binfmt_elf: Only report padzero() errors when PROT_WRITE

Errors with padzero() should be caught unless we're expecting a
pathological (non-writable) segment. Report -EFAULT only when PROT_WRITE
is present.

Additionally add some more documentation to padzero(), elf_map(), and
elf_load().

Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mm@kvack.org
Suggested-by: Eric Biederman <ebiederm@xmission.com>
Tested-by: Pedro Falcato <pedro.falcato@gmail.com>
Signed-off-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20230929032435.2391507-5-keescook@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f7012c1b8b05867144df1223d78f1ca34e3883b6..5397b552fbeb5422f46a0bbe7ef838977a718377 100644 (file)
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -110,19 +110,19 @@ static struct linux_binfmt elf_format = {
 
 #define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
 
-/* We need to explicitly zero any fractional pages
-   after the data section (i.e. bss).  This would
-   contain the junk from the file that should not
-   be in memory
+/*
+ * We need to explicitly zero any trailing portion of the page that follows
+ * p_filesz when it ends before the page ends (e.g. bss), otherwise this
+ * memory will contain the junk from the file that should not be present.
  */
-static int padzero(unsigned long elf_bss)
+static int padzero(unsigned long address)
 {
        unsigned long nbyte;
 
-       nbyte = ELF_PAGEOFFSET(elf_bss);
+       nbyte = ELF_PAGEOFFSET(address);
        if (nbyte) {
                nbyte = ELF_MIN_ALIGN - nbyte;
-               if (clear_user((void __user *) elf_bss, nbyte))
+               if (clear_user((void __user *)address, nbyte))
                        return -EFAULT;
        }
        return 0;
@@ -348,6 +348,11 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
        return 0;
 }
 
+/*
+ * Map "eppnt->p_filesz" bytes from "filep" offset "eppnt->p_offset"
+ * into memory at "addr". (Note that p_filesz is rounded up to the
+ * next page, so any extra bytes from the file must be wiped.)
+ */
 static unsigned long elf_map(struct file *filep, unsigned long addr,
                const struct elf_phdr *eppnt, int prot, int type,
                unsigned long total_size)
@@ -387,6 +392,11 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
        return(map_addr);
 }
 
+/*
+ * Map "eppnt->p_filesz" bytes from "filep" offset "eppnt->p_offset"
+ * into memory at "addr". Memory from "p_filesz" through "p_memsz"
+ * rounded up to the next page is zeroed.
+ */
 static unsigned long elf_load(struct file *filep, unsigned long addr,
                const struct elf_phdr *eppnt, int prot, int type,
                unsigned long total_size)
@@ -404,8 +414,12 @@ static unsigned long elf_load(struct file *filep, unsigned long addr,
                        zero_end = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) +
                                eppnt->p_memsz;
 
-                       /* Zero the end of the last mapped page */
-                       padzero(zero_start);
+                       /*
+                        * Zero the end of the last mapped page but ignore
+                        * any errors if the segment isn't writable.
+                        */
+                       if (padzero(zero_start) && (prot & PROT_WRITE))
+                               return -EFAULT;
                }
        } else {
                map_addr = zero_start = ELF_PAGESTART(addr);