Merge tag '4.9.204' of https://android.googlesource.com/kernel/common …

…into lotus

Conflicts:
       arch/arm64/Makefile
       fs/f2fs/data.c
       fs/f2fs/segment.c

Documentation/hw-vuln/mds.rst

@@ -265,8 +265,11 @@ time with the option "mds=". The valid arguments for this option are:
 
   ============  =============================================================
 
-Not specifying this option is equivalent to "mds=full".
-
+Not specifying this option is equivalent to "mds=full". For processors
+that are affected by both TAA (TSX Asynchronous Abort) and MDS,
+specifying just "mds=off" without an accompanying "tsx_async_abort=off"
+will have no effect as the same mitigation is used for both
+vulnerabilities.
 
 Mitigation selection guide
 --------------------------

Documentation/hw-vuln/tsx_async_abort.rst

@@ -174,7 +174,10 @@ the option "tsx_async_abort=". The valid arguments for this option are:
                 CPU is not vulnerable to cross-thread TAA attacks.
   ============  =============================================================
 
-Not specifying this option is equivalent to "tsx_async_abort=full".
+Not specifying this option is equivalent to "tsx_async_abort=full". For
+processors that are affected by both TAA and MDS, specifying just
+"tsx_async_abort=off" without an accompanying "mds=off" will have no
+effect as the same mitigation is used for both vulnerabilities.
 
 The kernel command line also allows to control the TSX feature using the
 parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used

Documentation/kernel-parameters.txt

@@ -2377,6 +2377,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				     SMT on vulnerable CPUs
 			off        - Unconditionally disable MDS mitigation
 
+			On TAA-affected machines, mds=off can be prevented by
+			an active TAA mitigation as both vulnerabilities are
+			mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify tsx_async_abort=off
+			too.
+
 			Not specifying this option is equivalent to
 			mds=full.
 
@@ -4623,6 +4629,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				     vulnerable to cross-thread TAA attacks.
 			off        - Unconditionally disable TAA mitigation
 
+			On MDS-affected machines, tsx_async_abort=off can be
+			prevented by an active MDS mitigation as both vulnerabilities
+			are mitigated with the same mechanism so in order to disable
+			this mitigation, you need to specify mds=off too.
+
 			Not specifying this option is equivalent to
 			tsx_async_abort=full.  On CPUs which are MDS affected
 			and deploy MDS mitigation, TAA mitigation is not

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 203
+SUBLEVEL = 204
 EXTRAVERSION =
 NAME = Roaring Lionus
 

arch/arc/kernel/perf_event.c

@@ -488,8 +488,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	/* loop thru all available h/w condition indexes */
 	for (j = 0; j < cc_bcr.c; j++) {
 		write_aux_reg(ARC_REG_CC_INDEX, j);
-		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
-		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
+		cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0));
+		cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1));
 
 		/* See if it has been mapped to a perf event_id */
 		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {

arch/arm/mm/mmu.c

@@ -1188,6 +1188,9 @@ void __init adjust_lowmem_bounds(void)
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (reg->base < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*

arch/arm64/Makefile

@@ -214,6 +214,7 @@ archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 	$(Q)$(MAKE) $(clean)=$(boot)/dts
 
+ifeq ($(KBUILD_EXTMOD),)
 # We need to generate vdso-offsets.h before compiling certain files in kernel/.
 # In order to do that, we should use the archprepare target, but we can't since
 # asm-offsets.h is included in some files used to generate vdso-offsets.h, and
@@ -225,6 +226,7 @@ vdso_prepare: prepare0
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
 	$(if $(CONFIG_VDSO32),$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
                                           include/generated/vdso32-offsets.h)
+endif
 
 define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'

arch/arm64/kernel/traps.c

@@ -697,7 +697,6 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 		handler[reason], smp_processor_id(), esr,
 		esr_get_class_string(esr));
 
-	die("Oops - bad mode", regs, 0);
 	local_irq_disable();
 	panic("bad mode");
 }

arch/m68k/kernel/uboot.c

@@ -103,5 +103,5 @@ __init void process_uboot_commandline(char *commandp, int size)
 	}
 
 	parse_uboot_commandline(commandp, len);
-	commandp[size - 1] = 0;
+	commandp[len - 1] = 0;
 }

arch/powerpc/include/asm/asm-prototypes.h

@@ -124,7 +124,10 @@ extern int __ucmpdi2(u64, u64);
 /* Patch sites */
 extern s32 patch__call_flush_count_cache;
 extern s32 patch__flush_count_cache_return;
+extern s32 patch__flush_link_stack_return;
+extern s32 patch__call_kvm_flush_link_stack;
 
 extern long flush_count_cache;
+extern long kvm_flush_link_stack;
 
