5.15.37-rc1 review

67 lines not on this page · raw message

@@ -293,6 +293,29 @@ bool bpf_map_meta_equal(const struct bpf
 
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
+/* bpf_type_flag contains a set of flags that are applicable to the values of
+ * arg_type, ret_type and reg_type. For example, a pointer value may be null,
+ * or a memory is read-only. We classify types into two categories: base types
+ * and extended types. Extended types are base types combined with a type flag.
+ *
+ * Currently there are no more than 32 base types in arg_type, ret_type and
+ * reg_types.
+ */
+#define BPF_BASE_TYPE_BITS	8
+
+enum bpf_type_flag {
+	/* PTR may be NULL. */
+	PTR_MAYBE_NULL		= BIT(0 + BPF_BASE_TYPE_BITS),
+
+	__BPF_TYPE_LAST_FLAG	= PTR_MAYBE_NULL,
+};
+
+/* Max number of base types. */
+#define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
+
+/* Max number of all types. */
+#define BPF_TYPE_LIMIT		(__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1))
+
 /* function argument constraints */
 enum bpf_arg_type {
 	ARG_DONTCARE = 0,	/* unused argument in helper function */

@@ -339,7 +362,13 @@ enum bpf_arg_type {
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
 	__BPF_ARG_TYPE_MAX,
+
+	/* This must be the last entry. Its purpose is to ensure the enum is
+	 * wide enough to hold the higher bits reserved for bpf_type_flag.
+	 */
+	__BPF_ARG_TYPE_LIMIT	= BPF_TYPE_LIMIT,
 };
+static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
 
 /* type of values returned from helper functions */
 enum bpf_return_type {

@@ -355,7 +384,14 @@ enum bpf_return_type {
 	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
 	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 	RET_PTR_TO_BTF_ID,		/* returns a pointer to a btf_id */
+	__BPF_RET_TYPE_MAX,
+
+	/* This must be the last entry. Its purpose is to ensure the enum is
+	 * wide enough to hold the higher bits reserved for bpf_type_flag.
+	 */
+	__BPF_RET_TYPE_LIMIT	= BPF_TYPE_LIMIT,
 };
+static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
  * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL

@@ -457,7 +493,13 @@ enum bpf_reg_type {
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
 	PTR_TO_MAP_KEY,		 /* reg points to a map element key */
 	__BPF_REG_TYPE_MAX,
+
+	/* This must be the last entry. Its purpose is to ensure the enum is
+	 * wide enough to hold the higher bits reserved for bpf_type_flag.
+	 */
+	__BPF_REG_TYPE_LIMIT	= BPF_TYPE_LIMIT,
 };
+static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
 
 /* The information passed from prog-specific *_is_valid_access
  * back to the verifier.

@@ -535,4 +535,18 @@ int bpf_check_attach_target(struct bpf_v
 			    u32 btf_id,
 			    struct bpf_attach_target_info *tgt_info);
 
+#define BPF_BASE_TYPE_MASK	GENMASK(BPF_BASE_TYPE_BITS - 1, 0)
+
+/* extract base type from bpf_{arg, return, reg}_type. */
+static inline u32 base_type(u32 type)
+{
+	return type & BPF_BASE_TYPE_MASK;
+}
+
+/* extract flags from an extended type. See bpf_type_flag in bpf.h. */
+static inline u32 type_flag(u32 type)
+{
+	return type & ~BPF_BASE_TYPE_MASK;
+}
+
 #endif /* _LINUX_BPF_VERIFIER_H */

@@ -327,13 +327,11 @@ enum bpf_arg_type {
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
 	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
-	ARG_PTR_TO_MAP_VALUE_OR_NULL,	/* pointer to stack used as map value or NULL */
 
 	/* the following constraints used to prototype bpf_memcmp() and other
 	 * functions that access data on eBPF program stack
 	 */
 	ARG_PTR_TO_MEM,		/* pointer to valid memory (stack, packet, map value) */
-	ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */
 	ARG_PTR_TO_UNINIT_MEM,	/* pointer to memory does not need to be initialized,
 				 * helper function must fill all bytes or clear
 				 * them in error case.

@@ -343,26 +341,31 @@ enum bpf_arg_type {
 	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */
 
 	ARG_PTR_TO_CTX,		/* pointer to context */
-	ARG_PTR_TO_CTX_OR_NULL,	/* pointer to context or NULL */
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
-	ARG_PTR_TO_SOCKET_OR_NULL,	/* pointer to bpf_sock (fullsock) or NULL */
 	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
-	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
 	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
 	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
 	ARG_PTR_TO_FUNC,	/* pointer to a bpf program function */
-	ARG_PTR_TO_STACK_OR_NULL,	/* pointer to stack or NULL */
+	ARG_PTR_TO_STACK,	/* pointer to stack */
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
 	__BPF_ARG_TYPE_MAX,
 
+	/* Extended arg_types. */
+	ARG_PTR_TO_MAP_VALUE_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE,
+	ARG_PTR_TO_MEM_OR_NULL		= PTR_MAYBE_NULL | ARG_PTR_TO_MEM,
+	ARG_PTR_TO_CTX_OR_NULL		= PTR_MAYBE_NULL | ARG_PTR_TO_CTX,
+	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
+	ARG_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM,
+	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
+
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
 	 */

@@ -478,14 +478,9 @@ static bool arg_type_may_be_refcounted(e
 	return type == ARG_PTR_TO_SOCK_COMMON;
 }
 
-static bool arg_type_may_be_null(enum bpf_arg_type type)
+static bool type_may_be_null(u32 type)
 {
-	return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
-	       type == ARG_PTR_TO_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_CTX_OR_NULL ||
-	       type == ARG_PTR_TO_SOCKET_OR_NULL ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_STACK_OR_NULL;
+	return type & PTR_MAYBE_NULL;
 }
 
 /* Determine whether the function releases some resources allocated by another

@@ -4796,9 +4791,8 @@ static int process_timer_func(struct bpf
 
 static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
 {
-	return type == ARG_PTR_TO_MEM ||
-	       type == ARG_PTR_TO_MEM_OR_NULL ||
-	       type == ARG_PTR_TO_UNINIT_MEM;
+	return base_type(type) == ARG_PTR_TO_MEM ||
+	       base_type(type) == ARG_PTR_TO_UNINIT_MEM;
 }
 
 static bool arg_type_is_mem_size(enum bpf_arg_type type)

@@ -4932,31 +4926,26 @@ static const struct bpf_reg_types *compa
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
 	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
 	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
-	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
 	[ARG_CONST_SIZE]		= &scalar_types,
 	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
 	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
 	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
 	[ARG_PTR_TO_CTX]		= &context_types,
-	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
 	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
 #ifdef CONFIG_NET
 	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
 #endif
 	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
-	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
 	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
 	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
 	[ARG_PTR_TO_MEM]		= &mem_types,
-	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
 	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
 	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
-	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
 	[ARG_PTR_TO_INT]		= &int_ptr_types,
 	[ARG_PTR_TO_LONG]		= &int_ptr_types,
 	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
 	[ARG_PTR_TO_FUNC]		= &func_ptr_types,
-	[ARG_PTR_TO_STACK_OR_NULL]	= &stack_ptr_types,
+	[ARG_PTR_TO_STACK]		= &stack_ptr_types,
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
 };

@@ -4970,7 +4959,7 @@ static int check_reg_type(struct bpf_ver
 	const struct bpf_reg_types *compatible;
 	int i, j;
 
-	compatible = compatible_reg_types[arg_type];
+	compatible = compatible_reg_types[base_type(arg_type)];
 	if (!compatible) {
 		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
 		return -EFAULT;

@@ -5051,15 +5040,14 @@ static int check_func_arg(struct bpf_ver
 		return -EACCES;
 	}
 
-	if (arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
+	if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+	    base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
 		err = resolve_map_arg_type(env, meta, &arg_type);
 		if (err)
 			return err;
 	}
 
-	if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+	if (register_is_null(reg) && type_may_be_null(arg_type))
 		/* A NULL register has a SCALAR_VALUE type, so skip
 		 * type checking.
 		 */

@@ -5128,10 +5116,11 @@ skip_type_check:
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->key_size, false,
 					      NULL);
-	} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
-		   (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
-		    !register_is_null(reg)) ||
-		   arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+	} else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE ||
+		   base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+		if (type_may_be_null(arg_type) && register_is_null(reg))
+			return 0;
+
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
 		 */

@@ -378,17 +378,22 @@ enum bpf_return_type {
 	RET_INTEGER,			/* function returns integer */
 	RET_VOID,			/* function doesn't return anything */
 	RET_PTR_TO_MAP_VALUE,		/* returns a pointer to map elem value */
-	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
-	RET_PTR_TO_SOCKET_OR_NULL,	/* returns a pointer to a socket or NULL */
-	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
-	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
-	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
-	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
-	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
+	RET_PTR_TO_SOCKET,		/* returns a pointer to a socket */
+	RET_PTR_TO_TCP_SOCK,		/* returns a pointer to a tcp_sock */
+	RET_PTR_TO_SOCK_COMMON,		/* returns a pointer to a sock_common */
+	RET_PTR_TO_ALLOC_MEM,		/* returns a pointer to dynamically allocated memory */
 	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 	RET_PTR_TO_BTF_ID,		/* returns a pointer to a btf_id */
 	__BPF_RET_TYPE_MAX,
 
+	/* Extended ret_types. */
+	RET_PTR_TO_MAP_VALUE_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE,
+	RET_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCKET,
+	RET_PTR_TO_TCP_SOCK_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
+	RET_PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
+	RET_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM,
+	RET_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
+
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
 	 */

@@ -667,7 +667,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *
 const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.func		= bpf_per_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 	.arg2_type	= ARG_ANYTHING,
 };

109 lines not on this page · raw message

@@ -461,18 +461,15 @@ enum bpf_reg_type {
 	PTR_TO_CTX,		 /* reg points to bpf_context */
 	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
 	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
-	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
+	PTR_TO_MAP_KEY,		 /* reg points to a map element key */
 	PTR_TO_STACK,		 /* reg == frame_pointer + offset */
 	PTR_TO_PACKET_META,	 /* skb->data - meta_len */
 	PTR_TO_PACKET,		 /* reg points to skb->data */
 	PTR_TO_PACKET_END,	 /* skb->data + headlen */
 	PTR_TO_FLOW_KEYS,	 /* reg points to bpf_flow_keys */
 	PTR_TO_SOCKET,		 /* reg points to struct bpf_sock */
-	PTR_TO_SOCKET_OR_NULL,	 /* reg points to struct bpf_sock or NULL */
 	PTR_TO_SOCK_COMMON,	 /* reg points to sock_common */
-	PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
 	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
-	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
 	/* PTR_TO_BTF_ID points to a kernel struct that does not need

@@ -490,18 +487,21 @@ enum bpf_reg_type {
 	 * been checked for null. Used primarily to inform the verifier
 	 * an explicit null check is required for this struct.
 	 */
-	PTR_TO_BTF_ID_OR_NULL,
 	PTR_TO_MEM,		 /* reg points to valid memory region */
-	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
 	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
-	PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
 	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
-	PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
 	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
-	PTR_TO_MAP_KEY,		 /* reg points to a map element key */
 	__BPF_REG_TYPE_MAX,
 
+	/* Extended reg_types. */
+	PTR_TO_MAP_VALUE_OR_NULL	= PTR_MAYBE_NULL | PTR_TO_MAP_VALUE,
+	PTR_TO_SOCKET_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_SOCKET,
+	PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
+	PTR_TO_TCP_SOCK_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
+	PTR_TO_BTF_ID_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_BTF_ID,
+	PTR_TO_MEM_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_MEM,
+
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.
 	 */

@@ -18,6 +18,8 @@
  * that converting umax_value to int cannot overflow.
  */
 #define BPF_MAX_VAR_SIZ	(1 << 29)
+/* size of type_str_buf in bpf_verifier. */
+#define TYPE_STR_BUF_LEN 64
 
 /* Liveness marks, used for registers and spilled-regs (in stack slots).
  * Read marks propagate upwards until they find a write mark; they record that

@@ -474,6 +476,8 @@ struct bpf_verifier_env {
 	/* longest register parentage chain walked for liveness marking */
 	u32 longest_mark_read_walk;
 	bpfptr_t fd_array;
+	/* buffer used in reg_type_str() to generate reg_type string */
+	char type_str_buf[TYPE_STR_BUF_LEN];
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,

@@ -4800,10 +4800,13 @@ bool btf_ctx_access(int off, int size, e
 	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
 	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
 		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
+		u32 type, flag;
 
+		type = base_type(ctx_arg_info->reg_type);
+		flag = type_flag(ctx_arg_info->reg_type);
 		if (ctx_arg_info->offset == off &&
-		    (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL ||
-		     ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) {
+		    (type == PTR_TO_RDWR_BUF || type == PTR_TO_RDONLY_BUF) &&
+		    (flag & PTR_MAYBE_NULL)) {
 			info->reg_type = ctx_arg_info->reg_type;
 			return true;
 		}

@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
-		  PTR_TO_RDONLY_BUF_OR_NULL },
+		  PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL },
 		{ offsetof(struct bpf_iter__bpf_map_elem, value),
-		  PTR_TO_RDWR_BUF_OR_NULL },
+		  PTR_TO_RDWR_BUF | PTR_MAYBE_NULL },
 	},
 };
 

604 lines not on this page · raw message

@@ -929,7 +929,7 @@ static struct bpf_iter_reg bpf_sk_storag
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, value),
-		  PTR_TO_RDWR_BUF_OR_NULL },
+		  PTR_TO_RDWR_BUF | PTR_MAYBE_NULL },
 	},
 	.seq_info		= &iter_seq_info,
 };

@@ -1575,7 +1575,7 @@ static struct bpf_iter_reg sock_map_iter
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__sockmap, key),
-		  PTR_TO_RDONLY_BUF_OR_NULL },
+		  PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL },
 		{ offsetof(struct bpf_iter__sockmap, sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},

@@ -307,7 +307,10 @@ enum bpf_type_flag {
 	/* PTR may be NULL. */
 	PTR_MAYBE_NULL		= BIT(0 + BPF_BASE_TYPE_BITS),
 
-	__BPF_TYPE_LAST_FLAG	= PTR_MAYBE_NULL,
+	/* MEM is read-only. */
+	MEM_RDONLY		= BIT(1 + BPF_BASE_TYPE_BITS),
+
+	__BPF_TYPE_LAST_FLAG	= MEM_RDONLY,
 };
 
 /* Max number of base types. */

@@ -488,8 +491,7 @@ enum bpf_reg_type {
 	 * an explicit null check is required for this struct.
 	 */
 	PTR_TO_MEM,		 /* reg points to valid memory region */
-	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
-	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
+	PTR_TO_BUF,		 /* reg points to a read/write buffer */
 	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
 	__BPF_REG_TYPE_MAX,

@@ -4804,8 +4804,7 @@ bool btf_ctx_access(int off, int size, e
 
 		type = base_type(ctx_arg_info->reg_type);
 		flag = type_flag(ctx_arg_info->reg_type);
-		if (ctx_arg_info->offset == off &&
-		    (type == PTR_TO_RDWR_BUF || type == PTR_TO_RDONLY_BUF) &&
+		if (ctx_arg_info->offset == off && type == PTR_TO_BUF &&
 		    (flag & PTR_MAYBE_NULL)) {
 			info->reg_type = ctx_arg_info->reg_type;
 			return true;

@@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),
-		  PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
 		{ offsetof(struct bpf_iter__bpf_map_elem, value),
-		  PTR_TO_RDWR_BUF | PTR_MAYBE_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL },
 	},
 };
 

143 lines not on this page · raw message

@@ -929,7 +929,7 @@ static struct bpf_iter_reg bpf_sk_storag
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, value),
-		  PTR_TO_RDWR_BUF | PTR_MAYBE_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL },
 	},
 	.seq_info		= &iter_seq_info,
 };

@@ -1575,7 +1575,7 @@ static struct bpf_iter_reg sock_map_iter
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__sockmap, key),
-		  PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL },
+		  PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY },
 		{ offsetof(struct bpf_iter__sockmap, sk),
 		  PTR_TO_BTF_ID_OR_NULL },
 	},

@@ -502,7 +502,6 @@ enum bpf_reg_type {
 	PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
 	PTR_TO_TCP_SOCK_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
 	PTR_TO_BTF_ID_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_BTF_ID,
-	PTR_TO_MEM_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_MEM,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
 	 * wide enough to hold the higher bits reserved for bpf_type_flag.

@@ -5719,7 +5719,7 @@ int btf_prepare_func_args(struct bpf_ver
 				return -EINVAL;
 			}
 
-			reg->type = PTR_TO_MEM_OR_NULL;
+			reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
 			reg->id = ++env->id_gen;
 
 			continue;

@@ -13135,7 +13135,7 @@ static int do_check_common(struct bpf_ve
 				mark_reg_known_zero(env, regs, i);
 			else if (regs[i].type == SCALAR_VALUE)
 				mark_reg_unknown(env, regs, i);
-			else if (regs[i].type == PTR_TO_MEM_OR_NULL) {
+			else if (base_type(regs[i].type) == PTR_TO_MEM) {
 				const u32 mem_size = regs[i].mem_size;
 
 				mark_reg_known_zero(env, regs, i);

@@ -667,7 +667,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *
 const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.func		= bpf_per_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 	.arg2_type	= ARG_ANYTHING,
 };

@@ -680,7 +680,7 @@ BPF_CALL_1(bpf_this_cpu_ptr, const void
 const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
 	.func		= bpf_this_cpu_ptr,
 	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID | MEM_RDONLY,
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 };
 

@@ -4166,15 +4166,30 @@ static int check_mem_access(struct bpf_v
 				mark_reg_unknown(env, regs, value_regno);
 			}
 		}
-	} else if (reg->type == PTR_TO_MEM) {
+	} else if (base_type(reg->type) == PTR_TO_MEM) {
+		bool rdonly_mem = type_is_rdonly_mem(reg->type);
+
+		if (type_may_be_null(reg->type)) {
+			verbose(env, "R%d invalid mem access '%s'\n", regno,
+				reg_type_str(env, reg->type));
+			return -EACCES;
+		}
+
+		if (t == BPF_WRITE && rdonly_mem) {
+			verbose(env, "R%d cannot write into %s\n",
+				regno, reg_type_str(env, reg->type));
+			return -EACCES;
+		}
+
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
 			verbose(env, "R%d leaks addr into mem\n", value_regno);
 			return -EACCES;
 		}
+
 		err = check_mem_region_access(env, regno, off, size,
 					      reg->mem_size, false);
-		if (!err && t == BPF_READ && value_regno >= 0)
+		if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;

@@ -6370,6 +6385,13 @@ static int check_helper_call(struct bpf_
 			regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
 			regs[BPF_REG_0].mem_size = tsize;
 		} else {
+			/* MEM_RDONLY may be carried from ret_flag, but it
+			 * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+			 * it will confuse the check of PTR_TO_BTF_ID in
+			 * check_mem_access().
+			 */
+			ret_flag &= ~MEM_RDONLY;
+
 			regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
 			regs[BPF_REG_0].btf = meta.ret_btf;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;

@@ -9172,7 +9194,7 @@ static int check_ld_imm(struct bpf_verif
 
 	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
 		dst_reg->type = aux->btf_var.reg_type;
-		switch (dst_reg->type) {
+		switch (base_type(dst_reg->type)) {
 		case PTR_TO_MEM:
 			dst_reg->mem_size = aux->btf_var.mem_size;
 			break;

