arm64: uaccess: remove set_fs()

Now that the uaccess primitives dont take addr_limit into account, 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 still need to adjust
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.

As the SDEI entry code repurposes the otherwise unnecessary
pt_regs::orig_addr_limit field to store the TTBR1 of the interrupted
context, for now we rename that to pt_regs::sdei_ttbr1. In future we can
consider factoring that out.

Signed-off-by: Mark Rutland <[e-mail]>
Acked-by: James Morse <[e-mail]>
Cc: Christoph Hellwig <[e-mail]>
Cc: Will Deacon <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Catalin Marinas <[e-mail]>

arch/arm64/Kconfig

···
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
-	select SET_FS
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE

arch/arm64/include/asm/exec.h

···
 #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 */

arch/arm64/include/asm/processor.h

···
 #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
···
 
 #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)

arch/arm64/include/asm/ptrace.h

···
 	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];

arch/arm64/include/asm/thread_info.h

···
 #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
···
 {									\
 	.flags		= _TIF_FOREIGN_FPSTATE,				\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.addr_limit	= KERNEL_DS,					\
 	INIT_SCS							\
 }
 

arch/arm64/include/asm/uaccess.h

···
 
 #define HAVE_GET_KERNEL_NOFAULT
 
-#define get_fs()	(current_thread_info()->addr_limit)
-
-static inline void set_fs(mm_segment_t fs)
-{
-	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));
-}
-
-#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
···
 }
 
 #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"			\
···
 }
 
 /*
- * 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)
···
 	"	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");
 

arch/arm64/kernel/asm-offsets.c

···
   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
···
   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));

arch/arm64/kernel/cpufeature.c

···
 		.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

arch/arm64/kernel/entry.S

···
 	.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
···
 	.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 */
···
 	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
···
  * 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

arch/arm64/kernel/process.c

···
 	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.
···
 	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);
 

arch/arm64/kernel/sdei.c

···
 __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/cleared bits in PSTATE that we may rely on. Initialize PAN, then
-	 * use force_uaccess_begin() to reset addr_limit.
+	 * set/cleared bits in PSTATE that we may rely on. Initialize PAN.
 	 */
 	__sdei_pstate_entry();
-	orig_addr_limit = force_uaccess_begin();
 
 	nmi_enter();
 
 	ret = _sdei_handler(regs, arg);
 
 	nmi_exit();
-
-	force_uaccess_end(orig_addr_limit);
 
 	return ret;
 }

arch/arm64/kernel/suspend.c

···
 	 * features that might not have been set correctly.
 	 */
 	__uaccess_enable_hw_pan();
-	uao_thread_switch(current);
 
 	/*
 	 * Restore HW breakpoint registers to sane values

arch/arm64/mm/fault.c

···
 	}
 
 	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);