powerpc: fix KUAP warning in VMX usercopy path

On powerpc with PREEMPT_FULL or PREEMPT_LAZY and function tracing enabled,
KUAP warnings can be triggered from the VMX usercopy path under memory
stress workloads.

KUAP requires that no subfunctions are called once userspace access has
been enabled. The existing VMX copy implementation violates this
requirement by invoking enter_vmx_usercopy() from the assembly path after
userspace access has already been enabled. If preemption occurs
in this window, the AMR state may not be preserved correctly,
leading to unexpected userspace access state and resulting in
KUAP warnings.

Fix this by restructuring the VMX usercopy flow so that VMX selection
and VMX state management are centralized in raw_copy_tofrom_user(),
which is invoked by the raw_copy_{to,from,in}_user() wrappers.

The new flow is:

  - raw_copy_{to,from,in}_user() calls raw_copy_tofrom_user()
  - raw_copy_tofrom_user() decides whether to use the VMX path
    based on size and CPU capability
  - Call enter_vmx_usercopy() before enabling userspace access
  - Enable userspace access as per the copy direction
    and perform the VMX copy
  - Disable userspace access as per the copy direction
  - Call exit_vmx_usercopy()
  - Fall back to the base copy routine if the VMX copy faults

With this change, the VMX assembly routines no longer perform VMX state
management or call helper functions; they only implement the
copy operations.
The previous feature-section based VMX selection inside
__copy_tofrom_user_power7() is removed, and a dedicated
__copy_tofrom_user_power7_vmx() entry point is introduced.

This ensures correct KUAP ordering, avoids subfunction calls
while KUAP is unlocked, and eliminates the warnings while preserving
the VMX fast path.

Fixes: de78a9c ("powerpc: Add a framework for Kernel Userspace Access Protection")
Reported-by: Shrikanth Hegde <[email protected]>
Closes: https://lore.kernel.org/all/[email protected]/
Suggested-by: Christophe Leroy (CS GROUP) <[email protected]>
Reviewed-by: Christophe Leroy (CS GROUP) <[email protected]>
Co-developed-by: Aboorva Devarajan <[email protected]>
Signed-off-by: Aboorva Devarajan <[email protected]>
Signed-off-by: Sayali Patil <[email protected]>
Tested-by: Shrikanth Hegde <[email protected]>
Tested-by: Venkat Rao Bagalkote <[email protected]>
Signed-off-by: Madhavan Srinivasan <[email protected]>
Link: https://patch.msgid.link/[email protected]

Author: Sayali Patil

arch/powerpc/include/asm/uaccess.h

@@ -15,6 +15,9 @@
 #define TASK_SIZE_MAX		TASK_SIZE_USER64
 #endif
 
+/* Threshold above which VMX copy path is used */
+#define VMX_COPY_THRESHOLD 3328
+
 #include <asm-generic/access_ok.h>
 
 /*
@@ -326,40 +329,62 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
-#ifdef __powerpc64__
-static inline unsigned long
-raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+unsigned long __copy_tofrom_user_base(void __user *to,
+				      const void __user *from, unsigned long size);
+
+unsigned long __copy_tofrom_user_power7_vmx(void __user *to,
+					    const void __user *from, unsigned long size);
+
+static __always_inline bool will_use_vmx(unsigned long n)
+{
+	return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) &&
+	       n > VMX_COPY_THRESHOLD;
+}
+
+static __always_inline unsigned long
+raw_copy_tofrom_user(void __user *to, const void __user *from,
+		     unsigned long n, unsigned long dir)
 {
 	unsigned long ret;
 
-	barrier_nospec();
-	allow_user_access(to, KUAP_READ_WRITE);
+	if (will_use_vmx(n) && enter_vmx_usercopy()) {
+		allow_user_access(to, dir);
+		ret = __copy_tofrom_user_power7_vmx(to, from, n);
+		prevent_user_access(dir);
+		exit_vmx_usercopy();
+
+		if (unlikely(ret)) {
+			allow_user_access(to, dir);
+			ret = __copy_tofrom_user_base(to, from, n);
+			prevent_user_access(dir);
+		}
+		return ret;
+	}
+
+	allow_user_access(to, dir);
 	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(KUAP_READ_WRITE);
+	prevent_user_access(dir);
 	return ret;
 }
-#endif /* __powerpc64__ */
 
-static inline unsigned long raw_copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+#ifdef CONFIG_PPC64
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
+	barrier_nospec();
+	return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE);
+}
+#endif /* CONFIG_PPC64 */
 
-	allow_user_access(NULL, KUAP_READ);
-	ret = __copy_tofrom_user((__force void __user *)to, from, n);
-	prevent_user_access(KUAP_READ);
-	return ret;
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(to, KUAP_WRITE);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
-	prevent_user_access(KUAP_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE);
 }
 
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);

arch/powerpc/lib/copyuser_64.S

@@ -562,3 +562,4 @@ exc;	std	r10,32(3)
 	li	r5,4096
 	b	.Ldst_aligned
 EXPORT_SYMBOL(__copy_tofrom_user)
+EXPORT_SYMBOL(__copy_tofrom_user_base)

arch/powerpc/lib/copyuser_power7.S

@@ -5,13 +5,9 @@
  *
  * Author: Anton Blanchard <[email protected]>
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 
-#ifndef SELFTEST_CASE
-/* 0 == don't use VMX, 1 == use VMX */
-#define SELFTEST_CASE	0
-#endif
-
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
@@ -47,10 +43,14 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	CFUNC(exit_vmx_usercopy)
+	ld      r6,STK_REG(R31)(r1)	/* original destination pointer */
+	ld      r5,STK_REG(R29)(r1)	/* original number of bytes */
+	subf    r7,r6,r3		/* #bytes copied */
+	subf    r3,r7,r5		/* #bytes not copied in r3 */
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
-	b	.Lexit
+	addi    r1,r1,STACKFRAMESIZE
+	blr
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
@@ -74,20 +74,13 @@
 
 _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
-	cmpldi	cr1,r5,3328
 
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
 	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
 
-#ifdef CONFIG_ALTIVEC
-test_feature = SELFTEST_CASE
-BEGIN_FTR_SECTION
-	bgt	cr1,.Lvmx_copy
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif
 
 .Lnonvmx_copy:
 	/* Get the source 8B aligned */
@@ -263,23 +256,14 @@ err1;	stb	r0,0(r3)
 15:	li	r3,0
 	blr
 
-.Lunwind_stack_nonvmx_copy:
-	addi	r1,r1,STACKFRAMESIZE
-	b	.Lnonvmx_copy
-
-.Lvmx_copy:
 #ifdef CONFIG_ALTIVEC
+_GLOBAL(__copy_tofrom_user_power7_vmx)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	CFUNC(enter_vmx_usercopy)
-	cmpwi	cr1,r3,0
-	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STK_REG(R31)(r1)
-	ld	r4,STK_REG(R30)(r1)
-	ld	r5,STK_REG(R29)(r1)
-	mtlr	r0
 
+	std     r3,STK_REG(R31)(r1)
+	std     r5,STK_REG(R29)(r1)
 	/*
 	 * We prefetch both the source and destination using enhanced touch
 	 * instructions. We use a stream ID of 0 for the load side and
@@ -300,8 +284,6 @@ err1;	stb	r0,0(r3)
 
 	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
-	beq	cr1,.Lunwind_stack_nonvmx_copy
-
 	/*
 	 * If source and destination are not relatively aligned we use a
 	 * slower permute loop.
@@ -478,7 +460,8 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -681,5 +664,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
+EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx)
 #endif /* CONFIG_ALTIVEC */

arch/powerpc/lib/vmx-helper.c

@@ -27,6 +27,7 @@ int enter_vmx_usercopy(void)
 
 	return 1;
 }
+EXPORT_SYMBOL(enter_vmx_usercopy);
 
 /*
  * This function must return 0 because we tail call optimise when calling
@@ -49,6 +50,7 @@ int exit_vmx_usercopy(void)
 		set_dec(1);
 	return 0;
 }
+EXPORT_SYMBOL(exit_vmx_usercopy);
 
 int enter_vmx_ops(void)
 {