@@ -11313,7 +11335,7 @@ static int check_pseudo_btf_id(struct bp
 			err = -EINVAL;
 			goto err_put;
 		}
-		aux->btf_var.reg_type = PTR_TO_MEM;
+		aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
 		aux->btf_var.mem_size = tsize;
 	} else {
 		aux->btf_var.reg_type = PTR_TO_BTF_ID;

@@ -307,7 +307,9 @@ enum bpf_type_flag {
 	/* PTR may be NULL. */
 	PTR_MAYBE_NULL		= BIT(0 + BPF_BASE_TYPE_BITS),
 
-	/* MEM is read-only. */
+	/* MEM is read-only. When applied on bpf_arg, it indicates the arg is
+	 * compatible with both mutable and immutable memory.
+	 */
 	MEM_RDONLY		= BIT(1 + BPF_BASE_TYPE_BITS),
 
 	__BPF_TYPE_LAST_FLAG	= MEM_RDONLY,

@@ -6231,7 +6231,7 @@ const struct bpf_func_proto bpf_btf_find
 	.func		= bpf_btf_find_by_name_kind,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_ANYTHING,

@@ -1753,7 +1753,7 @@ static const struct bpf_func_proto bpf_s
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 

@@ -530,7 +530,7 @@ const struct bpf_func_proto bpf_strtol_p
 	.func		= bpf_strtol,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,

@@ -558,7 +558,7 @@ const struct bpf_func_proto bpf_strtoul_
 	.func		= bpf_strtoul,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_LONG,

@@ -630,7 +630,7 @@ const struct bpf_func_proto bpf_event_ou
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_CONST_MAP_PTR,
 	.arg3_type      = ARG_ANYTHING,
-	.arg4_type      = ARG_PTR_TO_MEM,
+	.arg4_type      = ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -1013,7 +1013,7 @@ const struct bpf_func_proto bpf_snprintf
 	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_PTR_TO_CONST_STR,
-	.arg4_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type	= ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_
 	.func		= bpf_ringbuf_output,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };

@@ -4753,7 +4753,7 @@ static const struct bpf_func_proto bpf_s
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 

@@ -4890,7 +4890,6 @@ static const struct bpf_reg_types mem_ty
 		PTR_TO_MAP_VALUE,
 		PTR_TO_MEM,
 		PTR_TO_BUF,
-		PTR_TO_BUF | MEM_RDONLY,
 	},
 };
 

@@ -4960,6 +4959,21 @@ static int check_reg_type(struct bpf_ver
 		return -EFAULT;
 	}
 
+	/* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY,
+	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY
+	 *
+	 * Same for MAYBE_NULL:
+	 *
+	 * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
+	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
+	 *
+	 * Therefore we fold these flags depending on the arg_type before comparison.
+	 */
+	if (arg_type & MEM_RDONLY)
+		type &= ~MEM_RDONLY;
+	if (arg_type & PTR_MAYBE_NULL)
+		type &= ~PTR_MAYBE_NULL;
+
 	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
 		expected = compatible->types[i];
 		if (expected == NOT_INIT)

@@ -4969,14 +4983,14 @@ static int check_reg_type(struct bpf_ver
 			goto found;
 	}
 
-	verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, type));
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type));
 	for (j = 0; j + 1 < i; j++)
 		verbose(env, "%s, ", reg_type_str(env, compatible->types[j]));
 	verbose(env, "%s\n", reg_type_str(env, compatible->types[j]));
 	return -EACCES;
 
 found:
-	if (type == PTR_TO_BTF_ID) {
+	if (reg->type == PTR_TO_BTF_ID) {
 		if (!arg_btf_id) {
 			if (!compatible->btf_id) {
 				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");

@@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_p
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
 };
 

@@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_t
 	.func		= bpf_trace_printk,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 };
 

@@ -446,9 +446,9 @@ static const struct bpf_func_proto bpf_s
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE,
-	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type      = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -463,7 +463,7 @@ static const struct bpf_func_proto bpf_s
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -487,7 +487,7 @@ static const struct bpf_func_proto bpf_s
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
 	.arg1_btf_id	= &btf_seq_file_ids[0],
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };

@@ -648,7 +648,7 @@ static const struct bpf_func_proto bpf_p
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -958,7 +958,7 @@ const struct bpf_func_proto bpf_snprintf
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_MEM,
 	.arg2_type	= ARG_CONST_SIZE,
-	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg4_type	= ARG_CONST_SIZE,
 	.arg5_type	= ARG_ANYTHING,
 };

@@ -1207,7 +1207,7 @@ static const struct bpf_func_proto bpf_p
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -1429,7 +1429,7 @@ static const struct bpf_func_proto bpf_p
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 

@@ -1483,7 +1483,7 @@ static const struct bpf_func_proto bpf_g
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
 };

241 lines not on this page · raw message

@@ -7,6 +7,7 @@
 #include "test_ksyms_btf.skel.h"
 #include "test_ksyms_btf_null_check.skel.h"
 #include "test_ksyms_weak.skel.h"
+#include "test_ksyms_btf_write_check.skel.h"
 
 static int duration;
 

@@ -109,6 +110,16 @@ cleanup:
 	test_ksyms_weak__destroy(skel);
 }
 
+static void test_write_check(void)
+{
+	struct test_ksyms_btf_write_check *skel;
+
+	skel = test_ksyms_btf_write_check__open_and_load();
+	ASSERT_ERR_PTR(skel, "unexpected load of a prog writing to ksym memory\n");
+
+	test_ksyms_btf_write_check__destroy(skel);
+}
+
 void test_ksyms_btf(void)
 {
 	int percpu_datasec;

@@ -136,4 +147,7 @@ void test_ksyms_btf(void)
 
 	if (test__start_subtest("weak_ksyms"))
 		test_weak_syms();
+
+	if (test__start_subtest("write_check"))
+		test_write_check();
 }

@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+extern const int bpf_prog_active __ksym; /* int type global var. */
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	int *active;
+	__u32 cpu;
+
+	cpu = bpf_get_smp_processor_id();
+	active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+	if (active) {
+		/* Kernel memory obtained from bpf_{per,this}_cpu_ptr
+		 * is read-only, should _not_ pass verification.
+		 */
+		/* WRITE_ONCE */
+		*(volatile int *)active = -1;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

@@ -5510,9 +5510,9 @@ static int btf_check_func_arg_match(stru
 			if (reg->type == PTR_TO_BTF_ID) {
 				reg_btf = reg->btf;
 				reg_ref_id = reg->btf_id;
-			} else if (reg2btf_ids[reg->type]) {
+			} else if (reg2btf_ids[base_type(reg->type)]) {
 				reg_btf = btf_vmlinux;
-				reg_ref_id = *reg2btf_ids[reg->type];
+				reg_ref_id = *reg2btf_ids[base_type(reg->type)];
 			} else {
 				bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d is not a pointer to btf_id\n",
 					func_name, i,

@@ -36,6 +36,7 @@
 /* Quirks */
 #define CQSPI_NEEDS_WR_DELAY		BIT(0)
 #define CQSPI_DISABLE_DAC_MODE		BIT(1)
+#define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)

@@ -83,6 +84,7 @@ struct cqspi_st {
 	u32			wr_delay;
 	bool			use_direct_mode;
 	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
+	bool			wr_completion;
 };
 
 struct cqspi_driver_platdata {

@@ -797,9 +799,11 @@ static int cqspi_write_setup(struct cqsp
 	 * polling on the controller's side. spinand and spi-nor will take
 	 * care of polling the status register.
 	 */
-	reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
-	reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
-	writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	if (cqspi->wr_completion) {
+		reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	}
 
 	reg = readl(reg_base + CQSPI_REG_SIZE);
 	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;

@@ -1532,6 +1536,10 @@ static int cqspi_probe(struct platform_d
 
 	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
 	master->max_speed_hz = cqspi->master_ref_clk_hz;
+
+	/* write completion is supported by default */
+	cqspi->wr_completion = true;
+
 	ddata  = of_device_get_match_data(dev);
 	if (ddata) {
 		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)

@@ -1541,6 +1549,8 @@ static int cqspi_probe(struct platform_d
 			master->mode_bits |= SPI_RX_OCTAL | SPI_TX_OCTAL;
 		if (!(ddata->quirks & CQSPI_DISABLE_DAC_MODE))
 			cqspi->use_direct_mode = true;
+		if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION)
+			cqspi->wr_completion = false;
 	}
 
 	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,

@@ -1649,6 +1659,10 @@ static const struct cqspi_driver_platdat
 	.quirks = CQSPI_DISABLE_DAC_MODE,
 };
 
+static const struct cqspi_driver_platdata socfpga_qspi = {
+	.quirks = CQSPI_NO_SUPPORT_WR_COMPLETION,
+};
+
 static const struct of_device_id cqspi_dt_ids[] = {
 	{
 		.compatible = "cdns,qspi-nor",

@@ -1666,6 +1680,10 @@ static const struct of_device_id cqspi_d
 		.compatible = "intel,lgm-qspi",
 		.data = &intel_lgm_qspi,
 	},
+	{
+		.compatible = "intel,socfpga-qspi",
+		.data = (void *)&socfpga_qspi,
+	},
 	{ /* end of table */ }
 };
 

@@ -528,6 +528,8 @@ static bool __init kfence_init_pool(void
 	 * enters __slab_free() slow-path.
 	 */
 	for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) {
+		struct page *page = &pages[i];
+
 		if (!i || (i % 2))
 			continue;
 

@@ -535,7 +537,11 @@ static bool __init kfence_init_pool(void
 		if (WARN_ON(compound_head(&pages[i]) != &pages[i]))
 			goto err;
 
-		__SetPageSlab(&pages[i]);
+		__SetPageSlab(page);
+#ifdef CONFIG_MEMCG
+		page->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg |
+				   MEMCG_DATA_OBJCGS;
+#endif
 	}
 
