Merge tag 'riscv-for-linus-5.17-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Support for sv48 paging

 - Hart ID mappings are now sparse, which enables more CPUs to come up
   on systems with sparse hart IDs

 - A handful of cleanups and fixes

* tag 'riscv-for-linus-5.17-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (27 commits)
  RISC-V: nommu_virt: Drop unused SLAB_MERGE_DEFAULT
  RISC-V: Remove redundant err variable
  riscv: dts: sifive unmatched: Add gpio poweroff
  riscv: canaan: remove useless select of non-existing config SYSCON
  RISC-V: Do not use cpumask data structure for hartid bitmap
  RISC-V: Move spinwait booting method to its own config
  RISC-V: Move the entire hart selection via lottery to SMP
  RISC-V: Use __cpu_up_stack/task_pointer only for spinwait method
  RISC-V: Do not print the SBI version during HSM extension boot print
  RISC-V: Avoid using per cpu array for ordered booting
  riscv: default to CONFIG_RISCV_SBI_V01=n
  riscv: fix boolconv.cocci warnings
  riscv: Explicit comment about user virtual address space size
  riscv: Use pgtable_l4_enabled to output mmu_type in cpuinfo
  riscv: Implement sv48 support
  asm-generic: Prepare for riscv use of pud_alloc_one and pud_free
  riscv: Allow to dynamically define VA_BITS
  riscv: Introduce functions to switch pt_ops
  riscv: Split early kasan mapping to prepare sv48 introduction
  riscv: Move KASAN mapping next to the kernel mapping
  ...

Documentation/riscv/vm-layout.rst

@@ -47,12 +47,12 @@ RISC-V Linux Kernel SV39
                                                               | Kernel-space virtual memory, shared between all processes:
   ____________________________________________________________|___________________________________________________________
                     |            |                  |         |
-   ffffffc000000000 | -256    GB | ffffffc7ffffffff |   32 GB | kasan
-   ffffffcefee00000 | -196    GB | ffffffcefeffffff |    2 MB | fixmap
-   ffffffceff000000 | -196    GB | ffffffceffffffff |   16 MB | PCI io
-   ffffffcf00000000 | -196    GB | ffffffcfffffffff |    4 GB | vmemmap
-   ffffffd000000000 | -192    GB | ffffffdfffffffff |   64 GB | vmalloc/ioremap space
-   ffffffe000000000 | -128    GB | ffffffff7fffffff |  124 GB | direct mapping of all physical memory
+   ffffffc6fee00000 | -228    GB | ffffffc6feffffff |    2 MB | fixmap
+   ffffffc6ff000000 | -228    GB | ffffffc6ffffffff |   16 MB | PCI io
+   ffffffc700000000 | -228    GB | ffffffc7ffffffff |    4 GB | vmemmap
+   ffffffc800000000 | -224    GB | ffffffd7ffffffff |   64 GB | vmalloc/ioremap space
+   ffffffd800000000 | -160    GB | fffffff6ffffffff |  124 GB | direct mapping of all physical memory
+   fffffff700000000 |  -36    GB | fffffffeffffffff |   32 GB | kasan
   __________________|____________|__________________|_________|____________________________________________________________
                                                               |
                                                               |

arch/riscv/Kconfig

@@ -147,27 +147,16 @@ config MMU
 	  Select if you want MMU-based virtualised addressing space
 	  support by paged memory management. If unsure, say 'Y'.
 
-config VA_BITS
-	int
-	default 32 if 32BIT
-	default 39 if 64BIT
-
-config PA_BITS
-	int
-	default 34 if 32BIT
-	default 56 if 64BIT
-
 config PAGE_OFFSET
 	hex
-	default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
+	default 0xC0000000 if 32BIT
 	default 0x80000000 if 64BIT && !MMU
-	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
-	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
+	default 0xffffaf8000000000 if 64BIT
 
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN_GENERIC
-	default 0xdfffffc800000000 if 64BIT
+	default 0xdfffffff00000000 if 64BIT
 	default 0xffffffff if 32BIT
 
 config ARCH_FLATMEM_ENABLE
@@ -213,7 +202,7 @@ config FIX_EARLYCON_MEM
 
 config PGTABLE_LEVELS
 	int
-	default 3 if 64BIT
+	default 4 if 64BIT
 	default 2
 
 config LOCKDEP_SUPPORT
@@ -271,24 +260,6 @@ config MODULE_SECTIONS
 	bool
 	select HAVE_MOD_ARCH_SPECIFIC
 
-choice
-	prompt "Maximum Physical Memory"
-	default MAXPHYSMEM_1GB if 32BIT
-	default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
-	default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
-
-	config MAXPHYSMEM_1GB
-		depends on 32BIT
-		bool "1GiB"
-	config MAXPHYSMEM_2GB
-		depends on 64BIT
-		bool "2GiB"
-	config MAXPHYSMEM_128GB
-		depends on 64BIT && CMODEL_MEDANY
-		bool "128GiB"
-endchoice
-
-
 config SMP
 	bool "Symmetric Multi-Processing"
 	help
@@ -392,12 +363,25 @@ source "kernel/Kconfig.hz"
 
 config RISCV_SBI_V01
 	bool "SBI v0.1 support"
-	default y
 	depends on RISCV_SBI
 	help
 	  This config allows kernel to use SBI v0.1 APIs. This will be
 	  deprecated in future once legacy M-mode software are no longer in use.
 
+config RISCV_BOOT_SPINWAIT
+	bool "Spinwait booting method"
+	depends on SMP
+	default y
+	help
+	  This enables support for booting Linux via spinwait method. In the
+	  spinwait method, all cores randomly jump to Linux. One of the cores
+	  gets chosen via lottery and all other keep spinning on a percpu
+	  variable. This method cannot support CPU hotplug and sparse hartid
+	  scheme. It should be only enabled for M-mode Linux or platforms relying
+	  on older firmware without SBI HSM extension. All other platforms should
+	  rely on ordered booting via SBI HSM extension which gets chosen
+	  dynamically at runtime if the firmware supports it.
+
 config KEXEC
 	bool "Kexec system call"
 	select KEXEC_CORE

arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts

@@ -39,6 +39,11 @@ rtcclk: rtcclk {
 		clock-frequency = <RTCCLK_FREQ>;
 		clock-output-names = "rtcclk";
 	};
+
+	gpio-poweroff {
+		compatible = "gpio-poweroff";
+		gpios = <&gpio 2 GPIO_ACTIVE_LOW>;
+	};
 };
 
 &uart0 {

arch/riscv/configs/nommu_k210_defconfig

@@ -29,7 +29,6 @@ CONFIG_EMBEDDED=y
 CONFIG_SLOB=y
 # CONFIG_MMU is not set
 CONFIG_SOC_CANAAN=y
-CONFIG_MAXPHYSMEM_2GB=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0"

arch/riscv/configs/nommu_k210_sdcard_defconfig

@@ -21,7 +21,6 @@ CONFIG_EMBEDDED=y
 CONFIG_SLOB=y
 # CONFIG_MMU is not set
 CONFIG_SOC_CANAAN=y
-CONFIG_MAXPHYSMEM_2GB=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_CMDLINE="earlycon console=ttySIF0 rootdelay=2 root=/dev/mmcblk0p1 ro"

arch/riscv/configs/nommu_virt_defconfig

@@ -24,10 +24,8 @@ CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLOB=y
-# CONFIG_SLAB_MERGE_DEFAULT is not set
 # CONFIG_MMU is not set
 CONFIG_SOC_VIRT=y
-CONFIG_MAXPHYSMEM_2GB=y
 CONFIG_SMP=y
 CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0"
 CONFIG_CMDLINE_FORCE=y

arch/riscv/include/asm/cpu_ops.h

@@ -40,7 +40,5 @@ struct cpu_operations {
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
 void __init cpu_set_ops(int cpu);
-void cpu_update_secondary_bootdata(unsigned int cpuid,
-				   struct task_struct *tidle);
 
 #endif /* ifndef __ASM_CPU_OPS_H */

arch/riscv/include/asm/cpu_ops_sbi.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021 by Rivos Inc.
+ */
+#ifndef __ASM_CPU_OPS_SBI_H
+#define __ASM_CPU_OPS_SBI_H
+
+#ifndef __ASSEMBLY__
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+
+/**
+ * struct sbi_hart_boot_data - Hart specific boot used during booting and
+ *			       cpu hotplug.
+ * @task_ptr: A pointer to the hart specific tp
+ * @stack_ptr: A pointer to the hart specific sp
+ */
+struct sbi_hart_boot_data {
+	void *task_ptr;
+	void *stack_ptr;
+};
+#endif
+
+#endif /* ifndef __ASM_CPU_OPS_SBI_H */

arch/riscv/include/asm/csr.h

@@ -40,14 +40,13 @@
 #ifndef CONFIG_64BIT
 #define SATP_PPN	_AC(0x003FFFFF, UL)
 #define SATP_MODE_32	_AC(0x80000000, UL)
-#define SATP_MODE	SATP_MODE_32
 #define SATP_ASID_BITS	9
 #define SATP_ASID_SHIFT	22
 #define SATP_ASID_MASK	_AC(0x1FF, UL)
 #else
 #define SATP_PPN	_AC(0x00000FFFFFFFFFFF, UL)
 #define SATP_MODE_39	_AC(0x8000000000000000, UL)
-#define SATP_MODE	SATP_MODE_39
+#define SATP_MODE_48	_AC(0x9000000000000000, UL)
 #define SATP_ASID_BITS	16
 #define SATP_ASID_SHIFT	44
 #define SATP_ASID_MASK	_AC(0xFFFF, UL)

arch/riscv/include/asm/fixmap.h

@@ -24,6 +24,7 @@ enum fixed_addresses {
 	FIX_HOLE,
 	FIX_PTE,
 	FIX_PMD,
+	FIX_PUD,
 	FIX_TEXT_POKE1,
 	FIX_TEXT_POKE0,
 	FIX_EARLYCON_MEM_BASE,

arch/riscv/include/asm/kasan.h

@@ -27,13 +27,18 @@
  */
 #define KASAN_SHADOW_SCALE_SHIFT	3
 
-#define KASAN_SHADOW_SIZE	(UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
-#define KASAN_SHADOW_START	KERN_VIRT_START
-#define KASAN_SHADOW_END	(KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
+#define KASAN_SHADOW_SIZE	(UL(1) << ((VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
+/*
+ * Depending on the size of the virtual address space, the region may not be
+ * aligned on PGDIR_SIZE, so force its alignment to ease its population.
+ */
+#define KASAN_SHADOW_START	((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK)
+#define KASAN_SHADOW_END	MODULES_LOWEST_VADDR
 #define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
 
 void kasan_init(void);
 asmlinkage void kasan_early_init(void);
+void kasan_swapper_init(void);
 
