Merge tag 'mm-nonmm-stable-2024-05-22-17-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more non-mm updates from Andrew Morton:

 - A series ("kbuild: enable more warnings by default") from Arnd
   Bergmann which enables a number of additional build-time warnings. We
   fixed all the fallout which we could find, there may still be a few
   stragglers.

 - Samuel Holland has developed the series "Unified cross-architecture
   kernel-mode FPU API". This does a lot of consolidation of
   per-architecture kernel-mode FPU usage and enables the use of newer
   AMD GPUs on RISC-V.

 - Tao Su has fixed some selftests build warnings in the series
   "Selftests: Fix compilation warnings due to missing _GNU_SOURCE
   definition".

 - This pull also includes a nilfs2 fixup from Ryusuke Konishi.

* tag 'mm-nonmm-stable-2024-05-22-17-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (23 commits)
  nilfs2: make block erasure safe in nilfs_finish_roll_forward()
  selftests/harness: use 1024 in place of LINE_MAX
  Revert "selftests/harness: remove use of LINE_MAX"
  selftests/fpu: allow building on other architectures
  selftests/fpu: move FP code to a separate translation unit
  drm/amd/display: use ARCH_HAS_KERNEL_FPU_SUPPORT
  drm/amd/display: only use hard-float, not altivec on powerpc
  riscv: add support for kernel-mode FPU
  x86: implement ARCH_HAS_KERNEL_FPU_SUPPORT
  powerpc: implement ARCH_HAS_KERNEL_FPU_SUPPORT
  LoongArch: implement ARCH_HAS_KERNEL_FPU_SUPPORT
  lib/raid6: use CC_FLAGS_FPU for NEON CFLAGS
  arm64: crypto: use CC_FLAGS_FPU for NEON CFLAGS
  arm64: implement ARCH_HAS_KERNEL_FPU_SUPPORT
  ARM: crypto: use CC_FLAGS_FPU for NEON CFLAGS
  ARM: implement ARCH_HAS_KERNEL_FPU_SUPPORT
  arch: add ARCH_HAS_KERNEL_FPU_SUPPORT
  x86/fpu: fix asm/fpu/types.h include guard
  kbuild: enable -Wcast-function-type-strict unconditionally
  kbuild: enable -Wformat-truncation on clang
  ...

6 files changed, 64 insertions, 79 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4bcdb2fd17d8..59b6765d86b8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2925,7 +2925,7 @@ config TEST_FREE_PAGES
 
 config TEST_FPU
 	tristate "Test floating point operations in kernel space"
-	depends on X86 && !KCOV_INSTRUMENT_ALL
+	depends on ARCH_HAS_KERNEL_FPU_SUPPORT && !KCOV_INSTRUMENT_ALL
 	help
 	  Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu
 	  which will trigger a sequence of floating point operations. This is used
diff --git a/lib/Makefile b/lib/Makefile
index 7a1fdd1cce7a..3b1769045651 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -110,30 +110,10 @@ CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o
 obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o
 
-#
-# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns
-# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS
-# get appended last to CFLAGS and thus override those previous compiler options.
-#
-FPU_CFLAGS := -msse -msse2
-ifdef CONFIG_CC_IS_GCC
-# Stack alignment mismatch, proceed with caution.
-# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
-# (8B stack alignment).
-# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
-#
-# The "-msse" in the first argument is there so that the
-# -mpreferred-stack-boundary=3 build error:
-#
-#  -mpreferred-stack-boundary=3 is not between 4 and 12
-#
-# can be triggered. Otherwise gcc doesn't complain.
-FPU_CFLAGS += -mhard-float
-FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4)
-endif
-
 obj-$(CONFIG_TEST_FPU) += test_fpu.o
-CFLAGS_test_fpu.o += $(FPU_CFLAGS)
+test_fpu-y := test_fpu_glue.o test_fpu_impl.o
+CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU)
 
 # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module,
 # so we can't just use obj-$(CONFIG_KUNIT).
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 8785353c6140..29127dd05d63 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -33,25 +33,6 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float
 endif
 endif
 
