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

9 files changed, 88 insertions, 125 deletions

diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index ca8a657edf59..a09fc37ead9d 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -239,7 +239,6 @@ beyond_if:
 	(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;
 }
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 565ad755c785..f462895a33e4 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -42,6 +42,17 @@
 #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)
  */
 #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index d0c6c10c18a0..3f49dac03617 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -60,6 +60,44 @@
 #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).
  *
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5ac507586769..82a08b585818 100644
--- a/arch/x86/include/asm/processor.h
+++ b/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);
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 267701ae3d86..44733a4bfc42 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/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					\
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 477c503f2753..f13659523108 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -13,30 +13,6 @@
 #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);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 3ca07ad552ae..70b7154f4bdd 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -38,9 +38,6 @@ static void __used common(void)
 #endif
 
 	BLANK();
-	OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
-
-	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
 
 	BLANK();
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 2cd902e06062..fa1bc2104b32 100644
--- a/arch/x86/lib/getuser.S
+++ b/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
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index b34a17763f28..0ea344c5ea43 100644
--- a/arch/x86/lib/putuser.S
+++ b/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)