 	/*

@@ -911,6 +917,9 @@ void __kfence_free(void *addr)
 {
 	struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr);
 
+#ifdef CONFIG_MEMCG
+	KFENCE_WARN_ON(meta->objcg);
+#endif
 	/*
 	 * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing
 	 * the object, as the object page may be recycled for other-typed

@@ -89,6 +89,9 @@ struct kfence_metadata {
 	struct kfence_track free_track;
 	/* For updating alloc_covered on frees. */
 	u32 alloc_stack_hash;
+#ifdef CONFIG_MEMCG
+	struct obj_cgroup *objcg;
+#endif
 };
 
 extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS];

@@ -669,7 +669,8 @@ static void __init kvm_use_magic_page(vo
 	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
-	if (fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) {
+	if (fault_in_readable((const char __user *)KVM_MAGIC_PAGE,
+			      sizeof(u32))) {
 		kvm_patching_worked = false;
 		return;
 	}

@@ -1048,7 +1048,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucon
 	if (new_ctx == NULL)
 		return 0;
 	if (!access_ok(new_ctx, ctx_size) ||
-	    fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
+	    fault_in_readable((char __user *)new_ctx, ctx_size))
 		return -EFAULT;
 
 	/*

@@ -1239,7 +1239,7 @@ SYSCALL_DEFINE3(debug_setcontext, struct
 #endif
 
 	if (!access_ok(ctx, sizeof(*ctx)) ||
-	    fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx)))
+	    fault_in_readable((char __user *)ctx, sizeof(*ctx)))
 		return -EFAULT;
 
 	/*

@@ -688,7 +688,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucon
 	if (new_ctx == NULL)
 		return 0;
 	if (!access_ok(new_ctx, ctx_size) ||
-	    fault_in_pages_readable((u8 __user *)new_ctx, ctx_size))
+	    fault_in_readable((char __user *)new_ctx, ctx_size))
 		return -EFAULT;
 
 	/*

@@ -205,7 +205,7 @@ retry:
 	fpregs_unlock();
 
 	if (ret) {
-		if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size))
+		if (!fault_in_writeable(buf_fx, fpu_user_xstate_size))
 			goto retry;
 		return -EFAULT;
 	}

@@ -278,10 +278,9 @@ retry:
 		if (ret != -EFAULT)
 			return -EINVAL;
 
-		ret = fault_in_pages_readable(buf, size);
-		if (!ret)
+		if (!fault_in_readable(buf, size))
 			goto retry;
-		return ret;
+		return -EFAULT;
 	}
 
 	/*

@@ -336,7 +336,7 @@ int armada_gem_pwrite_ioctl(struct drm_d
 	struct drm_armada_gem_pwrite *args = data;
 	struct armada_gem_object *dobj;
 	char __user *ptr;
-	int ret;
+	int ret = 0;
 
 	DRM_DEBUG_DRIVER("handle %u off %u size %u ptr 0x%llx\n",
 		args->handle, args->offset, args->size, args->ptr);

@@ -349,9 +349,8 @@ int armada_gem_pwrite_ioctl(struct drm_d
 	if (!access_ok(ptr, args->size))
 		return -EFAULT;
 
-	ret = fault_in_pages_readable(ptr, args->size);
-	if (ret)
-		return ret;
+	if (fault_in_readable(ptr, args->size))
+		return -EFAULT;
 
 	dobj = armada_gem_object_lookup(file, args->handle);
 	if (dobj == NULL)

@@ -2258,9 +2258,8 @@ static noinline int search_ioctl(struct
 	key.offset = sk->min_offset;
 
 	while (1) {
-		ret = fault_in_pages_writeable(ubuf + sk_offset,
-					       *buf_size - sk_offset);
-		if (ret)
+		ret = -EFAULT;
+		if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset))
 			break;
 
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);

64 lines not on this page · raw message

@@ -191,7 +191,7 @@ static size_t copy_page_to_iter_iovec(st
 	buf = iov->iov_base + skip;
 	copy = min(bytes, iov->iov_len - skip);
 
-	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) {
+	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_writeable(buf, copy)) {
 		kaddr = kmap_atomic(page);
 		from = kaddr + offset;
 

@@ -275,7 +275,7 @@ static size_t copy_page_from_iter_iovec(
 	buf = iov->iov_base + skip;
 	copy = min(bytes, iov->iov_len - skip);
 
-	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) {
+	if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_readable(buf, copy)) {
 		kaddr = kmap_atomic(page);
 		to = kaddr + offset;
 

@@ -447,13 +447,11 @@ int iov_iter_fault_in_readable(const str
 			bytes = i->count;
 		for (p = i->iov, skip = i->iov_offset; bytes; p++, skip = 0) {
 			size_t len = min(bytes, p->iov_len - skip);
-			int err;
 
 			if (unlikely(!len))
 				continue;
-			err = fault_in_pages_readable(p->iov_base + skip, len);
-			if (unlikely(err))
-				return err;
+			if (fault_in_readable(p->iov_base + skip, len))
+				return -EFAULT;
 			bytes -= len;
 		}
 	}

@@ -90,7 +90,7 @@
  *      ->lock_page		(filemap_fault, access_process_vm)
  *
  *  ->i_rwsem			(generic_perform_write)
- *    ->mmap_lock		(fault_in_pages_readable->do_page_fault)
+ *    ->mmap_lock		(fault_in_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
  *    sb_lock			(fs/fs-writeback.c)

78 lines not on this page · raw message

@@ -1709,7 +1709,7 @@ static noinline ssize_t btrfs_buffered_w
 		 * Fault pages before locking them in prepare_pages
 		 * to avoid recursive lock
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, write_bytes))) {
 			ret = -EFAULT;
 			break;
 		}

@@ -4279,7 +4279,7 @@ static ssize_t f2fs_file_write_iter(stru
 		size_t target_size = 0;
 		int err;
 
-		if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+		if (fault_in_iov_iter_readable(from, iov_iter_count(from)))
 			set_inode_flag(inode, FI_NO_PREALLOC);
 
 		if ((iocb->ki_flags & IOCB_NOWAIT)) {

@@ -1164,7 +1164,7 @@ static ssize_t fuse_fill_write_pages(str
 
  again:
 		err = -EFAULT;
-		if (iov_iter_fault_in_readable(ii, bytes))
+		if (fault_in_iov_iter_readable(ii, bytes))
 			break;
 
 		err = -ENOMEM;

@@ -757,7 +757,7 @@ again:
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
 			status = -EFAULT;
 			break;
 		}

@@ -1829,7 +1829,7 @@ again:
 		 * pages being swapped out between us bringing them into memory
 		 * and doing the actual copying.
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
 			status = -EFAULT;
 			break;
 		}

@@ -989,7 +989,7 @@ static ssize_t ntfs_compress_write(struc
 		frame_vbo = pos & ~(frame_size - 1);
 		index = frame_vbo >> PAGE_SHIFT;
 
-		if (unlikely(iov_iter_fault_in_readable(from, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(from, bytes))) {
 			err = -EFAULT;
 			goto out;
 		}

@@ -133,7 +133,7 @@ size_t copy_page_from_iter_atomic(struct
 				  size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);

@@ -431,33 +431,42 @@ out:
 }
 
 /*
+ * fault_in_iov_iter_readable - fault in iov iterator for reading
+ * @i: iterator
+ * @size: maximum length
+ *
  * Fault in one or more iovecs of the given iov_iter, to a maximum length of
- * bytes.  For each iovec, fault in each page that constitutes the iovec.
+ * @size.  For each iovec, fault in each page that constitutes the iovec.
+ *
+ * Returns the number of bytes not faulted in (like copy_to_user() and
+ * copy_from_user()).
  *
- * Return 0 on success, or non-zero if the memory could not be accessed (i.e.
- * because it is an invalid address).
+ * Always returns 0 for non-userspace iterators.
  */
-int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes)
+size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size)
 {
 	if (iter_is_iovec(i)) {
+		size_t count = min(size, iov_iter_count(i));
 		const struct iovec *p;
 		size_t skip;
 
-		if (bytes > i->count)
-			bytes = i->count;
-		for (p = i->iov, skip = i->iov_offset; bytes; p++, skip = 0) {
-			size_t len = min(bytes, p->iov_len - skip);
+		size -= count;
+		for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+			size_t len = min(count, p->iov_len - skip);
+			size_t ret;
 
 			if (unlikely(!len))
 				continue;
-			if (fault_in_readable(p->iov_base + skip, len))
-				return -EFAULT;
-			bytes -= len;
+			ret = fault_in_readable(p->iov_base + skip, len);
+			count -= len - ret;
+			if (ret)
+				break;
 		}
+		return count + size;
 	}
 	return 0;
 }
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
+EXPORT_SYMBOL(fault_in_iov_iter_readable);
 
 void iov_iter_init(struct iov_iter *i, unsigned int direction,
 			const struct iovec *iov, unsigned long nr_segs,

@@ -3760,7 +3760,7 @@ again:
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
+		if (unlikely(fault_in_iov_iter_readable(i, bytes))) {
 			status = -EFAULT;
 			break;
 		}

@@ -736,6 +736,7 @@ extern void add_page_wait_queue(struct p
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
 size_t fault_in_readable(const char __user *uaddr, size_t size);
 
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,

@@ -134,6 +134,7 @@ size_t copy_page_from_iter_atomic(struct
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
 size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);

@@ -468,6 +468,45 @@ size_t fault_in_iov_iter_readable(const
 }
 EXPORT_SYMBOL(fault_in_iov_iter_readable);
 
