Merge branch 'kvm-ppc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

This fix was intended for 4.13, but didn't get in because both
maintainers were on vacation.

Paul Mackerras:
 "It adds mutual exclusion between list_add_rcu and list_del_rcu calls
  on the kvm->arch.spapr_tce_tables list.  Without this, userspace could
  potentially trigger corruption of the list and cause a host crash or
  worse."

34 files changed, 213 insertions, 169 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 781521b7cf9e..323cb065be5e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -100,6 +100,7 @@ config X86
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
+	select HARDLOCKUP_CHECK_TIMESTAMP	if X86_64
 	select HAVE_ACPI_APEI			if ACPI
 	select HAVE_ACPI_APEI_NMI		if ACPI
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
@@ -163,7 +164,7 @@ config X86
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if HAVE_PERF_EVENTS_NMI
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index f960a043cdeb..fc61739150e7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d271fb79248f..6d078b89a5e8 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1211,6 +1211,8 @@ ENTRY(nmi)
 	 * other IST entries.
 	 */
 
+	ASM_CLAC
+
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8e3db8f642a7..af12e294caed 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2114,7 +2114,7 @@ static void refresh_pce(void *ignored)
 	load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
 }
 
-static void x86_pmu_event_mapped(struct perf_event *event)
+static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 {
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
@@ -2129,22 +2129,20 @@ static void x86_pmu_event_mapped(struct perf_event *event)
 	 * For now, this can't happen because all callers hold mmap_sem
 	 * for write.  If this changes, we'll need a different solution.
 	 */
-	lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
 
-	if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1)
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
-static void x86_pmu_event_unmapped(struct perf_event *event)
+static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
 {
-	if (!current->mm)
-		return;
 
 	if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
 		return;
 
-	if (atomic_dec_and_test(&current->mm->context.perf_rdpmc_allowed))
-		on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
+	if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
 }
 
 static int x86_pmu_event_idx(struct perf_event *event)
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8ae8c5ce3a1f..ddd8d3516bfc 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -69,7 +69,7 @@ struct bts_buffer {
 	struct bts_phys	buf[0];
 };
 
-struct pmu bts_pmu;
+static struct pmu bts_pmu;
 
 static size_t buf_size(struct page *page)
 {
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index eb0533558c2b..d32c0eed38ca 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids
  * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are
  * either up to date automatically or not applicable at all.
  */
-struct p4_event_alias {
+static struct p4_event_alias {
 	u64 original;
 	u64 alternative;
 } p4_event_aliases[] = {
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index a45e2114a846..8e2457cb6b4a 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = {
 	.attrs = rapl_formats_attr,
 };
 
-const struct attribute_group *rapl_attr_groups[] = {
+static const struct attribute_group *rapl_attr_groups[] = {
 	&rapl_pmu_attr_group,
 	&rapl_pmu_format_group,
 	&rapl_pmu_events_group,
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 44ec523287f6..1c5390f1cf09 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group uncore_pmu_attr_group = {
+static const struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index cda569332005..6a5cbe90f859 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_ubox_format_group = {
+static const struct attribute_group nhmex_uncore_ubox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_ubox_formats_attr,
 };
@@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_cbox_format_group = {
+static const struct attribute_group nhmex_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_cbox_formats_attr,
 };
@@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_bbox_format_group = {
+static const struct attribute_group nhmex_uncore_bbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_bbox_formats_attr,
 };
@@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_sbox_format_group = {
+static const struct attribute_group nhmex_uncore_sbox_format_group = {
 	.name			= "format",
 	.attrs			= nhmex_uncore_sbox_formats_attr,
 };
@@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_mbox_format_group = {
+static const struct attribute_group nhmex_uncore_mbox_format_group = {
 	.name		= "format",
 	.attrs		= nhmex_uncore_mbox_formats_attr,
 };
@@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhmex_uncore_rbox_format_group = {
+static const struct attribute_group nhmex_uncore_rbox_format_group = {
 	.name = "format",
 	.attrs = nhmex_uncore_rbox_formats_attr,
 };
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index a3dcc12bef4a..db1127ce685e 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_format_group = {
+static const struct attribute_group snb_uncore_format_group = {
 	.name		= "format",
 	.attrs		= snb_uncore_formats_attr,
 };
@@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group snb_uncore_imc_format_group = {
+static const struct attribute_group snb_uncore_imc_format_group = {
 	.name = "format",
 	.attrs = snb_uncore_imc_formats_attr,
 };
@@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group nhm_uncore_format_group = {
+static const struct attribute_group nhm_uncore_format_group = {
 	.name = "format",
 	.attrs = nhm_uncore_formats_attr,
 };
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 4f9127644b80..db1fe377e6dd 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -602,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	{ /* end: all zeroes */ },
 };
 
-static struct attribute_group snbep_uncore_format_group = {
+static const struct attribute_group snbep_uncore_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_ubox_format_group = {
+static const struct attribute_group snbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_cbox_format_group = {
+static const struct attribute_group snbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_pcu_format_group = {
+static const struct attribute_group snbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group snbep_uncore_qpi_format_group = {
+static const struct attribute_group snbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = snbep_uncore_qpi_formats_attr,
 };
@@ -1431,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group ivbep_uncore_format_group = {
+static const struct attribute_group ivbep_uncore_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_ubox_format_group = {
+static const struct attribute_group ivbep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_ubox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_cbox_format_group = {
+static const struct attribute_group ivbep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_cbox_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_pcu_format_group = {
+static const struct attribute_group ivbep_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_pcu_formats_attr,
 };
 
-static struct attribute_group ivbep_uncore_qpi_format_group = {
+static const struct attribute_group ivbep_uncore_qpi_format_group = {
 	.name = "format",
 	.attrs = ivbep_uncore_qpi_formats_attr,
 };
@@ -1887,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_ubox_format_group = {
+static const struct attribute_group knl_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_ubox_formats_attr,
 };
@@ -1927,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_cha_format_group = {
+static const struct attribute_group knl_uncore_cha_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_cha_formats_attr,
 };
@@ -2037,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_pcu_format_group = {
+static const struct attribute_group knl_uncore_pcu_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_pcu_formats_attr,
 };
@@ -2187,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group knl_uncore_irp_format_group = {
+static const struct attribute_group knl_uncore_irp_format_group = {
 	.name = "format",
 	.attrs = knl_uncore_irp_formats_attr,
 };
@@ -2385,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_ubox_format_group = {
+static const struct attribute_group hswep_uncore_ubox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_ubox_formats_attr,
 };
@@ -2439,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_cbox_format_group = {
+static const struct attribute_group hswep_uncore_cbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_cbox_formats_attr,
 };
@@ -2621,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group hswep_uncore_sbox_format_group = {
+static const struct attribute_group hswep_uncore_sbox_format_group = {
 	.name = "format",
 	.attrs = hswep_uncore_sbox_formats_attr,
 };
@@ -3314,7 +3314,7 @@ static struct attribute *skx_uncore_cha_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_chabox_format_group = {
+static const struct attribute_group skx_uncore_chabox_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_cha_formats_attr,
 };
@@ -3427,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_iio_format_group = {
+static const struct attribute_group skx_uncore_iio_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_iio_formats_attr,
 };
@@ -3484,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_uncore_format_group = {
+static const struct attribute_group skx_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_uncore_formats_attr,
 };
@@ -3605,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = {
 	NULL,
 };
 
-static struct attribute_group skx_upi_uncore_format_group = {
+static const struct attribute_group skx_upi_uncore_format_group = {
 	.name = "format",
 	.attrs = skx_upi_uncore_formats_attr,
 };
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0e25e7a8ab03..ac030f7fbbdc 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -286,7 +286,7 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
 #define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1c18d83d3f09..9aeb91935ce0 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -247,11 +247,11 @@ extern int force_personality32;
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
 #define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
-						  0x100000000UL)
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 255645f60ca2..554cdb205d17 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
 	return 0;
 }
 
-static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask)
 {
 	if (use_xsave()) {
-		copy_kernel_to_xregs(&fpstate->xsave, -1);
+		copy_kernel_to_xregs(&fpstate->xsave, mask);
 	} else {
 		if (use_fxsr())
 			copy_kernel_to_fxregs(&fpstate->fxsave);
@@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 			: : [addr] "m" (fpstate));
 	}
 
-	__copy_kernel_to_fpregs(fpstate);
+	__copy_kernel_to_fpregs(fpstate, -1);
 }
 
 extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 21126155a739..0ead9dbb9130 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -43,6 +43,9 @@ struct hypervisor_x86 {
 
 	/* pin current vcpu to specified physical cpu (run rarely) */
 	void		(*pin_vcpu)(int);
+
+	/* called during init_mem_mapping() to setup early mappings. */
+	void		(*init_mem_mapping)(void);
 };
 
 extern const struct hypervisor_x86 *x86_hyper;
@@ -57,8 +60,15 @@ extern const struct hypervisor_x86 x86_hyper_kvm;
 extern void init_hypervisor_platform(void);
 extern bool hypervisor_x2apic_available(void);
 extern void hypervisor_pin_vcpu(int cpu);
+
+static inline void hypervisor_init_mem_mapping(void)
+{
+	if (x86_hyper && x86_hyper->init_mem_mapping)
+		x86_hyper->init_mem_mapping();
+}
 #else
 static inline void init_hypervisor_platform(void) { }
 static inline bool hypervisor_x2apic_available(void) { return false; }
+static inline void hypervisor_init_mem_mapping(void) { }
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index afa70749903e..702af26de87e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -492,6 +492,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 pkru;
 	u32 hflags;
 	u64 efer;
 	u64 apic_base;
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 7cf7c70b6ef2..0ee83321a313 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
 	ktime_t now = ktime_get();
 	s64 time_delta = ktime_ms_delta(now, s->time);
+	unsigned long flags;
 
 	/* Don't bother re-computing within the cache threshold time. */
 	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
+	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	local_irq_restore(flags);
 
 	aperf_delta = aperf - s->aperf;
 	mperf_delta = mperf - s->mperf;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d7cc190ae457..f7370abd33c6 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = {
 	NULL
 };
 
-static struct attribute_group thermal_attr_group = {
+static const struct attribute_group thermal_attr_group = {
 	.attrs	= thermal_throttle_attrs,
 	.name	= "thermal_throttle"
 };
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 9cb98ee103db..86e8f0b2537b 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = {
 	NULL
 };
 
-static struct attribute_group mc_attr_group = {
+static const struct attribute_group mc_attr_group = {
 	.attrs			= mc_default_attrs,
 	.name			= "microcode",
 };
@@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpu_root_microcode_group = {
+static const struct attribute_group cpu_root_microcode_group = {
 	.name  = "microcode",
 	.attrs = cpu_root_microcode_attrs,
 };
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index c5bb63be4ba1..40d5a8a75212 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ
 	stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask);
 }
 
+static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base,
+				unsigned long size, mtrr_type type)
+{
+	struct set_mtrr_data data = { .smp_reg = reg,
+				      .smp_base = base,
+				      .smp_size = size,
+				      .smp_type = type
+				    };
+
+	stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask);
+}
+
 static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base,
 				      unsigned long size, mtrr_type type)
 {
@@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	/* Search for an empty MTRR */
 	i = mtrr_if->get_free_region(base, size, replace);
 	if (i >= 0) {
-		set_mtrr(i, base, size, type);
+		set_mtrr_cpuslocked(i, base, size, type);
 		if (likely(replace < 0)) {
 			mtrr_usage_table[i] = 1;
 		} else {
@@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 			if (increment)
 				mtrr_usage_table[i]++;
 			if (unlikely(replace != i)) {
-				set_mtrr(replace, 0, 0, 0);
+				set_mtrr_cpuslocked(replace, 0, 0, 0);
 				mtrr_usage_table[replace] = 0;
 			}
 		}
@@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 		goto out;
 	}
 	if (--mtrr_usage_table[reg] < 1)
-		set_mtrr(reg, 0, 0, 0);
+		set_mtrr_cpuslocked(reg, 0, 0, 0);
 	error = reg;
  out:
 	mutex_unlock(&mtrr_mutex);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 46c3c73e7f43..9ba79543d9ee 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr)
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
 	int i;
+	unsigned int *next_pgt_ptr;
 
 	/* Is the address too large? */
 	if (physaddr >> MAX_PHYSMEM_BITS)
@@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr)
 	 * creates a bunch of nonsense entries but that is fine --
 	 * it avoids problems around wraparound.
 	 */
-
-	pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
-	pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
+	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
+	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 4afc67f5facc..06e1ff5562c0 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group boot_params_attr_group = {
+static const struct attribute_group boot_params_attr_group = {
 	.attrs = boot_params_version_attrs,
 	.bin_attrs = boot_params_data_attrs,
 };
@@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group setup_data_attr_group = {
+static const struct attribute_group setup_data_attr_group = {
 	.attrs = setup_data_type_attrs,
 	.bin_attrs = setup_data_data_attrs,
 };
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b474c8de7fba..54b9e89d4d6b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
  * Returns zero if CPU booted OK, else error code from
  * ->wakeup_secondary_cpu.
  */
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
+		       int *cpu0_nmi_registered)
 {
 	volatile u32 *trampoline_status =
 		(volatile u32 *) __va(real_mode_header->trampoline_status);
@@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long start_ip = real_mode_header->trampoline_start;
 
 	unsigned long boot_error = 0;
-	int cpu0_nmi_registered = 0;
 	unsigned long timeout;
 
 	idle->thread.sp = (unsigned long)task_pt_regs(idle);
@@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
 	else
 		boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
-						     &cpu0_nmi_registered);
+						     cpu0_nmi_registered);
 
 	if (!boot_error) {
 		/*
@@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		 */
 		smpboot_restore_warm_reset_vector();
 	}
-	/*
-	 * Clean up the nmi handler. Do this after the callin and callout sync
-	 * to avoid impact of possible long unregister time.
-	 */
-	if (cpu0_nmi_registered)
-		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
 
 	return boot_error;
 }
@@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int apicid = apic->cpu_present_to_apicid(cpu);
+	int cpu0_nmi_registered = 0;
 	unsigned long flags;
-	int err;
+	int err, ret = 0;
 
 	WARN_ON(irqs_disabled());
 
@@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	common_cpu_up(cpu, tidle);
 
-	err = do_boot_cpu(apicid, cpu, tidle);
+	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
-		return -EIO;
+		ret = -EIO;
+		goto unreg_nmi;
 	}
 
 	/*
@@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		touch_nmi_watchdog();
 	}
 
-	return 0;
+unreg_nmi:
+	/*
+	 * Clean up the nmi handler. Do this after the callin and callout sync
+	 * to avoid impact of possible long unregister time.
+	 */
+	if (cpu0_nmi_registered)
+		unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
+
+	return ret;
 }
 
 /**
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 1cea3ffba82d..0099e10eb045 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -474,7 +474,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
 			cpuid_mask(&entry->ecx, CPUID_7_ECX);
 			/* PKU is not yet implemented for shadow paging. */
-			if (!tdp_enabled)
+			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 				entry->ecx &= ~F(PKU);
 			entry->edx &= kvm_cpuid_7_0_edx_x86_features;
 			entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX);
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 0052317b2733..9add410f195f 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu)
 		| ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32);
 }
 
