags = 0;
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = TASK_SIZE;
@@ -122,7 +121,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
/* requested length too big for entire address space */
if (len > TASK_SIZE - mmap_min_addr)
@@ -185,10 +184,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
*/
if (mmap_is_legacy(rlim_stack)) {
mm->mmap_base = mmap_base_legacy(random_factor);
- mm->get_unmapped_area = arch_get_unmapped_area;
+ clear_bit(MMF_TOPDOWN, &mm->flags);
} else {
mm->mmap_base = mmap_base(random_factor, rlim_stack);
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ set_bit(MMF_TOPDOWN, &mm->flags);
}
}
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 85cddf904cb2..41c714e21292 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -13,7 +13,9 @@
#include <linux/slab.h>
#include <linux/sort.h>
#include <asm/page-states.h>
+#include <asm/abs_lowcore.h>
#include <asm/cacheflush.h>
+#include <asm/maccess.h>
#include <asm/nospec-branch.h>
#include <asm/ctlreg.h>
#include <asm/pgalloc.h>
@@ -21,6 +23,7 @@
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/set_memory.h>
+#include <asm/physmem_info.h>
static DEFINE_MUTEX(vmem_mutex);
@@ -436,7 +439,7 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add,
if (WARN_ON_ONCE(!PAGE_ALIGNED(start | end)))
return -EINVAL;
/* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
- if (WARN_ON_ONCE(end > VMALLOC_START))
+ if (WARN_ON_ONCE(end > __abs_lowcore))
return -EINVAL;
for (addr = start; addr < end; addr = next) {
next = pgd_addr_end(addr, end);
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-02 08:50:24 +0300