Merge tag 'riscv-for-linus-5.14-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:
 "We have a handful of new features for 5.14:

   - Support for transparent huge pages.

   - Support for generic PCI resources mapping.

   - Support for the mem= kernel parameter.

   - Support for KFENCE.

   - A handful of fixes to avoid W+X mappings in the kernel.

   - Support for VMAP_STACK based overflow detection.

   - An optimized copy_{to,from}_user"

* tag 'riscv-for-linus-5.14-mw0' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (37 commits)
  riscv: xip: Fix duplicate included asm/pgtable.h
  riscv: Fix PTDUMP output now BPF region moved back to module region
  riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall
  riscv: add VMAP_STACK overflow detection
  riscv: ptrace: add argn syntax
  riscv: mm: fix build errors caused by mk_pmd()
  riscv: Introduce structure that group all variables regarding kernel mapping
  riscv: Map the kernel with correct permissions the first time
  riscv: Introduce set_kernel_memory helper
  riscv: Enable KFENCE for riscv64
  RISC-V: Use asm-generic for {in,out}{bwlq}
  riscv: add ASID-based tlbflushing methods
  riscv: pass the mm_struct to __sbi_tlb_flush_range
  riscv: Add mem kernel parameter support
  riscv: Simplify xip and !xip kernel address conversion macros
  riscv: Remove CONFIG_PHYS_RAM_BASE_FIXED
  riscv: Only initialize swiotlb when necessary
  riscv: fix typo in init.c
  riscv: Cleanup unused functions
  riscv: mm: Use better bitmap_zalloc()
  ...

Author: torvalds

arch/riscv/Kconfig

@@ -65,11 +65,14 @@ config RISCV
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
 	select HAVE_ARCH_KASAN if MMU && 64BIT
 	select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT
+	select HAVE_ARCH_KFENCE if MMU && 64BIT
 	select HAVE_ARCH_KGDB if !XIP_KERNEL
 	select HAVE_ARCH_KGDB_QXFER_PKT
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
+	select HAVE_ARCH_VMAP_STACK if MMU && 64BIT
 	select HAVE_ASM_MODVERSIONS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
@@ -83,11 +86,14 @@ config RISCV
 	select HAVE_KPROBES if !XIP_KERNEL
 	select HAVE_KPROBES_ON_FTRACE if !XIP_KERNEL
 	select HAVE_KRETPROBES if !XIP_KERNEL
+	select HAVE_MOVE_PMD
+	select HAVE_MOVE_PUD
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
@@ -488,13 +494,8 @@ config STACKPROTECTOR_PER_TASK
 	def_bool y
 	depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS
 
-config PHYS_RAM_BASE_FIXED
-	bool "Explicitly specified physical RAM address"
-	default n
-
 config PHYS_RAM_BASE
 	hex "Platform Physical RAM address"
-	depends on PHYS_RAM_BASE_FIXED
 	default "0x80000000"
 	help
 	  This is the physical address of RAM in the system. It has to be
@@ -507,7 +508,6 @@ config XIP_KERNEL
 	# This prevents XIP from being enabled by all{yes,mod}config, which
 	# fail to build since XIP doesn't support large kernels.
 	depends on !COMPILE_TEST
-	select PHYS_RAM_BASE_FIXED
 	help
 	  Execute-In-Place allows the kernel to run from non-volatile storage
 	  directly addressable by the CPU, such as NOR flash. This saves RAM

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

@@ -25,4 +25,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
+asmlinkage unsigned long get_overflow_stack(void);
+asmlinkage void handle_bad_stack(struct pt_regs *regs);
+
 #endif /* _ASM_RISCV_PROTOTYPES_H */

arch/riscv/include/asm/io.h

@@ -52,19 +52,6 @@
 #define __io_pbw()	__asm__ __volatile__ ("fence iow,o" : : : "memory");
 #define __io_paw()	__asm__ __volatile__ ("fence o,io"  : : : "memory");
 
