Merge branch 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull initial set_fs() removal from Al Viro:
 "Christoph's set_fs base series + fixups"

* 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  fs: Allow a NULL pos pointer to __kernel_read
  fs: Allow a NULL pos pointer to __kernel_write
  powerpc: remove address space overrides using set_fs()
  powerpc: use non-set_fs based maccess routines
  x86: remove address space overrides using set_fs()
  x86: make TASK_SIZE_MAX usable from assembly code
  x86: move PAGE_OFFSET, TASK_SIZE & friends to page_{32,64}_types.h
  lkdtm: remove set_fs-based tests
  test_bitmap: remove user bitmap tests
  uaccess: add infrastructure for kernel builds with set_fs()
  fs: don't allow splice read/write without explicit ops
  fs: don't allow kernel reads and writes without iter ops
  sysctl: Convert to iter interfaces
  proc: add a read_iter method to proc proc_ops
  proc: cleanup the compat vs no compat file ops
  proc: remove a level of indentation in proc_get_inode

arch/Kconfig

@@ -24,6 +24,9 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config SET_FS
+	bool
+
 config HOTPLUG_SMT
 	bool
 

arch/alpha/Kconfig

@@ -39,6 +39,7 @@ config ALPHA
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
 	select MMU_GATHER_NO_RANGE
+	select SET_FS
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,

arch/arc/Kconfig

@@ -48,6 +48,7 @@ config ARC
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
+	select SET_FS
 
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y

arch/arm/Kconfig

@@ -120,6 +120,7 @@ config ARM
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.

arch/arm64/Kconfig

@@ -194,6 +194,7 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
+	select SET_FS
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE

arch/c6x/Kconfig

@@ -22,6 +22,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config MMU
 	def_bool n

arch/csky/Kconfig

@@ -78,6 +78,7 @@ config CSKY
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
+	select SET_FS
 
 config LOCKDEP_SUPPORT
 	def_bool y

arch/h8300/Kconfig

@@ -25,6 +25,7 @@ config H8300
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
+	select SET_FS
 	select UACCESS_MEMCPY
 
 config CPU_BIG_ENDIAN

arch/hexagon/Kconfig

@@ -31,6 +31,7 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
+	select SET_FS
 	help
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.

arch/ia64/Kconfig

@@ -56,6 +56,7 @@ config IA64
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
 	select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
+	select SET_FS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to

arch/m68k/Kconfig

@@ -31,6 +31,7 @@ config M68K
 	select NO_DMA if !MMU && !COLDFIRE
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
+	select SET_FS
 	select UACCESS_MEMCPY if !MMU
 	select VIRT_TO_BUS
 

arch/microblaze/Kconfig

@@ -47,6 +47,7 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
+	select SET_FS
 
 # Endianness selection
 choice

arch/mips/Kconfig

@@ -88,6 +88,7 @@ config MIPS
 	select PERF_USE_VMALLOC
 	select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
 	select RTC_LIB
+	select SET_FS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 

arch/nds32/Kconfig

@@ -48,6 +48,7 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select SET_FS
 	help
 	  Andes(nds32) Linux support.
 

arch/nios2/Kconfig

@@ -27,6 +27,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config GENERIC_CSUM
 	def_bool y

arch/openrisc/Kconfig

@@ -39,6 +39,7 @@ config OPENRISC
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y

arch/parisc/Kconfig

@@ -63,6 +63,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select SET_FS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used

arch/powerpc/include/asm/processor.h

@@ -83,10 +83,6 @@ struct task_struct;
 void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp);
 void release_thread(struct task_struct *);
 
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
 #define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
 #define TS_CKFPR(i) ckfp_state.fpr[i][TS_FPROFFSET]
 
@@ -148,7 +144,6 @@ struct thread_struct {
 	unsigned long	ksp_vsid;
 #endif
 	struct pt_regs	*regs;		/* Pointer to saved register state */
-	mm_segment_t	addr_limit;	/* for get_fs() validation */
 #ifdef CONFIG_BOOKE
 	/* BookE base exception scratch space; align on cacheline */
 	unsigned long	normsave[8] ____cacheline_aligned;
@@ -296,7 +291,6 @@ struct thread_struct {
 #define INIT_THREAD { \
 	.ksp = INIT_SP, \
 	.ksp_limit = INIT_SP_LIMIT, \
-	.addr_limit = KERNEL_DS, \
 	.pgdir = swapper_pg_dir, \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
 	SPEFSCR_INIT \
@@ -304,7 +298,6 @@ struct thread_struct {
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.addr_limit = KERNEL_DS, \
 	.fpexc_mode = 0, \
 }
 #endif

arch/powerpc/include/asm/thread_info.h

@@ -90,7 +90,6 @@ void arch_setup_new_exec(void);
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_FSCHECK		3	/* Check FS is USER_DS on return */
 #define TIF_SYSCALL_EMU		4	/* syscall emulation active */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
 #define TIF_PATCH_PENDING	6	/* pending live patching update */
@@ -130,7 +129,6 @@ void arch_setup_new_exec(void);
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
-#define _TIF_FSCHECK		(1<<TIF_FSCHECK)
 #define _TIF_SYSCALL_EMU	(1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
@@ -138,8 +136,7 @@ void arch_setup_new_exec(void);
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
-				 _TIF_FSCHECK)
+				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
 
