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
  ...

Author: torvalds

Documentation/core-api/floating-point.rst

@@ -0,0 +1,78 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+Floating-point API
+==================
+
+Kernel code is normally prohibited from using floating-point (FP) registers or
+instructions, including the C float and double data types. This rule reduces
+system call overhead, because the kernel does not need to save and restore the
+userspace floating-point register state.
+
+However, occasionally drivers or library functions may need to include FP code.
+This is supported by isolating the functions containing FP code to a separate
+translation unit (a separate source file), and saving/restoring the FP register
+state around calls to those functions. This creates "critical sections" of
+floating-point usage.
+
+The reason for this isolation is to prevent the compiler from generating code
+touching the FP registers outside these critical sections. Compilers sometimes
+use FP registers to optimize inlined ``memcpy`` or variable assignment, as
+floating-point registers may be wider than general-purpose registers.
+
+Usability of floating-point code within the kernel is architecture-specific.
+Additionally, because a single kernel may be configured to support platforms
+both with and without a floating-point unit, FPU availability must be checked
+both at build time and at run time.
+
+Several architectures implement the generic kernel floating-point API from
+``linux/fpu.h``, as described below. Some other architectures implement their
+own unique APIs, which are documented separately.
+
+Build-time API
+--------------
+
+Floating-point code may be built if the option ``ARCH_HAS_KERNEL_FPU_SUPPORT``
+is enabled. For C code, such code must be placed in a separate file, and that
+file must have its compilation flags adjusted using the following pattern::
+
+    CFLAGS_foo.o += $(CC_FLAGS_FPU)
+    CFLAGS_REMOVE_foo.o += $(CC_FLAGS_NO_FPU)
+
+Architectures are expected to define one or both of these variables in their
+top-level Makefile as needed. For example::
+
+    CC_FLAGS_FPU := -mhard-float
+
+or::
+
+    CC_FLAGS_NO_FPU := -msoft-float
+
+Normal kernel code is assumed to use the equivalent of ``CC_FLAGS_NO_FPU``.
+
+Runtime API
+-----------
+
+The runtime API is provided in ``linux/fpu.h``. This header cannot be included
+from files implementing FP code (those with their compilation flags adjusted as
+above). Instead, it must be included when defining the FP critical sections.
+
+.. c:function:: bool kernel_fpu_available( void )
+
+        This function reports if floating-point code can be used on this CPU or
+        platform. The value returned by this function is not expected to change
+        at runtime, so it only needs to be called once, not before every
+        critical section.
+
+.. c:function:: void kernel_fpu_begin( void )
+                void kernel_fpu_end( void )
+
+        These functions create a floating-point critical section. It is only
+        valid to call ``kernel_fpu_begin()`` after a previous call to
+        ``kernel_fpu_available()`` returned ``true``. These functions are only
+        guaranteed to be callable from (preemptible or non-preemptible) process
+        context.
+
+        Preemption may be disabled inside critical sections, so their size
+        should be minimized. They are *not* required to be reentrant. If the
+        caller expects to nest critical sections, it must implement its own
+        reference counting.

Documentation/core-api/index.rst

@@ -48,6 +48,7 @@ Library functionality that is used throughout the kernel.
    errseq
    wrappers/atomic_t
    wrappers/atomic_bitops
+   floating-point
 
 Low level entry and exit
 ========================

Makefile

@@ -970,6 +970,11 @@ KBUILD_CFLAGS	+= $(CC_FLAGS_CFI)
 export CC_FLAGS_CFI
 endif
 
+# Architectures can define flags to add/remove for floating-point support
+CC_FLAGS_FPU	+= -D_LINUX_FPU_COMPILATION_UNIT
+export CC_FLAGS_FPU
+export CC_FLAGS_NO_FPU
+
 ifneq ($(CONFIG_FUNCTION_ALIGNMENT),0)
 # Set the minimal function alignment. Use the newer GCC option
 # -fmin-function-alignment if it is available, or fall back to -falign-funtions.

arch/Kconfig

@@ -1594,6 +1594,12 @@ config ARCH_HAS_NONLEAF_PMD_YOUNG
 	  address translations. Page table walkers that clear the accessed bit
 	  may use this capability to reduce their search space.
 
