aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/mm')
-rw-r--r--arch/s390/mm/cmm.c46
-rw-r--r--arch/s390/mm/fault.c109
-rw-r--r--arch/s390/mm/gmap.c79
-rw-r--r--arch/s390/mm/hugetlbpage.c11
-rw-r--r--arch/s390/mm/init.c9
-rw-r--r--arch/s390/mm/mmap.c40
-rw-r--r--arch/s390/mm/pageattr.c16
-rw-r--r--arch/s390/mm/pgalloc.c108
-rw-r--r--arch/s390/mm/vmem.c4
9 files changed, 234 insertions, 188 deletions
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index a51c892f14f3..ae989b740376 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -19,7 +19,6 @@
#include <linux/swap.h>
#include <linux/kthread.h>
#include <linux/oom.h>
-#include <linux/suspend.h>
#include <linux/uaccess.h>
#include <asm/pgalloc.h>
@@ -49,7 +48,6 @@ static volatile long cmm_pages_target;
static volatile long cmm_timed_pages_target;
static long cmm_timeout_pages;
static long cmm_timeout_seconds;
-static int cmm_suspended;
static struct cmm_page_array *cmm_page_list;
static struct cmm_page_array *cmm_timed_page_list;
@@ -151,9 +149,9 @@ static int cmm_thread(void *dummy)
while (1) {
rc = wait_event_interruptible(cmm_thread_wait,
- (!cmm_suspended && (cmm_pages != cmm_pages_target ||
- cmm_timed_pages != cmm_timed_pages_target)) ||
- kthread_should_stop());
+ cmm_pages != cmm_pages_target ||
+ cmm_timed_pages != cmm_timed_pages_target ||
+ kthread_should_stop());
if (kthread_should_stop() || rc == -ERESTARTSYS) {
cmm_pages_target = cmm_pages;
cmm_timed_pages_target = cmm_timed_pages;
@@ -390,38 +388,6 @@ static void cmm_smsg_target(const char *from, char *msg)
static struct ctl_table_header *cmm_sysctl_header;
-static int cmm_suspend(void)
-{
- cmm_suspended = 1;
- cmm_free_pages(cmm_pages, &cmm_pages, &cmm_page_list);
- cmm_free_pages(cmm_timed_pages, &cmm_timed_pages, &cmm_timed_page_list);
- return 0;
-}
-
-static int cmm_resume(void)
-{
- cmm_suspended = 0;
- cmm_kick_thread();
- return 0;
-}
-
-static int cmm_power_event(struct notifier_block *this,
- unsigned long event, void *ptr)
-{
- switch (event) {
- case PM_POST_HIBERNATION:
- return cmm_resume();
- case PM_HIBERNATION_PREPARE:
- return cmm_suspend();
- default:
- return NOTIFY_DONE;
- }
-}
-
-static struct notifier_block cmm_power_notifier = {
- .notifier_call = cmm_power_event,
-};
-
static int __init cmm_init(void)
{
int rc = -ENOMEM;
@@ -446,16 +412,11 @@ static int __init cmm_init(void)
rc = register_oom_notifier(&cmm_oom_nb);
if (rc < 0)
goto out_oom_notify;
- rc = register_pm_notifier(&cmm_power_notifier);
- if (rc)
- goto out_pm;
cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
if (!IS_ERR(cmm_thread_ptr))
return 0;
rc = PTR_ERR(cmm_thread_ptr);
- unregister_pm_notifier(&cmm_power_notifier);
-out_pm:
unregister_oom_notifier(&cmm_oom_nb);
out_oom_notify:
#ifdef CONFIG_CMM_IUCV
@@ -475,7 +436,6 @@ static void __exit cmm_exit(void)
#ifdef CONFIG_CMM_IUCV