 /* Bits in local_flags */

arch/powerpc/include/asm/uaccess.h

@@ -8,62 +8,21 @@
 #include <asm/extable.h>
 #include <asm/kup.h>
 
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- *
- * The fs/ds values are now the highest legal address in the "segment".
- * This simplifies the checking in the routines below.
- */
-
-#define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
-
-#define KERNEL_DS	MAKE_MM_SEG(~0UL)
 #ifdef __powerpc64__
 /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */
-#define USER_DS		MAKE_MM_SEG(TASK_SIZE_USER64 - 1)
+#define TASK_SIZE_MAX		TASK_SIZE_USER64
 #else
-#define USER_DS		MAKE_MM_SEG(TASK_SIZE - 1)
+#define TASK_SIZE_MAX		TASK_SIZE
 #endif
 
-#define get_fs()	(current->thread.addr_limit)
-
-static inline void set_fs(mm_segment_t fs)
-{
-	current->thread.addr_limit = fs;
-	/* On user-mode return check addr_limit (fs) is correct */
-	set_thread_flag(TIF_FSCHECK);
-}
-
-#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
-#define user_addr_max()	(get_fs().seg)
-
-#ifdef __powerpc64__
-/*
- * This check is sufficient because there is a large enough
- * gap between user addresses and the kernel addresses
- */
-#define __access_ok(addr, size, segment)	\
-	(((addr) <= (segment).seg) && ((size) <= (segment).seg))
-
-#else
-
-static inline int __access_ok(unsigned long addr, unsigned long size,
-			mm_segment_t seg)
+static inline bool __access_ok(unsigned long addr, unsigned long size)
 {
-	if (addr > seg.seg)
-		return 0;
-	return (size == 0 || size - 1 <= seg.seg - addr);
+	return addr < TASK_SIZE_MAX && size <= TASK_SIZE_MAX - addr;
 }
 
-#endif
-
 #define access_ok(addr, size)		\
 	(__chk_user_ptr(addr),		\
-	 __access_ok((__force unsigned long)(addr), (size), get_fs()))
+	 __access_ok((unsigned long)(addr), (size)))
 
 /*
  * These are the main single-value transfer routines.  They automatically
@@ -604,4 +563,20 @@ do {									\
 		__put_user_goto(*(u8*)(_src + _i), (u8 __user *)(_dst + _i), e);\
 } while (0)
 
+#define HAVE_GET_KERNEL_NOFAULT
+
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	int __kr_err;							\
+									\
+	__get_user_size_allowed(*((type *)(dst)), (__force type __user *)(src),\
+			sizeof(type), __kr_err);			\
+	if (unlikely(__kr_err))						\
+		goto err_label;						\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+	__put_user_size_goto(*((type *)(src)),				\
+		(__force type __user *)(dst), sizeof(type), err_label)
+
 #endif	/* _ARCH_POWERPC_UACCESS_H */

arch/powerpc/kernel/signal.c

@@ -312,9 +312,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
 	user_exit();
 
-	/* Check valid addr_limit, TIF check is done there */
-	addr_limit_user_check();
-
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 

arch/powerpc/lib/sstep.c

@@ -108,11 +108,11 @@ static nokprobe_inline long address_ok(struct pt_regs *regs,
 {
 	if (!user_mode(regs))
 		return 1;
-	if (__access_ok(ea, nb, USER_DS))
+	if (__access_ok(ea, nb))
 		return 1;
-	if (__access_ok(ea, 1, USER_DS))
+	if (__access_ok(ea, 1))
 		/* Access overlaps the end of the user region */
-		regs->dar = USER_DS.seg;
+		regs->dar = TASK_SIZE_MAX - 1;
 	else
 		regs->dar = ea;
 	return 0;

arch/riscv/Kconfig

@@ -88,6 +88,7 @@ config RISCV
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
+	select SET_FS
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT

arch/s390/Kconfig

@@ -191,6 +191,7 @@ config S390
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
 	select PCI_MSI_ARCH_FALLBACKS	if PCI_MSI
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK

arch/sh/Kconfig

@@ -71,6 +71,7 @@ config SUPERH
 	select PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems

arch/sparc/Kconfig

@@ -51,6 +51,7 @@ config SPARC
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
+	select SET_FS
 
 config SPARC32
 	def_bool !64BIT

arch/um/Kconfig

@@ -19,6 +19,7 @@ config UML
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select HAVE_GCC_PLUGINS
+	select SET_FS
 	select TTY # Needed for line.c
 