-#define inb(c)		({ u8  __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-#define inw(c)		({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-#define inl(c)		({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
-
-#define outb(v,c)	({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-#define outw(v,c)	({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-#define outl(v,c)	({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
-
-#ifdef CONFIG_64BIT
-#define inq(c)		({ u64 __v; __io_pbr(); __v = readq_cpu((void*)(c)); __io_par(__v); __v; })
-#define outq(v,c)	({ __io_pbw(); writeq_cpu((v),(void*)(c)); __io_paw(); })
-#endif
-
 /*
  * Accesses from a single hart to a single I/O address must be ordered.  This
  * allows us to use the raw read macros, but we still need to fence before and

arch/riscv/include/asm/kfence.h

@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_KFENCE_H
+#define _ASM_RISCV_KFENCE_H
+
+#include <linux/kfence.h>
+#include <linux/pfn.h>
+#include <asm-generic/pgalloc.h>
+#include <asm/pgtable.h>
+
+static inline int split_pmd_page(unsigned long addr)
+{
+	int i;
+	unsigned long pfn = PFN_DOWN(__pa((addr & PMD_MASK)));
+	pmd_t *pmd = pmd_off_k(addr);
+	pte_t *pte = pte_alloc_one_kernel(&init_mm);
+
+	if (!pte)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(pte + i, pfn_pte(pfn + i, PAGE_KERNEL));
+	set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(pte)), PAGE_TABLE));
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	return 0;
+}
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int ret;
+	unsigned long addr;
+	pmd_t *pmd;
+
+	for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
+	     addr += PAGE_SIZE) {
+		pmd = pmd_off_k(addr);
+
+		if (pmd_leaf(*pmd)) {
+			ret = split_pmd_page(addr);
+			if (ret)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	return true;
+}
+
+#endif /* _ASM_RISCV_KFENCE_H */

arch/riscv/include/asm/kprobes.h

@@ -29,18 +29,11 @@ struct prev_kprobe {
 	unsigned int status;
 };
 
-/* Single step context for kprobe */
-struct kprobe_step_ctx {
-	unsigned long ss_pending;
-	unsigned long match_addr;
-};
-
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	unsigned long saved_status;
 	struct prev_kprobe prev_kprobe;
-	struct kprobe_step_ctx ss_ctx;
 };
 
 void arch_remove_kprobe(struct kprobe *p);

arch/riscv/include/asm/mmu_context.h

@@ -33,6 +33,8 @@ static inline int init_new_context(struct task_struct *tsk,
 	return 0;
 }
 
+DECLARE_STATIC_KEY_FALSE(use_asid_allocator);
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_RISCV_MMU_CONTEXT_H */

arch/riscv/include/asm/page.h

@@ -37,16 +37,6 @@
 
 #ifndef __ASSEMBLY__
 
-#define PAGE_UP(addr)	(((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1)))
-#define PAGE_DOWN(addr)	((addr)&(~((PAGE_SIZE)-1)))
-
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_UP(addr, size)	(((addr)+((size)-1))&(~((size)-1)))
-#define _ALIGN_DOWN(addr, size)	((addr)&(~((size)-1)))
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr, size)	_ALIGN_UP(addr, size)
-
 #define clear_page(pgaddr)			memset((pgaddr), 0, PAGE_SIZE)
 #define copy_page(to, from)			memcpy((to), (from), PAGE_SIZE)
 
@@ -89,59 +79,68 @@ typedef struct page *pgtable_t;
 #endif
 
 #ifdef CONFIG_MMU
-extern unsigned long va_pa_offset;
-#ifdef CONFIG_64BIT
-extern unsigned long va_kernel_pa_offset;
-#endif
-#ifdef CONFIG_XIP_KERNEL
-extern unsigned long va_kernel_xip_pa_offset;
-#endif
 extern unsigned long pfn_base;
 #define ARCH_PFN_OFFSET		(pfn_base)
 #else
-#define va_pa_offset		0
-#ifdef CONFIG_64BIT
-#define va_kernel_pa_offset	0
-#endif
 #define ARCH_PFN_OFFSET		(PAGE_OFFSET >> PAGE_SHIFT)
 #endif /* CONFIG_MMU */
 
