Merge patch series "riscv: Add independent irq/softirq stacks support"

guoren@kernel.org <guoren@kernel.org> says:

From: Guo Ren <guoren@linux.alibaba.com>

This patch series adds independent irq/softirq stacks to decrease the
press of the thread stack. Also, add a thread STACK_SIZE config for
users to adjust the proper size during compile time.

* b4-shazam-merge:
  riscv: stack: Add config of thread stack size
  riscv: stack: Support HAVE_SOFTIRQ_ON_OWN_STACK
  riscv: stack: Support HAVE_IRQ_EXIT_ON_IRQ_STACK

Link: https://lore.kernel.org/r/20230614013018.2168426-1-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/Kconfig

@@ -591,6 +591,25 @@ config FPU
 
 	  If you don't know what to do here, say Y.
 
+config IRQ_STACKS
+	bool "Independent irq & softirq stacks" if EXPERT
+	default y
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_SOFTIRQ_ON_OWN_STACK
+	help
+	  Add independent irq & softirq stacks for percpu to prevent kernel stack
+	  overflows. We may save some memory footprint by disabling IRQ_STACKS.
+
+config THREAD_SIZE_ORDER
+	int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT
+	range 0 4
+	default 1 if 32BIT && !KASAN
+	default 3 if 64BIT && KASAN
+	default 2
+	help
+	  Specify the Pages of thread stack size (from 4KB to 64KB), which also
+	  affects irq stack size, which is equal to thread stack size.
+
 endmenu # "Platform type"
 
 menu "Kernel features"

arch/riscv/include/asm/irq_stack.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_IRQ_STACK_H
+#define _ASM_RISCV_IRQ_STACK_H
+
+#include <linux/bug.h>
+#include <linux/gfp.h>
+#include <linux/kconfig.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <asm/thread_info.h>
+
+DECLARE_PER_CPU(ulong *, irq_stack_ptr);
+
+#ifdef CONFIG_VMAP_STACK
+/*
+ * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
+ * stacks need to have the same alignment.
+ */
+static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
+{
+	void *p;
+
+	p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
+			__builtin_return_address(0));
+	return kasan_reset_tag(p);
+}
+#endif /* CONFIG_VMAP_STACK */
+
+#endif /* _ASM_RISCV_IRQ_STACK_H */

arch/riscv/include/asm/thread_info.h

@@ -11,18 +11,8 @@
 #include <asm/page.h>
 #include <linux/const.h>
 
-#ifdef CONFIG_KASAN
-#define KASAN_STACK_ORDER 1
-#else
-#define KASAN_STACK_ORDER 0
-#endif
-
 /* thread information allocation */
-#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	CONFIG_THREAD_SIZE_ORDER
-#define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
-#else
-#define THREAD_SIZE_ORDER	(1 + KASAN_STACK_ORDER)
-#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 /*
@@ -40,6 +30,8 @@
 #define OVERFLOW_STACK_SIZE     SZ_4K
 #define SHADOW_OVERFLOW_STACK_SIZE (1024)
 
+#define IRQ_STACK_SIZE		THREAD_SIZE
+
 #ifndef __ASSEMBLY__
 
 extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];

arch/riscv/kernel/irq.c

@@ -11,6 +11,9 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <asm/sbi.h>
+#include <asm/smp.h>
+#include <asm/softirq_stack.h>
+#include <asm/stacktrace.h>
 
 static struct fwnode_handle *(*__get_intc_node)(void);
 
@@ -28,6 +31,70 @@ struct fwnode_handle *riscv_get_intc_hwnode(void)
 }
 EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode);
 
