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

Pull x86 mm updates from Ingo Molnar:
 "Various x86 low level modifications:

   - preparatory work to support virtually mapped kernel stacks (Andy
     Lutomirski)

   - support for 64-bit __get_user() on 32-bit kernels (Benjamin
     LaHaise)

   - (involved) workaround for Knights Landing CPU erratum (Dave Hansen)

   - MPX enhancements (Dave Hansen)

   - mremap() extension to allow remapping of the special VDSO vma, for
     purposes of user level context save/restore (Dmitry Safonov)

   - hweight and entry code cleanups (Borislav Petkov)

   - bitops code generation optimizations and cleanups with modern GCC
     (H. Peter Anvin)

   - syscall entry code optimizations (Paolo Bonzini)"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  x86/mm/cpa: Add missing comment in populate_pdg()
  x86/mm/cpa: Fix populate_pgd(): Stop trying to deallocate failed PUDs
  x86/syscalls: Add compat_sys_preadv64v2/compat_sys_pwritev64v2
  x86/smp: Remove unnecessary initialization of thread_info::cpu
  x86/smp: Remove stack_smp_processor_id()
  x86/uaccess: Move thread_info::addr_limit to thread_struct
  x86/dumpstack: Rename thread_struct::sig_on_uaccess_error to sig_on_uaccess_err
  x86/uaccess: Move thread_info::uaccess_err and thread_info::sig_on_uaccess_err to thread_struct
  x86/dumpstack: When OOPSing, rewind the stack before do_exit()
  x86/mm/64: In vmalloc_fault(), use CR3 instead of current->active_mm
  x86/dumpstack/64: Handle faults when printing the "Stack: " part of an OOPS
  x86/dumpstack: Try harder to get a call trace on stack overflow
  x86/mm: Remove kernel_unmap_pages_in_pgd() and efi_cleanup_page_tables()
  x86/mm/cpa: In populate_pgd(), don't set the PGD entry until it's populated
  x86/mm/hotplug: Don't remove PGD entries in remove_pagetable()
  x86/mm: Use pte_none() to test for empty PTE
  x86/mm: Disallow running with 32-bit PTEs to work around erratum
  x86/mm: Ignore A/D bits in pte/pmd/pud_none()
  x86/mm: Move swap offset/type up in PTE to work around erratum
  x86/entry: Inline enter_from_user_mode()
  ...

7 files changed, 53 insertions, 12 deletions

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 878e4b9940d9..0d41d68131cc 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -16,14 +16,16 @@
 #define BOOT_BITOPS_H
 #define _LINUX_BITOPS_H         /* Inhibit inclusion of <linux/bitops.h> */
 
-static inline int constant_test_bit(int nr, const void *addr)
+#include <linux/types.h>
+
+static inline bool constant_test_bit(int nr, const void *addr)
 {
         const u32 *p = (const u32 *)addr;
         return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0;
 }
-static inline int variable_test_bit(int nr, const void *addr)
+static inline bool variable_test_bit(int nr, const void *addr)
 {
-        u8 v;
+        bool v;
         const u32 *p = (const u32 *)addr;
 
         asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9011a88353de..e5612f3e3b57 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/edd.h>
 #include <asm/setup.h>
+#include <asm/asm.h>
 #include "bitops.h"
 #include "ctype.h"
 #include "cpuflags.h"
@@ -176,18 +177,18 @@ static inline void wrgs32(u32 v, addr_t addr)
 }
 
 /* Note: these only return true/false, not a signed return value! */
-static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
-        u8 diff;
-        asm volatile("fs; repe; cmpsb; setnz %0"
-                     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+        bool diff;
+        asm volatile("fs; repe; cmpsb" CC_SET(nz)
+                     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
         return diff;
 }
-static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
-        u8 diff;
-        asm volatile("gs; repe; cmpsb; setnz %0"
-                     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+        bool diff;
+        asm volatile("gs; repe; cmpsb" CC_SET(nz)
+                     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
         return diff;
 }
 
@@ -294,6 +295,7 @@ static inline int cmdline_find_option_bool(const char *option)
 
 /* cpu.c, cpucheck.c */
 int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
+int check_knl_erratum(void);
 int validate_cpu(void);
 
 /* early_serial_console.c */
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 29207f69ae8c..26240dde081e 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -93,6 +93,8 @@ int validate_cpu(void)
                 show_cap_strs(err_flags);
                 putchar('\n');
                 return -1;
+        } else if (check_knl_erratum()) {
+                return -1;
         } else {
                 return 0;
         }
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 1fd7d575092e..4ad7d70e8739 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -24,6 +24,7 @@
 # include "boot.h"
 #endif
 #include <linux/types.h>
+#include <asm/intel-family.h>
 #include <asm/processor-flags.h>
 #include <asm/required-features.h>
 #include <asm/msr-index.h>
@@ -175,6 +176,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
                         puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
                 }
         }
+        if (!err)
+                err = check_knl_erratum();
 
         if (err_flags_ptr)
                 *err_flags_ptr = err ? err_flags : NULL;
@@ -185,3 +188,33 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 
         return (cpu.level < req_level || err) ? -1 : 0;
 }
+
+int check_knl_erratum(void)
+{
+        /*
+         * First check for the affected model/family:
+         */
+        if (!is_intel() ||
+            cpu.family != 6 ||
+            cpu.model != INTEL_FAM6_XEON_PHI_KNL)
+                return 0;
+
+        /*
+         * This erratum affects the Accessed/Dirty bits, and can
+         * cause stray bits to be set in !Present PTEs.  We have
+         * enough bits in our 64-bit PTEs (which we have on real
+         * 64-bit mode or PAE) to avoid using these troublesome
+         * bits.  But, we do not have enough space in our 32-bit
+         * PTEs.  So, refuse to run on 32-bit non-PAE kernels.
+         */
+        if (IS_ENABLED(CONFIG_X86_64) || IS_ENABLED(CONFIG_X86_PAE))
+                return 0;
+
+        puts("This 32-bit kernel can not run on this Xeon Phi x200\n"
+             "processor due to a processor erratum.  Use a 64-bit\n"
+             "kernel, or enable PAE in this 32-bit kernel.\n\n");
+
+        return -1;
+}
+
+
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index 431fa5f84537..6687ab953257 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -102,6 +102,7 @@ void get_cpuflags(void)
                         cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
                               &cpu.flags[0]);
                         cpu.level = (tfms >> 8) & 15;
+                        cpu.family = cpu.level;
                         cpu.model = (tfms >> 4) & 15;
                         if (cpu.level >= 6)
                                 cpu.model += ((tfms >> 16) & 0xf) << 4;
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 4cb404fd45ce..15ad56a3f905 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -6,6 +6,7 @@
 
 struct cpu_features {
         int level;              /* Family, or 64 for x86-64 */
+        int family;             /* Family, always */
         int model;
         u32 flags[NCAPINTS];
 };
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b8465d302..cc3bd583dce1 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -17,7 +17,7 @@
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {
-        u8 diff;
+        bool diff;
         asm("repe; cmpsb; setnz %0"
             : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
         return diff;