Merge branch 'perf/urgent' into perf/core, to resolve conflict

Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 100 insertions, 15 deletions

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/events/intel/core.c b/arch/x86/events/intel/core.c
index 68fa55b4d42e..aff79884e17d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3639,6 +3639,7 @@ __init int intel_pmu_init(void)
 
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
+	case 85: /* 14nm Skylake Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index e657de1923c2..c9b7489ae8ee 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -744,6 +744,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(79, hsx_rapl_init),	/* Broadwell-Server */
 	X86_RAPL_MODEL_MATCH(60, hsw_rapl_init),	/* Haswell */
 	X86_RAPL_MODEL_MATCH(69, hsw_rapl_init),	/* Haswell-Celeron */
+	X86_RAPL_MODEL_MATCH(70, hsw_rapl_init),	/* Haswell GT3e */
 	X86_RAPL_MODEL_MATCH(61, hsw_rapl_init),	/* Broadwell */
 	X86_RAPL_MODEL_MATCH(71, hsw_rapl_init),	/* Broadwell-H */
 	X86_RAPL_MODEL_MATCH(45, snbep_rapl_init),	/* Sandy Bridge-EP */
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/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 319b08a5b6ed..2367ae07eb76 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -146,6 +146,31 @@ int default_check_phys_apicid_present(int phys_apicid)
 
 struct boot_params boot_params;
 
+/*
+ * Machine setup..
+ */
+static struct resource data_resource = {
+	.name	= "Kernel data",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
+};
+
+static struct resource code_resource = {
+	.name	= "Kernel code",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
+};
+
+static struct resource bss_resource = {
+	.name	= "Kernel bss",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
+};
+
+
 #ifdef CONFIG_X86_32
 /* cpu data as detected by the assembly code in head.S */
 struct cpuinfo_x86 new_cpu_data = {
@@ -924,6 +949,13 @@ void __init setup_arch(char **cmdline_p)
 
 	mpx_mm_init(&init_mm);
 
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext)-1;
+	data_resource.start = __pa_symbol(_etext);
+	data_resource.end = __pa_symbol(_edata)-1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop)-1;
+
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE
 	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
@@ -987,6 +1019,11 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.resources.probe_roms();
 
+	/* after parse_early_param, so could debug it */
+	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &data_resource);
+	insert_resource(&iomem_resource, &bss_resource);
+
 	e820_add_kernel_range();
 	trim_bios_range();
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8efb839948e5..bbbaa802d13e 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -534,6 +534,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			do_cpuid_1_ent(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
+				cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
 				entry[i].ebx = 0;
 				if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
 					entry[i].ebx =
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index b70df72e2b33..66b33b96a31b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -173,10 +173,9 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 	bool fault = (mmu->permissions[index] >> pte_access) & 1;
+	u32 errcode = PFERR_PRESENT_MASK;
 
 	WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK));
-	pfec |= PFERR_PRESENT_MASK;
-
 	if (unlikely(mmu->pkru_mask)) {
 		u32 pkru_bits, offset;
 
@@ -189,15 +188,15 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
-		offset = pfec - 1 +
+		offset = (pfec & ~1) +
 			((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));
 
 		pkru_bits &= mmu->pkru_mask >> offset;
-		pfec |= -pkru_bits & PFERR_PK_MASK;
+		errcode |= -pkru_bits & PFERR_PK_MASK;
 		fault |= (pkru_bits != 0);
 	}
 
-	return -(uint32_t)fault & pfec;
+	return -(u32)fault & errcode;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 1d971c7553c3..bc019f70e0b6 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -360,7 +360,7 @@ retry_walk:
 			goto error;
 
 		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
-			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
+			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0a2c70e43bc8..9b7798c7b210 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -700,7 +700,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
 			return 1;
 	}
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -6590,8 +6589,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
-	kvm_load_guest_xcr0(vcpu);
-
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6618,6 +6615,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6667,6 +6666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
+	kvm_put_guest_xcr0(vcpu);
+
 	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
@@ -7314,7 +7315,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 * and assume host would use all available bits.
 	 * Guest xcr0 would be loaded later.
 	 */
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7323,8 +7323,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	kvm_put_guest_xcr0(vcpu);
-
 	if (!vcpu->guest_fpu_loaded) {
 		vcpu->fpu_counter = 0;
 		return;