Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Misc fixes: two vdso fixes, two kbuild fixes and a boot failure fix
  with certain odd memory mappings"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, vdso: Use asm volatile in __getcpu
  x86/build: Clean auto-generated processor feature files
  x86: Fix mkcapflags.sh bash-ism
  x86: Fix step size adjustment during initial memory mapping
  x86_64, vdso: Fix the vdso address randomization algorithm

6 files changed, 53 insertions, 39 deletions

diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 5b016e2498f3..3db07f30636f 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -51,6 +51,7 @@ targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
         $(call if_changed,cpustr)
 endif
+clean-files += cpustr.h
 
 # ---------------------------------------------------------------------------
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index e7e9682a33e9..f556c4843aa1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -80,9 +80,11 @@ static inline unsigned int __getcpu(void)
 
         /*
          * Load per CPU data from GDT.  LSL is faster than RDTSCP and
-         * works on all CPUs.
+         * works on all CPUs.  This is volatile so that it orders
+         * correctly wrt barrier() and to keep gcc from cleverly
+         * hoisting it out of the calling function.
          */
-        asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+        asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 
         return p;
 }
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index e27b49d7c922..80091ae54c2b 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
         $(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index e2b22df964cd..36d99a337b49 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -28,7 +28,7 @@ function dump_array()
                 # If the /* comment */ starts with a quote string, grab that.
                 VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
                 [ -z "$VALUE" ] && VALUE="\"$NAME\""
-                [ "$VALUE" == '""' ] && continue
+                [ "$VALUE" = '""' ] && continue
 
                 # Name is uppercase, VALUE is all lowercase
                 VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a97ee0801475..08a7d313538a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -438,20 +438,20 @@ static unsigned long __init init_range_memory_mapping(
 static unsigned long __init get_new_step_size(unsigned long step_size)
 {
         /*
-         * Explain why we shift by 5 and why we don't have to worry about
-         * 'step_size << 5' overflowing:
-         *
-         * initial mapped size is PMD_SIZE (2M).
+         * Initial mapped size is PMD_SIZE (2M).
          * We can not set step_size to be PUD_SIZE (1G) yet.
          * In worse case, when we cross the 1G boundary, and
          * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
-         * to map 1G range with PTE. Use 5 as shift for now.
+         * to map 1G range with PTE. Hence we use one less than the
+         * difference of page table level shifts.
          *
-         * Don't need to worry about overflow, on 32bit, when step_size
-         * is 0, round_down() returns 0 for start, and that turns it
-         * into 0x100000000ULL.
+         * Don't need to worry about overflow in the top-down case, on 32bit,
+         * when step_size is 0, round_down() returns 0 for start, and that
+         * turns it into 0x100000000ULL.
+         * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+         * needs to be taken into consideration by the code below.
          */
-        return step_size << 5;
+        return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
 }
 
 /**
@@ -471,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start,
         unsigned long step_size;
         unsigned long addr;
         unsigned long mapped_ram_size = 0;
-        unsigned long new_mapped_ram_size;
 
         /* xen has big range in reserved near end of ram, skip it at first.*/
         addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
@@ -496,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start,
                                 start = map_start;
                 } else
                         start = map_start;
-                new_mapped_ram_size = init_range_memory_mapping(start,
+                mapped_ram_size += init_range_memory_mapping(start,
                                                         last_start);
                 last_start = start;
                 min_pfn_mapped = last_start >> PAGE_SHIFT;
-                /* only increase step_size after big range get mapped */
-                if (new_mapped_ram_size > mapped_ram_size)
+                if (mapped_ram_size >= step_size)
                         step_size = get_new_step_size(step_size);
-                mapped_ram_size += new_mapped_ram_size;
         }
 
         if (real_end < map_end)
@@ -524,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start,
 static void __init memory_map_bottom_up(unsigned long map_start,
                                         unsigned long map_end)
 {
-        unsigned long next, new_mapped_ram_size, start;
+        unsigned long next, start;
         unsigned long mapped_ram_size = 0;
         /* step_size need to be small so pgt_buf from BRK could cover it */
         unsigned long step_size = PMD_SIZE;
@@ -539,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start,
          * for page table.
          */
         while (start < map_end) {
-                if (map_end - start > step_size) {
+                if (step_size && map_end - start > step_size) {
                         next = round_up(start + 1, step_size);
                         if (next > map_end)
                                 next = map_end;
-                } else
+                } else {
                         next = map_end;
+                }
 
-                new_mapped_ram_size = init_range_memory_mapping(start, next);
+                mapped_ram_size += init_range_memory_mapping(start, next);
                 start = next;
 
-                if (new_mapped_ram_size > mapped_ram_size)
+                if (mapped_ram_size >= step_size)
                         step_size = get_new_step_size(step_size);
-                mapped_ram_size += new_mapped_ram_size;
         }
 }
 
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 009495b9ab4b..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -41,12 +41,17 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits.
-
-   Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 #ifdef CONFIG_X86_32
@@ -54,22 +59,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #else
         unsigned long addr, end;
         unsigned offset;
-        end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+        /*
+         * Round up the start address.  It can start out unaligned as a result
+         * of stack start randomization.
+         */
+        start = PAGE_ALIGN(start);
+
+        /* Round the lowest possible end address up to a PMD boundary. */
+        end = (start + len + PMD_SIZE - 1) & PMD_MASK;
         if (end >= TASK_SIZE_MAX)
                 end = TASK_SIZE_MAX;
         end -= len;
-        /* This loses some more bits than a modulo, but is cheaper */
-        offset = get_random_int() & (PTRS_PER_PTE - 1);
-        addr = start + (offset << PAGE_SHIFT);
-        if (addr >= end)
-                addr = end;
+
+        if (end > start) {
+                offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+                addr = start + (offset << PAGE_SHIFT);
+        } else {
+                addr = start;
+        }
 
         /*
-         * page-align it here so that get_unmapped_area doesn't
-         * align it wrongfully again to the next page. addr can come in 4K
-         * unaligned here as a result of stack start randomization.
+         * Forcibly align the final address in case we have a hardware
+         * issue that requires alignment for performance reasons.
          */
-        addr = PAGE_ALIGN(addr);
         addr = align_vdso_addr(addr);
 
         return addr;