RISC-V Fixes for 6.4-rc6

* A fix to avoid ISA-disallowed privilege mappings that can result from
   WRITE+EXEC mmap requests from userspace.
 * A fix for kfence to handle the huge pages.
 * A fix to avoid converting misaligned VAs to huge pages.
 * ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE has been selected so kprobe can
   understand user pointers.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmSDOpgTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYie+/D/oCjQbBFZaOEsRtZp2SlMz0COjVurXv
 ClQWSqPEvbWg28dZvapZzjRcBc6X7Th6P6ia1FIa/XDTLKTPBdBoVSo1iRfH12bm
 1CBsEKP08vMeN3b2nOD82B0XFl9PCB2AEHYo88a8k6ifEYMwfRU6g8ldHZC2HMF1
 3z2vT7XR40t9E7MNPBG7Kn+2JHob7iB8bqMAZfoxyth4q8H2s7QEGCCwtwFRWGix
 h6NW66WojWnTn+cniX8NbIY+5xV37xH/S4x2cFqGUklHD1/B8rCnXPpJqtmcSb9n
 pGV30m7sw8sYdWHPABjMutRVCRv0DpPmqUEHAOThLzAoIqBHv+4e9ov8PmU8pJcz
 5em6Cl+5Io/qzNa+uXT3cO1tfAzCid2r91cbpfa8RTBu8ZIf1GPS0SrgrdofU+Mw
 X5j90J8Hd7YH+egfI4DOZXxE+79VV8AVtH/aPWJxriOoAFjxzvP6OCckJo5ee4A7
 EWhxsdQZVQ+WMga7yWMBknmxFYlabNjZrZ+/bAhfHTseljVGkHxr5dF+78g5dyZt
 yvcnHMTiDXHKdRaHknquBh9hAVh2s4xNea00x3h0ybZR0GVJH3ZnWTdz7RLtyop7
 tWEcFHngQRtKJeIn33T6yioRkfUq2ODXKmBAJq0OwQCV8S8f42mE72iVw67fJQ9u
 XWJdYX0CqM3YPg==
 =CaWh
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-6.4-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

 - A fix to avoid ISA-disallowed privilege mappings that can result from
   WRITE+EXEC mmap requests from userspace.

 - A fix for kfence to handle the huge pages.

 - A fix to avoid converting misaligned VAs to huge pages.

 - ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE has been selected so kprobe
   can understand user pointers.

* tag 'riscv-for-linus-6.4-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: fix kprobe __user string arg print fault issue
  riscv: Check the virtual alignment before choosing a map size
  riscv: Fix kfence now that the linear mapping can be backed by PUD/P4D/PGD
  riscv: mm: Ensure prot of VM_WRITE and VM_EXEC must be readable

arch/riscv/Kconfig

@@ -26,6 +26,7 @@ config RISCV
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MMIOWB
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU

arch/riscv/include/asm/kfence.h

@@ -8,41 +8,8 @@
 #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;
 }
 

arch/riscv/include/asm/pgtable.h

@@ -165,8 +165,7 @@ extern struct pt_alloc_ops pt_ops __initdata;
 					 _PAGE_EXEC | _PAGE_WRITE)
 
 #define PAGE_COPY		PAGE_READ
-#define PAGE_COPY_EXEC		PAGE_EXEC
+#define PAGE_COPY_EXEC		PAGE_READ_EXEC
-#define PAGE_COPY_READ_EXEC	PAGE_READ_EXEC
 #define PAGE_SHARED		PAGE_WRITE
 #define PAGE_SHARED_EXEC	PAGE_WRITE_EXEC
 

arch/riscv/mm/init.c

@@ -23,6 +23,7 @@
 #ifdef CONFIG_RELOCATABLE
 #include <linux/elf.h>
 #endif
+#include <linux/kfence.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -293,7 +294,7 @@ static const pgprot_t protection_map[16] = {
 	[VM_EXEC]					= PAGE_EXEC,
 	[VM_EXEC | VM_READ]				= PAGE_READ_EXEC,
 	[VM_EXEC | VM_WRITE]				= PAGE_COPY_EXEC,
-	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_READ_EXEC,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_EXEC,
 	[VM_SHARED]					= PAGE_NONE,
 	[VM_SHARED | VM_READ]				= PAGE_READ,
 	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
@@ -659,18 +660,19 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 	create_pgd_next_mapping(nextp, va, pa, sz, prot);
 }
 
-static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
+static uintptr_t __init best_map_size(phys_addr_t pa, uintptr_t va,
+				      phys_addr_t size)
 {
-	if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
+	if (!(pa & (PGDIR_SIZE - 1)) && !(va & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
 		return PGDIR_SIZE;
 
-	if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+	if (!(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE)
 		return P4D_SIZE;
 
-	if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+	if (!(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE)
 		return PUD_SIZE;
 
-	if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE)
+	if (!(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE)
 		return PMD_SIZE;
 
 	return PAGE_SIZE;
@@ -1167,14 +1169,16 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 }
 
 static void __init create_linear_mapping_range(phys_addr_t start,
-					       phys_addr_t end)
+					       phys_addr_t end,
+					       uintptr_t fixed_map_size)
 {
 	phys_addr_t pa;
 	uintptr_t va, map_size;
 
 	for (pa = start; pa < end; pa += map_size) {
 		va = (uintptr_t)__va(pa);
-		map_size = best_map_size(pa, end - pa);
+		map_size = fixed_map_size ? fixed_map_size :
+					    best_map_size(pa, va, end - pa);
 
 		create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
 				   pgprot_from_va(va));
@@ -1184,6 +1188,7 @@ static void __init create_linear_mapping_range(phys_addr_t start,
 static void __init create_linear_mapping_page_table(void)
 {
 	phys_addr_t start, end;
+	phys_addr_t kfence_pool __maybe_unused;
 	u64 i;
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -1197,6 +1202,19 @@ static void __init create_linear_mapping_page_table(void)
 	memblock_mark_nomap(krodata_start, krodata_size);
 #endif
 
+#ifdef CONFIG_KFENCE
+	/*
+	 *  kfence pool must be backed by PAGE_SIZE mappings, so allocate it
+	 *  before we setup the linear mapping so that we avoid using hugepages
+	 *  for this region.
+	 */
+	kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE);
+	BUG_ON(!kfence_pool);
+
+	memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE);
+	__kfence_pool = __va(kfence_pool);
+#endif
+
 	/* Map all memory banks in the linear mapping */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -1207,17 +1225,25 @@ static void __init create_linear_mapping_page_table(void)
 		if (end >= __pa(PAGE_OFFSET) + memory_limit)
 			end = __pa(PAGE_OFFSET) + memory_limit;
 
-		create_linear_mapping_range(start, end);
+		create_linear_mapping_range(start, end, 0);
 	}
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
-	create_linear_mapping_range(ktext_start, ktext_start + ktext_size);
+	create_linear_mapping_range(ktext_start, ktext_start + ktext_size, 0);
 	create_linear_mapping_range(krodata_start,
-				    krodata_start + krodata_size);
+				    krodata_start + krodata_size, 0);
 
 	memblock_clear_nomap(ktext_start,  ktext_size);
 	memblock_clear_nomap(krodata_start, krodata_size);
 #endif
+
+#ifdef CONFIG_KFENCE
+	create_linear_mapping_range(kfence_pool,
+				    kfence_pool + KFENCE_POOL_SIZE,
+				    PAGE_SIZE);
+
+	memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE);
+#endif
 }
 
 static void __init setup_vm_final(void)