smsg_unregister_callback(SMSG_PREFIX, cmm_smsg_target);
#endif
- unregister_pm_notifier(&cmm_power_notifier);
unregister_oom_notifier(&cmm_oom_nb);
kthread_stop(cmm_thread_ptr);
del_timer_sync(&cmm_timer);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 7b0bb475c166..dedc28be27ab 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -38,17 +38,18 @@
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/facility.h>
+#include <asm/uv.h>
#include "../kernel/entry.h"
#define __FAIL_ADDR_MASK -4096L
#define __SUBCODE_MASK 0x0600
#define __PF_RES_FIELD 0x8000000000000000ULL
-#define VM_FAULT_BADCONTEXT 0x010000
-#define VM_FAULT_BADMAP 0x020000
-#define VM_FAULT_BADACCESS 0x040000
-#define VM_FAULT_SIGNAL 0x080000
-#define VM_FAULT_PFAULT 0x100000
+#define VM_FAULT_BADCONTEXT ((__force vm_fault_t) 0x010000)
+#define VM_FAULT_BADMAP ((__force vm_fault_t) 0x020000)
+#define VM_FAULT_BADACCESS ((__force vm_fault_t) 0x040000)
+#define VM_FAULT_SIGNAL ((__force vm_fault_t) 0x080000)
+#define VM_FAULT_PFAULT ((__force vm_fault_t) 0x100000)
enum fault_type {
KERNEL_FAULT,
@@ -122,7 +123,7 @@ static void dump_pagetable(unsigned long asce, unsigned long address)
if (*table & _REGION_ENTRY_INVALID)
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
+ fallthrough;
case _ASCE_TYPE_REGION2:
table += (address & _REGION2_INDEX) >> _REGION2_SHIFT;
if (bad_address(table))
@@ -131,7 +132,7 @@ static void dump_pagetable(unsigned long asce, unsigned long address)
if (*table & _REGION_ENTRY_INVALID)
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
+ fallthrough;
case _ASCE_TYPE_REGION3:
table += (address & _REGION3_INDEX) >> _REGION3_SHIFT;
if (bad_address(table))
@@ -140,7 +141,7 @@ static void dump_pagetable(unsigned long asce, unsigned long address)
if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE))
goto out;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* fallthrough */
+ fallthrough;
case _ASCE_TYPE_SEGMENT:
table += (address & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
if (bad_address(table))
@@ -327,7 +328,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access,
case VM_FAULT_BADACCESS:
if (access == VM_EXEC && signal_return(regs) == 0)
break;
- /* fallthrough */
+ fallthrough;
case VM_FAULT_BADMAP:
/* Bad memory access. Check if it is kernel or user space. */
if (user_mode(regs)) {
@@ -337,9 +338,8 @@ static noinline void do_fault_error(struct pt_regs *regs, int access,
do_sigsegv(regs, si_code);
break;
}
- /* fallthrough */
+ fallthrough;
case VM_FAULT_BADCONTEXT:
- /* fallthrough */
case VM_FAULT_PFAULT:
do_no_context(regs);
break;
@@ -429,7 +429,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
- flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ flags = FAULT_FLAG_DEFAULT;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
@@ -480,8 +480,7 @@ retry:
* the fault.
