5 files changed, 102 insertions, 54 deletions
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index a5cbbf3e26ec..3c61c29ff6ab 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -1212,7 +1212,7 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 
 #ifndef memset_io
 /**
- * memset_io	Set a range of I/O memory to a constant value
+ * memset_io -	Set a range of I/O memory to a constant value
  * @addr:	The beginning of the I/O-memory range to set
  * @val:	The value to set the memory to
  * @count:	The number of bytes to set
@@ -1224,7 +1224,7 @@ void memset_io(volatile void __iomem *addr, int val, size_t count);
 
 #ifndef memcpy_fromio
 /**
- * memcpy_fromio	Copy a block of data from I/O memory
+ * memcpy_fromio -	Copy a block of data from I/O memory
  * @dst:		The (RAM) destination for the copy
  * @src:		The (I/O memory) source for the data
  * @count:		The number of bytes to copy
@@ -1236,7 +1236,7 @@ void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count);
 
 #ifndef memcpy_toio
 /**
- * memcpy_toio		Copy a block of data into I/O memory
+ * memcpy_toio -	Copy a block of data into I/O memory
  * @dst:		The (I/O memory) destination for the copy
  * @src:		The (RAM) source for the data
  * @count:		The number of bytes to copy
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index a7bbe504e4f3..ccccb1cbf7df 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -28,9 +28,15 @@
 
 #define VTPM_BASE_ADDRESS 0xfed40000
 
+enum hv_partition_type {
+	HV_PARTITION_TYPE_GUEST,
+	HV_PARTITION_TYPE_ROOT,
+};
+
 struct ms_hyperv_info {
 	u32 features;
 	u32 priv_high;
+	u32 ext_features;
 	u32 misc_features;
 	u32 hints;
 	u32 nested_features;
@@ -58,15 +64,32 @@ struct ms_hyperv_info {
 };
 extern struct ms_hyperv_info ms_hyperv;
 extern bool hv_nested;
+extern u64 hv_current_partition_id;
+extern enum hv_partition_type hv_curr_partition_type;
 
 extern void * __percpu *hyperv_pcpu_input_arg;
 extern void * __percpu *hyperv_pcpu_output_arg;
 
-extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
-extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
+u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
+u64 hv_do_fast_hypercall8(u16 control, u64 input8);
+u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2);
+
 bool hv_isolation_type_snp(void);
 bool hv_isolation_type_tdx(void);
 
+/*
+ * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
+ * it doesn't provide a recommendation flag and AEOI must be disabled.
+ */
+static inline bool hv_recommend_using_aeoi(void)
+{
+#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
+	return !(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
+#else
+	return false;
+#endif
+}
+
 static inline struct hv_proximity_domain_info hv_numa_node_to_pxm_info(int node)
 {
 	struct hv_proximity_domain_info pxm_info = {};
@@ -185,12 +208,11 @@ void hv_setup_kexec_handler(void (*handler)(void));
 void hv_remove_kexec_handler(void);
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
 void hv_remove_crash_handler(void);
+void hv_setup_mshv_handler(void (*handler)(void));
 
 extern int vmbus_interrupt;
 extern int vmbus_irq;
 
-extern bool hv_root_partition;
-
 #if IS_ENABLED(CONFIG_HYPERV)
 /*
  * Hypervisor's notion of virtual processor ID is different from
@@ -207,10 +229,12 @@ extern u64 (*hv_read_reference_counter)(void);
 #define VP_INVAL	U32_MAX
 
 int __init hv_common_init(void);
+void __init hv_get_partition_id(void);
 void __init hv_common_free(void);
 void __init ms_hyperv_late_init(void);
 int hv_common_cpu_init(unsigned int cpu);
 int hv_common_cpu_die(unsigned int cpu);
+void hv_identify_partition_type(void);
 
 void *hv_alloc_hyperv_page(void);
 void *hv_alloc_hyperv_zeroed_page(void);
@@ -291,6 +315,20 @@ static inline int cpumask_to_vpset_skip(struct hv_vpset *vpset,
 	return __cpumask_to_vpset(vpset, cpus, func);
 }
 
+#define _hv_status_fmt(fmt) "%s: Hyper-V status: %#x = %s: " fmt
+#define hv_status_printk(level, status, fmt, ...) \
+do { \
+	u64 __status = (status); \
+	pr_##level(_hv_status_fmt(fmt), __func__, hv_result(__status), \
+		   hv_result_to_string(__status), ##__VA_ARGS__); \
+} while (0)
+#define hv_status_err(status, fmt, ...) \
+	hv_status_printk(err, status, fmt, ##__VA_ARGS__)
+#define hv_status_debug(status, fmt, ...) \
+	hv_status_printk(debug, status, fmt, ##__VA_ARGS__)
+
+const char *hv_result_to_string(u64 hv_status);
+int hv_result_to_errno(u64 status);
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
@@ -303,6 +341,7 @@ void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
 void hv_setup_dma_ops(struct device *dev, bool coherent);
 #else /* CONFIG_HYPERV */
+static inline void hv_identify_partition_type(void) {}
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline bool hv_is_hibernation_supported(void) { return false; }
 static inline void hyperv_cleanup(void) {}
@@ -314,4 +353,29 @@ static inline enum hv_isolation_type hv_get_isolation_type(void)
 }
 #endif /* CONFIG_HYPERV */
 
+#if IS_ENABLED(CONFIG_MSHV_ROOT)
+static inline bool hv_root_partition(void)
+{
+	return hv_curr_partition_type == HV_PARTITION_TYPE_ROOT;
+}
+int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
+int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
+int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
+
+#else /* CONFIG_MSHV_ROOT */
+static inline bool hv_root_partition(void) { return false; }
+static inline int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
+{
+	return -EOPNOTSUPP;
+}
+static inline int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id)
+{
+	return -EOPNOTSUPP;
+}
+static inline int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_MSHV_ROOT */
+
 #endif
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9..0755bc39b0d8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index 01dafd604188..b550afa15ecd 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -4,24 +4,35 @@
 
 #ifndef __ASSEMBLY__
 
-#ifndef __arch_get_k_vdso_data
-static __always_inline struct vdso_data *__arch_get_k_vdso_data(void)
+#ifdef CONFIG_GENERIC_VDSO_DATA_STORE
+
+#ifndef __arch_get_vdso_u_time_data
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
 {
-	return NULL;
+	return &vdso_u_time_data;
 }
-#endif /* __arch_get_k_vdso_data */
+#endif
+
+#ifndef __arch_get_vdso_u_rng_data
+static __always_inline const struct vdso_rng_data *__arch_get_vdso_u_rng_data(void)
+{
+	return &vdso_u_rng_data;
+}
+#endif
+
+#endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 #ifndef __arch_update_vsyscall
-static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata)
+static __always_inline void __arch_update_vsyscall(struct vdso_time_data *vdata)
 {
 }
 #endif /* __arch_update_vsyscall */
 
-#ifndef __arch_sync_vdso_data
-static __always_inline void __arch_sync_vdso_data(struct vdso_data *vdata)
+#ifndef __arch_sync_vdso_time_data
+static __always_inline void __arch_sync_vdso_time_data(struct vdso_time_data *vdata)
 {
 }
-#endif /* __arch_sync_vdso_data */
+#endif /* __arch_sync_vdso_time_data */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0d5b186abee8..58a635a6d5bd 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -385,6 +385,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(PAGE_SIZE);						\
 	__nosave_end = .;
 
+#define CACHE_HOT_DATA(align)						\
+	. = ALIGN(align);						\
+	*(SORT_BY_ALIGNMENT(.data..hot.*))				\
+	. = ALIGN(align);
+
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
 	*(.data..page_aligned)						\
@@ -404,7 +409,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__start_init_stack = .;						\
 	init_thread_union = .;						\
 	init_stack = .;							\
-	KEEP(*(.data..init_task))					\
 	KEEP(*(.data..init_thread_info))				\
 	. = __start_init_stack + THREAD_SIZE;				\
 	__end_init_stack = .;
@@ -1062,10 +1066,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
+	__per_cpu_hot_start = .;					\
+	*(SORT_BY_ALIGNMENT(.data..percpu..hot.*))			\
+	__per_cpu_hot_end = .;						\
+	. = ALIGN(cacheline);						\
 	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\
@@ -1074,52 +1081,17 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__per_cpu_end = .;
 
 /**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
  * @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
  *
  * Macro which expands to output section for percpu area.
  *
  * @cacheline is used to align subsections to avoid false cacheline
  * sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address.  If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank.  Be warned that
- * output PHDR is sticky.  If @phdr is specified, the next output
- * section in the linker script will go there too.  @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	__per_cpu_load = .;						\
-	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
-		PERCPU_INPUT(cacheline)					\
-	} phdr								\
-	. = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area.  This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
  */
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
@@ -1148,6 +1120,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 		INIT_TASK_DATA(inittask)				\
 		NOSAVE_DATA						\
 		PAGE_ALIGNED_DATA(pagealigned)				\
+		CACHE_HOT_DATA(cacheline)				\
 		CACHELINE_ALIGNED_DATA(cacheline)			\
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\