 #endif
 #endif

arch/riscv/include/asm/page.h

@@ -31,9 +31,20 @@
  * When not using MMU this corresponds to the first free page in
  * physical memory (aligned on a page boundary).
  */
+#ifdef CONFIG_64BIT
+#ifdef CONFIG_MMU
+#define PAGE_OFFSET		kernel_map.page_offset
+#else
 #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
-
-#define KERN_VIRT_SIZE (-PAGE_OFFSET)
+#endif
+/*
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
+ * define the PAGE_OFFSET value for SV39.
+ */
+#define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)
+#else
+#define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#endif /* CONFIG_64BIT */
 
 #ifndef __ASSEMBLY__
 
@@ -86,6 +97,7 @@ extern unsigned long riscv_pfn_base;
 #endif /* CONFIG_MMU */
 
 struct kernel_mapping {
+	unsigned long page_offset;
 	unsigned long virt_addr;
 	uintptr_t phys_addr;
 	uintptr_t size;

arch/riscv/include/asm/pgalloc.h

@@ -11,6 +11,8 @@
 #include <asm/tlb.h>
 
 #ifdef CONFIG_MMU
+#define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -36,6 +38,44 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 	set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
 }
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
+{
+	if (pgtable_l4_enabled) {
+		unsigned long pfn = virt_to_pfn(pud);
+
+		set_p4d(p4d, __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d,
+				     pud_t *pud)
+{
+	if (pgtable_l4_enabled) {
+		unsigned long pfn = virt_to_pfn(pud);
+
+		set_p4d_safe(p4d,
+			     __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE));
+	}
+}
+
+#define pud_alloc_one pud_alloc_one
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	if (pgtable_l4_enabled)
+		return __pud_alloc_one(mm, addr);
+
+	return NULL;
+}
+
+#define pud_free pud_free
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (pgtable_l4_enabled)
+		__pud_free(mm, pud);
+}
+
+#define __pud_free_tlb(tlb, pud, addr)  pud_free((tlb)->mm, pud)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)

arch/riscv/include/asm/pgtable-64.h

@@ -8,16 +8,36 @@
 
 #include <linux/const.h>
 
-#define PGDIR_SHIFT     30
+extern bool pgtable_l4_enabled;
+
+#define PGDIR_SHIFT_L3  30
+#define PGDIR_SHIFT_L4  39
+#define PGDIR_SIZE_L3   (_AC(1, UL) << PGDIR_SHIFT_L3)
+
+#define PGDIR_SHIFT     (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)
 /* Size of region mapped by a page global directory */
 #define PGDIR_SIZE      (_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK      (~(PGDIR_SIZE - 1))
 
+/* pud is folded into pgd in case of 3-level page table */
+#define PUD_SHIFT      30
+#define PUD_SIZE       (_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK       (~(PUD_SIZE - 1))
+
 #define PMD_SHIFT       21
 /* Size of region mapped by a page middle directory */
 #define PMD_SIZE        (_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK        (~(PMD_SIZE - 1))
 
+/* Page Upper Directory entry */
+typedef struct {
+	unsigned long pud;
+} pud_t;
+
+#define pud_val(x)      ((x).pud)
+#define __pud(x)        ((pud_t) { (x) })
+#define PTRS_PER_PUD    (PAGE_SIZE / sizeof(pud_t))
+
 /* Page Middle Directory entry */
 typedef struct {
 	unsigned long pmd;
@@ -59,6 +79,16 @@ static inline void pud_clear(pud_t *pudp)
 	set_pud(pudp, __pud(0));
 }
 
+static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot)
+{
+	return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
+}
+
+static inline unsigned long _pud_pfn(pud_t pud)
+{
+	return pud_val(pud) >> _PAGE_PFN_SHIFT;
+}
+
 static inline pmd_t *pud_pgtable(pud_t pud)
 {
 	return (pmd_t *)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
@@ -69,6 +99,17 @@ static inline struct page *pud_page(pud_t pud)
 	return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT);
 }
 
+#define mm_pud_folded  mm_pud_folded
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	if (pgtable_l4_enabled)
+		return false;
+
+	return true;
+}
+
+#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
 static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot)
 {
 	return __pmd((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
@@ -84,4 +125,69 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 
+#define pud_ERROR(e)   \
+	pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e))
+
+static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		*p4dp = p4d;
+	else
+		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
+}
+
+static inline int p4d_none(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (p4d_val(p4d) == 0);
+
+	return 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (p4d_val(p4d) & _PAGE_PRESENT);
+
+	return 1;
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return !p4d_present(p4d);
+
+	return 0;
+}
+
+static inline void p4d_clear(p4d_t *p4d)
+{
+	if (pgtable_l4_enabled)
+		set_p4d(p4d, __p4d(0));
+}
+
+static inline pud_t *p4d_pgtable(p4d_t p4d)
+{
+	if (pgtable_l4_enabled)
+		return (pud_t *)pfn_to_virt(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+
+	return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) });
+}
+
+static inline struct page *p4d_page(p4d_t p4d)
+{
+	return pfn_to_page(p4d_val(p4d) >> _PAGE_PFN_SHIFT);
+}
+
+#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+#define pud_offset pud_offset
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(*p4d) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+
 #endif /* _ASM_RISCV_PGTABLE_64_H */

arch/riscv/include/asm/pgtable.h

@@ -24,6 +24,17 @@
 #define KERNEL_LINK_ADDR	PAGE_OFFSET
 #endif
 
+/* Number of entries in the page global directory */
+#define PTRS_PER_PGD    (PAGE_SIZE / sizeof(pgd_t))
+/* Number of entries in the page table */
+#define PTRS_PER_PTE    (PAGE_SIZE / sizeof(pte_t))
+
+/*
+ * Half of the kernel address space (half of the entries of the page global
+ * directory) is for the direct mapping.
+ */
+#define KERN_VIRT_SIZE          ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2)
+
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      PAGE_OFFSET
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
@@ -39,8 +50,10 @@
 
 /* Modules always live before the kernel */
 #ifdef CONFIG_64BIT
-#define MODULES_VADDR	(PFN_ALIGN((unsigned long)&_end) - SZ_2G)
-#define MODULES_END	(PFN_ALIGN((unsigned long)&_start))
+/* This is used to define the end of the KASAN shadow region */
+#define MODULES_LOWEST_VADDR	(KERNEL_LINK_ADDR - SZ_2G)
+#define MODULES_VADDR		(PFN_ALIGN((unsigned long)&_end) - SZ_2G)
+#define MODULES_END		(PFN_ALIGN((unsigned long)&_start))
 #endif
 
 /*
@@ -48,8 +61,14 @@
  * struct pages to map half the virtual address space. Then
  * position vmemmap directly below the VMALLOC region.
  */
+#ifdef CONFIG_64BIT
+#define VA_BITS		(pgtable_l4_enabled ? 48 : 39)
+#else
+#define VA_BITS		32
+#endif
+
 #define VMEMMAP_SHIFT \
-	(CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
+	(VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
 #define VMEMMAP_SIZE	BIT(VMEMMAP_SHIFT)
 #define VMEMMAP_END	VMALLOC_START
 #define VMEMMAP_START	(VMALLOC_START - VMEMMAP_SIZE)
@@ -83,8 +102,7 @@
 
 #ifndef __ASSEMBLY__
 
-/* Page Upper Directory not used in RISC-V */
-#include <asm-generic/pgtable-nopud.h>
+#include <asm-generic/pgtable-nop4d.h>
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 #include <linux/mm_types.h>
@@ -107,12 +125,20 @@
 #define XIP_FIXUP(addr)		(addr)
 #endif /* CONFIG_XIP_KERNEL */
 
-#ifdef CONFIG_MMU
-/* Number of entries in the page global directory */
-#define PTRS_PER_PGD    (PAGE_SIZE / sizeof(pgd_t))
-/* Number of entries in the page table */
-#define PTRS_PER_PTE    (PAGE_SIZE / sizeof(pte_t))
+struct pt_alloc_ops {
+	pte_t *(*get_pte_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pte)(uintptr_t va);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pmd_t *(*get_pmd_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pmd)(uintptr_t va);
+	pud_t *(*get_pud_virt)(phys_addr_t pa);
+	phys_addr_t (*alloc_pud)(uintptr_t va);
+#endif
+};
+
+extern struct pt_alloc_ops pt_ops __initdata;
 
+#ifdef CONFIG_MMU
 /* Number of PGD entries that a user-mode program can use */
 #define USER_PTRS_PER_PGD   (TASK_SIZE / PGDIR_SIZE)
 
@@ -659,7 +685,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
  * and give the kernel the other (upper) half.
  */
 #ifdef CONFIG_64BIT
-#define KERN_VIRT_START	(-(BIT(CONFIG_VA_BITS)) + TASK_SIZE)
+#define KERN_VIRT_START	(-(BIT(VA_BITS)) + TASK_SIZE)
 #else
 #define KERN_VIRT_START	FIXADDR_START
 #endif
@@ -667,11 +693,22 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 /*
  * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
  * Note that PGDIR_SIZE must evenly divide TASK_SIZE.
+ * Task size is:
+ * -     0x9fc00000 (~2.5GB) for RV32.
+ * -   0x4000000000 ( 256GB) for RV64 using SV39 mmu
+ * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu
+ *
+ * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V
+ * Instruction Set Manual Volume II: Privileged Architecture" states that
+ * "load and store effective addresses, which are 64bits, must have bits
+ * 63–48 all equal to bit 47, or else a page-fault exception will occur."
  */
 #ifdef CONFIG_64BIT
-#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#define TASK_SIZE      (PGDIR_SIZE * PTRS_PER_PGD / 2)
+#define TASK_SIZE_MIN  (PGDIR_SIZE_L3 * PTRS_PER_PGD / 2)
 #else
-#define TASK_SIZE FIXADDR_START
+#define TASK_SIZE	FIXADDR_START
+#define TASK_SIZE_MIN	TASK_SIZE
 #endif
 
 #else /* CONFIG_MMU */
@@ -697,6 +734,8 @@ extern uintptr_t _dtb_early_pa;
 #define dtb_early_va	_dtb_early_va
 #define dtb_early_pa	_dtb_early_pa
 #endif /* CONFIG_XIP_KERNEL */
+extern u64 satp_mode;
+extern bool pgtable_l4_enabled;
 
 void paging_init(void);
 void misc_mem_init(void);

arch/riscv/include/asm/sbi.h

@@ -8,6 +8,7 @@
 #define _ASM_RISCV_SBI_H
 
 #include <linux/types.h>
+#include <linux/cpumask.h>
 
 #ifdef CONFIG_RISCV_SBI
 enum sbi_ext_id {
@@ -128,27 +129,27 @@ long sbi_get_mimpid(void);
 void sbi_set_timer(uint64_t stime_value);
 void sbi_shutdown(void);
 void sbi_clear_ipi(void);
-int sbi_send_ipi(const unsigned long *hart_mask);
-int sbi_remote_fence_i(const unsigned long *hart_mask);
-int sbi_remote_sfence_vma(const unsigned long *hart_mask,
+int sbi_send_ipi(const struct cpumask *cpu_mask);
+int sbi_remote_fence_i(const struct cpumask *cpu_mask);
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size);
 
