RISC-V: Introduce sv48 support without relocatable kernel

This patchset allows to have a single kernel for sv39 and sv48 without
being relocatable.

The idea comes from Arnd Bergmann who suggested to do the same as x86,
that is mapping the kernel to the end of the address space, which allows
the kernel to be linked at the same address for both sv39 and sv48 and
then does not require to be relocated at runtime.

This implements sv48 support at runtime. The kernel will try to boot
with 4-level page table and will fallback to 3-level if the HW does not
support it. Folding the 4th level into a 3-level page table has almost
no cost at runtime.

Note that kasan region had to be moved to the end of the address space
since its location must be known at compile-time and then be valid for
both sv39 and sv48 (and sv57 that is coming).

* riscv-sv48-v3:
  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
  riscv: Get rid of MAXPHYSMEM configs

Signed-off-by: Palmer Dabbelt <[email protected]>

Author: palmer-dabbelt

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

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

@@ -27,7 +27,6 @@ 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/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)