[PATCH 18/43] x86/entry/64: Move the IST stacks into cpu_entry_area

[Ingo Molnar]

From: Andy Lutomirski <luto@xxxxxxxxxx>

The IST stacks are needed when an IST exception occurs and are
accessed before any kernel code at all runs.  Move them into
cpu_entry_area.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Borislav Petkov <bpetkov@xxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/0ffddccdc0ce1953f950a553142662cf68258fb7.1511497875.git.luto@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/fixmap.h | 10 ++++++++++
 arch/x86/kernel/cpu/common.c  | 40 +++++++++++++++++++++++++---------------
 2 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7eb1b5490395..15cf010225c9 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -60,6 +60,16 @@ struct cpu_entry_area {
 	struct tss_struct tss;
 
 	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
 };
 
 #define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5a05db084659..6b949e6ea0f9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -503,6 +503,22 @@ static void set_percpu_fixmap_pages(int fixmap_index, void *ptr, int pages, pgpr
 DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 #endif
 
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
 /* Setup the fixmap mappings only once per-processor */
 static inline void setup_cpu_entry_area(int cpu)
 {
@@ -557,6 +573,14 @@ static inline void setup_cpu_entry_area(int cpu)
 #endif
 
 #ifdef CONFIG_X86_64
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+	BUILD_BUG_ON(sizeof(exception_stacks) !=
+		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks),
+				&per_cpu(exception_stacks, cpu),
+				sizeof(exception_stacks) / PAGE_SIZE,
+				PAGE_KERNEL);
+
 	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
 #endif
@@ -1407,20 +1431,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
@@ -1626,7 +1636,7 @@ void cpu_init(void)
 	 * set up and load the per-CPU TSS
 	 */
 	if (!oist->ist[0]) {
-		char *estacks = per_cpu(exception_stacks, cpu);
+		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
-- 
2.14.1