[S390] Remove data execution protection

The noexec support on s390 does not rely on a bit in the page table
entry but utilizes the secondary space mode to distinguish between
memory accesses for instructions vs. data. The noexec code relies
on the assumption that the cpu will always use the secondary space
page table for data accesses while it is running in the secondary
space mode. Up to the z9-109 class machines this has been the case.
Unfortunately this is not true anymore with z10 and later machines.
The load-relative-long instructions lrl, lgrl and lgfrl access the
memory operand using the same addressing-space mode that has been
used to fetch the instruction.
This breaks the noexec mode for all user space binaries compiled
with march=z10 or later. The only option is to remove the current
noexec support.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

3 files changed, 9 insertions, 108 deletions

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index ab98813..177745c 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -225,33 +225,6 @@ static noinline void do_sigbus(struct pt_regs *regs, long int_code,
 	force_sig_info(SIGBUS, &si, tsk);
 }
 
-#ifdef CONFIG_S390_EXEC_PROTECT
-static noinline int signal_return(struct pt_regs *regs, long int_code,
-				  unsigned long trans_exc_code)
-{
-	u16 instruction;
-	int rc;
-
-	rc = __get_user(instruction, (u16 __user *) regs->psw.addr);
-
-	if (!rc && instruction == 0x0a77) {
-		clear_tsk_thread_flag(current, TIF_PER_TRAP);
-		if (is_compat_task())
-			sys32_sigreturn();
-		else
-			sys_sigreturn();
-	} else if (!rc && instruction == 0x0aad) {
-		clear_tsk_thread_flag(current, TIF_PER_TRAP);
-		if (is_compat_task())
-			sys32_rt_sigreturn();
-		else
-			sys_rt_sigreturn();
-	} else
-		do_sigsegv(regs, int_code, SEGV_MAPERR, trans_exc_code);
-	return 0;
-}
-#endif /* CONFIG_S390_EXEC_PROTECT */
-
 static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 				    unsigned long trans_exc_code, int fault)
 {
@@ -259,13 +232,6 @@ static noinline void do_fault_error(struct pt_regs *regs, long int_code,
 
 	switch (fault) {
 	case VM_FAULT_BADACCESS:
-#ifdef CONFIG_S390_EXEC_PROTECT
-		if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
-		    (trans_exc_code & 3) == 0) {
-			signal_return(regs, int_code, trans_exc_code);
-			break;
-		}
-#endif /* CONFIG_S390_EXEC_PROTECT */
 	case VM_FAULT_BADMAP:
 		/* Bad memory access. Check if it is kernel or user space. */
 		if (regs->psw.mask & PSW_MASK_PSTATE) {
@@ -414,11 +380,6 @@ void __kprobes do_dat_exception(struct pt_regs *regs, long pgm_int_code,
 	int access, fault;
 
 	access = VM_READ | VM_EXEC | VM_WRITE;
-#ifdef CONFIG_S390_EXEC_PROTECT
-	if ((regs->psw.mask & PSW_MASK_ASC) == PSW_ASC_SECONDARY &&
-	    (trans_exc_code & 3) == 0)
-		access = VM_EXEC;
-#endif
 	fault = do_exception(regs, access, trans_exc_code);
 	if (unlikely(fault))
 		do_fault_error(regs, pgm_int_code & 255, trans_exc_code, fault);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 639cd21..a4d856d 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -13,7 +13,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *pteptr, pte_t pteval)
 {
 	pmd_t *pmdp = (pmd_t *) pteptr;
-	pte_t shadow_pteval = pteval;
 	unsigned long mask;
 
 	if (!MACHINE_HAS_HPAGE) {
@@ -21,18 +20,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		mask = pte_val(pteval) &
 				(_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO);
 		pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask;
-		if (mm->context.noexec) {
-			pteptr += PTRS_PER_PTE;
-			pte_val(shadow_pteval) =
-					(_SEGMENT_ENTRY + __pa(pteptr)) | mask;
-		}
 	}
 
 	pmd_val(*pmdp) = pte_val(pteval);
-	if (mm->context.noexec) {
-		pmdp = get_shadow_table(pmdp);
-		pmd_val(*pmdp) = pte_val(shadow_pteval);
-	}
 }
 
 int arch_prepare_hugepage(struct page *page)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index e1850c2..8d43306 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -40,7 +40,6 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
 