-int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid);
-int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size);
-int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long vmid);
-int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size);
-int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid);
@@ -183,7 +184,7 @@ static inline unsigned long sbi_mk_version(unsigned long major,
 
 int sbi_err_map_linux_errno(int err);
 #else /* CONFIG_RISCV_SBI */
-static inline int sbi_remote_fence_i(const unsigned long *hart_mask) { return -1; }
+static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; }
 static inline void sbi_init(void) {}
 #endif /* CONFIG_RISCV_SBI */
 #endif /* _ASM_RISCV_SBI_H */

arch/riscv/include/asm/smp.h

@@ -92,8 +92,6 @@ static inline void riscv_clear_ipi(void)
 
 #endif /* CONFIG_SMP */
 
-void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
-
 #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
 bool cpu_has_hotplug(unsigned int cpu);
 #else

arch/riscv/include/asm/sparsemem.h

@@ -4,7 +4,11 @@
 #define _ASM_RISCV_SPARSEMEM_H
 
 #ifdef CONFIG_SPARSEMEM
-#define MAX_PHYSMEM_BITS	CONFIG_PA_BITS
+#ifdef CONFIG_64BIT
+#define MAX_PHYSMEM_BITS	56
+#else
+#define MAX_PHYSMEM_BITS	34
+#endif /* CONFIG_64BIT */
 #define SECTION_SIZE_BITS	27
 #endif /* CONFIG_SPARSEMEM */
 

arch/riscv/kernel/Makefile

@@ -43,7 +43,8 @@ obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
-obj-$(CONFIG_SMP)		+= cpu_ops_spinwait.o
+
+obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_MODULE_SECTIONS)	+= module-sections.o
 

arch/riscv/kernel/asm-offsets.c

@@ -12,6 +12,7 @@
 #include <asm/kvm_host.h>
 #include <asm/thread_info.h>
 #include <asm/ptrace.h>
+#include <asm/cpu_ops_sbi.h>
 
 void asm_offsets(void);
 
@@ -468,4 +469,6 @@ void asm_offsets(void)
 	DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN));
 
 	OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr);
+	OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr);
+	OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
 }

arch/riscv/kernel/cpu.c

@@ -7,6 +7,7 @@
 #include <linux/seq_file.h>
 #include <linux/of.h>
 #include <asm/smp.h>
+#include <asm/pgtable.h>
 
 /*
  * Returns the hart ID of the given device tree node, or -ENODEV if the node
@@ -71,18 +72,19 @@ static void print_isa(struct seq_file *f, const char *isa)
 	seq_puts(f, "\n");
 }
 
-static void print_mmu(struct seq_file *f, const char *mmu_type)
+static void print_mmu(struct seq_file *f)
 {
+	char sv_type[16];
+
 #if defined(CONFIG_32BIT)
-	if (strcmp(mmu_type, "riscv,sv32") != 0)
-		return;
+	strncpy(sv_type, "sv32", 5);
 #elif defined(CONFIG_64BIT)
-	if (strcmp(mmu_type, "riscv,sv39") != 0 &&
-	    strcmp(mmu_type, "riscv,sv48") != 0)
-		return;
+	if (pgtable_l4_enabled)
+		strncpy(sv_type, "sv48", 5);
+	else
+		strncpy(sv_type, "sv39", 5);
 #endif
-
-	seq_printf(f, "mmu\t\t: %s\n", mmu_type+6);
+	seq_printf(f, "mmu\t\t: %s\n", sv_type);
 }
 
 static void *c_start(struct seq_file *m, loff_t *pos)
@@ -107,14 +109,13 @@ static int c_show(struct seq_file *m, void *v)
 {
 	unsigned long cpu_id = (unsigned long)v - 1;
 	struct device_node *node = of_get_cpu_node(cpu_id, NULL);
-	const char *compat, *isa, *mmu;
+	const char *compat, *isa;
 
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id));
 	if (!of_property_read_string(node, "riscv,isa", &isa))
 		print_isa(m, isa);
-	if (!of_property_read_string(node, "mmu-type", &mmu))
-		print_mmu(m, mmu);
+	print_mmu(m);
 	if (!of_property_read_string(node, "compatible", &compat)
 	    && strcmp(compat, "riscv"))
 		seq_printf(m, "uarch\t\t: %s\n", compat);

arch/riscv/kernel/cpu_ops.c

@@ -8,37 +8,29 @@
 #include <linux/of.h>
 #include <linux/string.h>
 #include <linux/sched.h>
-#include <linux/sched/task_stack.h>
 #include <asm/cpu_ops.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
-void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
-
 extern const struct cpu_operations cpu_ops_sbi;
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
 extern const struct cpu_operations cpu_ops_spinwait;
-
-void cpu_update_secondary_bootdata(unsigned int cpuid,
-				   struct task_struct *tidle)
-{
-	int hartid = cpuid_to_hartid_map(cpuid);
-
-	/* Make sure tidle is updated */
-	smp_mb();
-	WRITE_ONCE(__cpu_up_stack_pointer[hartid],
-		   task_stack_page(tidle) + THREAD_SIZE);
-	WRITE_ONCE(__cpu_up_task_pointer[hartid], tidle);
-}
+#else
+const struct cpu_operations cpu_ops_spinwait = {
+	.name		= "",
+	.cpu_prepare	= NULL,
+	.cpu_start	= NULL,
+};
+#endif
 
 void __init cpu_set_ops(int cpuid)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
 	if (sbi_probe_extension(SBI_EXT_HSM) > 0) {
 		if (!cpuid)
-			pr_info("SBI v0.2 HSM extension detected\n");
+			pr_info("SBI HSM extension detected\n");
 		cpu_ops[cpuid] = &cpu_ops_sbi;
 	} else
 #endif

arch/riscv/kernel/cpu_ops_sbi.c

@@ -7,13 +7,22 @@
 
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched/task_stack.h>
 #include <asm/cpu_ops.h>
+#include <asm/cpu_ops_sbi.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
 extern char secondary_start_sbi[];
 const struct cpu_operations cpu_ops_sbi;
 
+/*
+ * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
+ * be invoked from multiple threads in parallel. Define a per cpu data
+ * to handle that.
+ */
+DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
 {
@@ -55,14 +64,19 @@ static int sbi_hsm_hart_get_status(unsigned long hartid)
 
 static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
-	int rc;
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	int hartid = cpuid_to_hartid_map(cpuid);
-
-	cpu_update_secondary_bootdata(cpuid, tidle);
-	rc = sbi_hsm_hart_start(hartid, boot_addr, 0);
-
-	return rc;
+	unsigned long hsm_data;
+	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	bdata->task_ptr = tidle;
+	bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE;
+	/* Make sure boot data is updated */
+	smp_mb();
+	hsm_data = __pa(bdata);
+	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
 static int sbi_cpu_prepare(unsigned int cpuid)

arch/riscv/kernel/cpu_ops_spinwait.c

@@ -6,11 +6,36 @@
 #include <linux/errno.h>
 #include <linux/of.h>
 #include <linux/string.h>
+#include <linux/sched/task_stack.h>
 #include <asm/cpu_ops.h>
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
 const struct cpu_operations cpu_ops_spinwait;
+void *__cpu_spinwait_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_spinwait_task_pointer[NR_CPUS] __section(".data");
+
+static void cpu_update_secondary_bootdata(unsigned int cpuid,
+				   struct task_struct *tidle)
+{
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	/*
+	 * The hartid must be less than NR_CPUS to avoid out-of-bound access
+	 * errors for __cpu_spinwait_stack/task_pointer. That is not always possible
+	 * for platforms with discontiguous hartid numbering scheme. That's why
+	 * spinwait booting is not the recommended approach for any platforms
+	 * booting Linux in S-mode and can be disabled in the future.
+	 */
+	if (hartid == INVALID_HARTID || hartid >= NR_CPUS)
+		return;
+
+	/* Make sure tidle is updated */
+	smp_mb();
+	WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid],
+		   task_stack_page(tidle) + THREAD_SIZE);
+	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
+}
 
 static int spinwait_cpu_prepare(unsigned int cpuid)
 {
@@ -28,7 +53,7 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	 * selects the first cpu to boot the kernel and causes the remainder
 	 * of the cpus to spin in a loop waiting for their stack pointer to be
 	 * setup by that main cpu.  Writing to bootdata
-	 * (i.e __cpu_up_stack_pointer) signals to the spinning cpus that they
+	 * (i.e __cpu_spinwait_stack_pointer) signals to the spinning cpus that they
 	 * can continue the boot process.
 	 */
 	cpu_update_secondary_bootdata(cpuid, tidle);

arch/riscv/kernel/head.S

@@ -11,6 +11,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
+#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include "efi-header.S"
@@ -105,7 +106,8 @@ relocate:
 
 	/* Compute satp for kernel page tables, but don't load it yet */
 	srl a2, a0, PAGE_SHIFT
-	li a1, SATP_MODE
+	la a1, satp_mode
+	REG_L a1, 0(a1)
 	or a2, a2, a1
 
 	/*
@@ -167,15 +169,15 @@ secondary_start_sbi:
 	la a3, .Lsecondary_park
 	csrw CSR_TVEC, a3
 
-	slli a3, a0, LGREG
-	la a4, __cpu_up_stack_pointer
-	XIP_FIXUP_OFFSET a4
-	la a5, __cpu_up_task_pointer
-	XIP_FIXUP_OFFSET a5
-	add a4, a3, a4
-	add a5, a3, a5
-	REG_L sp, (a4)
-	REG_L tp, (a5)
+	/* a0 contains the hartid & a1 contains boot data */
+	li a2, SBI_HART_BOOT_TASK_PTR_OFFSET
+	XIP_FIXUP_OFFSET a2
+	add a2, a2, a1
+	REG_L tp, (a2)
+	li a3, SBI_HART_BOOT_STACK_PTR_OFFSET
+	XIP_FIXUP_OFFSET a3
+	add a3, a3, a1
+	REG_L sp, (a3)
 
 .Lsecondary_start_common:
 
@@ -257,13 +259,13 @@ pmp_done:
 	li t0, SR_FS
 	csrc CSR_STATUS, t0
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
 	li t0, CONFIG_NR_CPUS
 	blt a0, t0, .Lgood_cores
 	tail .Lsecondary_park
 .Lgood_cores:
-#endif
 
+	/* The lottery system is only required for spinwait booting method */
 #ifndef CONFIG_XIP_KERNEL
 	/* Pick one hart to run the main boot sequence */
 	la a3, hart_lottery
@@ -282,6 +284,10 @@ pmp_done:
 	/* first time here if hart_lottery in RAM is not set */
 	beq t0, t1, .Lsecondary_start
 
+#endif /* CONFIG_XIP */
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
+
+#ifdef CONFIG_XIP_KERNEL
 	la sp, _end + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	mv s0, a0
@@ -338,16 +344,16 @@ clear_bss_done:
 	call soc_early_init
 	tail start_kernel
 
+#if CONFIG_RISCV_BOOT_SPINWAIT
 .Lsecondary_start:
-#ifdef CONFIG_SMP
 	/* Set trap vector to spin forever to help debug */
 	la a3, .Lsecondary_park
 	csrw CSR_TVEC, a3
 
 	slli a3, a0, LGREG
-	la a1, __cpu_up_stack_pointer
+	la a1, __cpu_spinwait_stack_pointer
 	XIP_FIXUP_OFFSET a1
-	la a2, __cpu_up_task_pointer
+	la a2, __cpu_spinwait_task_pointer
 	XIP_FIXUP_OFFSET a2
 	add a1, a3, a1
 	add a2, a3, a2
@@ -365,7 +371,7 @@ clear_bss_done:
 	fence
 
 	tail .Lsecondary_start_common
-#endif
+#endif /* CONFIG_RISCV_BOOT_SPINWAIT */
 
 END(_start_kernel)
 

arch/riscv/kernel/head.h

@@ -16,7 +16,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa);
 asmlinkage void __init __copy_data(void);
 #endif
 
-extern void *__cpu_up_stack_pointer[];
-extern void *__cpu_up_task_pointer[];
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
+extern void *__cpu_spinwait_stack_pointer[];
+extern void *__cpu_spinwait_task_pointer[];
+#endif
 
 #endif /* __ASM_HEAD_H */

arch/riscv/kernel/ptrace.c

@@ -42,12 +42,10 @@ static int riscv_gpr_set(struct task_struct *target,
 			 unsigned int pos, unsigned int count,
 			 const void *kbuf, const void __user *ubuf)
 {
-	int ret;
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(target);
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
-	return ret;
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
 }
 
 #ifdef CONFIG_FPU

arch/riscv/kernel/sbi.c

@@ -16,8 +16,8 @@ unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT;
 EXPORT_SYMBOL(sbi_spec_version);
 
 static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init;
-static int (*__sbi_send_ipi)(const unsigned long *hart_mask) __ro_after_init;
-static int (*__sbi_rfence)(int fid, const unsigned long *hart_mask,
+static int (*__sbi_send_ipi)(const struct cpumask *cpu_mask) __ro_after_init;
+static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask,
 			   unsigned long start, unsigned long size,
 			   unsigned long arg4, unsigned long arg5) __ro_after_init;
 
@@ -67,6 +67,30 @@ int sbi_err_map_linux_errno(int err)
 EXPORT_SYMBOL(sbi_err_map_linux_errno);
 
 #ifdef CONFIG_RISCV_SBI_V01
+static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask)
+{
+	unsigned long cpuid, hartid;
+	unsigned long hmask = 0;
+
+	/*
+	 * There is no maximum hartid concept in RISC-V and NR_CPUS must not be
+	 * associated with hartid. As SBI v0.1 is only kept for backward compatibility
+	 * and will be removed in the future, there is no point in supporting hartid
+	 * greater than BITS_PER_LONG (32 for RV32 and 64 for RV64). Ideally, SBI v0.2
+	 * should be used for platforms with hartid greater than BITS_PER_LONG.
+	 */
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hartid >= BITS_PER_LONG) {
+			pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n");
+			break;
+		}
+		hmask |= 1 << hartid;
+	}
+
+	return hmask;
+}
+
 /**
  * sbi_console_putchar() - Writes given character to the console device.
  * @ch: The data to be written to the console.
@@ -132,33 +156,44 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
 #endif
 }
 
-static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
 {
-	sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)hart_mask,
+	unsigned long hart_mask;
+
+	if (!cpu_mask)
+		cpu_mask = cpu_online_mask;
+	hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
+
+	sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask),
 		  0, 0, 0, 0, 0);
 	return 0;
 }
 
-static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
 			    unsigned long start, unsigned long size,
 			    unsigned long arg4, unsigned long arg5)
 {
 	int result = 0;
+	unsigned long hart_mask;
+
+	if (!cpu_mask)
+		cpu_mask = cpu_online_mask;
+	hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask);
 
 	/* v0.2 function IDs are equivalent to v0.1 extension IDs */
 	switch (fid) {
 	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
 		sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0,
-			  (unsigned long)hart_mask, 0, 0, 0, 0, 0);
+			  (unsigned long)&hart_mask, 0, 0, 0, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
 		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0,
-			  (unsigned long)hart_mask, start, size,
+			  (unsigned long)&hart_mask, start, size,
 			  0, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
 		sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0,
-			  (unsigned long)hart_mask, start, size,
+			  (unsigned long)&hart_mask, start, size,
 			  arg4, 0, 0);
 		break;
 	default:
@@ -180,7 +215,7 @@ static void __sbi_set_timer_v01(uint64_t stime_value)
 		sbi_major_version(), sbi_minor_version());
 }
 
-static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v01(const struct cpumask *cpu_mask)
 {
 	pr_warn("IPI extension is not available in SBI v%lu.%lu\n",
 		sbi_major_version(), sbi_minor_version());
@@ -188,7 +223,7 @@ static int __sbi_send_ipi_v01(const unsigned long *hart_mask)
 	return 0;
 }
 
-static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask,
 			    unsigned long start, unsigned long size,
 			    unsigned long arg4, unsigned long arg5)
 {
@@ -212,37 +247,33 @@ static void __sbi_set_timer_v02(uint64_t stime_value)
 #endif
 }
 
-static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
+static int __sbi_send_ipi_v02(const struct cpumask *cpu_mask)
 {
-	unsigned long hartid, hmask_val, hbase;
-	struct cpumask tmask;
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0;
 	struct sbiret ret = {0};
 	int result;
 
-	if (!hart_mask || !(*hart_mask)) {
-		riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
-		hart_mask = cpumask_bits(&tmask);
-	}
+	if (!cpu_mask)
+		cpu_mask = cpu_online_mask;
 
-	hmask_val = 0;
-	hbase = 0;
-	for_each_set_bit(hartid, hart_mask, NR_CPUS) {
-		if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
 			ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
-					hmask_val, hbase, 0, 0, 0, 0);
+					hmask, hbase, 0, 0, 0, 0);
 			if (ret.error)
 				goto ecall_failed;
-			hmask_val = 0;
+			hmask = 0;
 			hbase = 0;
 		}
-		if (!hmask_val)
+		if (!hmask)
 			hbase = hartid;
-		hmask_val |= 1UL << (hartid - hbase);
+		hmask |= 1UL << (hartid - hbase);
 	}
 
-	if (hmask_val) {
+	if (hmask) {
 		ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI,
-				hmask_val, hbase, 0, 0, 0, 0);
+				hmask, hbase, 0, 0, 0, 0);
 		if (ret.error)
 			goto ecall_failed;
 	}
@@ -252,11 +283,11 @@ static int __sbi_send_ipi_v02(const unsigned long *hart_mask)
 ecall_failed:
 	result = sbi_err_map_linux_errno(ret.error);
 	pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
-	       __func__, hbase, hmask_val, result);
+	       __func__, hbase, hmask, result);
 	return result;
 }
 
-static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
+static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask,
 				 unsigned long hbase, unsigned long start,
 				 unsigned long size, unsigned long arg4,
 				 unsigned long arg5)
@@ -267,31 +298,31 @@ static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
 
 	switch (fid) {
 	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, 0, 0, 0, 0);
+		ret = sbi_ecall(ext, fid, hmask, hbase, 0, 0, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, arg4, 0);
 		break;
 
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, arg4, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, 0, 0);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
-		ret = sbi_ecall(ext, fid, hmask_val, hbase, start,
+		ret = sbi_ecall(ext, fid, hmask, hbase, start,
 				size, arg4, 0);
 		break;
 	default:
@@ -303,43 +334,39 @@ static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask_val,
 	if (ret.error) {
 		result = sbi_err_map_linux_errno(ret.error);
 		pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n",
-		       __func__, hbase, hmask_val, result);
+		       __func__, hbase, hmask, result);
 	}
 
 	return result;
 }
 
-static int __sbi_rfence_v02(int fid, const unsigned long *hart_mask,
+static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask,
 			    unsigned long start, unsigned long size,
 			    unsigned long arg4, unsigned long arg5)
 {
-	unsigned long hmask_val, hartid, hbase;
-	struct cpumask tmask;
+	unsigned long hartid, cpuid, hmask = 0, hbase = 0;
 	int result;
 
-	if (!hart_mask || !(*hart_mask)) {
-		riscv_cpuid_to_hartid_mask(cpu_online_mask, &tmask);
-		hart_mask = cpumask_bits(&tmask);
-	}
+	if (!cpu_mask)
+		cpu_mask = cpu_online_mask;
 
-	hmask_val = 0;
-	hbase = 0;
-	for_each_set_bit(hartid, hart_mask, NR_CPUS) {
-		if (hmask_val && ((hbase + BITS_PER_LONG) <= hartid)) {
-			result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+	for_each_cpu(cpuid, cpu_mask) {
+		hartid = cpuid_to_hartid_map(cpuid);
+		if (hmask && ((hbase + BITS_PER_LONG) <= hartid)) {
+			result = __sbi_rfence_v02_call(fid, hmask, hbase,
 						       start, size, arg4, arg5);
 			if (result)
 				return result;
-			hmask_val = 0;
+			hmask = 0;
 			hbase = 0;
 		}
-		if (!hmask_val)
+		if (!hmask)
 			hbase = hartid;
-		hmask_val |= 1UL << (hartid - hbase);
+		hmask |= 1UL << (hartid - hbase);
 	}
 
-	if (hmask_val) {
-		result = __sbi_rfence_v02_call(fid, hmask_val, hbase,
+	if (hmask) {
+		result = __sbi_rfence_v02_call(fid, hmask, hbase,
 					       start, size, arg4, arg5);
 		if (result)
 			return result;
@@ -361,44 +388,44 @@ void sbi_set_timer(uint64_t stime_value)
 
 /**
  * sbi_send_ipi() - Send an IPI to any hart.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
-int sbi_send_ipi(const unsigned long *hart_mask)
+int sbi_send_ipi(const struct cpumask *cpu_mask)
 {
-	return __sbi_send_ipi(hart_mask);
+	return __sbi_send_ipi(cpu_mask);
 }
 EXPORT_SYMBOL(sbi_send_ipi);
 
 /**
  * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
-int sbi_remote_fence_i(const unsigned long *hart_mask)
+int sbi_remote_fence_i(const struct cpumask *cpu_mask)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I,
-			    hart_mask, 0, 0, 0, 0);
+			    cpu_mask, 0, 0, 0, 0);
 }
 EXPORT_SYMBOL(sbi_remote_fence_i);
 
