[PATCH 11/13] arm64: uaccess: remove set_fs()

Mark Rutland mark.rutland at arm.com
Fri Sep 25 12:07:20 EDT 2020


Now that the uaccess primitives dont take addr_limit into acccount, we
have no need to manipulate this via set_fs() and get_fs(). Remove
support for these, along with some infrastructure this renders
redundant.

We no longer need to flip UAO to access kernel memory under KERNEL_DS,
and head.S unconditionally clears UAO for all kernel configurations via
an ERET in init_kernel_el. Thus, we don't need to dynamically flip UAO,
nor do we need to context-switch it. However, we do need to clear UAO
(and set PAN) during SDEI entry.

Masking of __user pointers no longer needs to use the dynamic value of
addr_limit, and can use a constant derived from the maximum possible
userspace task size. A new TASK_SIZE_MAX constant is introduced for
this, which is also used by core code. In configurations supporting
52-bit VAs, this may include a region of unusable VA space above a
48-bit TTBR0 limit, but never includes any portion of TTBR1.

Note that TASK_SIZE_MAX is an exclusive limit, while USER_DS and
KERNEL_DS were inclusive limits, and is converted to a mask by
subtracting one.

Signed-off-by: Mark Rutland <mark.rutland at arm.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Cc: Christoph Hellwig <hch at lst.de>
Cc: James Morse <james.morse at arm.com>
Cc: Will Deacon <will at kernel.org>
---
 arch/arm64/Kconfig                   |  1 -
 arch/arm64/include/asm/exec.h        |  1 -
 arch/arm64/include/asm/processor.h   |  4 +---
 arch/arm64/include/asm/ptrace.h      |  3 +--
 arch/arm64/include/asm/thread_info.h |  4 ----
 arch/arm64/include/asm/uaccess.h     | 41 ++++++++----------------------------
 arch/arm64/kernel/asm-offsets.c      |  3 +--
 arch/arm64/kernel/cpufeature.c       |  4 ----
 arch/arm64/kernel/entry.S            | 19 +++--------------
 arch/arm64/kernel/process.c          | 12 -----------
 arch/arm64/kernel/sdei.c             | 10 ++-------
 arch/arm64/kernel/suspend.c          |  3 +--
 arch/arm64/mm/fault.c                |  5 -----
 13 files changed, 18 insertions(+), 92 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fbd9e35bef096..6d232837cbeee 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -192,7 +192,6 @@ 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/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h
index 1aae6f9962fc1..9a1c22ce664b5 100644
--- a/arch/arm64/include/asm/exec.h
+++ b/arch/arm64/include/asm/exec.h
@@ -10,6 +10,5 @@
 #include <linux/sched.h>
 
 extern unsigned long arch_align_stack(unsigned long sp);
-void uao_thread_switch(struct task_struct *next);
 
 #endif	/* __ASM_EXEC_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 240fe5e5b7209..fa91351e7f928 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -8,9 +8,6 @@
 #ifndef __ASM_PROCESSOR_H
 #define __ASM_PROCESSOR_H
 
-#define KERNEL_DS		UL(-1)
-#define USER_DS			((UL(1) << VA_BITS) - 1)
-
 /*
  * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is
  * no point in shifting all network buffers by 2 bytes just to make some IP
@@ -47,6 +44,7 @@
 
 #define DEFAULT_MAP_WINDOW_64	(UL(1) << VA_BITS_MIN)
 #define TASK_SIZE_64		(UL(1) << vabits_actual)
+#define TASK_SIZE_MAX		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT
 #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 366075f228eb3..ab99512c257a8 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -181,8 +181,7 @@ struct pt_regs {
 	s32 syscallno;
 	u32 unused2;
 #endif
-
-	u64 orig_addr_limit;
+	u64 sdei_ttbr1;
 	/* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
 	u64 pmr_save;
 	u64 stackframe[2];
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 5e784e16ee895..f02181ec7028c 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -18,14 +18,11 @@ struct task_struct;
 #include <asm/stack_pointer.h>
 #include <asm/types.h>
 