 config MMU

arch/x86/ia32/ia32_aout.c

@@ -239,7 +239,6 @@ static int load_aout_binary(struct linux_binprm *bprm)
 	(regs)->ss = __USER32_DS;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 =
 	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
-	set_fs(USER_DS);
 	return 0;
 }
 

arch/x86/include/asm/page_32_types.h

@@ -41,6 +41,17 @@
 #define __VIRTUAL_MASK_SHIFT	32
 #endif	/* CONFIG_X86_PAE */
 
+/*
+ * User space process size: 3GB (default).
+ */
+#define IA32_PAGE_OFFSET	__PAGE_OFFSET
+#define TASK_SIZE		__PAGE_OFFSET
+#define TASK_SIZE_LOW		TASK_SIZE
+#define TASK_SIZE_MAX		TASK_SIZE
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
+#define STACK_TOP		TASK_SIZE
+#define STACK_TOP_MAX		STACK_TOP
+
 /*
  * Kernel image size is limited to 512 MB (see in arch/x86/kernel/head_32.S)
  */

arch/x86/include/asm/page_64_types.h

@@ -59,6 +59,44 @@
 #define __VIRTUAL_MASK_SHIFT	47
 #endif
 
+/*
+ * User space process size.  This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen.  This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
+ */
+#define TASK_SIZE_MAX	((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
+
+#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
+					0xc0000000 : 0xFFFFe000)
+
+#define TASK_SIZE_LOW		(test_thread_flag(TIF_ADDR32) ? \
+					IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
+#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
+
+#define STACK_TOP		TASK_SIZE_LOW
+#define STACK_TOP_MAX		TASK_SIZE_MAX
+
 /*
  * Maximum kernel image size is limited to 1 GiB, due to the fixmap living
  * in the next 1 GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S).

arch/x86/include/asm/processor.h

@@ -482,10 +482,6 @@ extern unsigned int fpu_user_xstate_size;
 
 struct perf_event;
 
-typedef struct {
-	unsigned long		seg;
-} mm_segment_t;
-
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
@@ -538,8 +534,6 @@ struct thread_struct {
 	 */
 	unsigned long		iopl_emul;
 
-	mm_segment_t		addr_limit;
-
 	unsigned int		sig_on_uaccess_err:1;
 
 	/* Floating point and extended processor state */
@@ -783,67 +777,15 @@ static inline void spin_lock_prefetch(const void *x)
 })
 
 #ifdef CONFIG_X86_32
-/*
- * User space process size: 3GB (default).
- */
-#define IA32_PAGE_OFFSET	PAGE_OFFSET
-#define TASK_SIZE		PAGE_OFFSET
-#define TASK_SIZE_LOW		TASK_SIZE
-#define TASK_SIZE_MAX		TASK_SIZE
-#define DEFAULT_MAP_WINDOW	TASK_SIZE
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		STACK_TOP
-
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
 	.sysenter_cs		= __KERNEL_CS,				  \
-	.addr_limit		= KERNEL_DS,				  \
 }
 
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
-/*
- * User space process size.  This is the first address outside the user range.
- * There are a few constraints that determine this:
- *
- * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
- * address, then that syscall will enter the kernel with a
- * non-canonical return address, and SYSRET will explode dangerously.
- * We avoid this particular problem by preventing anything executable
- * from being mapped at the maximum canonical address.
- *
- * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
- * CPUs malfunction if they execute code from the highest canonical page.
- * They'll speculate right off the end of the canonical space, and
- * bad things happen.  This is worked around in the same way as the
- * Intel problem.
- *
- * With page table isolation enabled, we map the LDT in ... [stay tuned]
- */
-#define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
-
-#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
-					0xc0000000 : 0xFFFFe000)
-
-#define TASK_SIZE_LOW		(test_thread_flag(TIF_ADDR32) ? \
-					IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW)
-#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-
-#define STACK_TOP		TASK_SIZE_LOW
-#define STACK_TOP_MAX		TASK_SIZE_MAX
-
-#define INIT_THREAD  {						\
-	.addr_limit		= KERNEL_DS,			\
-}
+#define INIT_THREAD { }
 
 extern unsigned long KSTK_ESP(struct task_struct *task);
 

arch/x86/include/asm/thread_info.h

@@ -102,7 +102,6 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 #define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
 #define TIF_X32			30	/* 32-bit native x86-64 binary */
-#define TIF_FSCHECK		31	/* Check FS is USER_DS on return */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -131,7 +130,6 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_ADDR32		(1 << TIF_ADDR32)
 #define _TIF_X32		(1 << TIF_X32)
-#define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE					\

