Merge branch 'work.set_fs' of git://git.kernel.org/pub/scm/linux/kern…

…el/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
josf · Oct 22, 2020 · f56e65d · f56e65d
2 parents 24717cf + 7b84b66
commit f56e65d
Show file tree

Hide file tree

Showing 52 changed files with 346 additions and 495 deletions.
diff --git a/arch/Kconfig b/arch/Kconfig
@@ -24,6 +24,9 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config SET_FS
+	bool
+
 config HOTPLUG_SMT
 	bool
 

diff --git a/arch/alpha/Kconfig b/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,

diff --git a/arch/arc/Kconfig b/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

diff --git a/arch/arm/Kconfig b/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.

diff --git a/arch/arm64/Kconfig b/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

diff --git a/arch/c6x/Kconfig b/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

diff --git a/arch/csky/Kconfig b/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

diff --git a/arch/h8300/Kconfig b/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

diff --git a/arch/hexagon/Kconfig b/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.

diff --git a/arch/ia64/Kconfig b/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

diff --git a/arch/m68k/Kconfig b/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
 

diff --git a/arch/microblaze/Kconfig b/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

diff --git a/arch/mips/Kconfig b/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
 

diff --git a/arch/nds32/Kconfig b/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.
 

diff --git a/arch/nios2/Kconfig b/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

diff --git a/arch/openrisc/Kconfig b/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

diff --git a/arch/parisc/Kconfig b/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

diff --git a/arch/powerpc/include/asm/processor.h b/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;
@@ -296,15 +291,13 @@ 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 \
 }
 #else
 #define INIT_THREAD  { \
 	.ksp = INIT_SP, \
-	.addr_limit = KERNEL_DS, \
 	.fpexc_mode = 0, \
 }
 #endif

diff --git a/arch/powerpc/include/asm/thread_info.h b/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 */
@@ -130,16 +129,14 @@ 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 | \
 				 _TIF_NOHZ | _TIF_SYSCALL_EMU)
 
 #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 */

diff --git a/arch/powerpc/include/asm/uaccess.h b/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)
+static inline bool __access_ok(unsigned long addr, unsigned long size)
 {
-	current->thread.addr_limit = fs;
-	/* On user-mode return check addr_limit (fs) is correct */
-	set_thread_flag(TIF_FSCHECK);
+	return addr < TASK_SIZE_MAX && size <= TASK_SIZE_MAX - addr;
 }
 
-#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)
-{
-	if (addr > seg.seg)
-		return 0;
-	return (size == 0 || size - 1 <= seg.seg - 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 */
diff --git a/arch/powerpc/kernel/signal.c b/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);
 

diff --git a/arch/powerpc/lib/sstep.c b/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;

diff --git a/arch/riscv/Kconfig b/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

diff --git a/arch/s390/Kconfig b/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

diff --git a/arch/sh/Kconfig b/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

diff --git a/arch/sparc/Kconfig b/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

diff --git a/arch/um/Kconfig b/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

diff --git a/arch/x86/ia32/ia32_aout.c b/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;
 }
 

diff --git a/arch/x86/include/asm/page_32_types.h b/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)
  */
-Original file line number
+Diff line change
@@ Expand Up / @@ -24,6 +24,9 @@ config KEXEC_ELF @@
     config HAVE_IMA_KEXEC
     	bool
+    config SET_FS
+    	bool
     config HOTPLUG_SMT
     	bool
@@ Expand Down @@