+/*
+ * fault_in_iov_iter_writeable - fault in iov iterator for writing
+ * @i: iterator
+ * @size: maximum length
+ *
+ * Faults in the iterator using get_user_pages(), i.e., without triggering
+ * hardware page faults.  This is primarily useful when we already know that
+ * some or all of the pages in @i aren't in memory.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ *
+ * Always returns 0 for non-user-space iterators.
+ */
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
+{
+	if (iter_is_iovec(i)) {
+		size_t count = min(size, iov_iter_count(i));
+		const struct iovec *p;
+		size_t skip;
+
+		size -= count;
+		for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+			size_t len = min(count, p->iov_len - skip);
+			size_t ret;
+
+			if (unlikely(!len))
+				continue;
+			ret = fault_in_safe_writeable(p->iov_base + skip, len);
+			count -= len - ret;
+			if (ret)
+				break;
+		}
+		return count + size;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(fault_in_iov_iter_writeable);
+
 void iov_iter_init(struct iov_iter *i, unsigned int direction,
 			const struct iovec *iov, unsigned long nr_segs,
 			size_t count)

69 lines not on this page · raw message

@@ -877,6 +877,20 @@ out_uninit:
 	return written ? written : ret;
 }
 
+static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	ssize_t ret;
+
+	current->backing_dev_info = inode_to_bdi(inode);
+	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+	current->backing_dev_info = NULL;
+	if (ret > 0)
+		iocb->ki_pos += ret;
+	return ret;
+}
+
 /**
  * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context

@@ -928,9 +942,7 @@ static ssize_t gfs2_file_write_iter(stru
 			goto out_unlock;
 
 		iocb->ki_flags |= IOCB_DSYNC;
-		current->backing_dev_info = inode_to_bdi(inode);
-		buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		current->backing_dev_info = NULL;
+		buffered = gfs2_file_buffered_write(iocb, from);
 		if (unlikely(buffered <= 0)) {
 			if (!ret)
 				ret = buffered;

@@ -944,7 +956,6 @@ static ssize_t gfs2_file_write_iter(stru
 		 * the direct I/O range as we don't know if the buffered pages
 		 * made it to disk.
 		 */
-		iocb->ki_pos += buffered;
 		ret2 = generic_write_sync(iocb, buffered);
 		invalidate_mapping_pages(mapping,
 				(iocb->ki_pos - buffered) >> PAGE_SHIFT,

@@ -952,13 +963,9 @@ static ssize_t gfs2_file_write_iter(stru
 		if (!ret || ret2 > 0)
 			ret += ret2;
 	} else {
-		current->backing_dev_info = inode_to_bdi(inode);
-		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
-		current->backing_dev_info = NULL;
-		if (likely(ret > 0)) {
-			iocb->ki_pos += ret;
+		ret = gfs2_file_buffered_write(iocb, from);
+		if (likely(ret > 0))
 			ret = generic_write_sync(iocb, ret);
-		}
 	}
 
 out_unlock:

@@ -301,46 +301,59 @@ void gfs2_glock_put(struct gfs2_glock *g
 }
 
 /**
- * may_grant - check if its ok to grant a new lock
+ * may_grant - check if it's ok to grant a new lock
  * @gl: The glock
+ * @current_gh: One of the current holders of @gl
  * @gh: The lock request which we wish to grant
  *
- * Returns: true if its ok to grant the lock
+ * With our current compatibility rules, if a glock has one or more active
+ * holders (HIF_HOLDER flag set), any of those holders can be passed in as
+ * @current_gh; they are all the same as far as compatibility with the new @gh
+ * goes.
+ *
+ * Returns true if it's ok to grant the lock.
  */
 
-static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
-{
-	const struct gfs2_holder *gh_head = list_first_entry(&gl->gl_holders, const struct gfs2_holder, gh_list);
+static inline bool may_grant(struct gfs2_glock *gl,
+			     struct gfs2_holder *current_gh,
+			     struct gfs2_holder *gh)
+{
+	if (current_gh) {
+		GLOCK_BUG_ON(gl, !test_bit(HIF_HOLDER, &current_gh->gh_iflags));
+
+		switch(current_gh->gh_state) {
+		case LM_ST_EXCLUSIVE:
+			/*
+			 * Here we make a special exception to grant holders
+			 * who agree to share the EX lock with other holders
+			 * who also have the bit set. If the original holder
+			 * has the LM_FLAG_NODE_SCOPE bit set, we grant more
+			 * holders with the bit set.
+			 */
+			return gh->gh_state == LM_ST_EXCLUSIVE &&
+			       (current_gh->gh_flags & LM_FLAG_NODE_SCOPE) &&
+			       (gh->gh_flags & LM_FLAG_NODE_SCOPE);
 
-	if (gh != gh_head) {
-		/**
-		 * Here we make a special exception to grant holders who agree
-		 * to share the EX lock with other holders who also have the
-		 * bit set. If the original holder has the LM_FLAG_NODE_SCOPE bit
-		 * is set, we grant more holders with the bit set.
-		 */
-		if (gh_head->gh_state == LM_ST_EXCLUSIVE &&
-		    (gh_head->gh_flags & LM_FLAG_NODE_SCOPE) &&
-		    gh->gh_state == LM_ST_EXCLUSIVE &&
-		    (gh->gh_flags & LM_FLAG_NODE_SCOPE))
-			return 1;
-		if ((gh->gh_state == LM_ST_EXCLUSIVE ||
-		     gh_head->gh_state == LM_ST_EXCLUSIVE))
-			return 0;
+		case LM_ST_SHARED:
+		case LM_ST_DEFERRED:
+			return gh->gh_state == current_gh->gh_state;
+
+		default:
+			return false;
+		}
 	}
+
 	if (gl->gl_state == gh->gh_state)
-		return 1;
+		return true;
 	if (gh->gh_flags & GL_EXACT)
-		return 0;
+		return false;
 	if (gl->gl_state == LM_ST_EXCLUSIVE) {
-		if (gh->gh_state == LM_ST_SHARED && gh_head->gh_state == LM_ST_SHARED)
-			return 1;
-		if (gh->gh_state == LM_ST_DEFERRED && gh_head->gh_state == LM_ST_DEFERRED)
-			return 1;
+		return gh->gh_state == LM_ST_SHARED ||
+		       gh->gh_state == LM_ST_DEFERRED;
 	}
-	if (gl->gl_state != LM_ST_UNLOCKED && (gh->gh_flags & LM_FLAG_ANY))
-		return 1;
-	return 0;
+	if (gh->gh_flags & LM_FLAG_ANY)
+		return gl->gl_state != LM_ST_UNLOCKED;
+	return false;
 }
 
 static void gfs2_holder_wake(struct gfs2_holder *gh)

@@ -381,6 +394,24 @@ static void do_error(struct gfs2_glock *
 }
 
 /**
+ * find_first_holder - find the first "holder" gh
+ * @gl: the glock
+ */
+
+static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	if (!list_empty(&gl->gl_holders)) {
+		gh = list_first_entry(&gl->gl_holders, struct gfs2_holder,
+				      gh_list);
+		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
  * do_promote - promote as many requests as possible on the current queue
  * @gl: The glock
  * 

@@ -393,14 +424,15 @@ __releases(&gl->gl_lockref.lock)
 __acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
-	struct gfs2_holder *gh, *tmp;
+	struct gfs2_holder *gh, *tmp, *first_gh;
 	int ret;
 
 restart:
+	first_gh = find_first_holder(gl);
 	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
 		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
 			continue;
-		if (may_grant(gl, gh)) {
+		if (may_grant(gl, first_gh, gh)) {
 			if (gh->gh_list.prev == &gl->gl_holders &&
 			    glops->go_lock) {
 				spin_unlock(&gl->gl_lockref.lock);

@@ -723,23 +755,6 @@ out:
 }
 
 /**
- * find_first_holder - find the first "holder" gh
- * @gl: the glock
- */
-
-static inline struct gfs2_holder *find_first_holder(const struct gfs2_glock *gl)
-{
-	struct gfs2_holder *gh;
-
-	if (!list_empty(&gl->gl_holders)) {
-		gh = list_first_entry(&gl->gl_holders, struct gfs2_holder, gh_list);
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
-			return gh;
-	}
-	return NULL;
-}
-
-/**
  * run_queue - do all outstanding tasks related to a glock
  * @gl: The glock in question
  * @nonblock: True if we must not block in run_queue

@@ -1354,8 +1369,12 @@ __acquires(&gl->gl_lockref.lock)
 		GLOCK_BUG_ON(gl, true);
 
 	if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
-		if (test_bit(GLF_LOCK, &gl->gl_flags))
-			try_futile = !may_grant(gl, gh);
+		if (test_bit(GLF_LOCK, &gl->gl_flags)) {
+			struct gfs2_holder *first_gh;
+
+			first_gh = find_first_holder(gl);
+			try_futile = !may_grant(gl, first_gh, gh);
+		}
 		if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
 			goto fail;
 	}

@@ -58,6 +58,7 @@ struct gfs2_glock_iter {
 typedef void (*glock_examiner) (struct gfs2_glock * gl);
 
 static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
+static void __gfs2_glock_dq(struct gfs2_holder *gh);
 
 static struct dentry *gfs2_root;
 static struct workqueue_struct *glock_workqueue;

@@ -197,6 +198,12 @@ static int demote_ok(const struct gfs2_g
 
 	if (gl->gl_state == LM_ST_UNLOCKED)
 		return 0;
+	/*
+	 * Note that demote_ok is used for the lru process of disposing of
+	 * glocks. For this purpose, we don't care if the glock's holders
+	 * have the HIF_MAY_DEMOTE flag set or not. If someone is using
+	 * them, don't demote.
+	 */
 	if (!list_empty(&gl->gl_holders))
 		return 0;
 	if (glops->go_demote_ok)

@@ -379,7 +386,7 @@ static void do_error(struct gfs2_glock *
 	struct gfs2_holder *gh, *tmp;
 
 	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+		if (!test_bit(HIF_WAIT, &gh->gh_iflags))
 			continue;
 		if (ret & LM_OUT_ERROR)
 			gh->gh_error = -EIO;

