Merge tag 's390-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Heiko Carstens:

 - Add support for the hugetlb_cma command line option to allocate
   gigantic hugepages using CMA

 - Add arch_get_random_long() support.

 - Add ap bus userspace notifications.

 - Increase default size of vmalloc area to 512GB and otherwise let it
   increase dynamically by the size of physical memory. This should fix
   all occurrences where the vmalloc area was not large enough.

 - Completely get rid of set_fs() (aka select SET_FS) and rework address
   space handling while doing that; making address space handling much
   more simple.

 - Reimplement getcpu vdso syscall in C.

 - Add support for extended SCLP responses (> 4k). This allows e.g. to
   handle also potential large system configurations.

 - Simplify KASAN by removing 3-level page table support and only
   supporting 4-levels from now on.

 - Improve debug-ability of the kernel decompressor code, which now
   prints also stack traces and symbols in case of problems to the
   console.

 - Remove more power management leftovers.

 - Other various fixes and improvements all over the place.

* tag 's390-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (62 commits)
  s390/mm: add support to allocate gigantic hugepages using CMA
  s390/crypto: add arch_get_random_long() support
  s390/smp: perform initial CPU reset also for SMT siblings
  s390/mm: use invalid asce for user space when switching to init_mm
  s390/idle: fix accounting with machine checks
  s390/idle: add missing mt_cycles calculation
  s390/boot: add build-id to decompressor
  s390/kexec_file: fix diag308 subcode when loading crash kernel
  s390/cio: fix use-after-free in ccw_device_destroy_console
  s390/cio: remove pm support from ccw bus driver
  s390/cio: remove pm support from css-bus driver
  s390/cio: remove pm support from IO subchannel drivers
  s390/cio: remove pm support from chsc subchannel driver
  s390/vmur: remove unused pm related functions
  s390/tape: remove unsupported PM functions
  s390/cio: remove pm support from eadm-sch drivers
  s390: remove pm support from console drivers
  s390/dasd: remove unused pm related functions
  s390/zfcp: remove pm support from zfcp driver
  s390/ap: let bus_register() add the AP bus sysfs attributes
  ...

6 files changed, 71 insertions, 116 deletions

diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 8f9ff7e7187d..e40a30647d99 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -255,7 +255,7 @@ static int pt_dump_init(void)
 	 */
 	max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2;
 	max_addr = 1UL << (max_addr * 11 + 31);
-	address_markers[IDENTITY_AFTER_END_NR].start_address = memory_end;
+	address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size;
 	address_markers[MODULES_NR].start_address = MODULES_VADDR;
 	address_markers[MODULES_END_NR].start_address = MODULES_END;
 	address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 996884dcc9fd..b8210103de14 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -53,7 +53,6 @@
 enum fault_type {
 	KERNEL_FAULT,
 	USER_FAULT,
-	VDSO_FAULT,
 	GMAP_FAULT,
 };
 