-static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu)
-{
-	return kvm_x86_ops->get_pkru(vcpu);
-}
-
 static inline void enter_guest_mode(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hflags |= HF_GUEST_MASK;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index e2999f57bfc4..64a2dbd2b1af 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -172,7 +172,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		* index of the protection domain, so pte_pkey * 2 is
 		* is the index of the first bit for the domain.
 		*/
-		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
+		pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
 		offset = (pfec & ~1) +
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9f6fb0ef206c..968f38dcb864 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1117,7 +1117,7 @@ static __init int svm_hardware_setup(void)
 
 	if (vls) {
 		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) ||
+		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
 		    !IS_ENABLED(CONFIG_X86_64)) {
 			vls = false;
 		} else {
@@ -1790,11 +1790,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
-static u32 svm_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	switch (reg) {
@@ -5436,8 +5431,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
 
-	.get_pkru = svm_get_pkru,
-
 	.tlb_flush = svm_flush_tlb,
 
 	.run = svm_vcpu_run,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ec6b1932dea9..c6efc1f88b25 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -641,8 +641,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	bool guest_pkru_valid;
-	u32 guest_pkru;
 	u32 host_pkru;
 
 	/*
@@ -2398,11 +2396,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
 }
 
-static u32 vmx_get_pkru(struct kvm_vcpu *vcpu)
-{
-	return to_vmx(vcpu)->guest_pkru;
-}
-
 static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -9291,8 +9284,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	if (vmx->guest_pkru_valid)
-		__write_pkru(vmx->guest_pkru);
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+	    vcpu->arch.pkru != vmx->host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
@@ -9440,13 +9435,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * back on host, so it is safe to read guest PKRU from current
 	 * XSAVE.
 	 */
-	if (boot_cpu_has(X86_FEATURE_OSPKE)) {
-		vmx->guest_pkru = __read_pkru();
-		if (vmx->guest_pkru != vmx->host_pkru) {
-			vmx->guest_pkru_valid = true;
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
+		vcpu->arch.pkru = __read_pkru();
+		if (vcpu->arch.pkru != vmx->host_pkru)
 			__write_pkru(vmx->host_pkru);
-		} else
-			vmx->guest_pkru_valid = false;
 	}
 
 	/*
@@ -11964,8 +11957,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
 
-	.get_pkru = vmx_get_pkru,
-
 	.tlb_flush = vmx_flush_tlb,
 
 	.run = vmx_vcpu_run,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3abaff61829d..afd9525b4b7c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3269,7 +3269,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest + offset, src, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(dest + offset, &vcpu->arch.pkru,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest + offset, src, size);
+
 		}
 
 		valid -= feature;
@@ -3307,7 +3312,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 			u32 size, offset, ecx, edx;
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
-			memcpy(dest, src + offset, size);
+			if (feature == XFEATURE_MASK_PKRU)
+				memcpy(&vcpu->arch.pkru, src + offset,
+				       sizeof(vcpu->arch.pkru));
+			else
+				memcpy(dest, src + offset, size);
 		}
 
 		valid -= feature;
@@ -7667,7 +7676,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 */
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
+	/* PKRU is separately restored in kvm_x86_ops->run.  */
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+				~XFEATURE_MASK_PKRU);
 	trace_kvm_fpu(1);
 }
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 673541eb3b3f..bf3f1065d6ad 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -18,6 +18,7 @@
 #include <asm/dma.h>		/* for MAX_DMA_PFN */
 #include <asm/microcode.h>
 #include <asm/kaslr.h>
+#include <asm/hypervisor.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -636,6 +637,8 @@ void __init init_mem_mapping(void)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 
+	hypervisor_init_mem_mapping();
+
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
 