@@ -394,6 +401,40 @@ static void do_error(struct gfs2_glock *
 }
 
 /**
+ * demote_incompat_holders - demote incompatible demoteable holders
+ * @gl: the glock we want to promote
+ * @new_gh: the new holder to be promoted
+ */
+static void demote_incompat_holders(struct gfs2_glock *gl,
+				    struct gfs2_holder *new_gh)
+{
+	struct gfs2_holder *gh;
+
+	/*
+	 * Demote incompatible holders before we make ourselves eligible.
+	 * (This holder may or may not allow auto-demoting, but we don't want
+	 * to demote the new holder before it's even granted.)
+	 */
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		/*
+		 * Since holders are at the front of the list, we stop when we
+		 * find the first non-holder.
+		 */
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return;
+		if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags) &&
+		    !may_grant(gl, new_gh, gh)) {
+			/*
+			 * We should not recurse into do_promote because
+			 * __gfs2_glock_dq only calls handle_callback,
+			 * gfs2_glock_add_to_lru and __gfs2_glock_queue_work.
+			 */
+			__gfs2_glock_dq(gh);
+		}
+	}
+}
+
+/**
  * find_first_holder - find the first "holder" gh
  * @gl: the glock
  */

@@ -412,6 +453,26 @@ static inline struct gfs2_holder *find_f
 }
 
 /**
+ * find_first_strong_holder - find the first non-demoteable holder
+ * @gl: the glock
+ *
+ * Find the first holder that doesn't have the HIF_MAY_DEMOTE flag set.
+ */
+static inline struct gfs2_holder *
+find_first_strong_holder(struct gfs2_glock *gl)
+{
+	struct gfs2_holder *gh;
+
+	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
+			return NULL;
+		if (!test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags))
+			return gh;
+	}
+	return NULL;
+}
+
+/**
  * do_promote - promote as many requests as possible on the current queue
  * @gl: The glock
  * 

@@ -425,14 +486,20 @@ __acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_holder *gh, *tmp, *first_gh;
+	bool incompat_holders_demoted = false;
 	int ret;
 
 restart:
-	first_gh = find_first_holder(gl);
+	first_gh = find_first_strong_holder(gl);
 	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
-		if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+		if (!test_bit(HIF_WAIT, &gh->gh_iflags))
 			continue;
 		if (may_grant(gl, first_gh, gh)) {
+			if (!incompat_holders_demoted) {
+				demote_incompat_holders(gl, first_gh);
+				incompat_holders_demoted = true;
+				first_gh = gh;
+			}
 			if (gh->gh_list.prev == &gl->gl_holders &&
 			    glops->go_lock) {
 				spin_unlock(&gl->gl_lockref.lock);

@@ -458,6 +525,11 @@ restart:
 			gfs2_holder_wake(gh);
 			continue;
 		}
+		/*
+		 * If we get here, it means we may not grant this holder for
+		 * some reason. If this holder is the head of the list, it
+		 * means we have a blocked holder at the head, so return 1.
+		 */
 		if (gh->gh_list.prev == &gl->gl_holders)
 			return 1;
 		do_error(gl, 0);

@@ -1372,7 +1444,7 @@ __acquires(&gl->gl_lockref.lock)
 		if (test_bit(GLF_LOCK, &gl->gl_flags)) {
 			struct gfs2_holder *first_gh;
 
-			first_gh = find_first_holder(gl);
+			first_gh = find_first_strong_holder(gl);
 			try_futile = !may_grant(gl, first_gh, gh);
 		}
 		if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))

@@ -1381,7 +1453,8 @@ __acquires(&gl->gl_lockref.lock)
 
 	list_for_each_entry(gh2, &gl->gl_holders, gh_list) {
 		if (unlikely(gh2->gh_owner_pid == gh->gh_owner_pid &&
-		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK)))
+		    (gh->gh_gl->gl_ops->go_type != LM_TYPE_FLOCK) &&
+		    !test_bit(HIF_MAY_DEMOTE, &gh2->gh_iflags)))
 			goto trap_recursive;
 		if (try_futile &&
 		    !(gh2->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))) {

@@ -1477,51 +1550,83 @@ int gfs2_glock_poll(struct gfs2_holder *
 	return test_bit(HIF_WAIT, &gh->gh_iflags) ? 0 : 1;
 }
 
-/**
- * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
- * @gh: the glock holder
- *
- */
+static inline bool needs_demote(struct gfs2_glock *gl)
+{
+	return (test_bit(GLF_DEMOTE, &gl->gl_flags) ||
+		test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags));
+}
 
-void gfs2_glock_dq(struct gfs2_holder *gh)
+static void __gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned delay = 0;
 	int fast_path = 0;
 
-	spin_lock(&gl->gl_lockref.lock);
 	/*
-	 * If we're in the process of file system withdraw, we cannot just
-	 * dequeue any glocks until our journal is recovered, lest we
-	 * introduce file system corruption. We need two exceptions to this
-	 * rule: We need to allow unlocking of nondisk glocks and the glock
-	 * for our own journal that needs recovery.
+	 * This while loop is similar to function demote_incompat_holders:
+	 * If the glock is due to be demoted (which may be from another node
+	 * or even if this holder is GL_NOCACHE), the weak holders are
+	 * demoted as well, allowing the glock to be demoted.
 	 */
-	if (test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags) &&
-	    glock_blocked_by_withdraw(gl) &&
-	    gh->gh_gl != sdp->sd_jinode_gl) {
-		sdp->sd_glock_dqs_held++;
-		spin_unlock(&gl->gl_lockref.lock);
-		might_sleep();
-		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
-			    TASK_UNINTERRUPTIBLE);
-		spin_lock(&gl->gl_lockref.lock);
-	}
-	if (gh->gh_flags & GL_NOCACHE)
-		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+	while (gh) {
+		/*
+		 * If we're in the process of file system withdraw, we cannot
+		 * just dequeue any glocks until our journal is recovered, lest
+		 * we introduce file system corruption. We need two exceptions
+		 * to this rule: We need to allow unlocking of nondisk glocks
+		 * and the glock for our own journal that needs recovery.
+		 */
+		if (test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags) &&
+		    glock_blocked_by_withdraw(gl) &&
+		    gh->gh_gl != sdp->sd_jinode_gl) {
+			sdp->sd_glock_dqs_held++;
+			spin_unlock(&gl->gl_lockref.lock);
+			might_sleep();
+			wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
+				    TASK_UNINTERRUPTIBLE);
+			spin_lock(&gl->gl_lockref.lock);
+		}
 
-	list_del_init(&gh->gh_list);
-	clear_bit(HIF_HOLDER, &gh->gh_iflags);
-	if (list_empty(&gl->gl_holders) &&
-	    !test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
-	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
-		fast_path = 1;
+		/*
+		 * This holder should not be cached, so mark it for demote.
+		 * Note: this should be done before the check for needs_demote
+		 * below.
+		 */
+		if (gh->gh_flags & GL_NOCACHE)
+			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+
+		list_del_init(&gh->gh_list);
+		clear_bit(HIF_HOLDER, &gh->gh_iflags);
+		trace_gfs2_glock_queue(gh, 0);
+
+		/*
+		 * If there hasn't been a demote request we are done.
+		 * (Let the remaining holders, if any, keep holding it.)
+		 */
+		if (!needs_demote(gl)) {
+			if (list_empty(&gl->gl_holders))
+				fast_path = 1;
+			break;
+		}
+		/*
+		 * If we have another strong holder (we cannot auto-demote)
+		 * we are done. It keeps holding it until it is done.
+		 */
+		if (find_first_strong_holder(gl))
+			break;
+
+		/*
+		 * If we have a weak holder at the head of the list, it
+		 * (and all others like it) must be auto-demoted. If there
+		 * are no more weak holders, we exit the while loop.
+		 */
+		gh = find_first_holder(gl);
+	}
 
 	if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl))
 		gfs2_glock_add_to_lru(gl);
 
-	trace_gfs2_glock_queue(gh, 0);
 	if (unlikely(!fast_path)) {
 		gl->gl_lockref.count++;
 		if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&

@@ -1530,6 +1635,19 @@ void gfs2_glock_dq(struct gfs2_holder *g
 			delay = gl->gl_hold_time;
 		__gfs2_glock_queue_work(gl, delay);
 	}
+}
+
+/**
+ * gfs2_glock_dq - dequeue a struct gfs2_holder from a glock (release a glock)
+ * @gh: the glock holder
+ *
+ */
+void gfs2_glock_dq(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	__gfs2_glock_dq(gh);
 	spin_unlock(&gl->gl_lockref.lock);
 }
 

@@ -1692,6 +1810,7 @@ void gfs2_glock_dq_m(unsigned int num_gh
 
 void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 {
+	struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, };
 	unsigned long delay = 0;
 	unsigned long holdtime;
 	unsigned long now = jiffies;

@@ -1706,6 +1825,28 @@ void gfs2_glock_cb(struct gfs2_glock *gl
 		if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
 			delay = gl->gl_hold_time;
 	}
+	/*
+	 * Note 1: We cannot call demote_incompat_holders from handle_callback
+	 * or gfs2_set_demote due to recursion problems like: gfs2_glock_dq ->
+	 * handle_callback -> demote_incompat_holders -> gfs2_glock_dq
+	 * Plus, we only want to demote the holders if the request comes from
+	 * a remote cluster node because local holder conflicts are resolved
+	 * elsewhere.
+	 *
+	 * Note 2: if a remote node wants this glock in EX mode, lock_dlm will
+	 * request that we set our state to UNLOCKED. Here we mock up a holder
+	 * to make it look like someone wants the lock EX locally. Any SH
+	 * and DF requests should be able to share the lock without demoting.
+	 *
+	 * Note 3: We only want to demote the demoteable holders when there
+	 * are no more strong holders. The demoteable holders might as well
+	 * keep the glock until the last strong holder is done with it.
+	 */
+	if (!find_first_strong_holder(gl)) {
+		if (state == LM_ST_UNLOCKED)
+			mock_gh.gh_state = LM_ST_EXCLUSIVE;
+		demote_incompat_holders(gl, &mock_gh);
+	}
 	handle_callback(gl, state, delay, true);
 	__gfs2_glock_queue_work(gl, delay);
 	spin_unlock(&gl->gl_lockref.lock);