-# The GCC option -ffreestanding is required in order to compile code containing
-# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
-ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-NEON_FLAGS := -ffreestanding
-# Enable <arm_neon.h>
-NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include)
-ifeq ($(ARCH),arm)
-NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon
-endif
-CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
-ifeq ($(ARCH),arm64)
-CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only
-endif
-endif
-
 quiet_cmd_unroll = UNROLL  $@
       cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@
 
@@ -75,10 +56,16 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c
 $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
-CFLAGS_neon1.o += $(NEON_FLAGS)
-CFLAGS_neon2.o += $(NEON_FLAGS)
-CFLAGS_neon4.o += $(NEON_FLAGS)
-CFLAGS_neon8.o += $(NEON_FLAGS)
+CFLAGS_neon1.o += $(CC_FLAGS_FPU)
+CFLAGS_neon2.o += $(CC_FLAGS_FPU)
+CFLAGS_neon4.o += $(CC_FLAGS_FPU)
+CFLAGS_neon8.o += $(CC_FLAGS_FPU)
+CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU)
 targets += neon1.c neon2.c neon4.c neon8.c
 $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
diff --git a/lib/test_fpu.h b/lib/test_fpu.h
new file mode 100644
index 000000000000..4459807084bc
--- /dev/null
+++ b/lib/test_fpu.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _LIB_TEST_FPU_H
+#define _LIB_TEST_FPU_H
+
+int test_fpu(void);
+
+#endif
diff --git a/lib/test_fpu.c b/lib/test_fpu_glue.c
index e82db19fed84..eef282a2715f 100644
--- a/lib/test_fpu.c
+++ b/lib/test_fpu_glue.c
@@ -17,39 +17,9 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
-#include <asm/fpu/api.h>
+#include <linux/fpu.h>
 
-static int test_fpu(void)
-{
-	/*
-	 * This sequence of operations tests that rounding mode is
-	 * to nearest and that denormal numbers are supported.
-	 * Volatile variables are used to avoid compiler optimizing
-	 * the calculations away.
-	 */
-	volatile double a, b, c, d, e, f, g;
-
-	a = 4.0;
-	b = 1e-15;
-	c = 1e-310;
-
-	/* Sets precision flag */
-	d = a + b;
-
-	/* Result depends on rounding mode */
-	e = a + b / 2;
-
-	/* Denormal and very large values */
-	f = b / c;
-
-	/* Depends on denormal support */
-	g = a + c * f;
-
-	if (d > a && e > a && g > a)
-		return 0;
-	else
-		return -EINVAL;
-}
+#include "test_fpu.h"
 
 static int test_fpu_get(void *data, u64 *val)
 {
@@ -68,6 +38,9 @@ static struct dentry *selftest_dir;
 
 static int __init test_fpu_init(void)
 {
+	if (!kernel_fpu_available())
+		return -EINVAL;
+
 	selftest_dir = debugfs_create_dir("selftest_helpers", NULL);
 	if (!selftest_dir)
 		return -ENOMEM;
diff --git a/lib/test_fpu_impl.c b/lib/test_fpu_impl.c
new file mode 100644
index 000000000000..777894dbbe86
--- /dev/null
+++ b/lib/test_fpu_impl.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/errno.h>
+
+#include "test_fpu.h"
+
+int test_fpu(void)
+{
+	/*
+	 * This sequence of operations tests that rounding mode is
+	 * to nearest and that denormal numbers are supported.
+	 * Volatile variables are used to avoid compiler optimizing
+	 * the calculations away.
+	 */
+	volatile double a, b, c, d, e, f, g;
+
+	a = 4.0;
+	b = 1e-15;
+	c = 1e-310;
+
+	/* Sets precision flag */
+	d = a + b;
+
+	/* Result depends on rounding mode */
+	e = a + b / 2;
+
+	/* Denormal and very large values */
+	f = b / c;
+
+	/* Depends on denormal support */
+	g = a + c * f;
+
+	if (d > a && e > a && g > a)
+		return 0;
+	else
+		return -EINVAL;
+}