[GIT pull] x86/pti updates for 4.16

From: Thomas Gleixner
Date: Sun Mar 11 2018 - 12:26:26 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

Yet another pile of melted spectrum related updates:

- Drop native vsyscall support finally as it causes more trouble than
benefit.

- Make microcode loading more robust. There were a few issues especially
related to late loading which are new surfacing because late loading of
the IB* microcodes addressing spectre issues has become more widely used.

- Simplfy and robistify the syscall handling in the entry code

- Prevent kprobes on the entry trampoline code which lead to kernel
crashes when the probe hits before CR3 is updated

- Don't check microcode versions when running on hypervisors as they are
considered as lying anyway.

- Fix the 32bit objtool build and a coment typo


Thanks,

tglx

------------------>
Andy Lutomirski (1):
x86/vsyscall/64: Drop "native" vsyscalls

Ashok Raj (4):
x86/microcode/intel: Check microcode revision before updating sibling threads
x86/microcode/intel: Writeback and invalidate caches before updating microcode
x86/microcode: Do not upload microcode if CPUs are offline
x86/microcode: Synchronize late microcode loading

Borislav Petkov (3):
x86/microcode: Get rid of struct apply_microcode_ctx
x86/microcode/intel: Look into the patch cache first
x86/microcode: Request microcode on the BSP

Dominik Brodowski (6):
x86/syscalls/32: Simplify $entry == $compat entries
x86/entry: Remove stale syscall prototype
x86/syscalls: Use proper syscall definition for sys_ioperm()
x86/syscalls: Use COMPAT_SYSCALL_DEFINEx() macros for x86-only compat syscalls
x86/entry: Do not special-case clone(2) in compat entry
x86/entry/64/compat: Save one instruction in entry_INT80_compat()

Francis Deslauriers (1):
x86/kprobes: Fix kernel crash when probing .entry_trampoline code

Josh Poimboeuf (1):
objtool: Fix 32-bit build

Konrad Rzeszutek Wilk (1):
x86/spectre_v2: Don't check microcode versions when running under hypervisors

Seunghun Han (1):
x86/pti: Fix a comment typo


arch/x86/Kconfig | 11 +-
arch/x86/entry/entry_64_compat.S | 16 +--
arch/x86/entry/syscalls/syscall_32.tbl | 38 +++----
arch/x86/entry/vsyscall/vsyscall_64.c | 16 +--
arch/x86/ia32/sys_ia32.c | 74 +++++++------
arch/x86/include/asm/pgtable_types.h | 2 -
arch/x86/include/asm/sections.h | 1 +
arch/x86/include/asm/sys_ia32.h | 48 +++++----
arch/x86/kernel/cpu/intel.c | 7 ++
arch/x86/kernel/cpu/microcode/core.c | 158 +++++++++++++++++++++-------
arch/x86/kernel/cpu/microcode/intel.c | 48 +++++++--
arch/x86/kernel/ioport.c | 2 +-
arch/x86/kernel/kprobes/core.c | 10 +-
arch/x86/kernel/vmlinux.lds.S | 2 +
arch/x86/mm/pti.c | 2 +-
tools/objtool/check.c | 27 ++---
tools/testing/selftests/x86/test_vsyscall.c | 11 +-
17 files changed, 291 insertions(+), 182 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1aed6c0e413..09c599e0900d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2266,7 +2266,7 @@ choice
it can be used to assist security vulnerability exploitation.

This setting can be changed at boot time via the kernel command
- line parameter vsyscall=[native|emulate|none].
+ line parameter vsyscall=[emulate|none].

On a system with recent enough glibc (2.14 or newer) and no
static binaries, you can say None without a performance penalty
@@ -2274,15 +2274,6 @@ choice

If unsure, select "Emulate".