arch/x86/include/asm/uaccess.h

@@ -12,30 +12,6 @@
 #include <asm/smap.h>
 #include <asm/extable.h>
 
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-#define KERNEL_DS	MAKE_MM_SEG(-1UL)
-#define USER_DS 	MAKE_MM_SEG(TASK_SIZE_MAX)
-
-#define get_fs()	(current->thread.addr_limit)
-static inline void set_fs(mm_segment_t fs)
-{
-	current->thread.addr_limit = fs;
-	/* On user-mode return, check fs is correct */
-	set_thread_flag(TIF_FSCHECK);
-}
-
-#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
-#define user_addr_max() (current->thread.addr_limit.seg)
-
 /*
  * Test whether a block of memory is a valid user space address.
  * Returns 0 if the range is valid, nonzero otherwise.
@@ -93,7 +69,7 @@ static inline bool pagefault_disabled(void);
 #define access_ok(addr, size)					\
 ({									\
 	WARN_ON_IN_IRQ();						\
-	likely(!__range_not_ok(addr, size, user_addr_max()));		\
+	likely(!__range_not_ok(addr, size, TASK_SIZE_MAX));		\
 })
 
 extern int __get_user_1(void);

arch/x86/kernel/asm-offsets.c

@@ -37,9 +37,6 @@ static void __used common(void)
 	OFFSET(TASK_stack_canary, task_struct, stack_canary);
 #endif
 
-	BLANK();
-	OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
-
 	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
 

arch/x86/lib/getuser.S

@@ -37,10 +37,19 @@
 
 #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
 
+#ifdef CONFIG_X86_5LEVEL
+#define LOAD_TASK_SIZE_MINUS_N(n) \
+	ALTERNATIVE __stringify(mov $((1 << 47) - 4096 - (n)),%rdx), \
+		    __stringify(mov $((1 << 56) - 4096 - (n)),%rdx), X86_FEATURE_LA57
+#else
+#define LOAD_TASK_SIZE_MINUS_N(n) \
+	mov $(TASK_SIZE_MAX - (n)),%_ASM_DX
+#endif
+
 	.text
 SYM_FUNC_START(__get_user_1)
-	mov PER_CPU_VAR(current_task), %_ASM_DX
-	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
+	LOAD_TASK_SIZE_MINUS_N(0)
+	cmp %_ASM_DX,%_ASM_AX
 	jae bad_get_user
 	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
 	and %_ASM_DX, %_ASM_AX
@@ -53,15 +62,13 @@ SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
 SYM_FUNC_START(__get_user_2)
-	add $1,%_ASM_AX
-	jc bad_get_user
-	mov PER_CPU_VAR(current_task), %_ASM_DX
-	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
+	LOAD_TASK_SIZE_MINUS_N(1)
+	cmp %_ASM_DX,%_ASM_AX
 	jae bad_get_user
 	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
 	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
-2:	movzwl -1(%_ASM_AX),%edx
+2:	movzwl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
 	ret
@@ -69,15 +76,13 @@ SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
 SYM_FUNC_START(__get_user_4)
-	add $3,%_ASM_AX
-	jc bad_get_user
-	mov PER_CPU_VAR(current_task), %_ASM_DX
-	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
+	LOAD_TASK_SIZE_MINUS_N(3)
+	cmp %_ASM_DX,%_ASM_AX
 	jae bad_get_user
 	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
 	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
-3:	movl -3(%_ASM_AX),%edx
+3:	movl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
 	ret
@@ -86,29 +91,25 @@ EXPORT_SYMBOL(__get_user_4)
 
 SYM_FUNC_START(__get_user_8)
 #ifdef CONFIG_X86_64
-	add $7,%_ASM_AX
-	jc bad_get_user
-	mov PER_CPU_VAR(current_task), %_ASM_DX
-	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
+	LOAD_TASK_SIZE_MINUS_N(7)
+	cmp %_ASM_DX,%_ASM_AX
 	jae bad_get_user
 	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
 	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
-4:	movq -7(%_ASM_AX),%rdx
+4:	movq (%_ASM_AX),%rdx
 	xor %eax,%eax
 	ASM_CLAC
 	ret
 #else
-	add $7,%_ASM_AX
-	jc bad_get_user_8
-	mov PER_CPU_VAR(current_task), %_ASM_DX
-	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
+	LOAD_TASK_SIZE_MINUS_N(7)
+	cmp %_ASM_DX,%_ASM_AX
 	jae bad_get_user_8
 	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
 	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
-4:	movl -7(%_ASM_AX),%edx
-5:	movl -3(%_ASM_AX),%ecx
+4:	movl (%_ASM_AX),%edx
+5:	movl 4(%_ASM_AX),%ecx
 	xor %eax,%eax
 	ASM_CLAC
 	ret

arch/x86/lib/putuser.S

@@ -33,12 +33,19 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	mov PER_CPU_VAR(current_task), %_ASM_BX
+#ifdef CONFIG_X86_5LEVEL
+#define LOAD_TASK_SIZE_MINUS_N(n) \
+	ALTERNATIVE __stringify(mov $((1 << 47) - 4096 - (n)),%rbx), \
+		    __stringify(mov $((1 << 56) - 4096 - (n)),%rbx), X86_FEATURE_LA57
+#else
+#define LOAD_TASK_SIZE_MINUS_N(n) \
+	mov $(TASK_SIZE_MAX - (n)),%_ASM_BX
+#endif
 