+config ARCH_HAS_KERNEL_FPU_SUPPORT
+	bool
+	help
+	  Architectures that select this option can run floating-point code in
+	  the kernel, as described in Documentation/core-api/floating-point.rst.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"

arch/arm/Makefile

@@ -130,6 +130,13 @@ endif
 # Accept old syntax despite ".syntax unified"
 AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
 
+# 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)
+CC_FLAGS_FPU	:= -ffreestanding
+# Enable <arm_neon.h>
+CC_FLAGS_FPU	+= -isystem $(shell $(CC) -print-file-name=include)
+CC_FLAGS_FPU	+= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
+
 ifeq ($(CONFIG_THUMB2_KERNEL),y)
 CFLAGS_ISA	:=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN)
 AFLAGS_ISA	:=$(CFLAGS_ISA) -Wa$(comma)-mthumb

arch/arm/include/asm/fpu.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_FPU_H
+#define __ASM_FPU_H
+
+#include <asm/neon.h>
+
+#define kernel_fpu_available()	cpu_has_neon()
+#define kernel_fpu_begin()	kernel_neon_begin()
+#define kernel_fpu_end()	kernel_neon_end()
+
+#endif /* ! __ASM_FPU_H */

arch/arm/lib/Makefile

@@ -40,8 +40,7 @@ $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-  NEON_FLAGS			:= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
-  CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
+  CFLAGS_xor-neon.o		+= $(CC_FLAGS_FPU)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif
 

arch/arm64/Kconfig

@@ -30,6 +30,7 @@ config ARM64
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT if KERNEL_MODE_NEON
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS

arch/arm64/Makefile

@@ -36,7 +36,14 @@ ifeq ($(CONFIG_BROKEN_GAS_INST),y)
 $(warning Detected assembler with broken .inst; disassembly will be unreliable)
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only	\
+# 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)
+CC_FLAGS_FPU	:= -ffreestanding
+# Enable <arm_neon.h>
+CC_FLAGS_FPU	+= -isystem $(shell $(CC) -print-file-name=include)
+CC_FLAGS_NO_FPU	:= -mgeneral-regs-only
+
+KBUILD_CFLAGS	+= $(CC_FLAGS_NO_FPU) \
 		   $(compat_vdso) $(cc_has_k_constraint)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
 KBUILD_AFLAGS	+= $(compat_vdso)

arch/arm64/include/asm/fpu.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef __ASM_FPU_H
+#define __ASM_FPU_H
+
+#include <asm/neon.h>
+
+#define kernel_fpu_available()	cpu_has_neon()
+#define kernel_fpu_begin()	kernel_neon_begin()
+#define kernel_fpu_end()	kernel_neon_end()
+
+#endif /* ! __ASM_FPU_H */

arch/arm64/lib/Makefile

@@ -7,10 +7,8 @@ lib-y		:= clear_user.o delay.o copy_from_user.o		\
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
 obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
-CFLAGS_REMOVE_xor-neon.o	+= -mgeneral-regs-only
-CFLAGS_xor-neon.o		+= -ffreestanding
-# Enable <arm_neon.h>
-CFLAGS_xor-neon.o		+= -isystem $(shell $(CC) -print-file-name=include)
+CFLAGS_xor-neon.o		+= $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_xor-neon.o	+= $(CC_FLAGS_NO_FPU)
 endif
 
 lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o

arch/loongarch/Kconfig

@@ -19,6 +19,7 @@ config LOONGARCH
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT if CPU_HAS_FPU
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_SPECIAL

arch/loongarch/Makefile

@@ -26,6 +26,9 @@ endif
 32bit-emul		= elf32loongarch
 64bit-emul		= elf64loongarch
 