@@ -2097,6 +2238,8 @@ static const char *hflags2str(char *buf,
 		*p++ = 'H';
 	if (test_bit(HIF_WAIT, &iflags))
 		*p++ = 'W';
+	if (test_bit(HIF_MAY_DEMOTE, &iflags))
+		*p++ = 'D';
 	*p = 0;
 	return buf;
 }

@@ -150,6 +150,8 @@ static inline struct gfs2_holder *gfs2_g
 	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
 		if (!test_bit(HIF_HOLDER, &gh->gh_iflags))
 			break;
+		if (test_bit(HIF_MAY_DEMOTE, &gh->gh_iflags))
+			continue;
 		if (gh->gh_owner_pid == pid)
 			goto out;
 	}

@@ -325,6 +327,24 @@ static inline void glock_clear_object(st
 	spin_unlock(&gl->gl_lockref.lock);
 }
 
+static inline void gfs2_holder_allow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	set_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
+static inline void gfs2_holder_disallow_demote(struct gfs2_holder *gh)
+{
+	struct gfs2_glock *gl = gh->gh_gl;
+
+	spin_lock(&gl->gl_lockref.lock);
+	clear_bit(HIF_MAY_DEMOTE, &gh->gh_iflags);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
 extern void gfs2_inode_remember_delete(struct gfs2_glock *gl, u64 generation);
 extern bool gfs2_inode_already_deleted(struct gfs2_glock *gl, u64 generation);
 

@@ -252,6 +252,7 @@ struct gfs2_lkstats {
 
 enum {
 	/* States */
+	HIF_MAY_DEMOTE		= 1,
 	HIF_HOLDER		= 6,  /* Set for gh that "holds" the glock */
 	HIF_WAIT		= 10,
 };

@@ -961,46 +961,6 @@ hole_found:
 	goto out;
 }
 
-static int gfs2_write_lock(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int error;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
-	if (error)
-		goto out_uninit;
-	if (&ip->i_inode == sdp->sd_rindex) {
-		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-
-		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
-					   GL_NOCACHE, &m_ip->i_gh);
-		if (error)
-			goto out_unlock;
-	}
-	return 0;
-
-out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
-out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
-	return error;
-}
-
-static void gfs2_write_unlock(struct inode *inode)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-
-	if (&ip->i_inode == sdp->sd_rindex) {
-		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-
-		gfs2_glock_dq_uninit(&m_ip->i_gh);
-	}
-	gfs2_glock_dq_uninit(&ip->i_gh);
-}
-
 static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
 				   unsigned len)
 {

@@ -1118,11 +1078,6 @@ out_qunlock:
 	return ret;
 }
 
-static inline bool gfs2_iomap_need_write_lock(unsigned flags)
-{
-	return (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT);
-}
-
 static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 			    unsigned flags, struct iomap *iomap,
 			    struct iomap *srcmap)

@@ -1135,12 +1090,6 @@ static int gfs2_iomap_begin(struct inode
 		iomap->flags |= IOMAP_F_BUFFER_HEAD;
 
 	trace_gfs2_iomap_start(ip, pos, length, flags);
-	if (gfs2_iomap_need_write_lock(flags)) {
-		ret = gfs2_write_lock(inode);
-		if (ret)
-			goto out;
-	}
-
 	ret = __gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
 	if (ret)
 		goto out_unlock;

@@ -1168,10 +1117,7 @@ static int gfs2_iomap_begin(struct inode
 	ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp);
 
 out_unlock:
-	if (ret && gfs2_iomap_need_write_lock(flags))
-		gfs2_write_unlock(inode);
 	release_metapath(&mp);
-out:
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
 }

@@ -1219,15 +1165,11 @@ static int gfs2_iomap_end(struct inode *
 	}
 
 	if (unlikely(!written))
-		goto out_unlock;
+		return 0;
 
 	if (iomap->flags & IOMAP_F_SIZE_CHANGED)
 		mark_inode_dirty(inode);
 	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
-
-out_unlock:
-	if (gfs2_iomap_need_write_lock(flags))
-		gfs2_write_unlock(inode);
 	return 0;
 }
 

@@ -881,13 +881,40 @@ static ssize_t gfs2_file_buffered_write(
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	ssize_t ret;
 
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	ret = gfs2_glock_nq(&ip->i_gh);
+	if (ret)
+		goto out_uninit;
+
+	if (inode == sdp->sd_rindex) {
+		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+		ret = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+					 GL_NOCACHE, &m_ip->i_gh);
+		if (ret)
+			goto out_unlock;
+	}
+
 	current->backing_dev_info = inode_to_bdi(inode);
 	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
 	current->backing_dev_info = NULL;
 	if (ret > 0)
 		iocb->ki_pos += ret;
+
+	if (inode == sdp->sd_rindex) {
+		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+		gfs2_glock_dq_uninit(&m_ip->i_gh);
+	}
+
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
 	return ret;
 }
 

@@ -877,16 +877,25 @@ out_uninit:
 	return written ? written : ret;
 }
 
-static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
+					struct iov_iter *from,
+					struct gfs2_holder *gh)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_holder *statfs_gh = NULL;
 	ssize_t ret;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	ret = gfs2_glock_nq(&ip->i_gh);
+	if (inode == sdp->sd_rindex) {
+		statfs_gh = kmalloc(sizeof(*statfs_gh), GFP_NOFS);
+		if (!statfs_gh)
+			return -ENOMEM;
+	}
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh);
+	ret = gfs2_glock_nq(gh);
 	if (ret)
 		goto out_uninit;
 

@@ -894,7 +903,7 @@ static ssize_t gfs2_file_buffered_write(
 		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 
 		ret = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
-					 GL_NOCACHE, &m_ip->i_gh);
+					 GL_NOCACHE, statfs_gh);
 		if (ret)
 			goto out_unlock;
 	}

@@ -905,16 +914,15 @@ static ssize_t gfs2_file_buffered_write(
 	if (ret > 0)
 		iocb->ki_pos += ret;
 
-	if (inode == sdp->sd_rindex) {
-		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-
-		gfs2_glock_dq_uninit(&m_ip->i_gh);
-	}
+	if (inode == sdp->sd_rindex)
+		gfs2_glock_dq_uninit(statfs_gh);
 
 out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
+	gfs2_glock_dq(gh);
 out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
+	gfs2_holder_uninit(gh);
+	if (statfs_gh)
+		kfree(statfs_gh);
 	return ret;
 }
 

@@ -969,7 +977,7 @@ static ssize_t gfs2_file_write_iter(stru
 			goto out_unlock;
 
 		iocb->ki_flags |= IOCB_DSYNC;
-		buffered = gfs2_file_buffered_write(iocb, from);
+		buffered = gfs2_file_buffered_write(iocb, from, &gh);
 		if (unlikely(buffered <= 0)) {
 			if (!ret)
 				ret = buffered;

@@ -990,7 +998,7 @@ static ssize_t gfs2_file_write_iter(stru
 		if (!ret || ret2 > 0)
 			ret += ret2;
 	} else {
-		ret = gfs2_file_buffered_write(iocb, from);
+		ret = gfs2_file_buffered_write(iocb, from, &gh);
 		if (likely(ret > 0))
 			ret = generic_write_sync(iocb, ret);
 	}

@@ -387,9 +387,8 @@ struct gfs2_inode {
 	u64 i_generation;
 	u64 i_eattr;
 	unsigned long i_flags;		/* GIF_... */
-	struct gfs2_glock *i_gl; /* Move into i_gh? */
+	struct gfs2_glock *i_gl;
 	struct gfs2_holder i_iopen_gh;
-	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_qadata *i_qadata; /* quota allocation data */
 	struct gfs2_holder i_rgd_gh;
 	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */

@@ -777,6 +777,36 @@ static int gfs2_fsync(struct file *file,
 	return ret ? ret : ret1;
 }
 
+static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i,
+					 size_t *prev_count,
+					 size_t *window_size)
+{
+	char __user *p = i->iov[0].iov_base + i->iov_offset;
+	size_t count = iov_iter_count(i);
+	int pages = 1;
+
+	if (likely(!count))
+		return false;
+	if (ret <= 0 && ret != -EFAULT)
+		return false;
+	if (!iter_is_iovec(i))
+		return false;
+
+	if (*prev_count != count || !*window_size) {
+		int pages, nr_dirtied;
+
+		pages = min_t(int, BIO_MAX_VECS,
+			      DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE));
+		nr_dirtied = max(current->nr_dirtied_pause -
+				 current->nr_dirtied, 1);
+		pages = min(pages, nr_dirtied);
+	}
+
+	*prev_count = count;
+	*window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p);
+	return true;
+}
+
 static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to,
 				     struct gfs2_holder *gh)
 {

@@ -841,9 +871,17 @@ static ssize_t gfs2_file_read_iter(struc
 {
 	struct gfs2_inode *ip;
 	struct gfs2_holder gh;
+	size_t prev_count = 0, window_size = 0;
 	size_t written = 0;
 	ssize_t ret;
 
+	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 */
+
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		ret = gfs2_file_direct_read(iocb, to, &gh);
 		if (likely(ret != -ENOTBLK))

@@ -865,13 +903,34 @@ static ssize_t gfs2_file_read_iter(struc
 	}
 	ip = GFS2_I(iocb->ki_filp->f_mapping->host);
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+retry:
 	ret = gfs2_glock_nq(&gh);
 	if (ret)
 		goto out_uninit;
+retry_under_glock:
+	pagefault_disable();
 	ret = generic_file_read_iter(iocb, to);
+	pagefault_enable();
 	if (ret > 0)
 		written += ret;
-	gfs2_glock_dq(&gh);
+
+	if (should_fault_in_pages(ret, to, &prev_count, &window_size)) {
+		size_t leftover;
+
+		gfs2_holder_allow_demote(&gh);
+		leftover = fault_in_iov_iter_writeable(to, window_size);
+		gfs2_holder_disallow_demote(&gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(&gh)) {
+				if (written)
+					goto out_uninit;
+				goto retry;
+			}
+			goto retry_under_glock;
+		}
+	}
+	if (gfs2_holder_queued(&gh))
+		gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
 	return written ? written : ret;