 /**
  * sbi_remote_sfence_vma() - Execute SFENCE.VMA instructions on given remote
  *			     harts for the specified virtual address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the virtual address
  * @size: Total size of the virtual address range.
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
-int sbi_remote_sfence_vma(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
-			    hart_mask, start, size, 0, 0);
+			    cpu_mask, start, size, 0, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma);
 
@@ -406,38 +433,38 @@ EXPORT_SYMBOL(sbi_remote_sfence_vma);
  * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given
  * remote harts for a virtual address range belonging to a specific ASID.
  *
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the virtual address
  * @size: Total size of the virtual address range.
  * @asid: The value of address space identifier (ASID).
  *
  * Return: 0 on success, appropriate linux error code otherwise.
  */
-int sbi_remote_sfence_vma_asid(const unsigned long *hart_mask,
+int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
-			    hart_mask, start, size, asid, 0);
+			    cpu_mask, start, size, asid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_sfence_vma_asid);
 
 /**
  * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote
  *			   harts for the specified guest physical address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the guest physical address
  * @size: Total size of the guest physical address range.
  *
  * Return: None
  */
-int sbi_remote_hfence_gvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
-			    hart_mask, start, size, 0, 0);
+			    cpu_mask, start, size, 0, 0);
 }
 EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
 
@@ -445,38 +472,38 @@ EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma);
  * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given
  * remote harts for a guest physical address range belonging to a specific VMID.
  *
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the guest physical address
  * @size: Total size of the guest physical address range.
  * @vmid: The value of guest ID (VMID).
  *
  * Return: 0 if success, Error otherwise.
  */
-int sbi_remote_hfence_gvma_vmid(const unsigned long *hart_mask,
+int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long vmid)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
-			    hart_mask, start, size, vmid, 0);
+			    cpu_mask, start, size, vmid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid);
 
 /**
  * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote
  *			     harts for the current guest virtual address range.
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the current guest virtual address
  * @size: Total size of the current guest virtual address range.
  *
  * Return: None
  */
-int sbi_remote_hfence_vvma(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask,
 			   unsigned long start,
 			   unsigned long size)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
-			    hart_mask, start, size, 0, 0);
+			    cpu_mask, start, size, 0, 0);
 }
 EXPORT_SYMBOL(sbi_remote_hfence_vvma);
 
@@ -485,20 +512,20 @@ EXPORT_SYMBOL(sbi_remote_hfence_vvma);
  * remote harts for current guest virtual address range belonging to a specific
  * ASID.
  *
- * @hart_mask: A cpu mask containing all the target harts.
+ * @cpu_mask: A cpu mask containing all the target harts.
  * @start: Start of the current guest virtual address
  * @size: Total size of the current guest virtual address range.
  * @asid: The value of address space identifier (ASID).
  *
  * Return: None
  */
-int sbi_remote_hfence_vvma_asid(const unsigned long *hart_mask,
+int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask,
 				unsigned long start,
 				unsigned long size,
 				unsigned long asid)
 {
 	return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
-			    hart_mask, start, size, asid, 0);
+			    cpu_mask, start, size, asid, 0);
 }
 EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid);
 
@@ -591,11 +618,7 @@ long sbi_get_mimpid(void)
 
 static void sbi_send_cpumask_ipi(const struct cpumask *target)
 {
-	struct cpumask hartid_mask;
-
-	riscv_cpuid_to_hartid_mask(target, &hartid_mask);
-
-	sbi_send_ipi(cpumask_bits(&hartid_mask));
+	sbi_send_ipi(target);
 }
 
 static const struct riscv_ipi_ops sbi_ipi_ops = {

arch/riscv/kernel/setup.c

@@ -59,16 +59,6 @@ atomic_t hart_lottery __section(".sdata")
 unsigned long boot_cpu_hartid;
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
-void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out)
-{
-	int cpu;
-
-	cpumask_clear(out);
-	for_each_cpu(cpu, in)
-		cpumask_set_cpu(cpuid_to_hartid_map(cpu), out);
-}
-EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask);
-
 /*
  * Place kernel memory regions on the resource tree so that
  * kexec-tools can retrieve them from /proc/iomem. While there

arch/riscv/kernel/smpboot.c

@@ -96,7 +96,7 @@ void __init setup_smp(void)
 		if (cpuid >= NR_CPUS) {
 			pr_warn("Invalid cpuid [%d] for hartid [%d]\n",
 				cpuid, hart);
-			break;
+			continue;
 		}
 
 		cpuid_to_hartid_map(cpuid) = hart;

arch/riscv/kvm/mmu.c

@@ -114,7 +114,6 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr,
 
 static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
 {
-	struct cpumask hmask;
 	unsigned long size = PAGE_SIZE;
 	struct kvm_vmid *vmid = &kvm->arch.vmid;
 
@@ -127,8 +126,7 @@ static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
 	 * where the Guest/VM is running.
 	 */
 	preempt_disable();
-	riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask);
-	sbi_remote_hfence_gvma_vmid(cpumask_bits(&hmask), addr, size,
+	sbi_remote_hfence_gvma_vmid(cpu_online_mask, addr, size,
 				    READ_ONCE(vmid->vmid));
 	preempt_enable();
 }

arch/riscv/kvm/vcpu_sbi_replace.c

@@ -82,7 +82,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 {
 	int ret = 0;
 	unsigned long i;
-	struct cpumask cm, hm;
+	struct cpumask cm;
 	struct kvm_vcpu *tmp;
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
@@ -90,7 +90,6 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 	unsigned long funcid = cp->a6;
 
 	cpumask_clear(&cm);
-	cpumask_clear(&hm);
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
@@ -103,17 +102,15 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 		cpumask_set_cpu(tmp->cpu, &cm);
 	}
 
-	riscv_cpuid_to_hartid_mask(&cm, &hm);
-
 	switch (funcid) {
 	case SBI_EXT_RFENCE_REMOTE_FENCE_I:
-		ret = sbi_remote_fence_i(cpumask_bits(&hm));
+		ret = sbi_remote_fence_i(&cm);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
-		ret = sbi_remote_hfence_vvma(cpumask_bits(&hm), cp->a2, cp->a3);
+		ret = sbi_remote_hfence_vvma(&cm, cp->a2, cp->a3);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
-		ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), cp->a2,
+		ret = sbi_remote_hfence_vvma_asid(&cm, cp->a2,
 						  cp->a3, cp->a4);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA:

arch/riscv/kvm/vcpu_sbi_v01.c

@@ -38,7 +38,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	int i, ret = 0;
 	u64 next_cycle;
 	struct kvm_vcpu *rvcpu;
-	struct cpumask cm, hm;
+	struct cpumask cm;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 
@@ -101,15 +101,12 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 				continue;
 			cpumask_set_cpu(rvcpu->cpu, &cm);
 		}
-		riscv_cpuid_to_hartid_mask(&cm, &hm);
 		if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I)
-			ret = sbi_remote_fence_i(cpumask_bits(&hm));
+			ret = sbi_remote_fence_i(&cm);
 		else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA)
-			ret = sbi_remote_hfence_vvma(cpumask_bits(&hm),
-						cp->a1, cp->a2);
+			ret = sbi_remote_hfence_vvma(&cm, cp->a1, cp->a2);
 		else
-			ret = sbi_remote_hfence_vvma_asid(cpumask_bits(&hm),
-						cp->a1, cp->a2, cp->a3);
+			ret = sbi_remote_hfence_vvma_asid(&cm, cp->a1, cp->a2, cp->a3);
 		break;
 	default:
 		ret = -EINVAL;

arch/riscv/kvm/vmid.c

@@ -67,7 +67,6 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu)
 {
 	unsigned long i;
 	struct kvm_vcpu *v;
-	struct cpumask hmask;
 	struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid;
 
 	if (!kvm_riscv_stage2_vmid_ver_changed(vmid))
@@ -102,8 +101,7 @@ void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu)
 		 * running, we force VM exits on all host CPUs using IPI and
 		 * flush all Guest TLBs.
 		 */
-		riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask);
-		sbi_remote_hfence_gvma(cpumask_bits(&hmask), 0, 0);
+		sbi_remote_hfence_gvma(cpu_online_mask, 0, 0);
 	}
 
 	vmid->vmid = vmid_next;

arch/riscv/mm/cacheflush.c

@@ -67,10 +67,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 */
 		smp_mb();
 	} else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
-		cpumask_t hartid_mask;
-
-		riscv_cpuid_to_hartid_mask(&others, &hartid_mask);
-		sbi_remote_fence_i(cpumask_bits(&hartid_mask));
+		sbi_remote_fence_i(&others);
 	} else {
 		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
 	}

arch/riscv/mm/context.c

@@ -192,7 +192,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 switch_mm_fast:
 	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) |
 		  ((cntx & asid_mask) << SATP_ASID_SHIFT) |
-		  SATP_MODE);
+		  satp_mode);
 
 	if (need_flush_tlb)
 		local_flush_tlb_all();
@@ -201,7 +201,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 static void set_mm_noasid(struct mm_struct *mm)
 {
 	/* Switch the page table and blindly nuke entire local TLB */
-	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | SATP_MODE);
+	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
 	local_flush_tlb_all();
 }
 

arch/riscv/mm/init.c

@@ -37,13 +37,19 @@ EXPORT_SYMBOL(kernel_map);
 #define kernel_map	(*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
 #endif
 
+#ifdef CONFIG_64BIT
+u64 satp_mode = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_48 : SATP_MODE_39;
+#else
+u64 satp_mode = SATP_MODE_32;
+#endif
+EXPORT_SYMBOL(satp_mode);
+
+bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+EXPORT_SYMBOL(pgtable_l4_enabled);
+
 phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
 
-#ifdef CONFIG_XIP_KERNEL
-extern char _xiprom[], _exiprom[], __data_loc;
-#endif
-
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 							__page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
@@ -53,15 +59,6 @@ extern char _start[];
 void *_dtb_early_va __initdata;
 uintptr_t _dtb_early_pa __initdata;
 
-struct pt_alloc_ops {
-	pte_t *(*get_pte_virt)(phys_addr_t pa);
-	phys_addr_t (*alloc_pte)(uintptr_t va);
-#ifndef __PAGETABLE_PMD_FOLDED
-	pmd_t *(*get_pmd_virt)(phys_addr_t pa);
-	phys_addr_t (*alloc_pmd)(uintptr_t va);
-#endif
-};
-
 static phys_addr_t dma32_phys_limit __initdata;
 
 static void __init zone_sizes_init(void)
@@ -102,10 +99,14 @@ static void __init print_vm_layout(void)
 		  (unsigned long)VMALLOC_END);
 	print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
 		  (unsigned long)high_memory);
-#ifdef CONFIG_64BIT
-	print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
-		  (unsigned long)ADDRESS_SPACE_END);
+	if (IS_ENABLED(CONFIG_64BIT)) {
+#ifdef CONFIG_KASAN
+		print_mlm("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
 #endif
+
+		print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
+			  (unsigned long)ADDRESS_SPACE_END);
+	}
 }
 #else
 static void print_vm_layout(void) { }
@@ -130,18 +131,8 @@ void __init mem_init(void)
 	print_vm_layout();
 }
 