+CC_FLAGS_FPU		:= -mfpu=64
+CC_FLAGS_NO_FPU		:= -msoft-float
+
 ifdef CONFIG_UNWINDER_ORC
 orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h
 orc_hash_sh := $(srctree)/scripts/orc_hash.sh
@@ -59,7 +62,7 @@ ld-emul			= $(64bit-emul)
 cflags-y		+= -mabi=lp64s
 endif
 
-cflags-y			+= -pipe -msoft-float
+cflags-y			+= -pipe $(CC_FLAGS_NO_FPU)
 LDFLAGS_vmlinux			+= -static -n -nostdlib
 
 # When the assembler supports explicit relocation hint, we must use it.

arch/loongarch/include/asm/fpu.h

@@ -21,6 +21,7 @@
 
 struct sigcontext;
 
+#define kernel_fpu_available() cpu_has_fpu
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 

arch/powerpc/Kconfig

@@ -137,6 +137,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT	if PPC_FPU
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN	if PPC_64S_HASH_MMU

arch/powerpc/Makefile

@@ -149,6 +149,9 @@ CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option, $(MULTIPLEWORD))
 
 CFLAGS-$(CONFIG_PPC32)	+= $(call cc-option,-mno-readonly-in-sdata)
 
+CC_FLAGS_FPU		:= $(call cc-option,-mhard-float)
+CC_FLAGS_NO_FPU		:= $(call cc-option,-msoft-float)
+
 ifdef CONFIG_FUNCTION_TRACER
 ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
 KBUILD_CPPFLAGS	+= -DCC_USING_PATCHABLE_FUNCTION_ENTRY
@@ -170,7 +173,7 @@ asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
 KBUILD_CPPFLAGS	+= -I $(srctree)/arch/powerpc $(asinstr)
 KBUILD_AFLAGS	+= $(AFLAGS-y)
-KBUILD_CFLAGS	+= $(call cc-option,-msoft-float)
+KBUILD_CFLAGS	+= $(CC_FLAGS_NO_FPU)
 KBUILD_CFLAGS	+= $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 

arch/powerpc/include/asm/fpu.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_POWERPC_FPU_H
+#define _ASM_POWERPC_FPU_H
+
+#include <linux/preempt.h>
+
+#include <asm/cpu_has_feature.h>
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available()	(!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE))
+
+static inline void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	enable_kernel_fp();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	disable_kernel_fp();
+	preempt_enable();
+}
+
+#endif /* ! _ASM_POWERPC_FPU_H */

arch/riscv/Kconfig

@@ -28,6 +28,7 @@ config RISCV
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MMIOWB

arch/riscv/Makefile

@@ -91,6 +91,9 @@ KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64i
 
 KBUILD_AFLAGS += -march=$(riscv-march-y)
 
+# For C code built with floating-point support, exclude V but keep F and D.
+CC_FLAGS_FPU  := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/')
+
 KBUILD_CFLAGS += -mno-save-restore
 KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET)
 

arch/riscv/include/asm/fpu.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_RISCV_FPU_H
+#define _ASM_RISCV_FPU_H
+
+#include <asm/switch_to.h>
+
+#define kernel_fpu_available()	has_fpu()
+
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
+
+#endif /* ! _ASM_RISCV_FPU_H */

arch/riscv/kernel/Makefile

@@ -67,6 +67,7 @@ obj-$(CONFIG_RISCV_MISALIGNED)	+= unaligned_access_speed.o
 obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS)	+= copy-unaligned.o
 
 obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o

arch/riscv/kernel/kernel_mode_fpu.c

@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#include <linux/export.h>
+#include <linux/preempt.h>
+
+#include <asm/csr.h>
+#include <asm/fpu.h>
+#include <asm/processor.h>
+#include <asm/switch_to.h>
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	fstate_save(current, task_pt_regs(current));
+	csr_set(CSR_SSTATUS, SR_FS);
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	csr_clear(CSR_SSTATUS, SR_FS);
+	fstate_restore(current, task_pt_regs(current));
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);

arch/x86/Kconfig

@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_KERNEL_FPU_SUPPORT
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS