riscv: Fix kfence now that the linear mapping can be backed by PUD/P4D/PGD

RISC-V Kfence implementation used to rely on the fact the linear mapping
was backed by at most PMD hugepages, which is not true anymore since
commit 3335068f8721 ("riscv: Use PUD/P4D/PGD pages for the linear
mapping").

Instead of splitting PUD/P4D/PGD mappings afterwards, directly map the
kfence pool region using PTE mappings by allocating this region before
setup_vm_final().

Reported-by: syzbot+a74d57bddabbedd75135@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=a74d57bddabbedd75135
Fixes: 3335068f8721 ("riscv: Use PUD/P4D/PGD pages for the linear mapping")
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20230606130444.25090-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h
index d887a54..0bbffd5 100644 (file)
--- a/arch/riscv/include/asm/kfence.h
+++ b/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;
 }
 

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 0fe75c9..38c4b4d 100644 (file)
--- a/arch/riscv/mm/init.c
+++ b/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>
@@ -1167,14 +1168,16 @@ 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, end - pa);
 
                create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
                                   pgprot_from_va(va));
@@ -1184,6 +1187,7 @@ 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 +1201,19 @@ 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 +1224,25 @@ 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)