-/*
- * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
- * whereas for 64-bit kernel, the end of the virtual address space is occupied
- * by the modules/BPF/kernel mappings which reduces the available size of the
- * linear mapping.
- * Limit the memory size via mem.
- */
-#ifdef CONFIG_64BIT
-static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
-#else
-static phys_addr_t memory_limit = -PAGE_OFFSET;
-#endif
+/* Limit the memory size via mem. */
+static phys_addr_t memory_limit;
 
 static int __init early_mem(char *p)
 {
@@ -162,35 +153,31 @@ early_param("mem", early_mem);
 static void __init setup_bootmem(void)
 {
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
-	phys_addr_t vmlinux_start = __pa_symbol(&_start);
-	phys_addr_t __maybe_unused max_mapped_addr;
-	phys_addr_t phys_ram_end;
+	phys_addr_t max_mapped_addr;
+	phys_addr_t phys_ram_end, vmlinux_start;
 
-#ifdef CONFIG_XIP_KERNEL
-	vmlinux_start = __pa_symbol(&_sdata);
-#endif
+	if (IS_ENABLED(CONFIG_XIP_KERNEL))
+		vmlinux_start = __pa_symbol(&_sdata);
+	else
+		vmlinux_start = __pa_symbol(&_start);
 
 	memblock_enforce_memory_limit(memory_limit);
 
-	/*
-	 * Reserve from the start of the kernel to the end of the kernel
-	 */
-#if defined(CONFIG_64BIT) && defined(CONFIG_STRICT_KERNEL_RWX)
 	/*
 	 * Make sure we align the reservation on PMD_SIZE since we will
 	 * map the kernel in the linear mapping as read-only: we do not want
 	 * any allocation to happen between _end and the next pmd aligned page.
 	 */
-	vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
-#endif
+	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
+	/*
+	 * Reserve from the start of the kernel to the end of the kernel
+	 */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-
 	phys_ram_end = memblock_end_of_DRAM();
-#ifndef CONFIG_XIP_KERNEL
-	phys_ram_base = memblock_start_of_DRAM();
-#endif
-#ifndef CONFIG_64BIT
+	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
+		phys_ram_base = memblock_start_of_DRAM();
 	/*
 	 * memblock allocator is not aware of the fact that last 4K bytes of
 	 * the addressable memory can not be mapped because of IS_ERR_VALUE
@@ -200,10 +187,11 @@ static void __init setup_bootmem(void)
 	 * address space is occupied by the kernel mapping then this check must
 	 * be done as soon as the kernel mapping base address is determined.
 	 */
-	max_mapped_addr = __pa(~(ulong)0);
-	if (max_mapped_addr == (phys_ram_end - 1))
-		memblock_set_current_limit(max_mapped_addr - 4096);
-#endif
+	if (!IS_ENABLED(CONFIG_64BIT)) {
+		max_mapped_addr = __pa(~(ulong)0);
+		if (max_mapped_addr == (phys_ram_end - 1))
+			memblock_set_current_limit(max_mapped_addr - 4096);
+	}
 
 	min_low_pfn = PFN_UP(phys_ram_base);
 	max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
@@ -229,13 +217,7 @@ static void __init setup_bootmem(void)
 }
 
 #ifdef CONFIG_MMU
-static struct pt_alloc_ops _pt_ops __initdata;
-
-#ifdef CONFIG_XIP_KERNEL
-#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&_pt_ops))
-#else
-#define pt_ops _pt_ops
-#endif
+struct pt_alloc_ops pt_ops __initdata;
 
 unsigned long riscv_pfn_base __ro_after_init;
 EXPORT_SYMBOL(riscv_pfn_base);
@@ -245,9 +227,11 @@ pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
 
 pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
+static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
 static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 #ifdef CONFIG_XIP_KERNEL
+#define pt_ops			(*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
 #define trampoline_pg_dir      ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
 #define fixmap_pte             ((pte_t *)XIP_FIXUP(fixmap_pte))
 #define early_pg_dir           ((pgd_t *)XIP_FIXUP(early_pg_dir))
@@ -333,6 +317,16 @@ static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 #define early_pmd      ((pmd_t *)XIP_FIXUP(early_pmd))
 #endif /* CONFIG_XIP_KERNEL */
 
+static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
+
+#ifdef CONFIG_XIP_KERNEL
+#define trampoline_pud ((pud_t *)XIP_FIXUP(trampoline_pud))
+#define fixmap_pud     ((pud_t *)XIP_FIXUP(fixmap_pud))
+#define early_pud      ((pud_t *)XIP_FIXUP(early_pud))
+#endif /* CONFIG_XIP_KERNEL */
+
 static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
 {
 	/* Before MMU is enabled */
@@ -352,7 +346,7 @@ static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
 
 static phys_addr_t __init alloc_pmd_early(uintptr_t va)
 {
-	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+	BUG_ON((va - kernel_map.virt_addr) >> PUD_SHIFT);
 
 	return (uintptr_t)early_pmd;
 }
@@ -399,21 +393,97 @@ static void __init create_pmd_mapping(pmd_t *pmdp,
 	create_pte_mapping(ptep, va, pa, sz, prot);
 }
 
-#define pgd_next_t		pmd_t
-#define alloc_pgd_next(__va)	pt_ops.alloc_pmd(__va)
-#define get_pgd_next_virt(__pa)	pt_ops.get_pmd_virt(__pa)
+static pud_t *__init get_pud_virt_early(phys_addr_t pa)
+{
+	return (pud_t *)((uintptr_t)pa);
+}
+
+static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa)
+{
+	clear_fixmap(FIX_PUD);
+	return (pud_t *)set_fixmap_offset(FIX_PUD, pa);
+}
+
+static pud_t *__init get_pud_virt_late(phys_addr_t pa)
+{
+	return (pud_t *)__va(pa);
+}
+
+static phys_addr_t __init alloc_pud_early(uintptr_t va)
+{
+	/* Only one PUD is available for early mapping */
+	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);
+
+	return (uintptr_t)early_pud;
+}
+
+static phys_addr_t __init alloc_pud_fixmap(uintptr_t va)
+{
+	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+}
+
+static phys_addr_t alloc_pud_late(uintptr_t va)
+{
+	unsigned long vaddr;
+
+	vaddr = __get_free_page(GFP_KERNEL);
+	BUG_ON(!vaddr);
+	return __pa(vaddr);
+}
+
+static void __init create_pud_mapping(pud_t *pudp,
+				      uintptr_t va, phys_addr_t pa,
+				      phys_addr_t sz, pgprot_t prot)
+{
+	pmd_t *nextp;
+	phys_addr_t next_phys;
+	uintptr_t pud_index = pud_index(va);
+
+	if (sz == PUD_SIZE) {
+		if (pud_val(pudp[pud_index]) == 0)
+			pudp[pud_index] = pfn_pud(PFN_DOWN(pa), prot);
+		return;
+	}
+
+	if (pud_val(pudp[pud_index]) == 0) {
+		next_phys = pt_ops.alloc_pmd(va);
+		pudp[pud_index] = pfn_pud(PFN_DOWN(next_phys), PAGE_TABLE);
+		nextp = pt_ops.get_pmd_virt(next_phys);
+		memset(nextp, 0, PAGE_SIZE);
+	} else {
+		next_phys = PFN_PHYS(_pud_pfn(pudp[pud_index]));
+		nextp = pt_ops.get_pmd_virt(next_phys);
+	}
+
+	create_pmd_mapping(nextp, va, pa, sz, prot);
+}
+
+#define pgd_next_t		pud_t
+#define alloc_pgd_next(__va)	(pgtable_l4_enabled ?			\
+		pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va))
+#define get_pgd_next_virt(__pa)	(pgtable_l4_enabled ?			\
+		pt_ops.get_pud_virt(__pa) : (pgd_next_t *)pt_ops.get_pmd_virt(__pa))
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
-	create_pmd_mapping(__nextp, __va, __pa, __sz, __prot)
-#define fixmap_pgd_next		fixmap_pmd
+				(pgtable_l4_enabled ?			\
+		create_pud_mapping(__nextp, __va, __pa, __sz, __prot) :	\
+		create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot))
+#define fixmap_pgd_next		(pgtable_l4_enabled ?			\
+		(uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd)
+#define trampoline_pgd_next	(pgtable_l4_enabled ?			\
+		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)
+#define early_dtb_pgd_next	(pgtable_l4_enabled ?			\
+		(uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)
 #else
 #define pgd_next_t		pte_t
 #define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
 #define get_pgd_next_virt(__pa)	pt_ops.get_pte_virt(__pa)
 #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
 	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
-#define fixmap_pgd_next		fixmap_pte
+#define fixmap_pgd_next		((uintptr_t)fixmap_pte)
+#define early_dtb_pgd_next	((uintptr_t)early_dtb_pmd)
+#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot)
 #define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot)
-#endif
+#endif /* __PAGETABLE_PMD_FOLDED */
 
 void __init create_pgd_mapping(pgd_t *pgdp,
 				      uintptr_t va, phys_addr_t pa,
@@ -452,6 +522,8 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 }
 
 #ifdef CONFIG_XIP_KERNEL
+extern char _xiprom[], _exiprom[], __data_loc;
+
 /* called from head.S with MMU off */
 asmlinkage void __init __copy_data(void)
 {
@@ -500,6 +572,57 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
 }
 #endif /* CONFIG_STRICT_KERNEL_RWX */
 
+#ifdef CONFIG_64BIT
+static void __init disable_pgtable_l4(void)
+{
+	pgtable_l4_enabled = false;
+	kernel_map.page_offset = PAGE_OFFSET_L3;
+	satp_mode = SATP_MODE_39;
+}
+
+/*
+ * There is a simple way to determine if 4-level is supported by the
+ * underlying hardware: establish 1:1 mapping in 4-level page table mode
+ * then read SATP to see if the configuration was taken into account
+ * meaning sv48 is supported.
+ */
+static __init void set_satp_mode(void)
+{
+	u64 identity_satp, hw_satp;
+	uintptr_t set_satp_mode_pmd;
+
+	set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
+	create_pgd_mapping(early_pg_dir,
+			   set_satp_mode_pmd, (uintptr_t)early_pud,
+			   PGDIR_SIZE, PAGE_TABLE);
+	create_pud_mapping(early_pud,
+			   set_satp_mode_pmd, (uintptr_t)early_pmd,
+			   PUD_SIZE, PAGE_TABLE);
+	/* Handle the case where set_satp_mode straddles 2 PMDs */
+	create_pmd_mapping(early_pmd,
+			   set_satp_mode_pmd, set_satp_mode_pmd,
+			   PMD_SIZE, PAGE_KERNEL_EXEC);
+	create_pmd_mapping(early_pmd,
+			   set_satp_mode_pmd + PMD_SIZE,
+			   set_satp_mode_pmd + PMD_SIZE,
+			   PMD_SIZE, PAGE_KERNEL_EXEC);
+
+	identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
+
+	local_flush_tlb_all();
+	csr_write(CSR_SATP, identity_satp);
+	hw_satp = csr_swap(CSR_SATP, 0ULL);
+	local_flush_tlb_all();
+
+	if (hw_satp != identity_satp)
+		disable_pgtable_l4();
+
+	memset(early_pg_dir, 0, PAGE_SIZE);
+	memset(early_pud, 0, PAGE_SIZE);
+	memset(early_pmd, 0, PAGE_SIZE);
+}
+#endif
+
 /*
  * setup_vm() is called from head.S with MMU-off.
  *
@@ -564,10 +687,15 @@ static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
 	uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
 
 	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
-			   IS_ENABLED(CONFIG_64BIT) ? (uintptr_t)early_dtb_pmd : pa,
+			   IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa,
 			   PGDIR_SIZE,
 			   IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
 
+	if (pgtable_l4_enabled) {
+		create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
+				   (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
+	}
+
 	if (IS_ENABLED(CONFIG_64BIT)) {
 		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
 				   pa, PMD_SIZE, PAGE_KERNEL);
@@ -589,11 +717,64 @@ static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
 	dtb_early_pa = dtb_pa;
 }
 
+/*
+ * MMU is not enabled, the page tables are allocated directly using
+ * early_pmd/pud/p4d and the address returned is the physical one.
+ */
+void __init pt_ops_set_early(void)
+{
+	pt_ops.alloc_pte = alloc_pte_early;
+	pt_ops.get_pte_virt = get_pte_virt_early;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_early;
+	pt_ops.get_pmd_virt = get_pmd_virt_early;
+	pt_ops.alloc_pud = alloc_pud_early;
+	pt_ops.get_pud_virt = get_pud_virt_early;
+#endif
+}
+
+/*
+ * MMU is enabled but page table setup is not complete yet.
+ * fixmap page table alloc functions must be used as a means to temporarily
+ * map the allocated physical pages since the linear mapping does not exist yet.
+ *
+ * Note that this is called with MMU disabled, hence kernel_mapping_pa_to_va,
+ * but it will be used as described above.
+ */
+void __init pt_ops_set_fixmap(void)
+{
+	pt_ops.alloc_pte = kernel_mapping_pa_to_va((uintptr_t)alloc_pte_fixmap);
+	pt_ops.get_pte_virt = kernel_mapping_pa_to_va((uintptr_t)get_pte_virt_fixmap);
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = kernel_mapping_pa_to_va((uintptr_t)alloc_pmd_fixmap);
+	pt_ops.get_pmd_virt = kernel_mapping_pa_to_va((uintptr_t)get_pmd_virt_fixmap);
+	pt_ops.alloc_pud = kernel_mapping_pa_to_va((uintptr_t)alloc_pud_fixmap);
+	pt_ops.get_pud_virt = kernel_mapping_pa_to_va((uintptr_t)get_pud_virt_fixmap);
+#endif
+}
+
+/*
+ * MMU is enabled and page table setup is complete, so from now, we can use
+ * generic page allocation functions to setup page table.
+ */
+void __init pt_ops_set_late(void)
+{
+	pt_ops.alloc_pte = alloc_pte_late;
+	pt_ops.get_pte_virt = get_pte_virt_late;
+#ifndef __PAGETABLE_PMD_FOLDED
+	pt_ops.alloc_pmd = alloc_pmd_late;
+	pt_ops.get_pmd_virt = get_pmd_virt_late;
+	pt_ops.alloc_pud = alloc_pud_late;
+	pt_ops.get_pud_virt = get_pud_virt_late;
+#endif
+}
+
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 {
 	pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;
 
 	kernel_map.virt_addr = KERNEL_LINK_ADDR;
+	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);
 
 #ifdef CONFIG_XIP_KERNEL
 	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
@@ -608,11 +789,24 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	kernel_map.phys_addr = (uintptr_t)(&_start);
 	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
 #endif
+
+#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+	set_satp_mode();
+#endif
+
 	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
 	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
 
 	riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
 
+	/*
+	 * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
+	 * kernel, whereas for 64-bit kernel, the end of the virtual address
+	 * space is occupied by the modules/BPF/kernel mappings which reduces
+	 * the available size of the linear mapping.
+	 */
+	memory_limit = KERN_VIRT_SIZE - (IS_ENABLED(CONFIG_64BIT) ? SZ_4G : 0);
+
 	/* Sanity check alignment and size */
 	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
 	BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0);
@@ -625,23 +819,25 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
 #endif
 
-	pt_ops.alloc_pte = alloc_pte_early;
-	pt_ops.get_pte_virt = get_pte_virt_early;
-#ifndef __PAGETABLE_PMD_FOLDED
-	pt_ops.alloc_pmd = alloc_pmd_early;
-	pt_ops.get_pmd_virt = get_pmd_virt_early;
-#endif
+	pt_ops_set_early();
+
 	/* Setup early PGD for fixmap */
 	create_pgd_mapping(early_pg_dir, FIXADDR_START,
-			   (uintptr_t)fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+			   fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);
 
 #ifndef __PAGETABLE_PMD_FOLDED
-	/* Setup fixmap PMD */
+	/* Setup fixmap PUD and PMD */
+	if (pgtable_l4_enabled)
+		create_pud_mapping(fixmap_pud, FIXADDR_START,
+				   (uintptr_t)fixmap_pmd, PUD_SIZE, PAGE_TABLE);
 	create_pmd_mapping(fixmap_pmd, FIXADDR_START,
 			   (uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
 	/* Setup trampoline PGD and PMD */
 	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
-			   (uintptr_t)trampoline_pmd, PGDIR_SIZE, PAGE_TABLE);
+			   trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE);
+	if (pgtable_l4_enabled)
+		create_pud_mapping(trampoline_pud, kernel_map.virt_addr,
+				   (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE);
 #ifdef CONFIG_XIP_KERNEL
 	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
 			   kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
@@ -669,7 +865,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
 	 * range can not span multiple pmds.
 	 */
-	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+	BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
 		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
 
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -694,6 +890,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 		pr_warn("FIX_BTMAP_BEGIN:     %d\n", FIX_BTMAP_BEGIN);
 	}
 #endif
+
+	pt_ops_set_fixmap();
 }
 
 static void __init setup_vm_final(void)
@@ -702,16 +900,6 @@ static void __init setup_vm_final(void)
 	phys_addr_t pa, start, end;
 	u64 i;
 
-	/**
-	 * MMU is enabled at this point. But page table setup is not complete yet.
-	 * fixmap page table alloc functions should be used at this point
-	 */
-	pt_ops.alloc_pte = alloc_pte_fixmap;
-	pt_ops.get_pte_virt = get_pte_virt_fixmap;
-#ifndef __PAGETABLE_PMD_FOLDED
-	pt_ops.alloc_pmd = alloc_pmd_fixmap;
-	pt_ops.get_pmd_virt = get_pmd_virt_fixmap;
-#endif
 	/* Setup swapper PGD for fixmap */
 	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
 			   __pa_symbol(fixmap_pgd_next),
@@ -736,26 +924,24 @@ static void __init setup_vm_final(void)
 		}
 	}
 
-#ifdef CONFIG_64BIT
 	/* Map the kernel */
-	create_kernel_page_table(swapper_pg_dir, false);
+	if (IS_ENABLED(CONFIG_64BIT))
+		create_kernel_page_table(swapper_pg_dir, false);
+
+#ifdef CONFIG_KASAN
+	kasan_swapper_init();
 #endif
 
 	/* Clear fixmap PTE and PMD mappings */
 	clear_fixmap(FIX_PTE);
 	clear_fixmap(FIX_PMD);
+	clear_fixmap(FIX_PUD);
 
 	/* Move to swapper page table */
-	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | SATP_MODE);
+	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode);
 	local_flush_tlb_all();
 
-	/* generic page allocation functions must be used to setup page table */
-	pt_ops.alloc_pte = alloc_pte_late;
-	pt_ops.get_pte_virt = get_pte_virt_late;
-#ifndef __PAGETABLE_PMD_FOLDED
-	pt_ops.alloc_pmd = alloc_pmd_late;
-	pt_ops.get_pmd_virt = get_pmd_virt_late;
-#endif
+	pt_ops_set_late();
 }
 #else
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
@@ -791,12 +977,10 @@ static void __init reserve_crashkernel(void)
 	 * since it doesn't make much sense and we have limited memory
 	 * resources.
 	 */
-#ifdef CONFIG_CRASH_DUMP
 	if (is_kdump_kernel()) {
 		pr_info("crashkernel: ignoring reservation request\n");
 		return;
 	}
-#endif
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base);

arch/riscv/mm/kasan_init.c

@@ -11,45 +11,27 @@
 #include <asm/fixmap.h>
 #include <asm/pgalloc.h>
 
-extern pgd_t early_pg_dir[PTRS_PER_PGD];
-asmlinkage void __init kasan_early_init(void)
-{
-	uintptr_t i;
-	pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
-
-	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
-		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
-
-	for (i = 0; i < PTRS_PER_PTE; ++i)
-		set_pte(kasan_early_shadow_pte + i,
-			mk_pte(virt_to_page(kasan_early_shadow_page),
-			       PAGE_KERNEL));
-
-	for (i = 0; i < PTRS_PER_PMD; ++i)
-		set_pmd(kasan_early_shadow_pmd + i,
-			pfn_pmd(PFN_DOWN
-				(__pa((uintptr_t) kasan_early_shadow_pte)),
-				__pgprot(_PAGE_TABLE)));
-
-	for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
-	     i += PGDIR_SIZE, ++pgd)
-		set_pgd(pgd,
-			pfn_pgd(PFN_DOWN
-				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
-				__pgprot(_PAGE_TABLE)));
-
-	/* init for swapper_pg_dir */
-	pgd = pgd_offset_k(KASAN_SHADOW_START);
-
-	for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
-	     i += PGDIR_SIZE, ++pgd)
-		set_pgd(pgd,
-			pfn_pgd(PFN_DOWN
-				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
-				__pgprot(_PAGE_TABLE)));
+/*
+ * Kasan shadow region must lie at a fixed address across sv39, sv48 and sv57
+ * which is right before the kernel.
+ *
+ * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate
+ * the page global directory with kasan_early_shadow_pmd.
+ *
+ * For sv48 and sv57, the region is not aligned on PGDIR_SIZE so the mapping
+ * must be divided as follows:
+ * - the first PGD entry, although incomplete, is populated with
+ *   kasan_early_shadow_pud/p4d
+ * - the PGD entries in the middle are populated with kasan_early_shadow_pud/p4d
+ * - the last PGD entry is shared with the kernel mapping so populated at the
+ *   lower levels pud/p4d
+ *
+ * In addition, when shallow populating a kasan region (for example vmalloc),
+ * this region may also not be aligned on PGDIR size, so we must go down to the
+ * pud level too.
+ */
 
