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

…inux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of fixes for x86:

   - Fix the swapped outb() parameters in the KASLR code

   - Fix the PKEY handling at fork which missed to preserve the pkey
     state for the child. Comes with a test case to validate that.

   - Fix the entry stack handling for XEN PV to respect that XEN PV
     systems enter the function already on the current thread stack and
     not on the trampoline.

   - Fix kexec load failure caused by using a stale value when the
     kexec_buf structure is reused for subsequent allocations.

   - Fix a bogus sizeof() in the memory encryption code

   - Enforce PCI dependency for the Intel Low Power Subsystem

   - Enforce PCI_LOCKLESS_CONFIG when PCI is enabled"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/Kconfig: Select PCI_LOCKLESS_CONFIG if PCI is enabled
  x86/entry/64/compat: Fix stack switching for XEN PV
  x86/kexec: Fix a kexec_file_load() failure
  x86/mm/mem_encrypt: Fix erroneous sizeof()
  x86/selftests/pkeys: Fork() to check for state being preserved
  x86/pkeys: Properly copy pkey state at fork()
  x86/kaslr: Fix incorrect i8254 outb() parameters
  x86/intel/lpss: Make PCI dependency explicit

arch/x86/Kconfig

@@ -198,7 +198,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
-	select PCI_LOCKLESS_CONFIG
+	select PCI_LOCKLESS_CONFIG		if PCI
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB

arch/x86/entry/entry_64_compat.S

@@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat)
 
 	/* Need to switch before accessing the thread stack. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
+	/* In the Xen PV case we already run on the thread stack. */
+	ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq	6*8(%rdi)		/* regs->ss */
@@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat)
 	pushq	3*8(%rdi)		/* regs->cs */
 	pushq	2*8(%rdi)		/* regs->ip */
 	pushq	1*8(%rdi)		/* regs->orig_ax */
-
 	pushq	(%rdi)			/* pt_regs->di */
+.Lint80_keep_stack:
+
 	pushq	%rsi			/* pt_regs->si */
 	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */

arch/x86/include/asm/mmu_context.h

@@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 
 void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+/*
+ * Init a new mm.  Used on mm copies, like at fork()
+ * and on mm's that are brand-new, like at execve().
+ */
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
@@ -228,8 +232,22 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+
+	/* Duplicate the oldmm pkey state in mm: */
+	mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+	mm->context.execute_only_pkey   = oldmm->context.execute_only_pkey;
+#endif
+}
+
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
+	arch_dup_pkeys(oldmm, mm);
 	paravirt_arch_dup_mmap(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }

arch/x86/kernel/crash.c

@@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image)
 
 	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret) {
 		vfree((void *)image->arch.elf_headers);

arch/x86/kernel/kexec-bzimage64.c

@@ -434,6 +434,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
 	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out_free_params;
@@ -448,6 +449,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out_free_params;

arch/x86/lib/kaslr.c

@@ -36,8 +36,8 @@ static inline u16 i8254(void)
 	u16 status, timer;
 
 	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+		     I8254_PORT_CONTROL);
 		status = inb(I8254_PORT_COUNTER0);
 		timer  = inb(I8254_PORT_COUNTER0);
 		timer |= inb(I8254_PORT_COUNTER0) << 8;

arch/x86/mm/mem_encrypt_identity.c

@@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 	pmd = pmd_offset(pud, ppd->vaddr);
 	if (pmd_none(*pmd)) {
 		pte = ppd->pgtable_area;
-		memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
-		ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+		memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE);
+		ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE;
 		set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
 	}
 

tools/testing/selftests/x86/protection_keys.c

@@ -1133,6 +1133,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 	pkey_assert(err);
 }
 
+void become_child(void)
+{
+	pid_t forkret;
+
+	forkret = fork();
+	pkey_assert(forkret >= 0);
+	dprintf3("[%d] fork() ret: %d\n", getpid(), forkret);
+
+	if (!forkret) {
+		/* in the child */
+		return;
+	}
+	exit(0);
+}
+
 /* Assumes that all pkeys other than 'pkey' are unallocated */
 void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 {
@@ -1141,7 +1156,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	int nr_allocated_pkeys = 0;
 	int i;
 
-	for (i = 0; i < NR_PKEYS*2; i++) {
+	for (i = 0; i < NR_PKEYS*3; i++) {
 		int new_pkey;
 		dprintf1("%s() alloc loop: %d\n", __func__, i);
 		new_pkey = alloc_pkey();
@@ -1152,20 +1167,26 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 		if ((new_pkey == -1) && (errno == ENOSPC)) {
 			dprintf2("%s() failed to allocate pkey after %d tries\n",
 				__func__, nr_allocated_pkeys);
-			break;
+		} else {
+			/*
+			 * Ensure the number of successes never
+			 * exceeds the number of keys supported
+			 * in the hardware.
+			 */
+			pkey_assert(nr_allocated_pkeys < NR_PKEYS);
+			allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
 		}
-		pkey_assert(nr_allocated_pkeys < NR_PKEYS);
-		allocated_pkeys[nr_allocated_pkeys++] = new_pkey;
+
+		/*
+		 * Make sure that allocation state is properly
+		 * preserved across fork().
+		 */
+		if (i == NR_PKEYS*2)
+			become_child();
 	}
 
 	dprintf3("%s()::%d\n", __func__, __LINE__);
 
-	/*
-	 * ensure it did not reach the end of the loop without
-	 * failure:
-	 */
-	pkey_assert(i < NR_PKEYS*2);
-
 	/*
 	 * There are 16 pkeys supported in hardware.  Three are
 	 * allocated by the time we get here: