x86/irq/64: Split the IRQ stack into its own pages

Currently, the IRQ stack is hardcoded as the first page of the percpu
area, and the stack canary lives on the IRQ stack. The former gets in
the way of adding an IRQ stack guard page, and the latter is a potential
weakness in the stack canary mechanism.

Split the IRQ stack into its own private percpu pages.

[ tglx: Make 64 and 32 bit share struct irq_stack ]

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: "Chang S. Bae" <chang.seok.bae@intel.com>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Feng Tang <feng.tang@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jordan Borgner <mail@jordan-borgner.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Maran Wilson <maran.wilson@oracle.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Nicolai Stange <nstange@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pu Wen <puwen@hygon.cn>
Cc: "Rafael Ávila de Espíndola" <rafael@espindo.la>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: x86-ml <x86@kernel.org>
Cc: xen-devel@lists.xenproject.org
Link: https://lkml.kernel.org/r/20190414160146.267376656@linutronix.de

6 files changed, 14 insertions, 15 deletions

diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f5281567e28e..d3d075226c0a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -73,7 +73,7 @@ int main(void)
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-	DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
+	DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
 	BLANK();
 #endif
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1222080838da..801c6f040faa 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1498,9 +1498,9 @@ static __init int setup_clearcpuid(char *arg)
 __setup("clearcpuid=", setup_clearcpuid);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(union irq_stack_union,
-		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
+DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
+		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
 /*
  * The following percpu variables are hot.  Align current_task to
@@ -1510,7 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(char *, hardirq_stack_ptr);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d1dbe8e4eb82..bcd206c8ac90 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -265,7 +265,7 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_code)
 	.quad	x86_64_start_kernel
 	GLOBAL(initial_gs)
-	.quad	INIT_PER_CPU_VAR(irq_stack_union)
+	.quad	INIT_PER_CPU_VAR(fixed_percpu_data)
 	GLOBAL(initial_stack)
 	/*
 	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index c0bea0d7d76a..c0f89d136b80 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -23,6 +23,9 @@
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
+DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
+DECLARE_INIT_PER_CPU(irq_stack_backing_store);
+
 int sysctl_panic_on_stackoverflow;
 
 /*
@@ -90,7 +93,7 @@ bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 
 static int map_irq_stack(unsigned int cpu)
 {
-	void *va = per_cpu_ptr(irq_stack_union.irq_stack, cpu);
+	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
 	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
 	return 0;
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 657343ecc2da..86663874ef04 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_cpu_to_logical_apicid, cpu) =
 			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
 #endif
-#ifdef CONFIG_X86_64
-		per_cpu(hardirq_stack_ptr, cpu) =
-			per_cpu(irq_stack_union.irq_stack, cpu) +
-			IRQ_STACK_SIZE;
-#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bad8c51fee6e..a5af9a7c4be4 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -403,7 +403,8 @@ SECTIONS
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
+INIT_PER_CPU(fixed_percpu_data);
+INIT_PER_CPU(irq_stack_backing_store);
 
 /*
  * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union);
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((irq_stack_union == 0),
-           "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((fixed_percpu_data == 0),
+           "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
 #endif /* CONFIG_X86_32 */