-	local_flush_tlb_all();
-}
+extern pgd_t early_pg_dir[PTRS_PER_PGD];
 
 static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
 {
@@ -73,15 +55,19 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE));
 }
 
-static void __init kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned long end)
+static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end)
 {
 	phys_addr_t phys_addr;
 	pmd_t *pmdp, *base_pmd;
 	unsigned long next;
 
-	base_pmd = (pmd_t *)pgd_page_vaddr(*pgd);
-	if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+	if (pud_none(*pud)) {
 		base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+	} else {
+		base_pmd = (pmd_t *)pud_pgtable(*pud);
+		if (base_pmd == lm_alias(kasan_early_shadow_pmd))
+			base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+	}
 
 	pmdp = base_pmd + pmd_index(vaddr);
 
@@ -105,59 +91,207 @@ static void __init kasan_populate_pmd(pgd_t *pgd, unsigned long vaddr, unsigned
 	 * it entirely, memblock could allocate a page at a physical address
 	 * where KASAN is not populated yet and then we'd get a page fault.
 	 */
-	set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+	set_pud(pud, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+}
+
+static void __init kasan_populate_pud(pgd_t *pgd,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
+{
+	phys_addr_t phys_addr;
+	pud_t *pudp, *base_pud;
+	unsigned long next;
+
+	if (early) {
+		/*
+		 * We can't use pgd_page_vaddr here as it would return a linear
+		 * mapping address but it is not mapped yet, but when populating
+		 * early_pg_dir, we need the physical address and when populating
+		 * swapper_pg_dir, we need the kernel virtual address so use
+		 * pt_ops facility.
+		 */
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
+	} else {
+		base_pud = (pud_t *)pgd_page_vaddr(*pgd);
+		if (base_pud == lm_alias(kasan_early_shadow_pud))
+			base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+	}
+
+	pudp = base_pud + pud_index(vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+			if (early) {
+				phys_addr = __pa(((uintptr_t)kasan_early_shadow_pmd));
+				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+				continue;
+			} else {
+				phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
+				if (phys_addr) {
+					set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
+			}
+		}
+
+		kasan_populate_pmd(pudp, vaddr, next);
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	/*
+	 * Wait for the whole PGD to be populated before setting the PGD in
+	 * the page table, otherwise, if we did set the PGD before populating
+	 * it entirely, memblock could allocate a page at a physical address
+	 * where KASAN is not populated yet and then we'd get a page fault.
+	 */
+	if (!early)
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
 }
 
-static void __init kasan_populate_pgd(unsigned long vaddr, unsigned long end)
+#define kasan_early_shadow_pgd_next			(pgtable_l4_enabled ?	\
+				(uintptr_t)kasan_early_shadow_pud :		\
+				(uintptr_t)kasan_early_shadow_pmd)
+#define kasan_populate_pgd_next(pgdp, vaddr, next, early)			\
+		(pgtable_l4_enabled ?						\
+			kasan_populate_pud(pgdp, vaddr, next, early) :		\
+			kasan_populate_pmd((pud_t *)pgdp, vaddr, next))
+
+static void __init kasan_populate_pgd(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end,
+				      bool early)
 {
 	phys_addr_t phys_addr;
-	pgd_t *pgdp = pgd_offset_k(vaddr);
 	unsigned long next;
 
 	do {
 		next = pgd_addr_end(vaddr, end);
 
-		/*
-		 * pgdp can't be none since kasan_early_init initialized all KASAN
-		 * shadow region with kasan_early_shadow_pmd: if this is stillthe case,
-		 * that means we can try to allocate a hugepage as a replacement.
-		 */
-		if (pgd_page_vaddr(*pgdp) == (unsigned long)lm_alias(kasan_early_shadow_pmd) &&
-		    IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
-			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
-			if (phys_addr) {
-				set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+		if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
+			if (early) {
+				phys_addr = __pa((uintptr_t)kasan_early_shadow_pgd_next);
+				set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
 				continue;
+			} else if (pgd_page_vaddr(*pgdp) ==
+				   (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) {
+				/*
+				 * pgdp can't be none since kasan_early_init
+				 * initialized all KASAN shadow region with
+				 * kasan_early_shadow_pud: if this is still the
+				 * case, that means we can try to allocate a
+				 * hugepage as a replacement.
+				 */
+				phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+				if (phys_addr) {
+					set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+					continue;
+				}
 			}
 		}
 
-		kasan_populate_pmd(pgdp, vaddr, next);
+		kasan_populate_pgd_next(pgdp, vaddr, next, early);
 	} while (pgdp++, vaddr = next, vaddr != end);
 }
 
+asmlinkage void __init kasan_early_init(void)
+{
+	uintptr_t i;
+
+	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_early_shadow_pte + i,
+			mk_pte(virt_to_page(kasan_early_shadow_page),
+			       PAGE_KERNEL));
+
+	for (i = 0; i < PTRS_PER_PMD; ++i)
+		set_pmd(kasan_early_shadow_pmd + i,
+			pfn_pmd(PFN_DOWN
+				(__pa((uintptr_t)kasan_early_shadow_pte)),
+				PAGE_TABLE));
+
+	if (pgtable_l4_enabled) {
+		for (i = 0; i < PTRS_PER_PUD; ++i)
+			set_pud(kasan_early_shadow_pud + i,
+				pfn_pud(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pmd))),
+					PAGE_TABLE));
+	}
+
+	kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
+			   KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+	local_flush_tlb_all();
+}
+
+void __init kasan_swapper_init(void)
+{
+	kasan_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
+			   KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+
+	local_flush_tlb_all();
+}
+
 static void __init kasan_populate(void *start, void *end)
 {
 	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
 	unsigned long vend = PAGE_ALIGN((unsigned long)end);
 
-	kasan_populate_pgd(vaddr, vend);
+	kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend, false);
 
 	local_flush_tlb_all();
 	memset(start, KASAN_SHADOW_INIT, end - start);
 }
 
+static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
+					      unsigned long vaddr, unsigned long end,
+					      bool kasan_populate)
+{
+	unsigned long next;
+	pud_t *pudp, *base_pud;
+	pmd_t *base_pmd;
+	bool is_kasan_pmd;
+
+	base_pud = (pud_t *)pgd_page_vaddr(*pgdp);
+	pudp = base_pud + pud_index(vaddr);
+
+	if (kasan_populate)
+		memcpy(base_pud, (void *)kasan_early_shadow_pgd_next,
+		       sizeof(pud_t) * PTRS_PER_PUD);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+		is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd));
+
+		if (is_kasan_pmd) {
+			base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+			set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
+		}
+	} while (pudp++, vaddr = next, vaddr != end);
+}
+
 static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
 {
 	unsigned long next;
 	void *p;
 	pgd_t *pgd_k = pgd_offset_k(vaddr);
+	bool is_kasan_pgd_next;
 
 	do {
 		next = pgd_addr_end(vaddr, end);
-		if (pgd_page_vaddr(*pgd_k) == (unsigned long)lm_alias(kasan_early_shadow_pmd)) {
+		is_kasan_pgd_next = (pgd_page_vaddr(*pgd_k) ==
+				     (unsigned long)lm_alias(kasan_early_shadow_pgd_next));
+
+		if (is_kasan_pgd_next) {
 			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 		}
+
+		if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE)
+			continue;
+
+		kasan_shallow_populate_pud(pgd_k, vaddr, next, is_kasan_pgd_next);
 	} while (pgd_k++, vaddr = next, vaddr != end);
 }
 

arch/riscv/mm/tlbflush.c

@@ -32,7 +32,6 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 				  unsigned long size, unsigned long stride)
 {
 	struct cpumask *cmask = mm_cpumask(mm);
-	struct cpumask hmask;
 	unsigned int cpuid;
 	bool broadcast;
 
@@ -46,9 +45,7 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 		unsigned long asid = atomic_long_read(&mm->context.id);
 
 		if (broadcast) {
-			riscv_cpuid_to_hartid_mask(cmask, &hmask);
-			sbi_remote_sfence_vma_asid(cpumask_bits(&hmask),
-						   start, size, asid);
+			sbi_remote_sfence_vma_asid(cmask, start, size, asid);
 		} else if (size <= stride) {
 			local_flush_tlb_page_asid(start, asid);
 		} else {
@@ -56,9 +53,7 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
 		}
 	} else {
 		if (broadcast) {
-			riscv_cpuid_to_hartid_mask(cmask, &hmask);
-			sbi_remote_sfence_vma(cpumask_bits(&hmask),
-					      start, size);
+			sbi_remote_sfence_vma(cmask, start, size);
 		} else if (size <= stride) {
 			local_flush_tlb_page(start);
 		} else {

arch/riscv/net/bpf_jit_comp64.c

@@ -497,7 +497,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	offset = pc - (long)&ex->insn;
 	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = pc;
+	ex->insn = offset;
 
 	/*
 	 * Since the extable follows the program, the fixup offset is always

drivers/firmware/efi/libstub/efi-stub.c

@@ -40,6 +40,8 @@
 
 #ifdef CONFIG_ARM64
 # define EFI_RT_VIRTUAL_LIMIT	DEFAULT_MAP_WINDOW_64
+#elif defined(CONFIG_RISCV)
+# define EFI_RT_VIRTUAL_LIMIT	TASK_SIZE_MIN
 #else
 # define EFI_RT_VIRTUAL_LIMIT	TASK_SIZE
 #endif

drivers/soc/canaan/Kconfig

@@ -5,7 +5,6 @@ config SOC_K210_SYSCTL
 	depends on RISCV && SOC_CANAAN && OF
 	default SOC_CANAAN
         select PM
-        select SYSCON
         select MFD_SYSCON
 	help
 	  Canaan Kendryte K210 SoC system controller driver.

include/asm-generic/pgalloc.h

@@ -147,6 +147,15 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
+static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	return (pud_t *)get_zeroed_page(gfp);
+}
+
 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE
 /**
  * pud_alloc_one - allocate a page for PUD-level page table
@@ -159,20 +168,23 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
  */
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	gfp_t gfp = GFP_PGTABLE_USER;
-
-	if (mm == &init_mm)
-		gfp = GFP_PGTABLE_KERNEL;
-	return (pud_t *)get_zeroed_page(gfp);
+	return __pud_alloc_one(mm, addr);
 }
 #endif
 
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
 {
 	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
 	free_page((unsigned long)pud);
 }
 
+#ifndef __HAVE_ARCH_PUD_FREE
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	__pud_free(mm, pud);
+}
+#endif
+
 #endif /* CONFIG_PGTABLE_LEVELS > 3 */
 
 #ifndef __HAVE_ARCH_PGD_FREE