[PATCH 6.19 200/220] x86-64: rename misleadingly named __copy_user_nocache() function

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

6.19-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Linus Torvalds <torvalds@linux-foundation.org>

commit d187a86de793f84766ea40b9ade7ac60aabbb4fe upstream.

This function was a masterclass in bad naming, for various historical
reasons.

It claimed to be a non-cached user copy.  It is literally _neither_ of
those things.  It's a specialty memory copy routine that uses
non-temporal stores for the destination (but not the source), and that
does exception handling for both source and destination accesses.

Also note that while it works for unaligned targets, any unaligned parts
(whether at beginning or end) will not use non-temporal stores, since
only words and quadwords can be non-temporal on x86.

The exception handling means that it _can_ be used for user space
accesses, but not on its own - it needs all the normal "start user space
access" logic around it.

But typically the user space access would be the source, not the
non-temporal destination.  That was the original intention of this,
where the destination was some fragile persistent memory target that
needed non-temporal stores in order to catch machine check exceptions
synchronously and deal with them gracefully.

Thus that non-descriptive name: one use case was to copy from user space
into a non-cached kernel buffer.  However, the existing users are a mix
of that intended use-case, and a couple of random drivers that just did
this as a performance tweak.

Some of those random drivers then actively misused the user copying
version (with STAC/CLAC and all) to do kernel copies without ever even
caring about the exception handling, _just_ for the non-temporal
destination.

Rename it as a first small step to actually make it halfway sane, and
change the prototype to be more normal: it doesn't take a user pointer
unless the caller has done the proper conversion, and the argument size
is the full size_t (it still won't actually copy more than 4GB in one
go, but there's also no reason to silently truncate the size argument in
the caller).

Finally, use this now sanely named function in the NTB code, which
mis-used a user copy version (with STAC/CLAC and all) of this interface
despite it not actually being a user copy at all.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/include/asm/uaccess_64.h    |    5 +++--
 arch/x86/lib/copy_user_uncached_64.S |    6 +++---
 arch/x86/lib/usercopy_64.c           |    4 ++--
 drivers/infiniband/sw/rdmavt/qp.c    |    8 +++-----
 drivers/ntb/ntb_transport.c          |    7 ++++---
 tools/objtool/check.c                |    2 +-
 6 files changed, 16 insertions(+), 16 deletions(-)

--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -147,7 +147,8 @@ raw_copy_to_user(void __user *dst, const
 	return copy_user_generic((__force void *)dst, src, size);
 }
 
-extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size);
+#define copy_to_nontemporal copy_to_nontemporal
+extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size);
 extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
 
 static inline int
@@ -157,7 +158,7 @@ __copy_from_user_inatomic_nocache(void *
 	long ret;
 	kasan_check_write(dst, size);
 	stac();
-	ret = __copy_user_nocache(dst, src, size);
+	ret = copy_to_nontemporal(dst, (__force const void *)src, size);
 	clac();
 	return ret;
 }
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -27,7 +27,7 @@
  * Output:
  * rax uncopied bytes or 0 if successful.
  */
-SYM_FUNC_START(__copy_user_nocache)
+SYM_FUNC_START(copy_to_nontemporal)
 	ANNOTATE_NOENDBR
 	/* If destination is not 7-byte aligned, we'll have to align it */
 	testb $7,%dil
@@ -240,5 +240,5 @@ _ASM_EXTABLE_UA(95b, .Ldone)
 _ASM_EXTABLE_UA(52b, .Ldone0)
 _ASM_EXTABLE_UA(53b, .Ldone0)
 
-SYM_FUNC_END(__copy_user_nocache)
-EXPORT_SYMBOL(__copy_user_nocache)
+SYM_FUNC_END(copy_to_nontemporal)
+EXPORT_SYMBOL(copy_to_nontemporal)
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -49,11 +49,11 @@ long __copy_user_flushcache(void *dst, c
 	long rc;
 
 	stac();
-	rc = __copy_user_nocache(dst, src, size);
+	rc = copy_to_nontemporal(dst, (__force const void *)src, size);
 	clac();
 
 	/*
-	 * __copy_user_nocache() uses non-temporal stores for the bulk
+	 * copy_to_nontemporal() uses non-temporal stores for the bulk
 	 * of the transfer, but we need to manually flush if the
 	 * transfer is unaligned. A cached memory copy is used when
 	 * destination or size is not naturally aligned. That is:
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -92,12 +92,10 @@ static int rvt_wss_llc_size(void)
 static void cacheless_memcpy(void *dst, void *src, size_t n)
 {
 	/*
-	 * Use the only available X64 cacheless copy.  Add a __user cast
-	 * to quiet sparse.  The src agument is already in the kernel so
-	 * there are no security issues.  The extra fault recovery machinery
-	 * is not invoked.
+	 * Use the only available X64 cacheless copy.
+	 * The extra fault recovery machinery is not invoked.
 	 */
-	__copy_user_nocache(dst, (void __user *)src, n);
+	copy_to_nontemporal(dst, src, n);
 }
 
 void rvt_wss_exit(struct rvt_dev_info *rdi)
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1810,12 +1810,13 @@ static void ntb_tx_copy_callback(void *d
 
 static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset)
 {
-#ifdef ARCH_HAS_NOCACHE_UACCESS
+#ifdef copy_to_nontemporal
 	/*
 	 * Using non-temporal mov to improve performance on non-cached
-	 * writes, even though we aren't actually copying from user space.
+	 * writes. This only works if __iomem is strictly memory-like,
+	 * but that is the case on x86-64
 	 */
-	__copy_from_user_inatomic_nocache(offset, entry->buf, entry->len);
+	copy_to_nontemporal(offset, entry->buf, entry->len);
 #else
 	memcpy_toio(offset, entry->buf, entry->len);
 #endif
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1261,7 +1261,7 @@ static const char *uaccess_safe_builtin[
 	"copy_mc_enhanced_fast_string",
 	"rep_stos_alternative",
 	"rep_movs_alternative",
-	"__copy_user_nocache",
+	"copy_to_nontemporal",
 	NULL
 };