- config LEGACY_VSYSCALL_NATIVE
- bool "Native"
- help
- Actual executable code is located in the fixed vsyscall
- address mapping, implementing time() efficiently. Since
- this makes the mapping executable, it can be used during
- security vulnerability exploitation (traditionally as
- ROP gadgets). This configuration is not recommended.
-
config LEGACY_VSYSCALL_EMULATE
bool "Emulate"
help
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index e811dd9c5e99..08425c42f8b7 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -363,9 +363,7 @@ ENTRY(entry_INT80_compat)
pushq 2*8(%rdi) /* regs->ip */
pushq 1*8(%rdi) /* regs->orig_ax */

- movq (%rdi), %rdi /* restore %rdi */
-
- pushq %rdi /* pt_regs->di */
+ pushq (%rdi) /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
@@ -406,15 +404,3 @@ ENTRY(entry_INT80_compat)
TRACE_IRQS_ON
jmp swapgs_restore_regs_and_return_to_usermode
END(entry_INT80_compat)
-
-ENTRY(stub32_clone)
- /*
- * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
- * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
- *
- * The native 64-bit kernel's sys_clone() implements the latter,
- * so we need to swap arguments here before calling it:
- */
- xchg %r8, %rcx
- jmp sys_clone
-ENDPROC(stub32_clone)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 448ac2161112..2a5e99cff859 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -8,12 +8,12 @@
#
0 i386 restart_syscall sys_restart_syscall
1 i386 exit sys_exit
-2 i386 fork sys_fork sys_fork
+2 i386 fork sys_fork
3 i386 read sys_read
4 i386 write sys_write
5 i386 open sys_open compat_sys_open
6 i386 close sys_close
-7 i386 waitpid sys_waitpid sys32_waitpid
+7 i386 waitpid sys_waitpid compat_sys_x86_waitpid
8 i386 creat sys_creat
9 i386 link sys_link
10 i386 unlink sys_unlink
@@ -78,7 +78,7 @@
69 i386 ssetmask sys_ssetmask
70 i386 setreuid sys_setreuid16
71 i386 setregid sys_setregid16
-72 i386 sigsuspend sys_sigsuspend sys_sigsuspend
+72 i386 sigsuspend sys_sigsuspend
73 i386 sigpending sys_sigpending compat_sys_sigpending
74 i386 sethostname sys_sethostname
75 i386 setrlimit sys_setrlimit compat_sys_setrlimit
@@ -96,7 +96,7 @@
87 i386 swapon sys_swapon
88 i386 reboot sys_reboot
89 i386 readdir sys_old_readdir compat_sys_old_readdir
-90 i386 mmap sys_old_mmap sys32_mmap
+90 i386 mmap sys_old_mmap compat_sys_x86_mmap
91 i386 munmap sys_munmap
92 i386 truncate sys_truncate compat_sys_truncate
93 i386 ftruncate sys_ftruncate compat_sys_ftruncate
@@ -126,7 +126,7 @@
117 i386 ipc sys_ipc compat_sys_ipc
118 i386 fsync sys_fsync
119 i386 sigreturn sys_sigreturn sys32_sigreturn
-120 i386 clone sys_clone stub32_clone
+120 i386 clone sys_clone compat_sys_x86_clone
121 i386 setdomainname sys_setdomainname
122 i386 uname sys_newuname
123 i386 modify_ldt sys_modify_ldt
@@ -186,8 +186,8 @@
177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
179 i386 rt_sigsuspend sys_rt_sigsuspend
-180 i386 pread64 sys_pread64 sys32_pread
-181 i386 pwrite64 sys_pwrite64 sys32_pwrite
+180 i386 pread64 sys_pread64 compat_sys_x86_pread
+181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite
182 i386 chown sys_chown16
183 i386 getcwd sys_getcwd
184 i386 capget sys_capget
@@ -196,14 +196,14 @@
187 i386 sendfile sys_sendfile compat_sys_sendfile
188 i386 getpmsg
189 i386 putpmsg
-190 i386 vfork sys_vfork sys_vfork
+190 i386 vfork sys_vfork
191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
192 i386 mmap2 sys_mmap_pgoff
-193 i386 truncate64 sys_truncate64 sys32_truncate64
-194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64
-195 i386 stat64 sys_stat64 sys32_stat64
-196 i386 lstat64 sys_lstat64 sys32_lstat64
-197 i386 fstat64 sys_fstat64 sys32_fstat64
+193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64
+194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64
+195 i386 stat64 sys_stat64 compat_sys_x86_stat64
+196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64
+197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64
198 i386 lchown32 sys_lchown
199 i386 getuid32 sys_getuid
200 i386 getgid32 sys_getgid
@@ -231,7 +231,7 @@
# 222 is unused
# 223 is unused
224 i386 gettid sys_gettid
-225 i386 readahead sys_readahead sys32_readahead
+225 i386 readahead sys_readahead compat_sys_x86_readahead
226 i386 setxattr sys_setxattr
227 i386 lsetxattr sys_lsetxattr
228 i386 fsetxattr sys_fsetxattr
@@ -256,7 +256,7 @@
247 i386 io_getevents sys_io_getevents compat_sys_io_getevents
248 i386 io_submit sys_io_submit compat_sys_io_submit
249 i386 io_cancel sys_io_cancel
-250 i386 fadvise64 sys_fadvise64 sys32_fadvise64
+250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64
# 251 is available for reuse (was briefly sys_set_zone_reclaim)
252 i386 exit_group sys_exit_group
253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
@@ -278,7 +278,7 @@
269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
270 i386 tgkill sys_tgkill
271 i386 utimes sys_utimes compat_sys_utimes
-272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64
+272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64
273 i386 vserver
274 i386 mbind sys_mbind
275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
@@ -306,7 +306,7 @@
297 i386 mknodat sys_mknodat
298 i386 fchownat sys_fchownat
299 i386 futimesat sys_futimesat compat_sys_futimesat
-300 i386 fstatat64 sys_fstatat64 sys32_fstatat
+300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat
301 i386 unlinkat sys_unlinkat
302 i386 renameat sys_renameat
303 i386 linkat sys_linkat
@@ -320,7 +320,7 @@
311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list
312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list
313 i386 splice sys_splice
-314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range
+314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range
315 i386 tee sys_tee
316 i386 vmsplice sys_vmsplice compat_sys_vmsplice
317 i386 move_pages sys_move_pages compat_sys_move_pages
@@ -330,7 +330,7 @@
321 i386 signalfd sys_signalfd compat_sys_signalfd
322 i386 timerfd_create sys_timerfd_create
323 i386 eventfd sys_eventfd
-324 i386 fallocate sys_fallocate sys32_fallocate
+324 i386 fallocate sys_fallocate compat_sys_x86_fallocate
325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 577fa8adb785..8560ef68a9d6 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -42,10 +42,8 @@
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"

-static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
-#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
- NATIVE;
-#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+static enum { EMULATE, NONE } vsyscall_mode =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
NONE;
#else
EMULATE;
@@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str)
if (str) {
if (!strcmp("emulate", str))
vsyscall_mode = EMULATE;
- else if (!strcmp("native", str))
- vsyscall_mode = NATIVE;
else if (!strcmp("none", str))
vsyscall_mode = NONE;
else
@@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)

WARN_ON_ONCE(address != regs->ip);

- /* This should be unreachable in NATIVE mode. */
- if (WARN_ON(vsyscall_mode == NATIVE))
- return false;
-
if (vsyscall_mode == NONE) {
warn_bad_vsyscall(KERN_INFO, regs,
"vsyscall attempted with vsyscall=none");
@@ -370,9 +362,7 @@ void __init map_vsyscall(void)

if (vsyscall_mode != NONE) {
__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
- vsyscall_mode == NATIVE
- ? PAGE_KERNEL_VSYSCALL
- : PAGE_KERNEL_VVAR);
+ PAGE_KERNEL_VVAR);
set_vsyscall_pgtable_user_bits(swapper_pg_dir);
}

diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 96cd33bbfc85..6512498bbef6 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -51,15 +51,14 @@
#define AA(__x) ((unsigned long)(__x))


-asmlinkage long sys32_truncate64(const char __user *filename,
- unsigned long offset_low,
- unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename,
+ unsigned long, offset_low, unsigned long, offset_high)
{
return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
}

-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
- unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd,
+ unsigned long, offset_low, unsigned long, offset_high)
{
return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
}
@@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
return 0;
}

-asmlinkage long sys32_stat64(const char __user *filename,
- struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename,
+ struct stat64 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_stat(filename, &stat);
@@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename,
return ret;
}