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 229d04a83f85..a88cfbfbd078 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -50,8 +50,7 @@ unsigned long tasksize_64bit(void)
 static unsigned long stack_maxrandom_size(unsigned long task_size)
 {
 	unsigned long max = 0;
-	if ((current->flags & PF_RANDOMIZE) &&
-		!(current->personality & ADDR_NO_RANDOMIZE)) {
+	if (current->flags & PF_RANDOMIZE) {
 		max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit());
 		max <<= PAGE_SHIFT;
 	}
@@ -79,13 +78,13 @@ static int mmap_is_legacy(void)
 
 static unsigned long arch_rnd(unsigned int rndbits)
 {
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
 	return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
 }
 
 unsigned long arch_mmap_rnd(void)
 {
-	if (!(current->flags & PF_RANDOMIZE))
-		return 0;
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3e4bdb442fbc..f44c0bc95aa2 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -26,7 +26,7 @@
 static struct bau_operations ops __ro_after_init;
 
 /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */
-static int timeout_base_ns[] = {
+static const int timeout_base_ns[] = {
 		20,
 		160,
 		1280,
@@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
  * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
  * Such a message must be ignored.
  */
-void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
 {
 	unsigned long mmr_image;
 	unsigned char swack_vec;
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 87d791356ea9..de503c225ae1 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -12,6 +12,7 @@
 #include <asm/setup.h>
 #include <asm/hypervisor.h>
 #include <asm/e820/api.h>
+#include <asm/early_ioremap.h>
 
 #include <asm/xen/cpuid.h>
 #include <asm/xen/hypervisor.h>
@@ -21,38 +22,50 @@
 #include "mmu.h"
 #include "smp.h"
 
-void __ref xen_hvm_init_shared_info(void)
+static unsigned long shared_info_pfn;
+
+void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
-	u64 pa;
-
-	if (HYPERVISOR_shared_info == &xen_dummy_shared_info) {
-		/*
-		 * Search for a free page starting at 4kB physical address.
-		 * Low memory is preferred to avoid an EPT large page split up
-		 * by the mapping.
-		 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
-		 * the BIOS used for HVM guests is well behaved and won't
-		 * clobber memory other than the first 4kB.
-		 */
-		for (pa = PAGE_SIZE;
-		     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
-		     memblock_is_reserved(pa);
-		     pa += PAGE_SIZE)
-			;
-
-		memblock_reserve(pa, PAGE_SIZE);
-		HYPERVISOR_shared_info = __va(pa);
-	}
 
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info);
+	xatp.gpfn = shared_info_pfn;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 }
 
+static void __init reserve_shared_info(void)
+{
+	u64 pa;
+
+	/*
+	 * Search for a free page starting at 4kB physical address.
+	 * Low memory is preferred to avoid an EPT large page split up
+	 * by the mapping.
+	 * Starting below X86_RESERVE_LOW (usually 64kB) is fine as
+	 * the BIOS used for HVM guests is well behaved and won't
+	 * clobber memory other than the first 4kB.
+	 */
+	for (pa = PAGE_SIZE;
+	     !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) ||
+	     memblock_is_reserved(pa);
+	     pa += PAGE_SIZE)
+		;
+
+	shared_info_pfn = PHYS_PFN(pa);
+
+	memblock_reserve(pa, PAGE_SIZE);
+	HYPERVISOR_shared_info = early_memremap(pa, PAGE_SIZE);
+}
+
+static void __init xen_hvm_init_mem_mapping(void)
+{
+	early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE);
+	HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+}
+
 static void __init init_hvm_pv_info(void)
 {
 	int major, minor;
@@ -153,6 +166,7 @@ static void __init xen_hvm_guest_init(void)
 
 	init_hvm_pv_info();
 
+	reserve_shared_info();
 	xen_hvm_init_shared_info();
 
 	/*
@@ -218,5 +232,6 @@ const struct hypervisor_x86 x86_hyper_xen_hvm = {
 	.init_platform          = xen_hvm_guest_init,
 	.pin_vcpu               = xen_pin_vcpu,
 	.x2apic_available       = xen_x2apic_para_available,
+	.init_mem_mapping	= xen_hvm_init_mem_mapping,
 };
 EXPORT_SYMBOL(x86_hyper_xen_hvm);