-typedef unsigned long mm_segment_t;
-
 /*
  * low level task data that entry.S needs immediate access to.
  */
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
-	mm_segment_t		addr_limit;	/* address limit */
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	u64			ttbr0;		/* saved TTBR0_EL1 */
 #endif
@@ -117,7 +114,6 @@ void arch_release_task_struct(struct task_struct *tsk);
 {									\
 	.flags		= _TIF_FOREIGN_FPSTATE,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.addr_limit	= KERNEL_DS,					\
 	INIT_SCS							\
 }
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index bc7f3ff24ccd5..6d3ac598777bc 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -26,44 +26,22 @@
 
 #define HAVE_GET_KERNEL_NOFAULT
 
-#define get_fs()	(current_thread_info()->addr_limit)
-
-static inline void set_fs(mm_segment_t fs)
+static inline void init_hw_uaccess_state(void)
 {
-	current_thread_info()->addr_limit = fs;
-
-	/*
-	 * Prevent a mispredicted conditional call to set_fs from forwarding
-	 * the wrong address limit to access_ok under speculation.
-	 */
-	spec_bar();
-
-	/* On user-mode return, check fs is correct */
-	set_thread_flag(TIF_FSCHECK);
-
-	/*
-	 * Enable/disable UAO so that copy_to_user() etc can access
-	 * kernel memory with the unprivileged instructions.
-	 */
-	if (IS_ENABLED(CONFIG_ARM64_UAO) && fs == KERNEL_DS)
-		asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO));
-	else
-		asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO,
-				CONFIG_ARM64_UAO));
+	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN));
+	asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO));
 }
 
-#define uaccess_kernel()	(get_fs() == KERNEL_DS)
-
 /*
  * Test whether a block of memory is a valid user space address.
  * Returns 1 if the range is valid, 0 otherwise.
  *
  * This is equivalent to the following test:
- * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
+ * (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX
  */
 static inline unsigned long __range_ok(const void __user *addr, unsigned long size)
 {
-	unsigned long ret, limit = current_thread_info()->addr_limit;
+	unsigned long ret, limit = TASK_SIZE_MAX - 1;
 
 	/*
 	 * Asynchronous I/O running in a kernel thread does not have the
@@ -96,7 +74,6 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 }
 
 #define access_ok(addr, size)	__range_ok(addr, size)
-#define user_addr_max			get_fs
 
 #define _ASM_EXTABLE(from, to)						\
 	"	.pushsection	__ex_table, \"a\"\n"			\
@@ -226,9 +203,9 @@ static inline void uaccess_enable_not_uao(void)
 }
 
 /*
- * Sanitise a uaccess pointer such that it becomes NULL if above the
- * current addr_limit. In case the pointer is tagged (has the top byte set),
- * untag the pointer before checking.
+ * Sanitise a uaccess pointer such that it becomes NULL if above the maximum
+ * user address. In case the pointer is tagged (has the top byte set), untag
+ * the pointer before checking.
  */
 #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
 static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
@@ -239,7 +216,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
 	"	bics	xzr, %3, %2\n"
 	"	csel	%0, %1, xzr, eq\n"
 	: "=&r" (safe_ptr)
-	: "r" (ptr), "r" (current_thread_info()->addr_limit),
+	: "r" (ptr), "r" (TASK_SIZE_MAX - 1),
 	  "r" (untagged_addr(ptr))
 	: "cc");
 
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7d32fc959b1a0..679b19b8a7ff2 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -30,7 +30,6 @@ int main(void)
   BLANK();
   DEFINE(TSK_TI_FLAGS,		offsetof(struct task_struct, thread_info.flags));
   DEFINE(TSK_TI_PREEMPT,	offsetof(struct task_struct, thread_info.preempt_count));
-  DEFINE(TSK_TI_ADDR_LIMIT,	offsetof(struct task_struct, thread_info.addr_limit));
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
   DEFINE(TSK_TI_TTBR0,		offsetof(struct task_struct, thread_info.ttbr0));
 #endif
@@ -70,7 +69,7 @@ int main(void)
   DEFINE(S_PSTATE,		offsetof(struct pt_regs, pstate));
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
-  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
+  DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6424584be01e6..3ac79d0935778 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1772,10 +1772,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.field_pos = ID_AA64MMFR2_UAO_SHIFT,
 		.min_field_value = 1,
-		/*
-		 * We rely on stop_machine() calling uao_thread_switch() to set
-		 * UAO immediately after patching.
-		 */
 	},
 #endif /* CONFIG_ARM64_UAO */
 #ifdef CONFIG_ARM64_PAN
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 55af8b504b65a..5d6033c606961 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -190,12 +190,6 @@ alternative_cb_end
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_current_task tsk
-	/* Save the task's original addr_limit and set USER_DS */
-	ldr	x20, [tsk, #TSK_TI_ADDR_LIMIT]
-	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
-	mov	x20, #USER_DS
-	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
-	/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
@@ -246,12 +240,6 @@ alternative_else_nop_endif
 	.macro	kernel_exit, el
 	.if	\el != 0
 	disable_daif
-
-	/* Restore the task's original addr_limit. */
-	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
-	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
-
-	/* No need to restore UAO, it will be restored from SPSR_EL1 */
 	.endif
 