+#ifdef CONFIG_IRQ_STACKS
+#include <asm/irq_stack.h>
+
+DEFINE_PER_CPU(ulong *, irq_stack_ptr);
+
+#ifdef CONFIG_VMAP_STACK
+static void init_irq_stacks(void)
+{
+	int cpu;
+	ulong *p;
+
+	for_each_possible_cpu(cpu) {
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+		per_cpu(irq_stack_ptr, cpu) = p;
+	}
+}
+#else
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU_ALIGNED(ulong [IRQ_STACK_SIZE/sizeof(ulong)], irq_stack);
+
+static void init_irq_stacks(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu);
+}
+#endif /* CONFIG_VMAP_STACK */
+
+#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK
+void do_softirq_own_stack(void)
+{
+#ifdef CONFIG_IRQ_STACKS
+	if (on_thread_stack()) {
+		ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id())
+					+ IRQ_STACK_SIZE/sizeof(ulong);
+		__asm__ __volatile(
+		"addi	sp, sp, -"RISCV_SZPTR  "\n"
+		REG_S"  ra, (sp)		\n"
+		"addi	sp, sp, -"RISCV_SZPTR  "\n"
+		REG_S"  s0, (sp)		\n"
+		"addi	s0, sp, 2*"RISCV_SZPTR "\n"
+		"move	sp, %[sp]		\n"
+		"call	__do_softirq		\n"
+		"addi	sp, s0, -2*"RISCV_SZPTR"\n"
+		REG_L"  s0, (sp)		\n"
+		"addi	sp, sp, "RISCV_SZPTR   "\n"
+		REG_L"  ra, (sp)		\n"
+		"addi	sp, sp, "RISCV_SZPTR   "\n"
+		:
+		: [sp] "r" (sp)
+		: "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
+		  "t0", "t1", "t2", "t3", "t4", "t5", "t6",
+		  "memory");
+	} else
+#endif
+		__do_softirq();
+}
+#endif /* CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK */
+
+#else
+static void init_irq_stacks(void) {}
+#endif /* CONFIG_IRQ_STACKS */
+
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	show_ipi_stats(p, prec);
@@ -36,6 +103,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 void __init init_IRQ(void)
 {
+	init_irq_stacks();
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");

arch/riscv/kernel/traps.c

@@ -27,6 +27,7 @@
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
 #include <asm/vector.h>
+#include <asm/irq_stack.h>
 
 int show_unhandled_signals = 1;
 
@@ -327,16 +328,46 @@ asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs)
 }
 #endif
 
-asmlinkage __visible noinstr void do_irq(struct pt_regs *regs)
+static void noinstr handle_riscv_irq(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
-	irqentry_state_t state = irqentry_enter(regs);
 
 	irq_enter_rcu();
 	old_regs = set_irq_regs(regs);
 	handle_arch_irq(regs);
 	set_irq_regs(old_regs);
 	irq_exit_rcu();
+}
+
+asmlinkage void noinstr do_irq(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+#ifdef CONFIG_IRQ_STACKS
+	if (on_thread_stack()) {
+		ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id())
+					+ IRQ_STACK_SIZE/sizeof(ulong);
+		__asm__ __volatile(
+		"addi	sp, sp, -"RISCV_SZPTR  "\n"
+		REG_S"  ra, (sp)		\n"
+		"addi	sp, sp, -"RISCV_SZPTR  "\n"
+		REG_S"  s0, (sp)		\n"
+		"addi	s0, sp, 2*"RISCV_SZPTR "\n"
+		"move	sp, %[sp]		\n"
+		"move	a0, %[regs]		\n"
+		"call	handle_riscv_irq	\n"
+		"addi	sp, s0, -2*"RISCV_SZPTR"\n"
+		REG_L"  s0, (sp)		\n"
+		"addi	sp, sp, "RISCV_SZPTR   "\n"
+		REG_L"  ra, (sp)		\n"
+		"addi	sp, sp, "RISCV_SZPTR   "\n"
+		:
+		: [sp] "r" (sp), [regs] "r" (regs)
+		: "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
+		  "t0", "t1", "t2", "t3", "t4", "t5", "t6",
+		  "memory");
+	} else
+#endif
+		handle_riscv_irq(regs);
 
 	irqentry_exit(regs, state);
 }