feat:rdna graphics card support

Changelogs:
    1. backport rdna graphics card support & optimize PLT/GOT entry counting
       SiFiveHolland and others added 9 commits May 26, 2025 14:50
       from: #11
       @SiFiveHolland @RevySR riscv: module: Optimize PLT/GOT entry counting
       @Pritesh201192 @RevySR riscv: module: fix compilation error of kvrealloc
       @SiFiveHolland @RevySR arch: add ARCH_HAS_KERNEL_FPU_SUPPORT
       @SiFiveHolland @RevySR riscv: add support for kernel-mode FPU
       @RevySR drm/amd/display: Remove migrate_en/dis from dc_fpu_begin().
       @RevySR drm/amd/display: Simplify the per-CPU usage.
       @RevySR drm/amd/display: Add a warning if the FPU is used outside from task c…
       @mpe @RevySR drm/amd/display: only use hard-float, not altivec on powerpc
       @SiFiveHolland @RevySR drm/amd/display: use ARCH_HAS_KERNEL_FPU_SUPPORT
    2. raw 9 commits include zhangyizhong optimimation code of arch/riscv/kernel/module-sections.c
       so revert zhangyizhong code and apply 9 commit patch

Signed-off-by: liwenkai <liwenkai@eswincomputing.com>

Author: liwenkai

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

@@ -981,6 +981,11 @@ 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 ($(CONFIG_FUNCTION_ALIGNMENT),0)
 KBUILD_CFLAGS += -falign-functions=$(CONFIG_FUNCTION_ALIGNMENT)
 endif

arch/Kconfig

@@ -1480,6 +1480,12 @@ 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/riscv/Kconfig

@@ -29,6 +29,7 @@ config RISCV
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU
 	select ARCH_HAS_MMIOWB
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API

arch/riscv/Makefile

@@ -77,6 +77,9 @@ 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

@@ -61,6 +61,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 
 obj-$(CONFIG_RISCV_M_MODE)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
+obj-$(CONFIG_FPU)		+= kernel_mode_fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.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/riscv/kernel/module-sections.c

@@ -123,7 +123,6 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned int num_gots = 0;
 	Elf_Rela *scratch = NULL;
 	size_t scratch_size = 0;
-	size_t old_size = 0;
 	int i;
 
 	/*
@@ -169,11 +168,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		 * close together, so sort a copy of the section to avoid interfering.
 		 */
 		if (sechdrs[i].sh_size > scratch_size) {
-			old_size = scratch_size;
-			scratch_size = sechdrs[i].sh_size;
-			scratch = kvrealloc(scratch, old_size, scratch_size, GFP_KERNEL);
+			scratch = kvrealloc(scratch, scratch_size, sechdrs[i].sh_size, GFP_KERNEL);
 			if (!scratch)
 				return -ENOMEM;
+			scratch_size = sechdrs[i].sh_size;
 		}
 
 		/* sort relocations requiring a PLT or GOT entry so duplicates are adjacent */