[PATCH 07/24] x86/mm/kaiser: Map the CPU entry area

[Ingo Molnar]

From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

There is now a special 'struct cpu_entry_area' that contains all
of the data needed to enter the kernel.  It's mapped in the fixmap
area and contains:

 * The GDT (hardware segment descriptor)

 * The TSS (thread information structure that points the hardware
   to the various stacks, and contains the entry stack).

 * The entry trampoline code itself

 * The exception stacks (aka IRQ stacks)

Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: daniel.gruss@xxxxxxxxxxxxxx
Cc: hughd@xxxxxxxxxx
Cc: keescook@xxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Cc: michael.schwarz@xxxxxxxxxxxxxx
Cc: moritz.lipp@xxxxxxxxxxxxxx
Cc: richard.fellner@xxxxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/20171123003453.D4CB33A9@xxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/kaiser.h |  6 ++++++
 arch/x86/kernel/cpu/common.c  |  4 ++++
 arch/x86/mm/kaiser.c          | 31 +++++++++++++++++++++++++++++++
 include/linux/kaiser.h        |  3 +++
 4 files changed, 44 insertions(+)

diff --git a/arch/x86/include/asm/kaiser.h b/arch/x86/include/asm/kaiser.h
index 3c2cc71b4058..040cb096d29d 100644
--- a/arch/x86/include/asm/kaiser.h
+++ b/arch/x86/include/asm/kaiser.h
@@ -33,6 +33,12 @@
 extern int kaiser_add_mapping(unsigned long addr, unsigned long size,
 			      unsigned long flags);
 
+/**
+ *  kaiser_add_mapping_cpu_entry - map the cpu entry area
+ *  @cpu: the CPU for which the entry area is being mapped
+ */
+extern void kaiser_add_mapping_cpu_entry(int cpu);
+
 /**
  *  kaiser_remove_mapping - remove a kernel mapping from the userpage tables
  *  @addr: the start address of the range
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1509f09abf5e..7b348cc33e2d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/percpu.h>
+#include <linux/kaiser.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
@@ -584,6 +585,9 @@ static inline void setup_cpu_entry_area(int cpu)
 	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
 #endif
+ 	/* CPU 0's mapping is done in kaiser_init() */
+	if (cpu)
+		kaiser_add_mapping_cpu_entry(cpu);
 }
 
 /* Load the original GDT from the per-cpu structure */
diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c
index 72dc15364390..10c0e9e6bf6b 100644
--- a/arch/x86/mm/kaiser.c
+++ b/arch/x86/mm/kaiser.c
@@ -353,6 +353,26 @@ static void __init kaiser_init_all_pgds(void)
 	WARN_ON(__ret);							\
 } while (0)
 
+void kaiser_add_mapping_cpu_entry(int cpu)
+{
+	kaiser_add_user_map_early(get_cpu_gdt_ro(cpu), PAGE_SIZE,
+				  __PAGE_KERNEL_RO);
+
+	/* includes the entry stack */
+	kaiser_add_user_map_early(&get_cpu_entry_area(cpu)->tss,
+				  sizeof(get_cpu_entry_area(cpu)->tss),
+				  __PAGE_KERNEL | _PAGE_GLOBAL);
+
+	/* Entry code, so needs to be EXEC */
+	kaiser_add_user_map_early(&get_cpu_entry_area(cpu)->entry_trampoline,
+				  sizeof(get_cpu_entry_area(cpu)->entry_trampoline),
+				  __PAGE_KERNEL_RX | _PAGE_GLOBAL);
+
+	kaiser_add_user_map_early(&get_cpu_entry_area(cpu)->exception_stacks,
+				 sizeof(get_cpu_entry_area(cpu)->exception_stacks),
+				 __PAGE_KERNEL | _PAGE_GLOBAL);
+}
+
 extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
 /*
  * If anything in here fails, we will likely die on one of the
@@ -393,6 +413,17 @@ void __init kaiser_init(void)
 	kaiser_add_user_map_early((void *)idt_descr.address,
 				  sizeof(gate_desc) * NR_VECTORS,
 				  __PAGE_KERNEL_RO | _PAGE_GLOBAL);
+
+	/*
+	 * We delay CPU 0's mappings because these structures are
+	 * created before the page allocator is up.  Deferring it
+	 * until here lets us use the plain page allocator
+	 * unconditionally in the page table code above.
+	 *
+	 * This is OK because kaiser_init() is called long before
+	 * we ever run userspace and need the KAISER mappings.
+	 */
+	kaiser_add_mapping_cpu_entry(0);
 }
 
 int kaiser_add_mapping(unsigned long addr, unsigned long size,
diff --git a/include/linux/kaiser.h b/include/linux/kaiser.h
index 0fd800efa95c..77db4230a0dd 100644
--- a/include/linux/kaiser.h
+++ b/include/linux/kaiser.h
@@ -25,5 +25,8 @@ static inline int kaiser_add_mapping(unsigned long addr, unsigned long size,
 	return 0;
 }
 
+static inline void kaiser_add_mapping_cpu_entry(int cpu)
+{
+}
 #endif /* !CONFIG_KAISER */
 #endif /* _INCLUDE_KAISER_H */
-- 
2.14.1