 .text
 SYM_FUNC_START(__put_user_1)
-	ENTER
-	cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
+	LOAD_TASK_SIZE_MINUS_N(0)
+	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL)
 	ASM_STAC
@@ -51,9 +58,7 @@ EXPORT_SYMBOL(__put_user_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
 
 SYM_FUNC_START(__put_user_2)
-	ENTER
-	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
-	sub $1,%_ASM_BX
+	LOAD_TASK_SIZE_MINUS_N(1)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL)
@@ -67,9 +72,7 @@ EXPORT_SYMBOL(__put_user_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
 
 SYM_FUNC_START(__put_user_4)
-	ENTER
-	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
-	sub $3,%_ASM_BX
+	LOAD_TASK_SIZE_MINUS_N(3)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL)
@@ -83,9 +86,7 @@ EXPORT_SYMBOL(__put_user_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
 
 SYM_FUNC_START(__put_user_8)
-	ENTER
-	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
-	sub $7,%_ASM_BX
+	LOAD_TASK_SIZE_MINUS_N(7)
 	cmp %_ASM_BX,%_ASM_CX
 	jae .Lbad_put_user
 SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL)

arch/xtensa/Kconfig

@@ -41,6 +41,7 @@ config XTENSA
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select PERF_USE_VMALLOC
+	select SET_FS
 	select VIRT_TO_BUS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica

drivers/misc/lkdtm/bugs.c

@@ -312,16 +312,6 @@ void lkdtm_CORRUPT_LIST_DEL(void)
 		pr_err("list_del() corruption not detected!\n");
 }
 
-/* Test if unbalanced set_fs(KERNEL_DS)/set_fs(USER_DS) check exists. */
-void lkdtm_CORRUPT_USER_DS(void)
-{
-	pr_info("setting bad task size limit\n");
-	set_fs(KERNEL_DS);
-
-	/* Make sure we do not keep running with a KERNEL_DS! */
-	force_sig(SIGKILL);
-}
-
 /* Test that VMAP_STACK is actually allocating with a leading guard page */
 void lkdtm_STACK_GUARD_PAGE_LEADING(void)
 {

drivers/misc/lkdtm/core.c

@@ -112,7 +112,6 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(CORRUPT_STACK_STRONG),
 	CRASHTYPE(CORRUPT_LIST_ADD),
 	CRASHTYPE(CORRUPT_LIST_DEL),
-	CRASHTYPE(CORRUPT_USER_DS),
 	CRASHTYPE(STACK_GUARD_PAGE_LEADING),
 	CRASHTYPE(STACK_GUARD_PAGE_TRAILING),
 	CRASHTYPE(UNSET_SMEP),
@@ -172,7 +171,6 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(USERCOPY_STACK_FRAME_FROM),
 	CRASHTYPE(USERCOPY_STACK_BEYOND),
 	CRASHTYPE(USERCOPY_KERNEL),
-	CRASHTYPE(USERCOPY_KERNEL_DS),
 	CRASHTYPE(STACKLEAK_ERASING),
 	CRASHTYPE(CFI_FORWARD_PROTO),
 #ifdef CONFIG_X86_32

drivers/misc/lkdtm/lkdtm.h

@@ -27,7 +27,6 @@ void lkdtm_OVERFLOW_UNSIGNED(void);
 void lkdtm_ARRAY_BOUNDS(void);
 void lkdtm_CORRUPT_LIST_ADD(void);
 void lkdtm_CORRUPT_LIST_DEL(void);
-void lkdtm_CORRUPT_USER_DS(void);
 void lkdtm_STACK_GUARD_PAGE_LEADING(void);
 void lkdtm_STACK_GUARD_PAGE_TRAILING(void);
 void lkdtm_UNSET_SMEP(void);
@@ -96,7 +95,6 @@ void lkdtm_USERCOPY_STACK_FRAME_TO(void);
 void lkdtm_USERCOPY_STACK_FRAME_FROM(void);
 void lkdtm_USERCOPY_STACK_BEYOND(void);
 void lkdtm_USERCOPY_KERNEL(void);
-void lkdtm_USERCOPY_KERNEL_DS(void);
 
 /* lkdtm_stackleak.c */
 void lkdtm_STACKLEAK_ERASING(void);

drivers/misc/lkdtm/usercopy.c

@@ -325,21 +325,6 @@ void lkdtm_USERCOPY_KERNEL(void)
 	vm_munmap(user_addr, PAGE_SIZE);
 }
 
