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: a binutils fix, an lguest fix, an mcelog fix and a missing
  documentation fix"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Avoid using object after free in genpool
  lguest, x86/entry/32: Fix handling of guest syscalls using interrupt gates
  x86/build: Build compressed x86 kernels as PIE
  x86/mm/pkeys: Add missing Documentation

8 files changed, 89 insertions, 5 deletions

diff --git a/Documentation/x86/protection-keys.txt b/Documentation/x86/protection-keys.txt
new file mode 100644
index 000000000000..c281ded1ba16
--- /dev/null
+++ b/Documentation/x86/protection-keys.txt
@@ -0,0 +1,27 @@
+Memory Protection Keys for Userspace (PKU aka PKEYs) is a CPU feature
+which will be found on future Intel CPUs.
+
+Memory Protection Keys provides a mechanism for enforcing page-based
+protections, but without requiring modification of the page tables
+when an application changes protection domains.  It works by
+dedicating 4 previously ignored bits in each page table entry to a
+"protection key", giving 16 possible keys.
+
+There is also a new user-accessible register (PKRU) with two separate
+bits (Access Disable and Write Disable) for each key.  Being a CPU
+register, PKRU is inherently thread-local, potentially giving each
+thread a different set of protections from every other thread.
+
+There are two new instructions (RDPKRU/WRPKRU) for reading and writing
+to the new register.  The feature is only available in 64-bit mode,
+even though there is theoretically space in the PAE PTEs.  These
+permissions are enforced on data access only and have no effect on
+instruction fetches.
+
+=========================== Config Option ===========================
+
+This config option adds approximately 1.5kb of text. and 50 bytes of
+data to the executable.  A workload which does large O_DIRECT reads
+of holes in XFS files was run to exercise get_user_pages_fast().  No
+performance delta was observed with the config option
+enabled or disabled.
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6915ff2bd996..8774cb23064f 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -26,7 +26,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -40,6 +40,18 @@ GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
+ifeq ($(CONFIG_RELOCATABLE),y)
+# If kernel is relocatable, build compressed kernel as PIE.
+ifeq ($(CONFIG_X86_32),y)
+LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
+else
+# To build 64-bit compressed kernel as PIE, we disable relocation
+# overflow check to avoid relocation overflow error with a new linker
+# command-line option, -z noreloc-overflow.
+LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
+	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
+endif
+endif
 LDFLAGS_vmlinux := -T
 
 hostprogs-y	:= mkpiggy
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 8ef964ddc18e..0256064da8da 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -31,6 +31,34 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
+ * relocation to get the symbol address in PIC.  When the compressed x86
+ * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
+ * relocations to their fixed symbol addresses.  However, when the
+ * compressed x86 kernel is loaded at a different address, it leads
+ * to the following load failure:
+ *
+ *   Failed to allocate space for phdrs
+ *
+ * during the decompression stage.
+ *
+ * If the compressed x86 kernel is relocatable at run-time, it should be
+ * compiled with -fPIE, instead of -fPIC, if possible and should be built as
+ * Position Independent Executable (PIE) so that linker won't optimize
+ * R_386_GOT32X relocation to its fixed symbol address.  Older
+ * linkers generate R_386_32 relocations against locally defined symbols,
+ * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
+ * R_386_32 relocations when relocating the kernel.  To generate
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index b0c0d16ef58d..86558a199139 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * Locally defined symbols should be marked hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 	.code32
 ENTRY(startup_32)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 0a850100c594..2658e2af74ec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ];
 void mce_gen_pool_process(void)
 {
 	struct llist_node *head;
-	struct mce_evt_llist *node;
+	struct mce_evt_llist *node, *tmp;
 	struct mce *mce;
 
 	head = llist_del_all(&mce_event_llist);
@@ -37,7 +37,7 @@ void mce_gen_pool_process(void)
 		return;
 
 	head = llist_reverse_order(head);
-	llist_for_each_entry(node, head, llnode) {
+	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		mce = &node->mce;
 		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index eb934b0242e0..67392b6ab845 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -331,7 +331,7 @@ void set_interrupt(struct lg_cpu *cpu, unsigned int irq)
  * Actually now I think of it, it's possible that Ron *is* half the Plan 9
  * userbase.  Oh well.
  */
-static bool could_be_syscall(unsigned int num)
+bool could_be_syscall(unsigned int num)
 {
 	/* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */
 	return num == IA32_SYSCALL_VECTOR || num == syscall_vector;
@@ -416,6 +416,10 @@ bool deliver_trap(struct lg_cpu *cpu, unsigned int num)
  *
  * This routine indicates if a particular trap number could be delivered
  * directly.
+ *
+ * Unfortunately, Linux 4.6 started using an interrupt gate instead of a
+ * trap gate for syscalls, so this trick is ineffective.  See Mastery for
+ * how we could do this anyway...
  */
 static bool direct_trap(unsigned int num)
 {
diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h
index ac8ad0461e80..69b3814afd2f 100644
--- a/drivers/lguest/lg.h
+++ b/drivers/lguest/lg.h
@@ -167,6 +167,7 @@ void guest_set_clockevent(struct lg_cpu *cpu, unsigned long delta);
 bool send_notify_to_eventfd(struct lg_cpu *cpu);
 void init_clockdev(struct lg_cpu *cpu);
 bool check_syscall_vector(struct lguest *lg);
+bool could_be_syscall(unsigned int num);
 int init_interrupts(void);
 void free_interrupts(void);
 
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 6a4cd771a2be..adc162c7040d 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -429,8 +429,12 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu)
 			return;
 		break;
 	case 32 ... 255:
+		/* This might be a syscall. */
+		if (could_be_syscall(cpu->regs->trapnum))
+			break;
+
 		/*
-		 * These values mean a real interrupt occurred, in which case
+		 * Other values mean a real interrupt occurred, in which case
 		 * the Host handler has already been run. We just do a
 		 * friendly check if another process should now be run, then
 		 * return to run the Guest again.