*/
fault = handle_mm_fault(vma, address, flags);
- /* No reason to continue if interrupted by SIGKILL. */
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+ if (fault_signal_pending(fault, regs)) {
fault = VM_FAULT_SIGNAL;
if (flags & FAULT_FLAG_RETRY_NOWAIT)
goto out_up;
@@ -514,10 +513,7 @@ retry:
fault = VM_FAULT_PFAULT;
goto out_up;
}
- /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
- * of starvation. */
- flags &= ~(FAULT_FLAG_ALLOW_RETRY |
- FAULT_FLAG_RETRY_NOWAIT);
+ flags &= ~FAULT_FLAG_RETRY_NOWAIT;
flags |= FAULT_FLAG_TRIED;
down_read(&mm->mmap_sem);
goto retry;
@@ -584,7 +580,7 @@ void do_dat_exception(struct pt_regs *regs)
int access;
vm_fault_t fault;
- access = VM_READ | VM_EXEC | VM_WRITE;
+ access = VM_ACCESS_FLAGS;
fault = do_exception(regs, access);
if (unlikely(fault))
do_fault_error(regs, access, fault);
@@ -816,3 +812,78 @@ out_extint:
early_initcall(pfault_irq_init);
#endif /* CONFIG_PFAULT */
+
+#if IS_ENABLED(CONFIG_PGSTE)
+void do_secure_storage_access(struct pt_regs *regs)
+{
+ unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm;
+ struct page *page;
+ int rc;
+
+ switch (get_fault_type(regs)) {
+ case USER_FAULT:
+ mm = current->mm;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, addr);
+ if (!vma) {
+ up_read(&mm->mmap_sem);
+ do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+ break;
+ }
+ page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET);
+ if (IS_ERR_OR_NULL(page)) {
+ up_read(&mm->mmap_sem);
+ break;
+ }
+ if (arch_make_page_accessible(page))
+ send_sig(SIGSEGV, current, 0);
+ put_page(page);
+ up_read(&mm->mmap_sem);
+ break;
+ case KERNEL_FAULT:
+ page = phys_to_page(addr);
+ if (unlikely(!try_get_page(page)))
+ break;
+ rc = arch_make_page_accessible(page);
+ put_page(page);
+ if (rc)
+ BUG();
+ break;
+ case VDSO_FAULT:
+ case GMAP_FAULT:
+ default:
+ do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+ WARN_ON_ONCE(1);
+ }
+}
+NOKPROBE_SYMBOL(do_secure_storage_access);
+
+void do_non_secure_storage_access(struct pt_regs *regs)
+{
+ unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK;
+ struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
+
+ if (get_fault_type(regs) != GMAP_FAULT) {
+ do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL)
+ send_sig(SIGSEGV, current, 0);
+}
+NOKPROBE_SYMBOL(do_non_secure_storage_access);
+
+#else
+void do_secure_storage_access(struct pt_regs *regs)
+{
+ default_trap_handler(regs);
+}
+
+void do_non_secure_storage_access(struct pt_regs *regs)
+{
+ default_trap_handler(regs);
+}
+#endif
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index edcdca97e85e..1a95d8809cc3 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -787,14 +787,18 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
static inline unsigned long *gmap_table_walk(struct gmap *gmap,
unsigned long gaddr, int level)
{
+ const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
unsigned long *table;
if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
return NULL;
if (gmap_is_shadow(gmap) && gmap->removed)
return NULL;
- if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+
+ if (asce_type != _ASCE_TYPE_REGION1 &&
+ gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
return NULL;
+
table = gmap->table;
switch (gmap->asce & _ASCE_TYPE_MASK) {
case _ASCE_TYPE_REGION1:
@@ -804,7 +808,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
if (*table & _REGION_ENTRY_INVALID)
return NULL;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* Fallthrough */
+ fallthrough;
case _ASCE_TYPE_REGION2:
table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT;
if (level == 3)
@@ -812,7 +816,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
if (*table & _REGION_ENTRY_INVALID)
return NULL;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* Fallthrough */
+ fallthrough;
case _ASCE_TYPE_REGION3:
table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT;
if (level == 2)
@@ -820,7 +824,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
if (*table & _REGION_ENTRY_INVALID)
return NULL;
table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
- /* Fallthrough */
+ fallthrough;
case _ASCE_TYPE_SEGMENT:
table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
if (level == 1)
@@ -1840,6 +1844,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
goto out_free;
} else if (*table & _REGION_ENTRY_ORIGIN) {
rc = -EAGAIN; /* Race with shadow */
+ goto out_free;
}
crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
/* mark as invalid as long as the parent table is not protected */
@@ -2548,6 +2553,23 @@ int s390_enable_sie(void)
}
EXPORT_SYMBOL_GPL(s390_enable_sie);
+int gmap_mark_unmergeable(void)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int ret;
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+ MADV_UNMERGEABLE, &vma->vm_flags);
+ if (ret)
+ return ret;
+ }
+ mm->def_flags &= ~VM_MERGEABLE;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(gmap_mark_unmergeable);
+
/*
* Enable storage key handling from now on and initialize the storage
* keys with the default key.
@@ -2593,7 +2615,6 @@ static const struct mm_walk_ops enable_skey_walk_ops = {
int s390_enable_skey(void)
{
struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
int rc = 0;
down_write(&mm->mmap_sem);
@@ -2601,16 +2622,11 @@ int s390_enable_skey(void)
goto out_up;
mm->context.uses_skeys = 1;
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
- MADV_UNMERGEABLE, &vma->vm_flags)) {
- mm->context.uses_skeys = 0;
- rc = -ENOMEM;
- goto out_up;
- }
+ rc = gmap_mark_unmergeable();
+ if (rc) {
+ mm->context.uses_skeys = 0;
+ goto out_up;
}
- mm->def_flags &= ~VM_MERGEABLE;
-
walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL);
out_up:
@@ -2640,3 +2656,38 @@ void s390_reset_cmma(struct mm_struct *mm)
up_write(&mm->mmap_sem);
}
EXPORT_SYMBOL_GPL(s390_reset_cmma);
+
+/*
+ * make inaccessible pages accessible again
+ */
+static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pte_t pte = READ_ONCE(*ptep);
+
+ if (pte_present(pte))
+ WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK));
+ return 0;
+}
+
+static const struct mm_walk_ops reset_acc_walk_ops = {
+ .pte_entry = __s390_reset_acc,
+};
+
+#include <linux/sched/mm.h>
+void s390_reset_acc(struct mm_struct *mm)
+{
+ /*
+ * we might be called during
+ * reset: we walk the pages and clear
+ * close of all kvm file descriptors: we walk the pages and clear
+ * exit of process on fd closure: vma already gone, do nothing
+ */
+ if (!mmget_not_zero(mm))
+ return;
+ down_read(&mm->mmap_sem);
+ walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+}
+EXPORT_SYMBOL_GPL(s390_reset_acc);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 5674710a4841..f01daddcbc5e 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -326,7 +326,6 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
struct hstate *h = hstate_file(file);
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- int rc;
if (len & ~huge_page_mask(h))
return -EINVAL;
@@ -353,15 +352,9 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
else
addr = hugetlb_get_unmapped_area_topdown(file, addr, len,
pgoff, flags);
- if (addr & ~PAGE_MASK)
+ if (offset_in_page(addr))
return addr;
check_asce_limit:
- if (addr + len > current->mm->context.asce_limit &&
- addr + len <= TASK_SIZE) {
- rc = crst_table_upgrade(mm, addr + len);
- if (rc)
- return (unsigned long) rc;
- }
- return addr;
+ return check_asce_limit(mm, addr, len);
}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ac44bd76db4b..87b2d024e75a 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -268,20 +268,23 @@ device_initcall(s390_cma_mem_init);
#endif /* CONFIG_CMA */
int arch_add_memory(int nid, u64 start, u64 size,
- struct mhp_restrictions *restrictions)
+ struct mhp_params *params)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long size_pages = PFN_DOWN(size);
int rc;
- if (WARN_ON_ONCE(restrictions->altmap))
+ if (WARN_ON_ONCE(params->altmap))
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(params->pgprot.pgprot != PAGE_KERNEL.pgprot))
return -EINVAL;
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
- rc = __add_pages(nid, start_pfn, size_pages, restrictions);
+ rc = __add_pages(nid, start_pfn, size_pages, params);
if (rc)
vmem_remove_mapping(start, size);
return rc;
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index cbc718ba6d78..1b78f630a9ca 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -72,14 +72,13 @@ static inline unsigned long mmap_base(unsigned long rnd,
return PAGE_ALIGN(STACK_TOP - gap - rnd);
}
-unsigned long
-arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
- int rc;
if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
@@ -105,30 +104,20 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
addr = vm_unmapped_area(&info);
- if (addr & ~PAGE_MASK)
+ if (offset_in_page(addr))
return addr;
check_asce_limit:
- if (addr + len > current->mm->context.asce_limit &&
- addr + len <= TASK_SIZE) {
- rc = crst_table_upgrade(mm, addr + len);
- if (rc)
- return (unsigned long) rc;
- }
-
- return addr;
+ return check_asce_limit(mm, addr, len);
}
-unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
+unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- unsigned long addr = addr0;
struct vm_unmapped_area_info info;
- int rc;
/* requested length too big for entire address space */
if (len > TASK_SIZE - mmap_min_addr)
@@ -163,25 +152,18 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
* can happen with large stack limits and large mmap()
* allocations.
*/
- if (addr & ~PAGE_MASK) {
+ if (offset_in_page(addr)) {
VM_BUG_ON(addr != -ENOMEM);
info.flags = 0;
info.low_limit = TASK_UNMAPPED_BASE;
info.high_limit = TASK_SIZE;
addr = vm_unmapped_area(&info);
- if (addr & ~PAGE_MASK)
+ if (offset_in_page(addr))
return addr;
}
check_asce_limit:
- if (addr + len > current->mm->context.asce_limit &&
- addr + len <= TASK_SIZE) {
- rc = crst_table_upgrade(mm, addr + len);
- if (rc)
- return (unsigned long) rc;
- }
-
- return addr;
+ return check_asce_limit(mm, addr, len);
}
/*
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index f8c6faab41f4..e22c06d5f206 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -367,20 +367,4 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
}
}
-#ifdef CONFIG_HIBERNATION
-bool kernel_page_present(struct page *page)
-{
- unsigned long addr;
- int cc;
-
- addr = page_to_phys(page);
- asm volatile(
- " lra %1,0(%1)\n"
- " ipm %0\n"
- " srl %0,28"
- : "=d" (cc), "+a" (addr) : : "cc");
- return cc == 0;
-}
-#endif /* CONFIG_HIBERNATION */
-
#endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 3dd253f81a77..498c98a312f4 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -77,67 +77,65 @@ static void __crst_table_upgrade(void *arg)
int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
{
- unsigned long *table, *pgd;
- int rc, notify;
+ unsigned long *pgd = NULL, *p4d = NULL, *__pgd;
+ unsigned long asce_limit = mm->context.asce_limit;
/* upgrade should only happen from 3 to 4, 3 to 5, or 4 to 5 levels */
- VM_BUG_ON(mm->context.asce_limit < _REGION2_SIZE);
- rc = 0;
- notify = 0;
- while (mm->context.asce_limit < end) {
- table = crst_table_alloc(mm);
- if (!table) {
- rc = -ENOMEM;
- break;
- }
- spin_lock_bh(&mm->page_table_lock);
- pgd = (unsigned long *) mm->pgd;
- if (mm->context.asce_limit == _REGION2_SIZE) {
- crst_table_init(table, _REGION2_ENTRY_EMPTY);
- p4d_populate(mm, (p4d_t *) table, (pud_t *) pgd);
- mm->pgd = (pgd_t *) table;
- mm->context.asce_limit = _REGION1_SIZE;
- mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
- mm_inc_nr_puds(mm);
- } else {
- crst_table_init(table, _REGION1_ENTRY_EMPTY);
- pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
- mm->pgd = (pgd_t *) table;
- mm->context.asce_limit = -PAGE_SIZE;
- mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS | _ASCE_TYPE_REGION1;
- }
- notify = 1;
- spin_unlock_bh(&mm->page_table_lock);
- }
- if (notify)
- on_each_cpu(__crst_table_upgrade, mm, 0);
- return rc;
-}
+ VM_BUG_ON(asce_limit < _REGION2_SIZE);
-void crst_table_downgrade(struct mm_struct *mm)
-{
- pgd_t *pgd;
+ if (end <= asce_limit)
+ return 0;
- /* downgrade should only happen from 3 to 2 levels (compat only) */
- VM_BUG_ON(mm->context.asce_limit != _REGION2_SIZE);
+ if (asce_limit == _REGION2_SIZE) {