-void lkdtm_USERCOPY_KERNEL_DS(void)
-{
-	char __user *user_ptr =
-		(char __user *)(0xFUL << (sizeof(unsigned long) * 8 - 4));
-	mm_segment_t old_fs = get_fs();
-	char buf[10] = {0};
-
-	pr_info("attempting copy_to_user() to noncanonical address: %px\n",
-		user_ptr);
-	set_fs(KERNEL_DS);
-	if (copy_to_user(user_ptr, buf, sizeof(buf)) == 0)
-		pr_err("copy_to_user() to noncanonical address succeeded!?\n");
-	set_fs(old_fs);
-}
-
 void __init lkdtm_usercopy_init(void)
 {
 	/* Prepare cache that lacks SLAB_USERCOPY flag. */

fs/proc/inode.c

@@ -297,6 +297,21 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	return rv;
 }
 
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
 static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	typeof_member(struct proc_ops, proc_read) read;
@@ -572,9 +587,18 @@ static const struct file_operations proc_reg_file_ops = {
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= proc_reg_compat_ioctl,
-#endif
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -582,12 +606,26 @@ static const struct file_operations proc_reg_file_ops = {
 };
 
 #ifdef CONFIG_COMPAT
-static const struct file_operations proc_reg_file_ops_no_compat = {
+static const struct file_operations proc_reg_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
 	.read		= proc_reg_read,
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -619,15 +657,19 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
 	struct inode *inode = new_inode(sb);
 
-	if (inode) {
+	if (!inode) {
+		pde_put(de);
+		return NULL;
+	}
+
 	inode->i_ino = de->low_ino;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	PROC_I(inode)->pde = de;
-
 	if (is_empty_pde(de)) {
 		make_empty_dir_inode(inode);
 		return inode;
 	}
+
 	if (de->mode) {
 		inode->i_mode = de->mode;
 		inode->i_uid = de->uid;
@@ -640,10 +682,16 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
 			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-			if (!de->proc_ops->proc_compat_ioctl) {
-				inode->i_fop = &proc_reg_file_ops_no_compat;
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
 		}
 #endif
 	} else if (S_ISDIR(inode->i_mode)) {
@@ -652,9 +700,8 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 	} else if (S_ISLNK(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
 		inode->i_fop = NULL;
-		} else
+	} else {
 		BUG();
-	} else
-	       pde_put(de);
+	}
 	return inode;
 }

fs/proc/proc_sysctl.c

@@ -12,6 +12,7 @@
 #include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/uio.h>
 #include <linux/module.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/mount.h>
@@ -540,13 +541,14 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 	return err;
 }
 
-static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
-		size_t count, loff_t *ppos, int write)
+static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
+		int write)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	void *kbuf;
+	size_t count = iov_iter_count(iter);
+	char *kbuf;
 	ssize_t error;
 
 	if (IS_ERR(head))
@@ -569,32 +571,30 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 	error = -ENOMEM;
 	if (count >= KMALLOC_MAX_SIZE)
 		goto out;
-
-	if (write) {
-		kbuf = memdup_user_nul(ubuf, count);
-		if (IS_ERR(kbuf)) {
-			error = PTR_ERR(kbuf);
-			goto out;
-		}
-	} else {
-		kbuf = kzalloc(count, GFP_KERNEL);
+	kbuf = kzalloc(count + 1, GFP_KERNEL);
 	if (!kbuf)
 		goto out;
+
+	if (write) {
+		error = -EFAULT;
+		if (!copy_from_iter_full(kbuf, count, iter))
+			goto out_free_buf;
+		kbuf[count] = '\0';
 	}
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
-					   ppos);
+					   &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	/* careful: calling conventions are nasty here */
-	error = table->proc_handler(table, write, kbuf, &count, ppos);
+	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	if (!write) {
 		error = -EFAULT;
-		if (copy_to_user(ubuf, kbuf, count))
+		if (copy_to_iter(kbuf, count, iter) < count)
 			goto out_free_buf;
 	}
 
@@ -607,16 +607,14 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 	return error;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+	return proc_sys_call_handler(iocb, iter, 0);
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
+	return proc_sys_call_handler(iocb, iter, 1);
 }
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
@@ -853,8 +851,10 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
 static const struct file_operations proc_sys_file_operations = {
 	.open		= proc_sys_open,
 	.poll		= proc_sys_poll,
-	.read		= proc_sys_read,
-	.write		= proc_sys_write,
+	.read_iter	= proc_sys_read,
+	.write_iter	= proc_sys_write,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 	.llseek		= default_llseek,
 };
 

fs/read_write.c

@@ -419,27 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_warn_ratelimited(
+		"kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs = get_fs();
+	struct kvec iov = {
+		.iov_base	= buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
 		return -EINVAL;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
+	/*
+	 * Also fail if ->read_iter and ->read are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->read_iter || file->f_op->read))
+		return warn_unsupported(file, "read");
 
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	set_fs(KERNEL_DS);
-	if (file->f_op->read)
-		ret = file->f_op->read(file, (void __user *)buf, count, pos);
-	else if (file->f_op->read_iter)
-		ret = new_sync_read(file, (void __user *)buf, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = pos ? *pos : 0;
+	iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len);
+	ret = file->f_op->read_iter(&kiocb, &iter);
 	if (ret > 0) {
+		if (pos)
+			*pos = kiocb.ki_pos;
 		fsnotify_access(file);
 		add_rchar(current, ret);
 	}
@@ -510,28 +525,32 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 /* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	const char __user *p;
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct kiocb kiocb;
+	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
+	/*
+	 * Also fail if ->write_iter and ->write are both wired up as that
+	 * implies very convoluted semantics.
+	 */
+	if (unlikely(!file->f_op->write_iter || file->f_op->write))
+		return warn_unsupported(file, "write");
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	p = (__force const char __user *)buf;
-	if (count > MAX_RW_COUNT)
-		count =  MAX_RW_COUNT;
-	if (file->f_op->write)
-		ret = file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		ret = new_sync_write(file, p, count, pos);
-	else
-		ret = -EINVAL;
-	set_fs(old_fs);
+	init_sync_kiocb(&kiocb, file);
+	kiocb.ki_pos = pos ? *pos : 0;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	ret = file->f_op->write_iter(&kiocb, &iter);
 	if (ret > 0) {
+		if (pos)
+			*pos = kiocb.ki_pos;
 		fsnotify_modify(file);
 		add_wchar(current, ret);
 	}
@@ -889,7 +908,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];

fs/splice.c

@@ -341,89 +341,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -807,33 +724,6 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -855,15 +745,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	if (out->f_op->splice_write)
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
 	return out->f_op->splice_write(pipe, out, ppos, len, flags);
-	return default_file_splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -885,9 +783,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
 	return in->f_op->splice_read(in, ppos, pipe, len, flags);
-	return default_file_splice_read(in, ppos, pipe, len, flags);
 }
 
 /**

include/linux/bpf-cgroup.h

@@ -136,7 +136,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,

include/linux/fs.h

@@ -1894,8 +1894,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
-		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,

include/linux/proc_fs.h

@@ -30,6 +30,7 @@ struct proc_ops {
 	unsigned int proc_flags;
 	int	(*proc_open)(struct inode *, struct file *);
 	ssize_t	(*proc_read)(struct file *, char __user *, size_t, loff_t *);
+	ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *);
 	ssize_t	(*proc_write)(struct file *, const char __user *, size_t, loff_t *);
 	loff_t	(*proc_lseek)(struct file *, loff_t, int);
 	int	(*proc_release)(struct inode *, struct file *);

include/linux/uaccess.h

@@ -10,6 +10,7 @@
 
 #include <asm/uaccess.h>
 
+#ifdef CONFIG_SET_FS
 /*
  * Force the uaccess routines to be wired up for actual userspace access,
  * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
@@ -27,6 +28,23 @@ static inline void force_uaccess_end(mm_segment_t oldfs)
 {
 	set_fs(oldfs);
 }
+#else /* CONFIG_SET_FS */
+typedef struct {
+	/* empty dummy */
+} mm_segment_t;
+
+#define uaccess_kernel()		(false)
+#define user_addr_max()			(TASK_SIZE_MAX)
+
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	return (mm_segment_t) { };
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+}
+#endif /* CONFIG_SET_FS */
 
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())

kernel/bpf/cgroup.c

@@ -1226,7 +1226,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {

lib/test_bitmap.c

@@ -354,50 +354,37 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = {
 
 };
 
-static void __init __test_bitmap_parselist(int is_user)
+static void __init test_bitmap_parselist(void)
 {
 	int i;
 	int err;
 	ktime_t time;
 	DECLARE_BITMAP(bmap, 2048);
-	char *mode = is_user ? "_user"  : "";
 
 	for (i = 0; i < ARRAY_SIZE(parselist_tests); i++) {
 #define ptest parselist_tests[i]
 
-		if (is_user) {
-			mm_segment_t orig_fs = get_fs();
-			size_t len = strlen(ptest.in);
-
-			set_fs(KERNEL_DS);
-			time = ktime_get();
-			err = bitmap_parselist_user((__force const char __user *)ptest.in, len,
-						    bmap, ptest.nbits);
-			time = ktime_get() - time;
-			set_fs(orig_fs);
-		} else {
 		time = ktime_get();
 		err = bitmap_parselist(ptest.in, bmap, ptest.nbits);
 		time = ktime_get() - time;
-		}
 
 		if (err != ptest.errno) {
-			pr_err("parselist%s: %d: input is %s, errno is %d, expected %d\n",
-					mode, i, ptest.in, err, ptest.errno);
+			pr_err("parselist: %d: input is %s, errno is %d, expected %d\n",
+					i, ptest.in, err, ptest.errno);
 			continue;
 		}
 
 		if (!err && ptest.expected
 			 && !__bitmap_equal(bmap, ptest.expected, ptest.nbits)) {
-			pr_err("parselist%s: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
-					mode, i, ptest.in, bmap[0],
+			pr_err("parselist: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
+					i, ptest.in, bmap[0],
 					*ptest.expected);
 			continue;
 		}
 
 		if (ptest.flags & PARSE_TIME)
-			pr_err("parselist%s: %d: input is '%s' OK, Time: %llu\n",
-					mode, i, ptest.in, time);
+			pr_err("parselist: %d: input is '%s' OK, Time: %llu\n",
+					i, ptest.in, time);
 
 #undef ptest
 	}
@@ -443,75 +430,41 @@ static const struct test_bitmap_parselist parse_tests[] __initconst = {
 #undef step
 };
 
-static void __init __test_bitmap_parse(int is_user)
+static void __init test_bitmap_parse(void)
 {
 	int i;
 	int err;
 	ktime_t time;
 	DECLARE_BITMAP(bmap, 2048);
-	char *mode = is_user ? "_user"  : "";
 
 	for (i = 0; i < ARRAY_SIZE(parse_tests); i++) {
 		struct test_bitmap_parselist test = parse_tests[i];
+		size_t len = test.flags & NO_LEN ? UINT_MAX : strlen(test.in);
 
-		if (is_user) {
-			size_t len = strlen(test.in);
-			mm_segment_t orig_fs = get_fs();
-
-			set_fs(KERNEL_DS);
-			time = ktime_get();
-			err = bitmap_parse_user((__force const char __user *)test.in, len,
-						bmap, test.nbits);
-			time = ktime_get() - time;
-			set_fs(orig_fs);
-		} else {
-			size_t len = test.flags & NO_LEN ?
-				UINT_MAX : strlen(test.in);
 		time = ktime_get();
 		err = bitmap_parse(test.in, len, bmap, test.nbits);
 		time = ktime_get() - time;
-		}
 
 		if (err != test.errno) {
-			pr_err("parse%s: %d: input is %s, errno is %d, expected %d\n",
-					mode, i, test.in, err, test.errno);
+			pr_err("parse: %d: input is %s, errno is %d, expected %d\n",
+					i, test.in, err, test.errno);
 			continue;
 		}
 
 		if (!err && test.expected
 			 && !__bitmap_equal(bmap, test.expected, test.nbits)) {
-			pr_err("parse%s: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
-					mode, i, test.in, bmap[0],
+			pr_err("parse: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
+					i, test.in, bmap[0],
 					*test.expected);
 			continue;
 		}
 
 		if (test.flags & PARSE_TIME)
-			pr_err("parse%s: %d: input is '%s' OK, Time: %llu\n",
-					mode, i, test.in, time);
+			pr_err("parse: %d: input is '%s' OK, Time: %llu\n",
+					i, test.in, time);
 	}
 }
 
-static void __init test_bitmap_parselist(void)
-{
-	__test_bitmap_parselist(0);
-}
-
-static void __init test_bitmap_parselist_user(void)
-{
-	__test_bitmap_parselist(1);
-}
-
-static void __init test_bitmap_parse(void)
-{
-	__test_bitmap_parse(0);
-}
-
-static void __init test_bitmap_parse_user(void)
-{
-	__test_bitmap_parse(1);
-}
-
 #define EXP1_IN_BITS	(sizeof(exp1) * 8)
 
 static void __init test_bitmap_arr32(void)
@@ -675,9 +628,7 @@ static void __init selftest(void)
 	test_replace();
 	test_bitmap_arr32();
 	test_bitmap_parse();
-	test_bitmap_parse_user();
 	test_bitmap_parselist();
-	test_bitmap_parselist_user();
 	test_mem_optimisations();
 	test_for_each_set_clump8();
 	test_bitmap_cut();

tools/testing/selftests/lkdtm/tests.txt

@@ -9,7 +9,6 @@ EXCEPTION
 #CORRUPT_STACK_STRONG Crashes entire system on success
 CORRUPT_LIST_ADD list_add corruption
 CORRUPT_LIST_DEL list_del corruption
-CORRUPT_USER_DS Invalid address limit on user-mode return
 STACK_GUARD_PAGE_LEADING
 STACK_GUARD_PAGE_TRAILING
 UNSET_SMEP CR4 bits went missing
@@ -67,6 +66,5 @@ USERCOPY_STACK_FRAME_TO
 USERCOPY_STACK_FRAME_FROM
 USERCOPY_STACK_BEYOND
 USERCOPY_KERNEL
-USERCOPY_KERNEL_DS
 STACKLEAK_ERASING OK: the rest of the thread stack is properly erased
 CFI_FORWARD_PROTO