@@ -77,22 +76,16 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
 	trans_exc_code = regs->int_parm_long & 3;
 	if (likely(trans_exc_code == 0)) {
 		/* primary space exception */
-		if (IS_ENABLED(CONFIG_PGSTE) &&
-		    test_pt_regs_flag(regs, PIF_GUEST_FAULT))
-			return GMAP_FAULT;
-		if (current->thread.mm_segment == USER_DS)
+		if (user_mode(regs))
 			return USER_FAULT;
-		return KERNEL_FAULT;
-	}
-	if (trans_exc_code == 2) {
-		/* secondary space exception */
-		if (current->thread.mm_segment & 1) {
-			if (current->thread.mm_segment == USER_DS_SACF)
-				return USER_FAULT;
+		if (!IS_ENABLED(CONFIG_PGSTE))
 			return KERNEL_FAULT;
-		}
-		return VDSO_FAULT;
+		if (test_pt_regs_flag(regs, PIF_GUEST_FAULT))
+			return GMAP_FAULT;
+		return KERNEL_FAULT;
 	}
+	if (trans_exc_code == 2)
+		return USER_FAULT;
 	if (trans_exc_code == 1) {
 		/* access register mode, not used in the kernel */
 		return USER_FAULT;
@@ -188,10 +181,6 @@ static void dump_fault_info(struct pt_regs *regs)
 		asce = S390_lowcore.user_asce;
 		pr_cont("user ");
 		break;
-	case VDSO_FAULT:
-		asce = S390_lowcore.vdso_asce;
-		pr_cont("vdso ");
-		break;
 	case GMAP_FAULT:
 		asce = ((struct gmap *) S390_lowcore.gmap)->asce;
 		pr_cont("gmap ");
@@ -414,9 +403,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	switch (type) {
 	case KERNEL_FAULT:
 		goto out;
-	case VDSO_FAULT:
-		fault = VM_FAULT_BADMAP;
-		goto out;
 	case USER_FAULT:
 	case GMAP_FAULT:
 		if (faulthandler_disabled() || !mm)
@@ -834,7 +820,6 @@ void do_secure_storage_access(struct pt_regs *regs)
 		if (rc)
 			BUG();
 		break;
-	case VDSO_FAULT:
 	case GMAP_FAULT:
 	default:
 		do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 77767850d0d0..73a163065b95 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,9 @@
 #include <linux/virtio_config.h>
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
+static pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
+
+unsigned long s390_invalid_asce;
 
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
@@ -92,6 +95,9 @@ void __init paging_init(void)
 	unsigned long pgd_type, asce_bits;
 	psw_t psw;
 
+	s390_invalid_asce  = (unsigned long)invalid_pg_dir;
+	s390_invalid_asce |= _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
+	crst_table_init((unsigned long *)invalid_pg_dir, _REGION3_ENTRY_EMPTY);
 	init_mm.pgd = swapper_pg_dir;
 	if (VMALLOC_END > _REGION2_SIZE) {
 		asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
@@ -102,14 +108,14 @@ void __init paging_init(void)
 	}
 	init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
 	S390_lowcore.kernel_asce = init_mm.context.asce;
-	S390_lowcore.user_asce = S390_lowcore.kernel_asce;
+	S390_lowcore.user_asce = s390_invalid_asce;
 	crst_table_init((unsigned long *) init_mm.pgd, pgd_type);
 	vmem_map_init();
-	kasan_copy_shadow(init_mm.pgd);
+	kasan_copy_shadow_mapping();
 
 	/* enable virtual mapping in kernel mode */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
-	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	__ctl_load(S390_lowcore.user_asce, 7, 7);
 	__ctl_load(S390_lowcore.kernel_asce, 13, 13);
 	psw.mask = __extract_psw();
 	psw_bits(psw).dat = 1;
diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c
index 5646b39c728a..db4d303aaaa9 100644
--- a/arch/s390/mm/kasan_init.c
+++ b/arch/s390/mm/kasan_init.c
@@ -87,7 +87,7 @@ enum populate_mode {
 	POPULATE_ZERO_SHADOW,
 	POPULATE_SHALLOW
 };
-static void __init kasan_early_vmemmap_populate(unsigned long address,
+static void __init kasan_early_pgtable_populate(unsigned long address,
 						unsigned long end,
 						enum populate_mode mode)
 {
@@ -123,8 +123,7 @@ static void __init kasan_early_vmemmap_populate(unsigned long address,
 			pgd_populate(&init_mm, pg_dir, p4_dir);
 		}
 
-		if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) &&
-		    mode == POPULATE_SHALLOW) {
+		if (mode == POPULATE_SHALLOW) {
 			address = (address + P4D_SIZE) & P4D_MASK;
 			continue;
 		}
@@ -143,12 +142,6 @@ static void __init kasan_early_vmemmap_populate(unsigned long address,
 			p4d_populate(&init_mm, p4_dir, pu_dir);
 		}
 
-		if (!IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) &&
-		    mode == POPULATE_SHALLOW) {
-			address = (address + PUD_SIZE) & PUD_MASK;
-			continue;
-		}
-
 		pu_dir = pud_offset(p4_dir, address);
 		if (pud_none(*pu_dir)) {
 			if (mode == POPULATE_ZERO_SHADOW &&
@@ -281,7 +274,6 @@ void __init kasan_early_init(void)
 	unsigned long shadow_alloc_size;
 	unsigned long vmax_unlimited;
 	unsigned long initrd_end;
-	unsigned long asce_type;
 	unsigned long memsize;
 	unsigned long pgt_prot = pgprot_val(PAGE_KERNEL_RO);
 	pte_t pte_z;
@@ -297,32 +289,26 @@ void __init kasan_early_init(void)
 	memsize = get_mem_detect_end();
 	if (!memsize)
 		kasan_early_panic("cannot detect physical memory size\n");
-	/* respect mem= cmdline parameter */
-	if (memory_end_set && memsize > memory_end)
-		memsize = memory_end;
-	if (IS_ENABLED(CONFIG_CRASH_DUMP) && OLDMEM_BASE)
-		memsize = min(memsize, OLDMEM_SIZE);
-	memsize = min(memsize, KASAN_SHADOW_START);
-
-	if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING)) {
-		/* 4 level paging */
-		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, P4D_SIZE));
-		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE));
-		crst_table_init((unsigned long *)early_pg_dir,
-				_REGION2_ENTRY_EMPTY);
-		untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE;
-		if (has_uv_sec_stor_limit())
-			kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr);
-		asce_type = _ASCE_TYPE_REGION2;
-	} else {
-		/* 3 level paging */
-		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PUD_SIZE));
-		BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PUD_SIZE));
-		crst_table_init((unsigned long *)early_pg_dir,
-				_REGION3_ENTRY_EMPTY);
-		untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION2_SIZE;
-		asce_type = _ASCE_TYPE_REGION3;
-	}
+	/*
+	 * Kasan currently supports standby memory but only if it follows
+	 * online memory (default allocation), i.e. no memory holes.
+	 * - memsize represents end of online memory
+	 * - ident_map_size represents online + standby and memory limits
+	 *   accounted.
+	 * Kasan maps "memsize" right away.
+	 * [0, memsize]			- as identity mapping
+	 * [__sha(0), __sha(memsize)]	- shadow memory for identity mapping
+	 * The rest [memsize, ident_map_size] if memsize < ident_map_size
+	 * could be mapped/unmapped dynamically later during memory hotplug.
+	 */
+	memsize = min(memsize, ident_map_size);
+
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, P4D_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE));
+	crst_table_init((unsigned long *)early_pg_dir, _REGION2_ENTRY_EMPTY);
+	untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE;
+	if (has_uv_sec_stor_limit())
+		kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr);
 