+ p4d = crst_table_alloc(mm);
+ if (unlikely(!p4d))
+ goto err_p4d;
+ crst_table_init(p4d, _REGION2_ENTRY_EMPTY);
+ }
+ if (end > _REGION1_SIZE) {
+ pgd = crst_table_alloc(mm);
+ if (unlikely(!pgd))
+ goto err_pgd;
+ crst_table_init(pgd, _REGION1_ENTRY_EMPTY);
+ }
- if (current->active_mm == mm) {
- clear_user_asce();
- __tlb_flush_mm(mm);
+ spin_lock_bh(&mm->page_table_lock);
+
+ /*
+ * This routine gets called with mmap_sem lock held and there is
+ * no reason to optimize for the case of otherwise. However, if
+ * that would ever change, the below check will let us know.
+ */
+ VM_BUG_ON(asce_limit != mm->context.asce_limit);
+
+ if (p4d) {
+ __pgd = (unsigned long *) mm->pgd;
+ p4d_populate(mm, (p4d_t *) p4d, (pud_t *) __pgd);
+ mm->pgd = (pgd_t *) p4d;
+ mm->context.asce_limit = _REGION1_SIZE;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+ mm_inc_nr_puds(mm);
+ }
+ if (pgd) {
+ __pgd = (unsigned long *) mm->pgd;
+ pgd_populate(mm, (pgd_t *) pgd, (p4d_t *) __pgd);
+ mm->pgd = (pgd_t *) pgd;
+ mm->context.asce_limit = TASK_SIZE_MAX;
+ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
+ _ASCE_USER_BITS | _ASCE_TYPE_REGION1;
}
- pgd = mm->pgd;
- mm_dec_nr_pmds(mm);
- mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
- mm->context.asce_limit = _REGION3_SIZE;
- mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
- _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
- crst_table_free(mm, (unsigned long *) pgd);
+ spin_unlock_bh(&mm->page_table_lock);
- if (current->active_mm == mm)
- set_user_asce(mm);
+ on_each_cpu(__crst_table_upgrade, mm, 0);
+
+ return 0;
+
+err_pgd:
+ crst_table_free(mm, p4d);
+err_p4d:
+ return -ENOMEM;
}
static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
@@ -304,7 +302,7 @@ void __tlb_remove_table(void *_table)
mask >>= 24;
if (mask != 0)
break;
- /* fallthrough */
+ fallthrough;
case 3: /* 4K page table with pgstes */
if (mask & 3)
atomic_xor_bits(&page->_refcount, 3 << 24);
@@ -529,7 +527,7 @@ void base_asce_free(unsigned long asce)
base_region2_walk(table, 0, _REGION1_SIZE, 0);
break;
case _ASCE_TYPE_REGION1:
- base_region1_walk(table, 0, -_PAGE_SIZE, 0);
+ base_region1_walk(table, 0, TASK_SIZE_MAX, 0);
break;
}
base_crst_free(table);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b403fa14847d..f810930aff42 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -415,6 +415,10 @@ void __init vmem_map_init(void)
SET_MEMORY_RO | SET_MEMORY_X);
__set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
SET_MEMORY_RO | SET_MEMORY_X);
+
+ /* we need lowcore executable for our LPSWE instructions */
+ set_memory_x(0, 1);
+
pr_info("Write protected kernel read-only data: %luk\n",
(unsigned long)(__end_rodata - _stext) >> 10);
}
Powered by cgit, Gruvboxed by Blaster4385.