Merge tag 'v4.0-rc6' into timers/core, before applying new patches

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

15 files changed, 135 insertions, 73 deletions

diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index f1ad9c2ab2e9..a857794432d6 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -622,7 +622,7 @@
 		};
 
 		sgenet0: ethernet@1f210000 {
-			compatible = "apm,xgene-enet";
+			compatible = "apm,xgene1-sgenet";
 			status = "disabled";
 			reg = <0x0 0x1f210000 0x0 0xd100>,
 			      <0x0 0x1f200000 0x0 0Xc300>,
@@ -636,7 +636,7 @@
 		};
 
 		xgenet: ethernet@1f610000 {
-			compatible = "apm,xgene-enet";
+			compatible = "apm,xgene1-xgenet";
 			status = "disabled";
 			reg = <0x0 0x1f610000 0x0 0xd100>,
 			      <0x0 0x1f600000 0x0 0Xc300>,
diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
index ea2b5666a16f..c9b89efe0f56 100644
--- a/arch/arm64/boot/dts/arm/juno-clocks.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
@@ -8,7 +8,7 @@
  */
 
 	/* SoC fixed clocks */
-	soc_uartclk: refclk72738khz {
+	soc_uartclk: refclk7273800hz {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <7273800>;
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index cb9593079f29..d8c25b7b18fb 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -246,14 +246,30 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
-#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-
-#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
-	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
-				o1, o2, n1, n2)
+#define _protect_cmpxchg_local(pcp, o, n)			\
+({								\
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
+	preempt_disable();					\
+	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
+	preempt_enable();					\
+	__ret;							\
+})
+
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
+({									\
+	int __ret;							\
+	preempt_disable();						\
+	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
+					raw_cpu_ptr(&(ptr2)),		\
+					o1, o2, n1, n2);		\
+	preempt_enable();						\
+	__ret;								\
+})
 
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 94674eb7e7bb..54bb4ba97441 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -129,6 +129,9 @@
  * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
  * not known to exist and will break with this configuration.
  *
+ * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
+ * (see hyp-init.S).
+ *
  * Note that when using 4K pages, we concatenate two first level page tables
  * together.
  *
@@ -138,7 +141,6 @@
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
@@ -150,7 +152,6 @@
 #else
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6458b5373142..bbfb600fa822 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
@@ -171,43 +173,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #define KVM_PREALLOC_LEVEL	(0)
 #endif
 
-/**
- * kvm_prealloc_hwpgd - allocate inital table for VTTBR
- * @kvm:	The KVM struct pointer for the VM.
- * @pgd:	The kernel pseudo pgd
- *
- * When the kernel uses more levels of page tables than the guest, we allocate
- * a fake PGD and pre-populate it to point to the next-level page table, which
- * will be the real initial page table pointed to by the VTTBR.
- *
- * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
- * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
- * allocate 2 consecutive PUD pages.
- */
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	unsigned int i;
-	unsigned long hwpgd;
-
-	if (KVM_PREALLOC_LEVEL == 0)
-		return 0;
-
-	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
-	if (!hwpgd)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-		if (KVM_PREALLOC_LEVEL == 1)
-			pgd_populate(NULL, pgd + i,
-				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-		else if (KVM_PREALLOC_LEVEL == 2)
-			pud_populate(NULL, pud_offset(pgd, 0) + i,
-				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-	}
-
-	return 0;
-}
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	pgd_t *pgd = kvm->arch.pgd;
@@ -224,12 +189,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm)
 	return pmd_offset(pud, 0);
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	if (KVM_PREALLOC_LEVEL > 0) {
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
-	}
+	if (KVM_PREALLOC_LEVEL > 0)
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 static inline bool kvm_page_empty(void *ptr)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33dfa62..101a42bde728 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 09da25bc596f..4fde8c1df97f 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -204,25 +204,47 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	return ret;
 }
 
+#define _percpu_read(pcp)						\
+({									\
+	typeof(pcp) __retval;						\
+	preempt_disable();						\
+	__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), 	\
+					      sizeof(pcp));		\
+	preempt_enable();						\
+	__retval;							\
+})
+
+#define _percpu_write(pcp, val)						\
+do {									\
+	preempt_disable();						\
+	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), 	\
+				sizeof(pcp));				\
+	preempt_enable();						\
+} while(0)								\
+
+#define _pcp_protect(operation, pcp, val)			\
+({								\
+	typeof(pcp) __retval;					\
+	preempt_disable();					\
+	__retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)),	\
+					  (val), sizeof(pcp));	\
+	preempt_enable();					\
+	__retval;						\
+})
+
 #define _percpu_add(pcp, val) \
-	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+	_pcp_protect(__percpu_add, pcp, val)
 
-#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
 
 #define _percpu_and(pcp, val) \
-	__percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+	_pcp_protect(__percpu_and, pcp, val)
 