-asmlinkage long sys32_lstat64(const char __user *filename,
- struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename,
+ struct stat64 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_lstat(filename, &stat);
@@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename,
return ret;
}

-asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd,
+ struct stat64 __user *, statbuf)
{
struct kstat stat;
int ret = vfs_fstat(fd, &stat);
@@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
return ret;
}

-asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename,
- struct stat64 __user *statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd,
+ const char __user *, filename,
+ struct stat64 __user *, statbuf, int, flag)
{
struct kstat stat;
int error;
@@ -153,7 +154,7 @@ struct mmap_arg_struct32 {
unsigned int offset;
};

-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
+COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg)
{
struct mmap_arg_struct32 a;

@@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
a.offset>>PAGE_SHIFT);
}

-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr,
- int options)
+COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *,
+ stat_addr, int, options)
{
return compat_sys_wait4(pid, stat_addr, options, NULL);
}

/* warning: next two assume little endian */
-asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
- u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf,
+ u32, count, u32, poslo, u32, poshi)
{
return sys_pread64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
}

-asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
- u32 count, u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf,
+ u32, count, u32, poslo, u32, poshi)
{
return sys_pwrite64(fd, ubuf, count,
((loff_t)AA(poshi) << 32) | AA(poslo));
@@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
* Some system calls that need sign extended arguments. This could be
* done by a generic wrapper.
*/
-long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
- __u32 len_low, __u32 len_high, int advice)
+COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low,
+ __u32, offset_high, __u32, len_low, __u32, len_high,
+ int, advice)
{
return sys_fadvise64_64(fd,
(((u64)offset_high)<<32) | offset_low,
@@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
advice);
}

-asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
- size_t count)
+COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo,
+ unsigned int, off_hi, size_t, count)
{
return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
}

-asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
- unsigned n_low, unsigned n_hi, int flags)
+COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low,
+ unsigned int, off_hi, unsigned int, n_low,
+ unsigned int, n_hi, int, flags)
{
return sys_sync_file_range(fd,
((u64)off_hi << 32) | off_low,
((u64)n_hi << 32) | n_low, flags);
}

-asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
- size_t len, int advice)
+COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo,
+ unsigned int, offset_hi, size_t, len, int, advice)
{
return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
len, advice);
}

-asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
- unsigned offset_hi, unsigned len_lo,
- unsigned len_hi)
+COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode,
+ unsigned int, offset_lo, unsigned int, offset_hi,
+ unsigned int, len_lo, unsigned int, len_hi)
{
return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
((u64)len_hi << 32) | len_lo);
}
+
+/*
+ * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS
+ */
+COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
+ unsigned long, newsp, int __user *, parent_tidptr,
+ unsigned long, tls_val, int __user *, child_tidptr)
+{
+ return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr,
+ tls_val);
+}
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 246f15b4e64c..acfe755562a6 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -174,7 +174,6 @@ enum page_cache_mode {
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE)
-#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER)
#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
@@ -206,7 +205,6 @@ enum page_cache_mode {
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC)
#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)

#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO)
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index d6baf23782bc..5c019d23d06b 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[];

#if defined(CONFIG_X86_64)
extern char __end_rodata_hpage_align[];
+extern char __entry_trampoline_start[], __entry_trampoline_end[];
#endif

#endif /* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 82c34ee25a65..906794aa034e 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -20,31 +20,43 @@
#include <asm/ia32.h>

/* ia32/sys_ia32.c */
-asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long);
-asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long);
+asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long,
+ unsigned long);
+asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long,
+ unsigned long);

-asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long sys32_fstatat(unsigned int, const char __user *,
+asmlinkage long compat_sys_x86_stat64(const char __user *,
+ struct stat64 __user *);
+asmlinkage long compat_sys_x86_lstat64(const char __user *,
+ struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *,
struct stat64 __user *, int);
struct mmap_arg_struct32;
-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *);
+asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *);

-asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int);
+asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *,
+ int);

-asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32);
-asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
+asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32,
+ u32);
+asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32,
+ u32, u32);

-long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int);
-long sys32_vm86_warning(void);
+asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32,
+ int);

-asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t);
-asmlinkage long sys32_sync_file_range(int, unsigned, unsigned,
- unsigned, unsigned, int);
-asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int);
-asmlinkage long sys32_fallocate(int, int, unsigned,
- unsigned, unsigned, unsigned);
+asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int,
+ size_t);
+asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int,
+ unsigned int, unsigned int,
+ int);
+asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int,
+ size_t, int);
+asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int,
+ unsigned int, unsigned int);
+asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *,
+ unsigned long, int __user *);

/* ia32/ia32_signal.c */
asmlinkage long sys32_sigreturn(void);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d19e903214b4..4aa9fd379390 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
{
int i;

+ /*
+ * We know that the hypervisor lie to us on the microcode version so
+ * we may as well hope that it is running the correct version.
+ */
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return false;
+
for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
if (c->x86_model == spectre_bad_microcodes[i].model &&
c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index aa1b9a422f2b..70ecbc8099c9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
#define pr_fmt(fmt) "microcode: " fmt

#include <linux/platform_device.h>
+#include <linux/stop_machine.h>
#include <linux/syscore_ops.h>
#include <linux/miscdevice.h>
#include <linux/capability.h>
#include <linux/firmware.h>
#include <linux/kernel.h>
+#include <linux/delay.h>
#include <linux/mutex.h>
#include <linux/cpu.h>
+#include <linux/nmi.h>
#include <linux/fs.h>
#include <linux/mm.h>

@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
*/
static DEFINE_MUTEX(microcode_mutex);

+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];

struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
return ret;
}

-struct apply_microcode_ctx {
- enum ucode_state err;
-};
-
static void apply_microcode_local(void *arg)
{
- struct apply_microcode_ctx *ctx = arg;
+ enum ucode_state *err = arg;

- ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+ *err = microcode_ops->apply_microcode(smp_processor_id());
}

static int apply_microcode_on_target(int cpu)
{
- struct apply_microcode_ctx ctx = { .err = 0 };
+ enum ucode_state err;
int ret;

- ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
- if (!ret)
- ret = ctx.err;
-
+ ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+ if (!ret) {
+ if (err == UCODE_ERROR)
+ ret = 1;
+ }
return ret;
}

@@ -489,19 +494,100 @@ static void __exit microcode_dev_exit(void)
/* fake device for request_firmware */
static struct platform_device *microcode_pdev;

-static enum ucode_state reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ * is loading microcode in order to avoid any negative interactions caused by
+ * the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ * requirement can be relaxed in the future. Right now, this is conservative
+ * and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- enum ucode_state ustate;
+ if (num_online_cpus() == num_present_cpus())
+ return 0;

- if (!uci->valid)
- return UCODE_OK;
+ pr_err("Not all CPUs online, aborting microcode update.\n");
+
+ return -EINVAL;
+}
+
+static atomic_t late_cpus;
+
+/*
+ * Returns:
+ * < 0 - on error
+ * 0 - no update done
+ * 1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+ unsigned int timeout = NSEC_PER_SEC;
+ int all_cpus = num_online_cpus();
+ int cpu = smp_processor_id();
+ enum ucode_state err;
+ int ret = 0;
+
+ atomic_dec(&late_cpus);
+
+ /*
+ * Wait for all CPUs to arrive. A load will not be attempted unless all
+ * CPUs show up.
+ * */
+ while (atomic_read(&late_cpus)) {
+ if (timeout < SPINUNIT) {
+ pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+ atomic_read(&late_cpus));
+ return -1;
+ }

- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
- if (ustate != UCODE_OK)
- return ustate;
+ ndelay(SPINUNIT);
+ timeout -= SPINUNIT;

