Received-SPF: pass (google.com: domain of linux-kernel+bounces-206927-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Sender: Ingo Molnar <mingo.kernel.org@gmail.com>
From: Ingo Molnar <mingo@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Andy Lutomirski <luto@amacapital.net>,
	Andrew Morton <akpm@linux-foundation.org>,
	Dave Hansen <dave@sr71.net>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>,
	Brian Gerst <brgerst@gmail.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Oleg Nesterov <oleg@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Uros Bizjak <ubizjak@gmail.com>
Subject: [PATCH 4/9] x86/fpu: Remove the thread::fpu pointer
Date: Sat,  8 Jun 2024 09:31:29 +0200
Message-ID: <20240608073134.264210-5-mingo@kernel.org>
In-Reply-To: <20240608073134.264210-1-mingo@kernel.org>
References: <20240608073134.264210-1-mingo@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

As suggested by Oleg, remove the thread::fpu pointer, as we can
calculate it via x86_task_fpu() at compile-time.

This improves code generation a bit:

   kepler:~/tip> size vmlinux.before vmlinux.after
   text        data        bss        dec         hex        filename
   26475405    10435342    1740804    38651551    24dc69f    vmlinux.before
   26475339    10959630    1216516    38651485    24dc65d    vmlinux.after

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20240605083557.2051480-3-mingo@kernel.org
---
 arch/x86/include/asm/processor.h | 5 +----
 arch/x86/kernel/fpu/core.c       | 4 +---
 arch/x86/kernel/fpu/init.c       | 1 -
 arch/x86/kernel/process.c        | 2 --
 arch/x86/kernel/vmlinux.lds.S    | 4 ++++
 5 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 64509c7f26c8..3de609aad0af 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -502,12 +502,9 @@ struct thread_struct {
 
 	struct thread_shstk	shstk;
 #endif
-
-	/* Floating point and extended processor state */
-	struct fpu		*fpu;
 };
 
-#define x86_task_fpu(task) ((task)->thread.fpu)
+#define x86_task_fpu(task)	((struct fpu *)((void *)(task) + sizeof(*(task))))
 
 /*
  * X86 doesn't need any embedded-FPU-struct quirks:
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index f0c4367804b3..167a9c7ed6d3 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -591,13 +591,11 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
 	 * This is safe because task_struct size is a multiple of cacheline size.
 	 */
 	struct fpu *src_fpu = x86_task_fpu(current);
-	struct fpu *dst_fpu = (void *)dst + sizeof(*dst);
+	struct fpu *dst_fpu = x86_task_fpu(dst);
 
 	BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0);
 	BUG_ON(!src_fpu);
 
-	dst->thread.fpu = dst_fpu;
-
 	/* The new task's FPU state cannot be valid in the hardware. */
 	dst_fpu->last_cpu = -1;
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 4e8d37b5a90b..794682b52373 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -78,7 +78,6 @@ static void __init fpu__init_system_early_generic(void)
 	int this_cpu = smp_processor_id();
 
 	fpstate_reset(&x86_init_fpu);
-	current->thread.fpu = &x86_init_fpu;
 	per_cpu(fpu_fpregs_owner_ctx, this_cpu) = &x86_init_fpu;
 	x86_init_fpu.last_cpu = this_cpu;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 5bb73bc0e31a..4184c085627e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -96,8 +96,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 #ifdef CONFIG_VM86
 	dst->thread.vm86 = NULL;
 #endif
-	/* Drop the copied pointer to current's fpstate */
-	dst->thread.fpu = NULL;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3509afc6a672..226244a894da 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -170,6 +170,10 @@ SECTIONS
 		/* equivalent to task_pt_regs(&init_task) */
 		__top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE;
 
+		__x86_init_fpu_begin = .;
+		. = __x86_init_fpu_begin + 128*PAGE_SIZE;
+		__x86_init_fpu_end = .;
+
 #ifdef CONFIG_X86_32
 		/* 32 bit has nosave before _edata */
 		NOSAVE_DATA
-- 
2.43.0