[pull] master from torvalds:master

MAINTAINERS

@@ -8799,6 +8799,7 @@ F:	include/linux/gpio/regmap.h
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
 M:	Bartosz Golaszewski <brgl@bgdev.pl>
+R:	Andy Shevchenko <andy@kernel.org>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git

arch/riscv/Kconfig

@@ -26,6 +26,7 @@ config RISCV
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MMIOWB
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU

arch/riscv/include/asm/kfence.h

@@ -8,41 +8,8 @@
 #include <asm-generic/pgalloc.h>
 #include <asm/pgtable.h>
 
-static inline int split_pmd_page(unsigned long addr)
-{
-	int i;
-	unsigned long pfn = PFN_DOWN(__pa((addr & PMD_MASK)));
-	pmd_t *pmd = pmd_off_k(addr);
-	pte_t *pte = pte_alloc_one_kernel(&init_mm);
-
-	if (!pte)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_PTE; i++)
-		set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL));
-	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(pte)), PAGE_TABLE));
-
-	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
-	return 0;
-}
-
 static inline bool arch_kfence_init_pool(void)
 {
-	int ret;
-	unsigned long addr;
-	pmd_t *pmd;
-
-	for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
-	     addr += PAGE_SIZE) {
-		pmd = pmd_off_k(addr);
-
-		if (pmd_leaf(*pmd)) {
-			ret = split_pmd_page(addr);
-			if (ret)
-				return false;
-		}
-	}
-
 	return true;
 }
 

arch/riscv/include/asm/pgtable.h

@@ -165,8 +165,7 @@ extern struct pt_alloc_ops pt_ops __initdata;
 					 _PAGE_EXEC | _PAGE_WRITE)
 
 #define PAGE_COPY		PAGE_READ
-#define PAGE_COPY_EXEC		PAGE_EXEC
-#define PAGE_COPY_READ_EXEC	PAGE_READ_EXEC
+#define PAGE_COPY_EXEC		PAGE_READ_EXEC
 #define PAGE_SHARED		PAGE_WRITE
 #define PAGE_SHARED_EXEC	PAGE_WRITE_EXEC
 

arch/riscv/mm/init.c

@@ -23,6 +23,7 @@
 #ifdef CONFIG_RELOCATABLE
 #include <linux/elf.h>
 #endif
+#include <linux/kfence.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -293,7 +294,7 @@ static const pgprot_t protection_map[16] = {
 	[VM_EXEC]					= PAGE_EXEC,
 	[VM_EXEC | VM_READ]				= PAGE_READ_EXEC,
 	[VM_EXEC | VM_WRITE]				= PAGE_COPY_EXEC,
-	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_READ_EXEC,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_EXEC,
 	[VM_SHARED]					= PAGE_NONE,
 	[VM_SHARED | VM_READ]				= PAGE_READ,
 	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
@@ -659,18 +660,19 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 	create_pgd_next_mapping(nextp, va, pa, sz, prot);
 }
 
-static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
+static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va,
+				      phys_addr_t size)
 {
-	if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
+	if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
 		return PGDIR_SIZE;
 
-	if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+	if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
 		return P4D_SIZE;
 
-	if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+	if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
 		return PUD_SIZE;
 
-	if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE)
+	if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
@@ -1167,14 +1169,16 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 }
 
 static void __init create_linear_mapping_range(phys_addr_t start,
-					       phys_addr_t end)
+					       phys_addr_t end,
+					       uintptr_t fixed_map_size)
 {
 	phys_addr_t pa;
 	uintptr_t va, map_size;
 
 	for (pa = start; pa < end; pa += map_size) {
 		va = (uintptr_t)__va(pa);
-		map_size = best_map_size(pa, end - pa);
+		map_size = fixed_map_size ? fixed_map_size :
+					    best_map_size(pa, va, end - pa);
 
 		create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
 				   pgprot_from_va(va));
@@ -1184,6 +1188,7 @@ static void __init create_linear_mapping_range(phys_addr_t start,
 static void __init create_linear_mapping_page_table(void)
 {
 	phys_addr_t start, end;
+	phys_addr_t kfence_pool __maybe_unused;
 	u64 i;
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -1197,6 +1202,19 @@ static void __init create_linear_mapping_page_table(void)
 	memblock_mark_nomap(krodata_start, krodata_size);
 #endif
 
+#ifdef CONFIG_KFENCE
+	/*
+	 *  kfence pool must be backed by PAGE_SIZE mappings, so allocate it
+	 *  before we setup the linear mapping so that we avoid using hugepages
+	 *  for this region.
+	 */
+	kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+	BUG_ON(!kfence_pool);
+
+	memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+	__kfence_pool = __va(kfence_pool);
+#endif
+
 	/* Map all memory banks in the linear mapping */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -1207,17 +1225,25 @@ static void __init create_linear_mapping_page_table(void)
 		if (end >= __pa(PAGE_OFFSET) + memory_limit)
 			end = __pa(PAGE_OFFSET) + memory_limit;
 
-		create_linear_mapping_range(start, end);
+		create_linear_mapping_range(start, end, 0);
 	}
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-	create_linear_mapping_range(ktext_start, ktext_start + ktext_size);
+	create_linear_mapping_range(ktext_start, ktext_start + ktext_size, 0);
 	create_linear_mapping_range(krodata_start,
-				    krodata_start + krodata_size);
+				    krodata_start + krodata_size, 0);
 
 	memblock_clear_nomap(ktext_start,  ktext_size);
 	memblock_clear_nomap(krodata_start, krodata_size);
 #endif
+
+#ifdef CONFIG_KFENCE
+	create_linear_mapping_range(kfence_pool,
+				    kfence_pool + KFENCE_POOL_SIZE,
+				    PAGE_SIZE);
+
+	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+#endif
 }
 
 static void __init setup_vm_final(void)

arch/s390/purgatory/Makefile

@@ -26,6 +26,7 @@ KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))

block/blk-mq.c

@@ -683,6 +683,10 @@ static void __blk_mq_free_request(struct request *rq)
 	blk_crypto_free_request(rq);
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
+
+	if (rq->rq_flags & RQF_MQ_INFLIGHT)
+		__blk_mq_dec_active_requests(hctx);
+
 	if (rq->tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
 	if (sched_tag != BLK_MQ_NO_TAG)
@@ -694,15 +698,11 @@ static void __blk_mq_free_request(struct request *rq)
 void blk_mq_free_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	if ((rq->rq_flags & RQF_ELVPRIV) &&
 	    q->elevator->type->ops.finish_request)
 		q->elevator->type->ops.finish_request(rq);
 
-	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		__blk_mq_dec_active_requests(hctx);
-
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->disk->bdi);
 

drivers/block/null_blk/main.c

@@ -2244,6 +2244,7 @@ static void null_destroy_dev(struct nullb *nullb)
 	struct nullb_device *dev = nullb->dev;
 
 	null_del_dev(nullb);
+	null_free_device_storage(dev, false);
 	null_free_dev(dev);
 }
 

drivers/block/rbd.c

@@ -1334,14 +1334,30 @@ static bool rbd_obj_is_tail(struct rbd_obj_request *obj_req)
 /*
  * Must be called after rbd_obj_calc_img_extents().
  */
-static bool rbd_obj_copyup_enabled(struct rbd_obj_request *obj_req)
+static void rbd_obj_set_copyup_enabled(struct rbd_obj_request *obj_req)
 {
-	if (!obj_req->num_img_extents ||
-	    (rbd_obj_is_entire(obj_req) &&
-	     !obj_req->img_request->snapc->num_snaps))
-		return false;
+	rbd_assert(obj_req->img_request->snapc);
 
-	return true;
+	if (obj_req->img_request->op_type == OBJ_OP_DISCARD) {
+		dout("%s %p objno %llu discard\n", __func__, obj_req,
+		     obj_req->ex.oe_objno);
+		return;
+	}
+
+	if (!obj_req->num_img_extents) {
+		dout("%s %p objno %llu not overlapping\n", __func__, obj_req,
+		     obj_req->ex.oe_objno);
+		return;
+	}
+
+	if (rbd_obj_is_entire(obj_req) &&
+	    !obj_req->img_request->snapc->num_snaps) {
+		dout("%s %p objno %llu entire\n", __func__, obj_req,
+		     obj_req->ex.oe_objno);
+		return;
+	}
+
+	obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED;
 }
 
 static u64 rbd_obj_img_extents_bytes(struct rbd_obj_request *obj_req)
@@ -1442,6 +1458,7 @@ __rbd_obj_add_osd_request(struct rbd_obj_request *obj_req,
 static struct ceph_osd_request *
 rbd_obj_add_osd_request(struct rbd_obj_request *obj_req, int num_ops)
 {
+	rbd_assert(obj_req->img_request->snapc);
 	return __rbd_obj_add_osd_request(obj_req, obj_req->img_request->snapc,
 					 num_ops);
 }
@@ -1578,15 +1595,18 @@ static void rbd_img_request_init(struct rbd_img_request *img_request,
 	mutex_init(&img_request->state_mutex);
 }
 
+/*
+ * Only snap_id is captured here, for reads.  For writes, snapshot
+ * context is captured in rbd_img_object_requests() after exclusive
+ * lock is ensured to be held.
+ */
 static void rbd_img_capture_header(struct rbd_img_request *img_req)
 {
 	struct rbd_device *rbd_dev = img_req->rbd_dev;
 
 	lockdep_assert_held(&rbd_dev->header_rwsem);
 
-	if (rbd_img_is_write(img_req))
-		img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc);
-	else
+	if (!rbd_img_is_write(img_req))
 		img_req->snap_id = rbd_dev->spec->snap_id;
 
 	if (rbd_dev_parent_get(rbd_dev))
@@ -2233,9 +2253,6 @@ static int rbd_obj_init_write(struct rbd_obj_request *obj_req)
 	if (ret)
 		return ret;
 
-	if (rbd_obj_copyup_enabled(obj_req))
-		obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED;
-
 	obj_req->write_state = RBD_OBJ_WRITE_START;
 	return 0;
 }
@@ -2341,8 +2358,6 @@ static int rbd_obj_init_zeroout(struct rbd_obj_request *obj_req)
 	if (ret)
 		return ret;
 
-	if (rbd_obj_copyup_enabled(obj_req))
-		obj_req->flags |= RBD_OBJ_FLAG_COPYUP_ENABLED;
 	if (!obj_req->num_img_extents) {
 		obj_req->flags |= RBD_OBJ_FLAG_NOOP_FOR_NONEXISTENT;
 		if (rbd_obj_is_entire(obj_req))
@@ -3286,6 +3301,7 @@ static bool rbd_obj_advance_write(struct rbd_obj_request *obj_req, int *result)
 	case RBD_OBJ_WRITE_START:
 		rbd_assert(!*result);
 
+		rbd_obj_set_copyup_enabled(obj_req);
 		if (rbd_obj_write_is_noop(obj_req))
 			return true;
 
@@ -3472,9 +3488,19 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
 
 static void rbd_img_object_requests(struct rbd_img_request *img_req)
 {
+	struct rbd_device *rbd_dev = img_req->rbd_dev;
 	struct rbd_obj_request *obj_req;
 
 	rbd_assert(!img_req->pending.result && !img_req->pending.num_pending);
+	rbd_assert(!need_exclusive_lock(img_req) ||
+		   __rbd_is_lock_owner(rbd_dev));
+
+	if (rbd_img_is_write(img_req)) {
+		rbd_assert(!img_req->snapc);
+		down_read(&rbd_dev->header_rwsem);
+		img_req->snapc = ceph_get_snap_context(rbd_dev->header.snapc);
+		up_read(&rbd_dev->header_rwsem);
+	}
 
 	for_each_obj_request(img_req, obj_req) {
 		int result = 0;
@@ -3492,7 +3518,6 @@ static void rbd_img_object_requests(struct rbd_img_request *img_req)
 
 static bool rbd_img_advance(struct rbd_img_request *img_req, int *result)
 {
-	struct rbd_device *rbd_dev = img_req->rbd_dev;
 	int ret;
 
 again:
@@ -3513,9 +3538,6 @@ static bool rbd_img_advance(struct rbd_img_request *img_req, int *result)
 		if (*result)
 			return true;
 
-		rbd_assert(!need_exclusive_lock(img_req) ||
-			   __rbd_is_lock_owner(rbd_dev));
-
 		rbd_img_object_requests(img_req);
 		if (!img_req->pending.num_pending) {
 			*result = img_req->pending.result;
@@ -3977,6 +3999,10 @@ static int rbd_post_acquire_action(struct rbd_device *rbd_dev)
 {
 	int ret;
 
+	ret = rbd_dev_refresh(rbd_dev);
+	if (ret)
+		return ret;
+
 	if (rbd_dev->header.features & RBD_FEATURE_OBJECT_MAP) {
 		ret = rbd_object_map_open(rbd_dev);
 		if (ret)