 static void __page_table_free(struct mm_struct *mm, unsigned long *table);
-static void __crst_table_free(struct mm_struct *mm, unsigned long *table);
 
 static struct rcu_table_freelist *rcu_table_freelist_get(struct mm_struct *mm)
 {
@@ -67,7 +66,7 @@ static void rcu_table_freelist_callback(struct rcu_head *head)
 	while (batch->pgt_index > 0)
 		__page_table_free(batch->mm, batch->table[--batch->pgt_index]);
 	while (batch->crst_index < RCU_FREELIST_SIZE)
-		__crst_table_free(batch->mm, batch->table[batch->crst_index++]);
+		crst_table_free(batch->mm, batch->table[batch->crst_index++]);
 	free_page((unsigned long) batch);
 }
 
@@ -125,63 +124,33 @@ static int __init parse_vmalloc(char *arg)
 }
 early_param("vmalloc", parse_vmalloc);
 
-unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
+unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
 	struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
 
 	if (!page)
 		return NULL;
-	page->index = 0;
-	if (noexec) {
-		struct page *shadow = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
-		if (!shadow) {
-			__free_pages(page, ALLOC_ORDER);
-			return NULL;
-		}
-		page->index = page_to_phys(shadow);
-	}
-	spin_lock_bh(&mm->context.list_lock);
-	list_add(&page->lru, &mm->context.crst_list);
-	spin_unlock_bh(&mm->context.list_lock);
 	return (unsigned long *) page_to_phys(page);
 }
 
-static void __crst_table_free(struct mm_struct *mm, unsigned long *table)
-{
-	unsigned long *shadow = get_shadow_table(table);
-
-	if (shadow)
-		free_pages((unsigned long) shadow, ALLOC_ORDER);
-	free_pages((unsigned long) table, ALLOC_ORDER);
-}
-
 void crst_table_free(struct mm_struct *mm, unsigned long *table)
 {
-	struct page *page = virt_to_page(table);
-
-	spin_lock_bh(&mm->context.list_lock);
-	list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
-	__crst_table_free(mm, table);
+	free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
 void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 {
 	struct rcu_table_freelist *batch;
-	struct page *page = virt_to_page(table);
 
-	spin_lock_bh(&mm->context.list_lock);
-	list_del(&page->lru);
-	spin_unlock_bh(&mm->context.list_lock);
 	if (atomic_read(&mm->mm_users) < 2 &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		__crst_table_free(mm, table);
+		crst_table_free(mm, table);
 		return;
 	}
 	batch = rcu_table_freelist_get(mm);
 	if (!batch) {
 		smp_call_function(smp_sync, NULL, 1);
-		__crst_table_free(mm, table);
+		crst_table_free(mm, table);
 		return;
 	}
 	batch->table[--batch->crst_index] = table;
@@ -197,7 +166,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 
 	BUG_ON(limit > (1UL << 53));
 repeat:
-	table = crst_table_alloc(mm, mm->context.noexec);
+	table = crst_table_alloc(mm);
 	if (!table)
 		return -ENOMEM;
 	spin_lock_bh(&mm->page_table_lock);
@@ -273,7 +242,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	unsigned long *table;
 	unsigned long bits;
 
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	spin_lock_bh(&mm->context.list_lock);
 	page = NULL;
 	if (!list_empty(&mm->context.pgtable_list)) {
@@ -329,7 +298,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 	struct page *page;
 	unsigned long bits;
 
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
@@ -366,7 +335,7 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 		page_table_free(mm, table);
 		return;
 	}
-	bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
+	bits = (mm->context.has_pgste) ? 3UL : 1UL;
 	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
@@ -379,25 +348,6 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 		rcu_table_freelist_finish();
 }
 
-void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
-{
-	struct page *page;
-
-	spin_lock_bh(&mm->context.list_lock);
-	/* Free shadow region and segment tables. */
-	list_for_each_entry(page, &mm->context.crst_list, lru)
-		if (page->index) {
-			free_pages((unsigned long) page->index, ALLOC_ORDER);
-			page->index = 0;
-		}
-	/* "Free" second halves of page tables. */
-	list_for_each_entry(page, &mm->context.pgtable_list, lru)
-		page->flags &= ~SECOND_HALVES;
-	spin_unlock_bh(&mm->context.list_lock);
-	mm->context.noexec = 0;
-	update_mm(mm, tsk);
-}
-
 /*
  * switch on pgstes for its userspace process (for kvm)
  */