[PATCH] binfmt_elf: Support segments with 0 filesz and misaligned starts

["Eric W. Biederman" <ebiederm@xmission.com>]

Implement a helper elf_load that wraps elf_map and performs all
of the necessary work to ensure that when "memsz > filesz"
the bytes described by "memsz > filesz" are zeroed.

Link: https://lkml.kernel.org/r/20230914-bss-alloc-v1-1-78de67d2c6dd@weissschuh.net
Reported-by: Sebastian Ott <sebott@redhat.com>
Reported-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/binfmt_elf.c | 111 +++++++++++++++++++++---------------------------
 1 file changed, 48 insertions(+), 63 deletions(-)

Can you please test this one?

With this patch I can boot a machine, and I like the structure much
better.  Overall this seems a more reviewable and safer patch although
it is almost as aggressive in the cleanups.

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 7b3d2d491407..8bea9d974361 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -110,25 +110,6 @@ static struct linux_binfmt elf_format = {
 
 #define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
 
-static int set_brk(unsigned long start, unsigned long end, int prot)
-{
-	start = ELF_PAGEALIGN(start);
-	end = ELF_PAGEALIGN(end);
-	if (end > start) {
-		/*
-		 * Map the last of the bss segment.
-		 * If the header is requesting these pages to be
-		 * executable, honour that (ppc32 needs this).
-		 */
-		int error = vm_brk_flags(start, end - start,
-				prot & PROT_EXEC ? VM_EXEC : 0);
-		if (error)
-			return error;
-	}
-	current->mm->start_brk = current->mm->brk = end;
-	return 0;
-}
-
 /* 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
@@ -406,6 +387,51 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
 	return(map_addr);
 }
 
+static unsigned long elf_load(struct file *filep, unsigned long addr,
+		const struct elf_phdr *eppnt, int prot, int type,
+		unsigned long total_size)
+{
+	unsigned long zero_start, zero_end;
+	unsigned long map_addr;
+
+	if (eppnt->p_filesz) {
+		map_addr = elf_map(filep, addr, eppnt, prot, type, total_size);
+		if (BAD_ADDR(map_addr))
+			return map_addr;
+		if (eppnt->p_memsz > eppnt->p_filesz) {
+			zero_start = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) +
+				eppnt->p_filesz;
+			zero_end = map_addr + ELF_PAGEOFFSET(eppnt->p_vaddr) +
+				eppnt->p_memsz;
+
+			/* Zero the end of the last mapped page */
+			padzero(zero_start);
+		}
+	} else {
+		zero_start = ELF_PAGESTART(addr);
+		zero_end = zero_start + ELF_PAGEOFFSET(eppnt->p_vaddr) +
+			eppnt->p_memsz;
+	}
+	if (eppnt->p_memsz > eppnt->p_filesz) {
+		/*
+		 * Map the last of the segment.
+		 * If the header is requesting these pages to be
+		 * executable, honour that (ppc32 needs this).
+		 */
+		int error;
+
+		zero_start = ELF_PAGEALIGN(zero_start);
+		zero_end = ELF_PAGEALIGN(zero_end);
+
+		error = vm_brk_flags(zero_start, zero_end - zero_start,
+				     prot & PROT_EXEC ? VM_EXEC : 0);
+		if (error)
+			map_addr = error;
+	}
+	return map_addr;
+}
+
+
 static unsigned long total_mapping_size(const struct elf_phdr *phdr, int nr)
 {
 	elf_addr_t min_addr = -1;
@@ -829,7 +855,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
 	struct elf_phdr *elf_property_phdata = NULL;
 	unsigned long elf_bss, elf_brk;
-	int bss_prot = 0;
 	int retval, i;
 	unsigned long elf_entry;
 	unsigned long e_entry;
@@ -1040,33 +1065,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		if (elf_ppnt->p_type != PT_LOAD)
 			continue;
 
-		if (unlikely (elf_brk > elf_bss)) {
-			unsigned long nbyte;
-
-			/* There was a PT_LOAD segment with p_memsz > p_filesz
-			   before this one. Map anonymous pages, if needed,
-			   and clear the area.  */
-			retval = set_brk(elf_bss + load_bias,
-					 elf_brk + load_bias,
-					 bss_prot);
-			if (retval)
-				goto out_free_dentry;
-			nbyte = ELF_PAGEOFFSET(elf_bss);
-			if (nbyte) {
-				nbyte = ELF_MIN_ALIGN - nbyte;
-				if (nbyte > elf_brk - elf_bss)
-					nbyte = elf_brk - elf_bss;
-				if (clear_user((void __user *)elf_bss +
-							load_bias, nbyte)) {
-					/*
-					 * This bss-zeroing can fail if the ELF
-					 * file specifies odd protections. So
-					 * we don't check the return value
-					 */
-				}
-			}
-		}
-
 		elf_prot = make_prot(elf_ppnt->p_flags, &arch_state,
 				     !!interpreter, false);
 
@@ -1162,7 +1160,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			}
 		}
 
-		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
+		error = elf_load(bprm->file, load_bias + vaddr, elf_ppnt,
 				elf_prot, elf_flags, total_size);
 		if (BAD_ADDR(error)) {
 			retval = IS_ERR_VALUE(error) ?
@@ -1217,10 +1215,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		if (end_data < k)
 			end_data = k;
 		k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
-		if (k > elf_brk) {
-			bss_prot = elf_prot;
+		if (k > elf_brk)
 			elf_brk = k;
-		}
 	}
 
 	e_entry = elf_ex->e_entry + load_bias;
@@ -1232,18 +1228,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	start_data += load_bias;
 	end_data += load_bias;
 
-	/* Calling set_brk effectively mmaps the pages that we need
-	 * for the bss and break sections.  We must do this before
-	 * mapping in the interpreter, to make sure it doesn't wind
-	 * up getting placed where the bss needs to go.
-	 */
-	retval = set_brk(elf_bss, elf_brk, bss_prot);
-	if (retval)
-		goto out_free_dentry;
-	if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
-		retval = -EFAULT; /* Nobody gets to see this, but.. */
-		goto out_free_dentry;
-	}
+	current->mm->start_brk = current->mm->brk = ELF_PAGEALIGN(elf_brk);
 
 	if (interpreter) {
 		elf_entry = load_elf_interp(interp_elf_ex,
-- 
2.41.0