-extern unsigned long kernel_virt_addr;
-
+struct kernel_mapping {
+	unsigned long virt_addr;
+	uintptr_t phys_addr;
+	uintptr_t size;
+	/* Offset between linear mapping virtual address and kernel load address */
+	unsigned long va_pa_offset;
 #ifdef CONFIG_64BIT
-#define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + va_pa_offset))
+	/* Offset between kernel mapping virtual address and kernel load address */
+	unsigned long va_kernel_pa_offset;
+#endif
+	unsigned long va_kernel_xip_pa_offset;
 #ifdef CONFIG_XIP_KERNEL
+	uintptr_t xiprom;
+	uintptr_t xiprom_sz;
+#endif
+};
+
+extern struct kernel_mapping kernel_map;
+
+#ifdef CONFIG_64BIT
+#define is_kernel_mapping(x)	\
+	((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
+#define is_linear_mapping(x)	\
+	((x) >= PAGE_OFFSET && (x) < kernel_map.virt_addr)
+
+#define linear_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
 #define kernel_mapping_pa_to_va(y)	({						\
 	unsigned long _y = y;								\
 	(_y >= CONFIG_PHYS_RAM_BASE) ?							\
-		(void *)((unsigned long)(_y) + va_kernel_pa_offset + XIP_OFFSET) :	\
-		(void *)((unsigned long)(_y) + va_kernel_xip_pa_offset);		\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET) :	\
+		(void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset);		\
 	})
-#else
-#define kernel_mapping_pa_to_va(x)	((void *)((unsigned long)(x) + va_kernel_pa_offset))
-#endif
 #define __pa_to_va_nodebug(x)		linear_mapping_pa_to_va(x)
 
-#define linear_mapping_va_to_pa(x)	((unsigned long)(x) - va_pa_offset)
-#ifdef CONFIG_XIP_KERNEL
+#define linear_mapping_va_to_pa(x)	((unsigned long)(x) - kernel_map.va_pa_offset)
 #define kernel_mapping_va_to_pa(y) ({						\
 	unsigned long _y = y;							\
-	(_y < kernel_virt_addr + XIP_OFFSET) ?					\
-		((unsigned long)(_y) - va_kernel_xip_pa_offset) :		\
-		((unsigned long)(_y) - va_kernel_pa_offset - XIP_OFFSET);	\
+	(_y < kernel_map.virt_addr + XIP_OFFSET) ?					\
+		((unsigned long)(_y) - kernel_map.va_kernel_xip_pa_offset) :		\
+		((unsigned long)(_y) - kernel_map.va_kernel_pa_offset - XIP_OFFSET);	\
 	})
-#else
-#define kernel_mapping_va_to_pa(x)	((unsigned long)(x) - va_kernel_pa_offset)
-#endif
+
 #define __va_to_pa_nodebug(x)	({						\
 	unsigned long _x = x;							\
-	(_x < kernel_virt_addr) ?						\
+	is_linear_mapping(_x) ?							\
 		linear_mapping_va_to_pa(_x) : kernel_mapping_va_to_pa(_x);	\
 	})
 #else
-#define __pa_to_va_nodebug(x)  ((void *)((unsigned long) (x) + va_pa_offset))
-#define __va_to_pa_nodebug(x)  ((unsigned long)(x) - va_pa_offset)
-#endif
+#define is_kernel_mapping(x)	\
+	((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size))
+#define is_linear_mapping(x)	\
+	((x) >= PAGE_OFFSET)
+
+#define __pa_to_va_nodebug(x)  ((void *)((unsigned long) (x) + kernel_map.va_pa_offset))
+#define __va_to_pa_nodebug(x)  ((unsigned long)(x) - kernel_map.va_pa_offset)
+#endif /* CONFIG_64BIT */
 
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern phys_addr_t __virt_to_phys(unsigned long x);

arch/riscv/include/asm/pci.h

@@ -18,6 +18,8 @@
 /* RISC-V shim does not initialize PCI bus */
 #define pcibios_assign_all_busses() 1
 
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
+
 extern int isa_dma_bridge_buggy;
 
 #ifdef CONFIG_PCI

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

@@ -46,8 +46,7 @@ static inline int pud_bad(pud_t pud)
 #define pud_leaf	pud_leaf
 static inline int pud_leaf(pud_t pud)
 {
-	return pud_present(pud) &&
-	       (pud_val(pud) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+	return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -80,6 +79,8 @@ static inline unsigned long _pmd_pfn(pmd_t pmd)
 	return pmd_val(pmd) >> _PAGE_PFN_SHIFT;
 }
 
+#define mk_pmd(page, prot)    pfn_pmd(page_to_pfn(page), prot)
+
 #define pmd_ERROR(e) \
 	pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
 

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

@@ -39,5 +39,10 @@
 #define _PAGE_CHG_MASK  (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ |	\
 					  _PAGE_WRITE | _PAGE_EXEC |	\
 					  _PAGE_USER | _PAGE_GLOBAL))
+/*
+ * when all of R/W/X are zero, the PTE is a pointer to the next level
+ * of the page table; otherwise, it is a leaf PTE.
+ */
+#define _PAGE_LEAF (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 
 #endif /* _ASM_RISCV_PGTABLE_BITS_H */