@@ -886,8 +945,17 @@ static ssize_t gfs2_file_buffered_write(
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_holder *statfs_gh = NULL;
+	size_t prev_count = 0, window_size = 0;
+	size_t read = 0;
 	ssize_t ret;
 
+	/*
+	 * In this function, we disable page faults when we're holding the
+	 * inode glock while doing I/O.  If a page fault occurs, we indicate
+	 * that the inode glock may be dropped, fault in the pages manually,
+	 * and retry.
+	 */
+
 	if (inode == sdp->sd_rindex) {
 		statfs_gh = kmalloc(sizeof(*statfs_gh), GFP_NOFS);
 		if (!statfs_gh)

@@ -895,10 +963,11 @@ static ssize_t gfs2_file_buffered_write(
 	}
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh);
+retry:
 	ret = gfs2_glock_nq(gh);
 	if (ret)
 		goto out_uninit;
-
+retry_under_glock:
 	if (inode == sdp->sd_rindex) {
 		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 

@@ -909,21 +978,41 @@ static ssize_t gfs2_file_buffered_write(
 	}
 
 	current->backing_dev_info = inode_to_bdi(inode);
+	pagefault_disable();
 	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+	pagefault_enable();
 	current->backing_dev_info = NULL;
-	if (ret > 0)
+	if (ret > 0) {
 		iocb->ki_pos += ret;
+		read += ret;
+	}
 
 	if (inode == sdp->sd_rindex)
 		gfs2_glock_dq_uninit(statfs_gh);
 
+	if (should_fault_in_pages(ret, from, &prev_count, &window_size)) {
+		size_t leftover;
+
+		gfs2_holder_allow_demote(gh);
+		leftover = fault_in_iov_iter_readable(from, window_size);
+		gfs2_holder_disallow_demote(gh);
+		if (leftover != window_size) {
+			if (!gfs2_holder_queued(gh)) {
+				if (read)
+					goto out_uninit;
+				goto retry;
+			}
+			goto retry_under_glock;
+		}
+	}
 out_unlock:
-	gfs2_glock_dq(gh);
+	if (gfs2_holder_queued(gh))
+		gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);
 	if (statfs_gh)
 		kfree(statfs_gh);
-	return ret;
+	return read ? read : ret;
 }
 
 /**

@@ -371,6 +371,8 @@ static loff_t iomap_dio_hole_iter(const
 	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
 
 	dio->size += length;
+	if (!length)
+		return -EFAULT;
 	return length;
 }
 

@@ -402,6 +404,8 @@ static loff_t iomap_dio_inline_iter(cons
 		copied = copy_to_iter(inline_data, length, iter);
 	}
 	dio->size += copied;
+	if (!copied)
+		return -EFAULT;
 	return copied;
 }
 

@@ -581,6 +581,12 @@ __iomap_dio_rw(struct kiocb *iocb, struc
 	if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size)
 		iov_iter_revert(iter, iomi.pos - dio->i_size);
 
+	if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) {
+		if (!(iocb->ki_flags & IOCB_NOWAIT))
+			wait_for_completion = true;
+		ret = 0;
+	}
+
 	/* magic error code to fall back to buffered I/O */
 	if (ret == -ENOTBLK) {
 		wait_for_completion = true;

@@ -330,6 +330,13 @@ struct iomap_dio_ops {
   */
 #define IOMAP_DIO_OVERWRITE_ONLY	(1 << 1)
 
+/*
+ * When a page fault occurs, return a partial synchronous result and allow
+ * the caller to retry the rest of the operation after dealing with the page
+ * fault.
+ */
+#define IOMAP_DIO_PARTIAL		(1 << 2)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags);

@@ -1956,7 +1956,7 @@ relock:
 	}
 
 	dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			     0);
+			     0, 0);
 
 	btrfs_inode_unlock(inode, ilock_flags);
 

@@ -3668,7 +3668,8 @@ static ssize_t btrfs_direct_read(struct
 		return 0;
 
 	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0);
+	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
+			   0, 0);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	return ret;
 }

@@ -287,7 +287,7 @@ static ssize_t erofs_file_read_iter(stru
 
 		if (!err)
 			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-					    NULL, 0);
+					    NULL, 0, 0);
 		if (err < 0)
 			return err;
 	}

@@ -74,7 +74,7 @@ static ssize_t ext4_dio_read_iter(struct
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);

@@ -566,7 +566,8 @@ static ssize_t ext4_dio_write_iter(struc
 	if (ilock_shared)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
-			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0);
+			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
+			   0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 

@@ -823,7 +823,7 @@ static ssize_t gfs2_file_direct_read(str
 	if (ret)
 		goto out_uninit;
 
-	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0, 0);
 	gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);

@@ -857,7 +857,7 @@ static ssize_t gfs2_file_direct_write(st
 	if (offset + len > i_size_read(&ip->i_inode))
 		goto out;
 
-	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0, 0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 out:

@@ -31,6 +31,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	size_t			done_before;
 	bool			wait_for_completion;
 
 	union {

@@ -124,6 +125,9 @@ ssize_t iomap_dio_complete(struct iomap_
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
+	if (ret > 0)
+		ret += dio->done_before;
+
 	kfree(dio);
 
 	return ret;

@@ -450,13 +454,21 @@ static loff_t iomap_dio_iter(const struc
  * may be pure data writes. In that case, we still need to do a full data sync
  * completion.
  *
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer.  In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred.  The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);

@@ -486,6 +498,7 @@ __iomap_dio_rw(struct kiocb *iocb, struc
 	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->done_before = done_before;
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;

@@ -652,11 +665,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);

@@ -259,7 +259,7 @@ xfs_file_dio_read(
 	ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED);
 	if (ret)
 		return ret;
-	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;

@@ -569,7 +569,7 @@ xfs_file_dio_write_aligned(
 	}
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0);
+			   &xfs_dio_write_ops, 0, 0);
 out_unlock:
 	if (iolock)
 		xfs_iunlock(ip, iolock);

@@ -647,7 +647,7 @@ retry_exclusive:
 
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, flags);
+			   &xfs_dio_write_ops, flags, 0);
 
 	/*
 	 * Retry unaligned I/O with exclusive blocking semantics if the DIO

@@ -852,7 +852,7 @@ static ssize_t zonefs_file_dio_write(str
 		ret = zonefs_file_dio_append(iocb, from);
 	else
 		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-				   &zonefs_write_dio_ops, 0);
+				   &zonefs_write_dio_ops, 0, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)

@@ -987,7 +987,7 @@ static ssize_t zonefs_file_read_iter(str
 		}
 		file_accessed(iocb->ki_filp);
 		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, 0);
+				   &zonefs_read_dio_ops, 0, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)

@@ -339,10 +339,10 @@ struct iomap_dio_ops {
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 

@@ -2858,7 +2858,8 @@ struct page *follow_page(struct vm_area_
 #define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
 #define FOLL_NOWAIT	0x20	/* if a disk transfer is needed, start the IO
 				 * and return without waiting upon it */
-#define FOLL_POPULATE	0x40	/* fault in page */
+#define FOLL_POPULATE	0x40	/* fault in pages (with FOLL_MLOCK) */
+#define FOLL_NOFAULT	0x80	/* do not fault in pages */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */

@@ -943,6 +943,8 @@ static int faultin_page(struct vm_area_s
 	/* mlock all present pages, but do not fault in new pages */
 	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
 		return -ENOENT;
+	if (*flags & FOLL_NOFAULT)
+		return -EFAULT;
 	if (*flags & FOLL_WRITE)
 		fault_flags |= FAULT_FLAG_WRITE;
 	if (*flags & FOLL_REMOTE)

@@ -2868,7 +2870,7 @@ static int internal_get_user_pages_fast(
 
 	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
 				       FOLL_FORCE | FOLL_PIN | FOLL_GET |
-				       FOLL_FAST_ONLY)))
+				       FOLL_FAST_ONLY | FOLL_NOFAULT)))
 		return -EINVAL;
 
 	if (gup_flags & FOLL_PIN)

@@ -35,6 +35,7 @@ struct iov_iter_state {
 
 struct iov_iter {
 	u8 iter_type;
+	bool nofault;
 	bool data_source;
 	size_t iov_offset;
 	size_t count;

@@ -514,6 +514,7 @@ void iov_iter_init(struct iov_iter *i, u
 	WARN_ON(direction & ~(READ | WRITE));
 	*i = (struct iov_iter) {
 		.iter_type = ITER_IOVEC,
+		.nofault = false,
 		.data_source = direction,
 		.iov = iov,
 		.nr_segs = nr_segs,

@@ -1529,13 +1530,17 @@ ssize_t iov_iter_get_pages(struct iov_it
 		return 0;
 
 	if (likely(iter_is_iovec(i))) {
+		unsigned int gup_flags = 0;
 		unsigned long addr;
 
+		if (iov_iter_rw(i) != WRITE)
+			gup_flags |= FOLL_WRITE;
+		if (i->nofault)
+			gup_flags |= FOLL_NOFAULT;
+
 		addr = first_iovec_segment(i, &len, start, maxsize, maxpages);
 		n = DIV_ROUND_UP(len, PAGE_SIZE);
-		res = get_user_pages_fast(addr, n,
-				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0,
-				pages);
+		res = get_user_pages_fast(addr, n, gup_flags, pages);
 		if (unlikely(res <= 0))
 			return res;
 		return (res == n ? len : res * PAGE_SIZE) - *start;