- return apply_microcode_on_target(cpu);
+ touch_nmi_watchdog();
+ }
+
+ spin_lock(&update_lock);
+ apply_microcode_local(&err);
+ spin_unlock(&update_lock);
+
+ if (err > UCODE_NFOUND) {
+ pr_warn("Error reloading microcode on CPU %d\n", cpu);
+ ret = -1;
+ } else if (err == UCODE_UPDATED) {
+ ret = 1;
+ }
+
+ atomic_inc(&late_cpus);
+
+ while (atomic_read(&late_cpus) != all_cpus)
+ cpu_relax();
+
+ return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+ int ret;
+
+ atomic_set(&late_cpus, num_online_cpus());
+
+ ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+ if (ret < 0)
+ return ret;
+ else if (ret > 0)
+ microcode_check();
+
+ return ret;
}

static ssize_t reload_store(struct device *dev,
@@ -509,10 +595,9 @@ static ssize_t reload_store(struct device *dev,
const char *buf, size_t size)
{
enum ucode_state tmp_ret = UCODE_OK;
- bool do_callback = false;
+ int bsp = boot_cpu_data.cpu_index;
unsigned long val;
ssize_t ret = 0;
- int cpu;

ret = kstrtoul(buf, 0, &val);
if (ret)
@@ -521,29 +606,24 @@ static ssize_t reload_store(struct device *dev,
if (val != 1)
return size;

- get_online_cpus();
- mutex_lock(&microcode_mutex);
- for_each_online_cpu(cpu) {
- tmp_ret = reload_for_cpu(cpu);
- if (tmp_ret > UCODE_NFOUND) {
- pr_warn("Error reloading microcode on CPU %d\n", cpu);
-
- /* set retval for the first encountered reload error */
- if (!ret)
- ret = -EINVAL;
- }
+ tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+ if (tmp_ret != UCODE_OK)
+ return size;

- if (tmp_ret == UCODE_UPDATED)
- do_callback = true;
- }
+ get_online_cpus();

- if (!ret && do_callback)
- microcode_check();
+ ret = check_online_cpus();
+ if (ret)
+ goto put;

+ mutex_lock(&microcode_mutex);
+ ret = microcode_reload_late();
mutex_unlock(&microcode_mutex);
+
+put:
put_online_cpus();

- if (!ret)
+ if (ret >= 0)
ret = size;

return ret;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 923054a6b760..2aded9db1d42 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
if (!mc)
return 0;

+ /*
+ * Save us the MSR write below - which is a particular expensive
+ * operation - when the other hyperthread has updated the microcode
+ * already.
+ */
+ rev = intel_get_microcode_revision();
+ if (rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = rev;
+ return UCODE_OK;
+ }
+
+ /*
+ * Writeback and invalidate caches before updating microcode to avoid
+ * internal issues depending on what the microcode is updating.
+ */
+ native_wbinvd();
+
/* write microcode via MSR 0x79 */
native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);

@@ -774,9 +791,9 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)

static enum ucode_state apply_microcode_intel(int cpu)
{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
struct microcode_intel *mc;
- struct ucode_cpu_info *uci;
- struct cpuinfo_x86 *c;
static int prev_rev;
u32 rev;

@@ -784,15 +801,32 @@ static enum ucode_state apply_microcode_intel(int cpu)
if (WARN_ON(raw_smp_processor_id() != cpu))
return UCODE_ERROR;

- uci = ucode_cpu_info + cpu;
- mc = uci->mc;
+ /* Look for a newer patch in our cache: */
+ mc = find_patch(uci);
if (!mc) {
- /* Look for a newer patch in our cache: */
- mc = find_patch(uci);
+ mc = uci->mc;
if (!mc)
return UCODE_NFOUND;
}

+ /*
+ * Save us the MSR write below - which is a particular expensive
+ * operation - when the other hyperthread has updated the microcode
+ * already.
+ */
+ rev = intel_get_microcode_revision();
+ if (rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = rev;
+ c->microcode = rev;
+ return UCODE_OK;
+ }
+
+ /*
+ * Writeback and invalidate caches before updating microcode to avoid
+ * internal issues depending on what the microcode is updating.
+ */
+ native_wbinvd();
+
/* write microcode via MSR 0x79 */
wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);

@@ -813,8 +847,6 @@ static enum ucode_state apply_microcode_intel(int cpu)
prev_rev = rev;
}