 #define _percpu_or(pcp, val) \
-	__percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
-
-#define _percpu_read(pcp) (typeof(pcp))	\
-	(__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
-
-#define _percpu_write(pcp, val) \
-	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
+	_pcp_protect(__percpu_or, pcp, val)
 
 #define _percpu_xchg(pcp, val) (typeof(pcp)) \
-	(__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+	_pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))
 
 #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
 #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84f8fb2..941c375616e2 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -39,7 +39,11 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
-#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
+#define cpu_switch_mm(pgd,mm)				\
+do {							\
+	BUG_ON(pgd == swapper_pg_dir);			\
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);		\
+} while (0)
 
 #define cpu_get_pgd()					\
 ({							\
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index c028fe37456f..53d9c354219f 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -48,6 +48,7 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	pgtable_page_dtor(pte);
 	tlb_remove_entry(tlb, pte);
 }
@@ -56,6 +57,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
@@ -64,6 +66,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
+	__flush_tlb_pgtable(tlb->mm, addr);
 	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 4abe9b945f77..c3bb05b98616 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -144,6 +144,19 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 }
 
 /*
+ * Used to invalidate the TLB (walk caches) corresponding to intermediate page
+ * table levels (pgd/pud/pmd).
+ */
+static inline void __flush_tlb_pgtable(struct mm_struct *mm,
+				       unsigned long uaddr)
+{
+	unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+
+	dsb(ishst);
+	asm("tlbi	vae1is, %0" : : "r" (addr));
+	dsb(ish);
+}
+/*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
  */
 static inline void update_mmu_cache(struct vm_area_struct *vma,
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index b42c7b480e1e..ab21e0d58278 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -337,7 +337,11 @@ core_initcall(arm64_dmi_init);
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	cpu_switch_mm(mm->pgd, mm);
+	if (mm == &init_mm)
+		cpu_set_reserved_ttbr0();
+	else
+		cpu_switch_mm(mm->pgd, mm);
+
 	flush_tlb_all();
 	if (icache_is_aivivt())
 		__flush_icache_all();
@@ -354,3 +358,12 @@ void efi_virtmap_unload(void)
 	efi_set_pgd(current->active_mm);
 	preempt_enable();
 }
+
+/*
+ * UpdateCapsule() depends on the system being shutdown via
+ * ResetSystem().
+ */
+bool efi_poweroff_required(void)
+{
+	return efi_enabled(EFI_RUNTIME_SERVICES);
+}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 8ce88e08c030..07f930540f4a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -585,8 +585,8 @@ ENDPROC(set_cpu_boot_mode_flag)
  * zeroing of .bss would clobber it.
  */
 	.pushsection	.data..cacheline_aligned
-ENTRY(__boot_cpu_mode)
 	.align	L1_CACHE_SHIFT
+ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	0
 	.popsection
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index fde9923af859..c6b1f3b96f45 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -21,6 +21,7 @@
 #include <stdarg.h>
 
 #include <linux/compat.h>
+#include <linux/efi.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -150,6 +151,13 @@ void machine_restart(char *cmd)
 	local_irq_disable();
 	smp_send_stop();
 
+	/*
+	 * UpdateCapsule() depends on the system being reset via
+	 * ResetSystem().
+	 */
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		efi_reboot(reboot_mode, NULL);
+
 	/* Now call the architecture specific reboot code. */
 	if (arm_pm_restart)
 		arm_pm_restart(reboot_mode, cmd);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 58e0c2bdde04..ef7d112f5ce0 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -51,7 +51,7 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
-static void *__alloc_from_pool(size_t size, struct page **ret_page)
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 {
 	unsigned long val;
 	void *ptr = NULL;
@@ -67,6 +67,8 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		if (flags & __GFP_ZERO)
+			memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +103,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
+		void *addr;
 
 		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -109,7 +112,10 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 			return NULL;
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		return page_address(page);
+		addr = page_address(page);
+		if (flags & __GFP_ZERO)
+			memset(addr, 0, size);
+		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
 	}
@@ -146,7 +152,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 
 	if (!coherent && !(flags & __GFP_WAIT)) {
 		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page);
+		void *addr = __alloc_from_pool(size, &page, flags);
 
 		if (addr)
 			*dma_handle = phys_to_dma(dev, page_to_phys(page));
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index bb0ea94c4ba1..1d3ec3ddd84b 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -51,7 +51,10 @@ static int change_memory_common(unsigned long addr, int numpages,
 		WARN_ON_ONCE(1);
 	}
 
-	if (!is_module_address(start) || !is_module_address(end - 1))
+	if (start < MODULES_VADDR || start >= MODULES_END)
+		return -EINVAL;
+
+	if (end < MODULES_VADDR || end >= MODULES_END)
 		return -EINVAL;
 
 	data.set_mask = set_mask;