 	/* init kasan zero shadow */
 	crst_table_init((unsigned long *)kasan_early_shadow_p4d,
@@ -388,27 +374,25 @@ void __init kasan_early_init(void)
 	 * +-----------------+	   +- shadow end ---+
 	 */
 	/* populate kasan shadow (for identity mapping and zero page mapping) */
-	kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP);
+	kasan_early_pgtable_populate(__sha(0), __sha(memsize), POPULATE_MAP);
 	if (IS_ENABLED(CONFIG_MODULES))
 		untracked_mem_end = kasan_vmax - MODULES_LEN;
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
 		untracked_mem_end = kasan_vmax - vmalloc_size - MODULES_LEN;
 		/* shallowly populate kasan shadow for vmalloc and modules */
-		kasan_early_vmemmap_populate(__sha(untracked_mem_end),
-					     __sha(kasan_vmax), POPULATE_SHALLOW);
+		kasan_early_pgtable_populate(__sha(untracked_mem_end), __sha(kasan_vmax),
+					     POPULATE_SHALLOW);
 	}
 	/* populate kasan shadow for untracked memory */
-	kasan_early_vmemmap_populate(__sha(max_physmem_end),
-				     __sha(untracked_mem_end),
+	kasan_early_pgtable_populate(__sha(ident_map_size), __sha(untracked_mem_end),
 				     POPULATE_ZERO_SHADOW);
-	kasan_early_vmemmap_populate(__sha(kasan_vmax),
-				     __sha(vmax_unlimited),
+	kasan_early_pgtable_populate(__sha(kasan_vmax), __sha(vmax_unlimited),
 				     POPULATE_ZERO_SHADOW);
 	/* memory allocated for identity mapping structs will be freed later */
 	pgalloc_freeable = pgalloc_pos;
 	/* populate identity mapping */
-	kasan_early_vmemmap_populate(0, memsize, POPULATE_ONE2ONE);
-	kasan_set_pgd(early_pg_dir, asce_type);
+	kasan_early_pgtable_populate(0, memsize, POPULATE_ONE2ONE);
+	kasan_set_pgd(early_pg_dir, _ASCE_TYPE_REGION2);
 	kasan_enable_dat();
 	/* enable kasan */
 	init_task.kasan_depth = 0;
@@ -416,7 +400,7 @@ void __init kasan_early_init(void)
 	sclp_early_printk("KernelAddressSanitizer initialized\n");
 }
 
-void __init kasan_copy_shadow(pgd_t *pg_dir)
+void __init kasan_copy_shadow_mapping(void)
 {
 	/*
 	 * At this point we are still running on early pages setup early_pg_dir,
@@ -428,24 +412,13 @@ void __init kasan_copy_shadow(pgd_t *pg_dir)
 	pgd_t *pg_dir_dst;
 	p4d_t *p4_dir_src;
 	p4d_t *p4_dir_dst;
-	pud_t *pu_dir_src;
-	pud_t *pu_dir_dst;
 
 	pg_dir_src = pgd_offset_raw(early_pg_dir, KASAN_SHADOW_START);
-	pg_dir_dst = pgd_offset_raw(pg_dir, KASAN_SHADOW_START);
+	pg_dir_dst = pgd_offset_raw(init_mm.pgd, KASAN_SHADOW_START);
 	p4_dir_src = p4d_offset(pg_dir_src, KASAN_SHADOW_START);
 	p4_dir_dst = p4d_offset(pg_dir_dst, KASAN_SHADOW_START);
-	if (!p4d_folded(*p4_dir_src)) {
-		/* 4 level paging */
-		memcpy(p4_dir_dst, p4_dir_src,
-		       (KASAN_SHADOW_SIZE >> P4D_SHIFT) * sizeof(p4d_t));
-		return;
-	}
-	/* 3 level paging */
-	pu_dir_src = pud_offset(p4_dir_src, KASAN_SHADOW_START);
-	pu_dir_dst = pud_offset(p4_dir_dst, KASAN_SHADOW_START);
-	memcpy(pu_dir_dst, pu_dir_src,
-	       (KASAN_SHADOW_SIZE >> PUD_SHIFT) * sizeof(pud_t));
+	memcpy(p4_dir_dst, p4_dir_src,
+	       (KASAN_SHADOW_SIZE >> P4D_SHIFT) * sizeof(p4d_t));
 }
 
 void __init kasan_free_early_identity(void)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 11d2c8395e2a..4e87c819ddea 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -70,19 +70,10 @@ static void __crst_table_upgrade(void *arg)
 {
 	struct mm_struct *mm = arg;
 
-	/* we must change all active ASCEs to avoid the creation of new TLBs */
+	/* change all active ASCEs to avoid the creation of new TLBs */
 	if (current->active_mm == mm) {
 		S390_lowcore.user_asce = mm->context.asce;
-		if (current->thread.mm_segment == USER_DS) {
-			__ctl_load(S390_lowcore.user_asce, 1, 1);
-			/* Mark user-ASCE present in CR1 */
-			clear_cpu_flag(CIF_ASCE_PRIMARY);
-		}
-		if (current->thread.mm_segment == USER_DS_SACF) {
-			__ctl_load(S390_lowcore.user_asce, 7, 7);
-			/* enable_sacf_uaccess does all or nothing */
-			WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
-		}
+		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	}
 	__tlb_flush_local();
 }
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b239f2ba93b0..01f3a5f58e64 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -76,20 +76,20 @@ static void vmem_pte_free(unsigned long *table)
 
 /*
  * The unused vmemmap range, which was not yet memset(PAGE_UNUSED) ranges
- * from unused_pmd_start to next PMD_SIZE boundary.
+ * from unused_sub_pmd_start to next PMD_SIZE boundary.
  */
-static unsigned long unused_pmd_start;
+static unsigned long unused_sub_pmd_start;
 
-static void vmemmap_flush_unused_pmd(void)
+static void vmemmap_flush_unused_sub_pmd(void)
 {
-	if (!unused_pmd_start)
+	if (!unused_sub_pmd_start)
 		return;
-	memset(__va(unused_pmd_start), PAGE_UNUSED,
-	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
-	unused_pmd_start = 0;
+	memset(__va(unused_sub_pmd_start), PAGE_UNUSED,
+	       ALIGN(unused_sub_pmd_start, PMD_SIZE) - unused_sub_pmd_start);
+	unused_sub_pmd_start = 0;
 }
 
-static void __vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+static void vmemmap_mark_sub_pmd_used(unsigned long start, unsigned long end)
 {
 	/*
 	 * As we expect to add in the same granularity as we remove, it's
@@ -106,24 +106,24 @@ static void vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
 	 * We only optimize if the new used range directly follows the
 	 * previously unused range (esp., when populating consecutive sections).
 	 */
-	if (unused_pmd_start == start) {
-		unused_pmd_start = end;
-		if (likely(IS_ALIGNED(unused_pmd_start, PMD_SIZE)))
-			unused_pmd_start = 0;
+	if (unused_sub_pmd_start == start) {
+		unused_sub_pmd_start = end;
+		if (likely(IS_ALIGNED(unused_sub_pmd_start, PMD_SIZE)))
+			unused_sub_pmd_start = 0;
 		return;
 	}
-	vmemmap_flush_unused_pmd();
-	__vmemmap_use_sub_pmd(start, end);
+	vmemmap_flush_unused_sub_pmd();
+	vmemmap_mark_sub_pmd_used(start, end);
 }
 
 static void vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
 {
 	void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
 
-	vmemmap_flush_unused_pmd();
+	vmemmap_flush_unused_sub_pmd();
 
 	/* Could be our memmap page is filled with PAGE_UNUSED already ... */
-	__vmemmap_use_sub_pmd(start, end);
+	vmemmap_mark_sub_pmd_used(start, end);
 
 	/* Mark the unused parts of the new memmap page PAGE_UNUSED. */
 	if (!IS_ALIGNED(start, PMD_SIZE))
@@ -134,7 +134,7 @@ static void vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
 	 * unused range in the populated PMD.
 	 */
 	if (!IS_ALIGNED(end, PMD_SIZE))
-		unused_pmd_start = end;
+		unused_sub_pmd_start = end;
 }
 
 /* Returns true if the PMD is completely unused and can be freed. */
@@ -142,7 +142,7 @@ static bool vmemmap_unuse_sub_pmd(unsigned long start, unsigned long end)
 {
 	void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
 
-	vmemmap_flush_unused_pmd();
+	vmemmap_flush_unused_sub_pmd();
 	memset(__va(start), PAGE_UNUSED, end - start);
 	return !memchr_inv(page, PAGE_UNUSED, PMD_SIZE);
 }
@@ -223,7 +223,7 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
 		if (!add) {
 			if (pmd_none(*pmd))
 				continue;
-			if (pmd_large(*pmd) && !add) {
+			if (pmd_large(*pmd)) {
 				if (IS_ALIGNED(addr, PMD_SIZE) &&
 				    IS_ALIGNED(next, PMD_SIZE)) {
 					if (!direct)