[GIT pull] x86/pti: Fixes and updates for 4.15

From: Thomas Gleixner
Date: Fri Jan 05 2018 - 13:54:06 EST

Linus,

please pull the latest x86-pti-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-pti-for-linus

Another small stash of fixes for fallout from the PTI work:

- Fix the modules vs. KASAN breakage which was caused by making
MODULES_END depend of the fixmap size. That was done when the cpu entry
area moved into the fixmap, but now that we have a separate map space
for that this is causing more issues than it solves.

- Use the proper cache flush methods for the debugstore buffers as they
are mapped/unmapped during runtime and not statically mapped at boot
time like the rest of the cpu entry area.

- Make the map layout of the cpu_entry_area consistent for 4 and 5 level
paging and fix the KASLR vaddr_end wreckage.

- Use PER_CPU_EXPORT for per cpu variable and while at it unbreak nvidia
gfx drivers by dropping the GPL export. The subject line of the commit
tells it the other way around, but I noticed that too late.

- Fix the ASM alternative macros so they can be used in the middle of an
inline asm block.

- Rename the BUG_CPU_INSECURE flag to BUG_CPU_MELTDOWN so the attack
vector is properly identified. The Spectre mitigations will come with
their own bug bits later.

Thanks,

tglx

------------------>
Andrey Ryabinin (1):
x86/mm: Set MODULES_END to 0xffffffffff000000

David Woodhouse (1):
x86/alternatives: Add missing '\n' at end of ALTERNATIVE inline asm

Peter Zijlstra (1):
x86/events/intel/ds: Use the proper cache flush method for mapping ds buffers

Thomas Gleixner (4):
x86/mm: Map cpu_entry_area at the same place on 4/5 level
x86/kaslr: Fix the vaddr_end mess
x86/tlb: Drop the _GPL from the cpu_tlbstate export
x86/pti: Rename BUG_CPU_INSECURE to BUG_CPU_MELTDOWN


Documentation/x86/x86_64/mm.txt | 18 +++++++++++-------
arch/x86/events/intel/ds.c | 16 ++++++++++++++++
arch/x86/include/asm/alternative.h | 4 ++--
arch/x86/include/asm/cpufeatures.h | 2 +-
arch/x86/include/asm/pgtable_64_types.h | 14 ++++++++++----
arch/x86/kernel/cpu/common.c | 2 +-
arch/x86/mm/dump_pagetables.c | 2 +-
arch/x86/mm/init.c | 2 +-
arch/x86/mm/kaslr.c | 32 +++++++++-----------------------
arch/x86/mm/pti.c | 6 +++---
10 files changed, 55 insertions(+), 43 deletions(-)

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index ad41b3813f0a..ea91cb61a602 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,8 +12,9 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
... unused hole ...
-fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
-fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
+ 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
... unused hole ...
ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
@@ -37,13 +38,15 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
... unused hole ...
ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
... unused hole ...
-fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
+ vaddr_end for KASLR
+fffffe0000000000 - fffffe7fffffffff (=39 bits) cpu_entry_area mapping
+... unused hole ...
ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
... unused hole ...
ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
... unused hole ...
ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0
-ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space
+ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
[fixmap start] - ffffffffff5fffff kernel-internal fixmap range
ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
@@ -67,9 +70,10 @@ memory window (this size is arbitrary, it can be raised later if needed).
The mappings are not part of any other kernel PGD and are only available
during EFI runtime calls.

-The module mapping space size changes based on the CONFIG requirements for the
-following fixmap section.
-
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/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8f0aace08b87..8156e47da7ba 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -5,6 +5,7 @@

#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
+#include <asm/tlbflush.h>
#include <asm/insn.h>

#include "../perf_event.h"
@@ -283,20 +284,35 @@ static DEFINE_PER_CPU(void *, insn_buffer);

static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
+ unsigned long start = (unsigned long)cea;
phys_addr_t pa;
size_t msz = 0;

pa = virt_to_phys(addr);
+
+ preempt_disable();
for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
cea_set_pte(cea, pa, prot);
+
+ /*
+ * This is a cross-CPU update of the cpu_entry_area, we must shoot down
+ * all TLB entries for it.
+ */
+ flush_tlb_kernel_range(start, start + size);
+ preempt_enable();
}

static void ds_clear_cea(void *cea, size_t size)
{
+ unsigned long start = (unsigned long)cea;
size_t msz = 0;

+ preempt_disable();
for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
cea_set_pte(cea, 0, PAGE_NONE);
+
+ flush_tlb_kernel_range(start, start + size);
+ preempt_enable();
}

static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index dbfd0854651f..cf5961ca8677 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
- ".popsection"
+ ".popsection\n"

#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR_2(oldinstr, 1, 2) \
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
- ".popsection"
+ ".popsection\n"

/*
* Alternative instructions for different CPU types or capabilities.
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 07cdd1715705..21ac898df2d8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -341,6 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
+#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */

#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index b97a539bcdee..6b8f73dcbc2c 100644
--- 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
@@ -88,7 +94,7 @@ typedef struct { pteval_t pte; } pte_t;
# define VMALLOC_SIZE_TB _AC(32, UL)
# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
-# define LDT_PGD_ENTRY _AC(-4, UL)
+# define LDT_PGD_ENTRY _AC(-3, UL)
# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif

@@ -104,13 +110,13 @@ typedef struct { pteval_t pte; } pte_t;

#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
/* The module sections ends with the start of the fixmap */
-#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1)
+#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)

#define ESPFIX_PGD_ENTRY _AC(-2, UL)
#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)

-#define CPU_ENTRY_AREA_PGD _AC(-3, UL)
+#define CPU_ENTRY_AREA_PGD _AC(-4, UL)
#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT)

#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b1be494ab4e8..2d3bd2215e5b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -900,7 +900,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_force_cpu_cap(X86_FEATURE_ALWAYS);

if (c->x86_vendor != X86_VENDOR_AMD)
- setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
+ setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);

fpu__init_system(c);

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index f56902c1f04b..2a4849e92831 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -61,10 +61,10 @@ enum address_markers_idx {
KASAN_SHADOW_START_NR,
KASAN_SHADOW_END_NR,
#endif
+ CPU_ENTRY_AREA_NR,
#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
LDT_NR,
#endif
- CPU_ENTRY_AREA_NR,
#ifdef CONFIG_X86_ESPFIX64
ESPFIX_START_NR,
#endif
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 80259ad8c386..6b462a472a7b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -870,7 +870,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
.next_asid = 1,
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
};
-EXPORT_SYMBOL_GPL(cpu_tlbstate);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate);

void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
{
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 879ef930e2c2..aedebd2ebf1e 100644
--- 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())
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 2da28ba97508..43d4a4a29037 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -56,13 +56,13 @@

static void __init pti_print_if_insecure(const char *reason)
{
- if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
pr_info("%s\n", reason);
}

static void __init pti_print_if_secure(const char *reason)
{
- if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
pr_info("%s\n", reason);
}

@@ -96,7 +96,7 @@ void __init pti_check_boottime_disable(void)
}

autosel:
- if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
return;
enable:
setup_force_cpu_cap(X86_FEATURE_PTI);