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

arch/powerpc/include/asm/security_features.h

@@ -81,6 +81,9 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Software required to flush count cache on context switch
 #define SEC_FTR_FLUSH_COUNT_CACHE	0x0000000000000400ull
 
+// Software required to flush link stack on context switch
+#define SEC_FTR_FLUSH_LINK_STACK	0x0000000000001000ull
+
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \

arch/powerpc/kernel/eeh_pe.c

@@ -370,7 +370,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 		while (parent) {
 			if (!(parent->type & EEH_PE_INVALID))
 				break;
-			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
+			parent->type &= ~EEH_PE_INVALID;
 			parent = parent->parent;
 		}
 

arch/powerpc/kernel/entry_64.S

@@ -510,6 +510,7 @@ flush_count_cache:
 	/* Save LR into r9 */
 	mflr	r9
 
+	// Flush the link stack
 	.rept 64
 	bl	.+4
 	.endr
@@ -519,6 +520,11 @@ flush_count_cache:
 	.balign 32
 	/* Restore LR */
 1:	mtlr	r9
+
+	// If we're just flushing the link stack, return here
+3:	nop
+	patch_site 3b patch__flush_link_stack_return
+
 	li	r9,0x7fff
 	mtctr	r9
 

arch/powerpc/kernel/process.c

@@ -576,12 +576,11 @@ void flush_all_to_thread(struct task_struct *tsk)
 	if (tsk->thread.regs) {
 		preempt_disable();
 		BUG_ON(tsk != current);
-		save_all(tsk);
-
 #ifdef CONFIG_SPE
 		if (tsk->thread.regs->msr & MSR_SPE)
 			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
 #endif
+		save_all(tsk);
 
 		preempt_enable();
 	}

arch/powerpc/kernel/security.c

@@ -25,11 +25,12 @@ enum count_cache_flush_type {
 	COUNT_CACHE_FLUSH_HW	= 0x4,
 };
 static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+static bool link_stack_flush_enabled;
 
 bool barrier_nospec_enabled;
 static bool no_nospec;
 static bool btb_flush_enabled;
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
 static bool no_spectrev2;
 #endif
 
@@ -107,14 +108,17 @@ static __init int barrier_nospec_debugfs_init(void)
 device_initcall(barrier_nospec_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
-#ifdef CONFIG_PPC_FSL_BOOK3E
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3S_64)
 static int __init handle_nospectre_v2(char *p)
 {
 	no_spectrev2 = true;
 
 	return 0;
 }
 early_param("nospectre_v2", handle_nospectre_v2);
+#endif /* CONFIG_PPC_FSL_BOOK3E || CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
 void setup_spectre_v2(void)
 {
 	if (no_spectrev2)
@@ -202,11 +206,19 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
 
 		if (ccd)
 			seq_buf_printf(&s, "Indirect branch cache disabled");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
 	} else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) {
 		seq_buf_printf(&s, "Mitigation: Software count cache flush");
 
 		if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW)
 			seq_buf_printf(&s, " (hardware accelerated)");
+
+		if (link_stack_flush_enabled)
+			seq_buf_printf(&s, ", Software link stack flush");
+
 	} else if (btb_flush_enabled) {
 		seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
 	} else {
@@ -367,18 +379,49 @@ static __init int stf_barrier_debugfs_init(void)
 device_initcall(stf_barrier_debugfs_init);
 #endif /* CONFIG_DEBUG_FS */
 
+static void no_count_cache_flush(void)
+{
+	count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
+	pr_info("count-cache-flush: software flush disabled.\n");
+}
+
 static void toggle_count_cache_flush(bool enable)
 {
-	if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) &&
+	    !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK))
+		enable = false;
+
+	if (!enable) {
 		patch_instruction_site(&patch__call_flush_count_cache, PPC_INST_NOP);
-		count_cache_flush_type = COUNT_CACHE_FLUSH_NONE;
-		pr_info("count-cache-flush: software flush disabled.\n");
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+		patch_instruction_site(&patch__call_kvm_flush_link_stack, PPC_INST_NOP);
+#endif
+		pr_info("link-stack-flush: software flush disabled.\n");
+		link_stack_flush_enabled = false;
+		no_count_cache_flush();
 		return;
 	}
 