- c = &cpu_data(cpu);
-
uci->cpu_sig.rev = rev;
c->microcode = rev;

diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 2f723301eb58..38deafebb21b 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
/*
* this changes the io permissions bitmap in the current task.
*/
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
{
struct thread_struct *t = &current->thread;
struct tss_struct *tss;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd36f3c33cd0..0715f827607c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);

bool arch_within_kprobe_blacklist(unsigned long addr)
{
+ bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+ is_in_entry_trampoline_section =
+ (addr >= (unsigned long)__entry_trampoline_start &&
+ addr < (unsigned long)__entry_trampoline_end);
+#endif
return (addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end) ||
(addr >= (unsigned long)__entry_text_start &&
- addr < (unsigned long)__entry_text_end);
+ addr < (unsigned long)__entry_text_end) ||
+ is_in_entry_trampoline_section;
}

int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9b138a06c1a4..b854ebf5851b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS

#ifdef CONFIG_X86_64
. = ALIGN(PAGE_SIZE);
+ VMLINUX_SYMBOL(__entry_trampoline_start) = .;
_entry_trampoline = .;
*(.entry_trampoline)
. = ALIGN(PAGE_SIZE);
+ VMLINUX_SYMBOL(__entry_trampoline_end) = .;
ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
#endif

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index ce38f165489b..631507f0c198 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void)
}

/*
- * Clone the ESPFIX P4D into the user space visinble page table
+ * Clone the ESPFIX P4D into the user space visible page table
*/
static void __init pti_setup_espfix64(void)
{
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 46c1d239cc1b..92b6a2c21631 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1116,42 +1116,29 @@ static int read_unwind_hints(struct objtool_file *file)

static int read_retpoline_hints(struct objtool_file *file)
{
- struct section *sec, *relasec;
+ struct section *sec;
struct instruction *insn;
struct rela *rela;
- int i;

- sec = find_section_by_name(file->elf, ".discard.retpoline_safe");
+ sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe");
if (!sec)
return 0;

- relasec = sec->rela;
- if (!relasec) {
- WARN("missing .rela.discard.retpoline_safe section");
- return -1;
- }
-
- if (sec->len % sizeof(unsigned long)) {
- WARN("retpoline_safe size mismatch: %d %ld", sec->len, sizeof(unsigned long));
- return -1;
- }
-
- for (i = 0; i < sec->len / sizeof(unsigned long); i++) {
- rela = find_rela_by_dest(sec, i * sizeof(unsigned long));
- if (!rela) {
- WARN("can't find rela for retpoline_safe[%d]", i);
+ list_for_each_entry(rela, &sec->rela_list, list) {
+ if (rela->sym->type != STT_SECTION) {
+ WARN("unexpected relocation symbol type in %s", sec->name);
return -1;
}

insn = find_insn(file, rela->sym->sec, rela->addend);
if (!insn) {
- WARN("can't find insn for retpoline_safe[%d]", i);
+ WARN("bad .discard.retpoline_safe entry");
return -1;
}

if (insn->type != INSN_JUMP_DYNAMIC &&
insn->type != INSN_CALL_DYNAMIC) {
- WARN_FUNC("retpoline_safe hint not a indirect jump/call",
+ WARN_FUNC("retpoline_safe hint not an indirect jump/call",
insn->sec, insn->offset);
return -1;
}
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index be81621446f0..0b4f1cc2291c 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
num_vsyscall_traps++;
}

-static int test_native_vsyscall(void)
+static int test_emulation(void)
{
time_t tmp;
bool is_native;
@@ -458,7 +458,7 @@ static int test_native_vsyscall(void)
if (!vtime)
return 0;

- printf("[RUN]\tchecking for native vsyscall\n");
+ printf("[RUN]\tchecking that vsyscalls are emulated\n");
sethandler(SIGTRAP, sigtrap, 0);
set_eflags(get_eflags() | X86_EFLAGS_TF);
vtime(&tmp);
@@ -474,11 +474,12 @@ static int test_native_vsyscall(void)
*/
is_native = (num_vsyscall_traps > 1);

- printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+ printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+ (is_native ? "FAIL" : "OK"),
(is_native ? "native" : "emulated"),
(int)num_vsyscall_traps);

- return 0;
+ return is_native;
}
#endif

@@ -498,7 +499,7 @@ int main(int argc, char **argv)
nerrs += test_vsys_r();

#ifdef __x86_64__
- nerrs += test_native_vsyscall();
+ nerrs += test_emulation();
#endif

return nerrs ? 1 : 0;