x86/kaslr: Fix the vaddr_end mess

vaddr_end for KASLR is only documented in the KASLR code itself and is
adjusted depending on config options. So it's not surprising that a change
of the memory layout causes KASLR to have the wrong vaddr_end. This can map
arbitrary stuff into other areas causing hard to understand problems.

Remove the whole ifdef magic and define the start of the cpu_entry_area to
be the end of the KASLR vaddr range.

Add documentation to that effect.

Fixes: 92a0f81d8957 ("x86/cpu_entry_area: Move it out of the fixmap")
Reported-by: Benjamin Gilbert <benjamin.gilbert@coreos.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Benjamin Gilbert <benjamin.gilbert@coreos.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: stable <stable@vger.kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Garnier <thgarnie@google.com>,
Cc: Alexander Kuleshov <kuleshovmail@gmail.com>
Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1801041320360.1771@nanos

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index f7dabe1f01e9b5d0c03ab621bac540b805ad74c2..ea91cb61a60297ac658a4160cee200da75e6f00d 100644 (file)
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,7 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+                                   vaddr_end for KASLR
 fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
 fffffe8000000000 - fffffeffffffffff (=39 bits) LDT remap for PTI
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
@@ -37,6 +38,7 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+                                   vaddr_end for KASLR
 fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
 ... unused hole ...
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
@@ -71,3 +73,7 @@ during EFI runtime calls.
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
+
+Be very careful vs. KASLR when changing anything here. The KASLR address
+range must not overlap with anything except the KASAN shadow area, which is
+correct as KASAN disables KASLR.

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 61b4b60bdc133d5a64606c3bb3366155e5449864..6b8f73dcbc2c2b6a835e17ac0828d8b6484f4dce 100644 (file)
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -75,7 +75,13 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE     (_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK     (~(PGDIR_SIZE - 1))
 
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
+/*
+ * See Documentation/x86/x86_64/mm.txt for a description of the memory map.
+ *
+ * Be very careful vs. KASLR when changing anything here. The KASLR address
+ * range must not overlap with anything except the KASAN shadow area, which
+ * is correct as KASAN disables KASLR.
+ */
 #define MAXMEM                 _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 
 #ifdef CONFIG_X86_5LEVEL

diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 879ef930e2c2b04d60c85efec9f6e0fa5555fa2a..aedebd2ebf1ead0ff2b1b17816ff80d9fce88b8f 100644 (file)
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -34,25 +34,14 @@
 #define TB_SHIFT 40
 
 /*
- * Virtual address start and end range for randomization. The end changes base
- * on configuration to have the highest amount of space for randomization.
- * It increases the possible random position for each randomized region.
+ * Virtual address start and end range for randomization.
  *
- * You need to add an if/def entry if you introduce a new memory region
- * compatible with KASLR. Your entry must be in logical order with memory
- * layout. For example, ESPFIX is before EFI because its virtual address is
- * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to
- * ensure that this order is correct and won't be changed.
+ * The end address could depend on more configuration options to make the
+ * highest amount of space for randomization available, but that's too hard
+ * to keep straight and caused issues already.
  */
 static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
-
-#if defined(CONFIG_X86_ESPFIX64)
-static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
-#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_END;
-#else
-static const unsigned long vaddr_end = __START_KERNEL_map;
-#endif
+static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
 
 /* Default values */
 unsigned long page_offset_base = __PAGE_OFFSET_BASE;
@@ -101,15 +90,12 @@ void __init kernel_randomize_memory(void)
        unsigned long remain_entropy;
 
        /*
-        * All these BUILD_BUG_ON checks ensures the memory layout is
-        * consistent with the vaddr_start/vaddr_end variables.
+        * These BUILD_BUG_ON checks ensure the memory layout is consistent
+        * with the vaddr_start/vaddr_end variables. These checks are very
+        * limited....
         */
        BUILD_BUG_ON(vaddr_start >= vaddr_end);
-       BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
-                    vaddr_end >= EFI_VA_END);
-       BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
-                     IS_ENABLED(CONFIG_EFI)) &&
-                    vaddr_end >= __START_KERNEL_map);
+       BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
        BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
 
        if (!kaslr_memory_enabled())