+	// This enables the branch from _switch to flush_count_cache
 	patch_branch_site(&patch__call_flush_count_cache,
 			  (u64)&flush_count_cache, BRANCH_SET_LINK);
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	// This enables the branch from guest_exit_cont to kvm_flush_link_stack
+	patch_branch_site(&patch__call_kvm_flush_link_stack,
+			  (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+#endif
+
+	pr_info("link-stack-flush: software flush enabled.\n");
+	link_stack_flush_enabled = true;
+
+	// If we just need to flush the link stack, patch an early return
+	if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+		patch_instruction_site(&patch__flush_link_stack_return, PPC_INST_BLR);
+		no_count_cache_flush();
+		return;
+	}
+
 	if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
 		count_cache_flush_type = COUNT_CACHE_FLUSH_SW;
 		pr_info("count-cache-flush: full software flush sequence enabled.\n");
@@ -392,7 +435,26 @@ static void toggle_count_cache_flush(bool enable)
 
 void setup_count_cache_flush(void)
 {
-	toggle_count_cache_flush(true);
+	bool enable = true;
+
+	if (no_spectrev2 || cpu_mitigations_off()) {
+		if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) ||
+		    security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED))
+			pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n");
+
+		enable = false;
+	}
+
+	/*
+	 * There's no firmware feature flag/hypervisor bit to tell us we need to
+	 * flush the link stack on context switch. So we set it here if we see
+	 * either of the Spectre v2 mitigations that aim to protect userspace.
+	 */
+	if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) ||
+	    security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
+		security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
+
+	toggle_count_cache_flush(enable);
 }
 
 #ifdef CONFIG_DEBUG_FS

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -18,6 +18,7 @@
  */
 
 #include <asm/ppc_asm.h>
+#include <asm/code-patching-asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
 #include <asm/mmu.h>
@@ -1266,6 +1267,10 @@ mc_cont:
 	bl	kvmhv_accumulate_time
 #endif
 
+	/* Possibly flush the link stack here. */
+1:	nop
+	patch_site 1b patch__call_kvm_flush_link_stack
+
 	stw	r12, STACK_SLOT_TRAP(r1)
 	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
@@ -1685,6 +1690,28 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtlr	r0
 	blr
 
+.balign 32
+.global kvm_flush_link_stack
+kvm_flush_link_stack:
+	/* Save LR into r0 */
+	mflr	r0
+
+	/* Flush the link stack. On Power8 it's up to 32 entries in size. */
+	.rept 32
+	bl	.+4
+	.endr
+
+	/* And on Power9 it's up to 64. */
+BEGIN_FTR_SECTION
+	.rept 32
+	bl	.+4
+	.endr
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+	/* Restore LR */
+	mtlr	r0
+	blr
+
 /*
  * Check whether an HDSI is an HPTE not found fault or something else.
  * If it is an HPTE not found fault that is due to the guest accessing

arch/powerpc/platforms/ps3/os-area.c

@@ -664,7 +664,7 @@ static int update_flash_db(void)
 	db_set_64(db, &os_area_db_id_rtc_diff, saved_params.rtc_diff);
 
 	count = os_area_flash_write(db, sizeof(struct os_area_db), pos);
-	if (count < sizeof(struct os_area_db)) {
+	if (count < 0 || count < sizeof(struct os_area_db)) {
 		pr_debug("%s: os_area_flash_write failed %zd\n", __func__,
 			 count);
 		error = count < 0 ? count : -EIO;

arch/powerpc/platforms/pseries/hotplug-memory.c

@@ -616,7 +616,7 @@ static int dlpar_add_lmb(struct of_drconf_cell *lmb)
 	nid = memory_add_physaddr_to_nid(lmb->base_addr);
 
 	/* Add the memory */
-	rc = add_memory(nid, lmb->base_addr, block_sz);
+	rc = __add_memory(nid, lmb->base_addr, block_sz);
 	if (rc) {
 		dlpar_remove_device_tree_lmb(lmb);
 		dlpar_release_drc(lmb->drc_index);