 	/* Restore pmr */
@@ -963,10 +951,9 @@ SYM_CODE_START(__sdei_asm_entry_trampoline)
 	mov	x4, xzr
 
 	/*
-	 * Use reg->interrupted_regs.addr_limit to remember whether to unmap
-	 * the kernel on exit.
+	 * Remember whether to unmap the kernel on exit.
 	 */
-1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)]
 
 #ifdef CONFIG_RANDOMIZE_BASE
 	adr	x4, tramp_vectors + PAGE_SIZE
@@ -987,7 +974,7 @@ NOKPROBE(__sdei_asm_entry_trampoline)
  * x4: struct sdei_registered_event argument from registration time.
  */
 SYM_CODE_START(__sdei_asm_exit_trampoline)
-	ldr	x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
+	ldr	x4, [x4, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)]
 	cbnz	x4, 1f
 
 	tramp_unmap_kernel	tmp=x4
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f1804496b9350..6ec12f4cb546f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -455,17 +455,6 @@ static void tls_thread_switch(struct task_struct *next)
 	write_sysreg(*task_user_tls(next), tpidr_el0);
 }
 
-/* Restore the UAO state depending on next's addr_limit */
-void uao_thread_switch(struct task_struct *next)
-{
-	if (IS_ENABLED(CONFIG_ARM64_UAO)) {
-		if (task_thread_info(next)->addr_limit == KERNEL_DS)
-			asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO));
-		else
-			asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO));
-	}
-}
-
 /*
  * Force SSBS state on context-switch, since it may be lost after migrating
  * from a CPU which treats the bit as RES0 in a heterogeneous system.
@@ -559,7 +548,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	hw_breakpoint_thread_switch(next);
 	contextidr_thread_switch(next);
 	entry_task_switch(next);
-	uao_thread_switch(next);
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(prev, next);
 
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 4a5f24602aa0c..f5e8797ac3b9b 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -221,16 +221,12 @@ asmlinkage __kprobes notrace unsigned long
 __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
 {
 	unsigned long ret;
-	mm_segment_t orig_addr_limit;
 
 	/*
 	 * We didn't take an exception to get here, so the HW hasn't set PAN or
-	 * cleared UAO, and the exception entry code hasn't reset addr_limit.
-	 * Set PAN, then use force_uaccess_begin() to clear UAO and reset
-	 * addr_limit.
+	 * cleared UAO. Reset these to their expected state.
 	 */
-	__uaccess_enable_hw_pan();
-	orig_addr_limit = force_uaccess_begin();
+	init_hw_uaccess_state();
 
 	nmi_enter();
 
@@ -238,7 +234,5 @@ __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
 
 	nmi_exit();
 
-	force_uaccess_end(orig_addr_limit);
-
 	return ret;
 }
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index c1dee9066ff97..8f0cd958b1411 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -56,8 +56,7 @@ void notrace __cpu_suspend_exit(void)
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.
 	 */
-	__uaccess_enable_hw_pan();
-	uao_thread_switch(current);
+	init_hw_uaccess_state();
 
 	/*
 	 * Restore HW breakpoint registers to sane values
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f07333e86c2ff..bf984b8323888 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -477,11 +477,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) {
-		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
-		if (regs->orig_addr_limit == KERNEL_DS)
-			die_kernel_fault("access to user memory with fs=KERNEL_DS",
-					 addr, esr, regs);
-
 		if (is_el1_instruction_abort(esr))
 			die_kernel_fault("execution of user memory",
 					 addr, esr, regs);
-- 
2.11.0




More information about the linux-arm-kernel mailing list