1 files changed, 163 insertions, 122 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 89e7e4826efc..762704eed9ce 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -109,25 +109,6 @@ 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
@@ -248,7 +229,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	} while (0)
 
 #ifdef ARCH_DLINFO
-	/* 
+	/*
 	 * ARCH_DLINFO must come first so PPC can do its special alignment of
 	 * AUXV.
 	 * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in
@@ -401,6 +382,51 @@ 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 {
+		map_addr = 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;
@@ -829,8 +855,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	unsigned long error;
 	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;
+	unsigned long elf_brk;
+	bool brk_moved = false;
 	int retval, i;
 	unsigned long elf_entry;
 	unsigned long e_entry;
@@ -1021,8 +1047,7 @@ out_free_interp:
 				 executable_stack);
 	if (retval < 0)
 		goto out_free_dentry;
-	
-	elf_bss = 0;
+
 	elf_brk = 0;
 
 	start_code = ~0UL;
@@ -1042,33 +1067,6 @@ out_free_interp:
 		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);
 
@@ -1096,15 +1094,49 @@ out_free_interp:
 			 * Header for ET_DYN binaries to calculate the
 			 * randomization (load_bias) for all the LOAD
 			 * Program Headers.
+			 */
+
+			/*
+			 * Calculate the entire size of the ELF mapping
+			 * (total_size), used for the initial mapping,
+			 * due to load_addr_set which is set to true later
+			 * once the initial mapping is performed.
+			 *
+			 * Note that this is only sensible when the LOAD
+			 * segments are contiguous (or overlapping). If
+			 * used for LOADs that are far apart, this would
+			 * cause the holes between LOADs to be mapped,
+			 * running the risk of having the mapping fail,
+			 * as it would be larger than the ELF file itself.
+			 *
+			 * As a result, only ET_DYN does this, since
+			 * some ET_EXEC (e.g. ia64) may have large virtual
+			 * memory holes between LOADs.
+			 *
+			 */
+			total_size = total_mapping_size(elf_phdata,
+							elf_ex->e_phnum);
+			if (!total_size) {
+				retval = -EINVAL;
+				goto out_free_dentry;
+			}
+
+			/* Calculate any requested alignment. */
+			alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
+
+			/**
+			 * DOC: PIE handling
 			 *
-			 * There are effectively two types of ET_DYN
-			 * binaries: programs (i.e. PIE: ET_DYN with INTERP)
-			 * and loaders (ET_DYN without INTERP, since they
-			 * _are_ the ELF interpreter). The loaders must
-			 * be loaded away from programs since the program
-			 * may otherwise collide with the loader (especially
-			 * for ET_EXEC which does not have a randomized
-			 * position). For example to handle invocations of
+			 * There are effectively two types of ET_DYN ELF
+			 * binaries: programs (i.e. PIE: ET_DYN with
+			 * PT_INTERP) and loaders (i.e. static PIE: ET_DYN
+			 * without PT_INTERP, usually the ELF interpreter
+			 * itself). Loaders must be loaded away from programs
+			 * since the program may otherwise collide with the
+			 * loader (especially for ET_EXEC which does not have
+			 * a randomized position).
+			 *
+			 * For example, to handle invocations of
 			 * "./ld.so someprog" to test out a new version of
 			 * the loader, the subsequent program that the
 			 * loader loads must avoid the loader itself, so
@@ -1117,17 +1149,49 @@ out_free_interp:
 			 * ELF_ET_DYN_BASE and loaders are loaded into the
 			 * independently randomized mmap region (0 load_bias
 			 * without MAP_FIXED nor MAP_FIXED_NOREPLACE).
+			 *
+			 * See below for "brk" handling details, which is
+			 * also affected by program vs loader and ASLR.
 			 */
 			if (interpreter) {
+				/* On ET_DYN with PT_INTERP, we do the ASLR. */
 				load_bias = ELF_ET_DYN_BASE;
 				if (current->flags & PF_RANDOMIZE)
 					load_bias += arch_mmap_rnd();
-				alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
+				/* Adjust alignment as requested. */
 				if (alignment)
 					load_bias &= ~(alignment - 1);
 				elf_flags |= MAP_FIXED_NOREPLACE;
-			} else
-				load_bias = 0;
+			} else {
+				/*
+				 * For ET_DYN without PT_INTERP, we rely on
+				 * the architectures's (potentially ASLR) mmap
+				 * base address (via a load_bias of 0).
+				 *
+				 * When a large alignment is requested, we
+				 * must do the allocation at address "0" right
+				 * now to discover where things will load so
+				 * that we can adjust the resulting alignment.
+				 * In this case (load_bias != 0), we can use
+				 * MAP_FIXED_NOREPLACE to make sure the mapping
+				 * doesn't collide with anything.
+				 */
+				if (alignment > ELF_MIN_ALIGN) {
+					load_bias = elf_load(bprm->file, 0, elf_ppnt,
+							     elf_prot, elf_flags, total_size);
+					if (BAD_ADDR(load_bias)) {
+						retval = IS_ERR_VALUE(load_bias) ?
+							 PTR_ERR((void*)load_bias) : -EINVAL;
+						goto out_free_dentry;
+					}
+					vm_munmap(load_bias, total_size);
+					/* Adjust alignment as requested. */
+					if (alignment)
+						load_bias &= ~(alignment - 1);
+					elf_flags |= MAP_FIXED_NOREPLACE;
+				} else
+					load_bias = 0;
+			}
 
 			/*
 			 * Since load_bias is used for all subsequent loading
@@ -1137,34 +1201,9 @@ out_free_interp:
 			 * is then page aligned.
 			 */
 			load_bias = ELF_PAGESTART(load_bias - vaddr);
-
-			/*
-			 * Calculate the entire size of the ELF mapping
-			 * (total_size), used for the initial mapping,
-			 * due to load_addr_set which is set to true later
-			 * once the initial mapping is performed.
-			 *
-			 * Note that this is only sensible when the LOAD
-			 * segments are contiguous (or overlapping). If
-			 * used for LOADs that are far apart, this would
-			 * cause the holes between LOADs to be mapped,
-			 * running the risk of having the mapping fail,
-			 * as it would be larger than the ELF file itself.
-			 *
-			 * As a result, only ET_DYN does this, since
-			 * some ET_EXEC (e.g. ia64) may have large virtual
-			 * memory holes between LOADs.
-			 *
-			 */
-			total_size = total_mapping_size(elf_phdata,
-							elf_ex->e_phnum);
-			if (!total_size) {
-				retval = -EINVAL;
-				goto out_free_dentry;
-			}
 		}
 
-		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((void *)error) ?
@@ -1212,41 +1251,23 @@ out_free_interp:
 
 		k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz;
 
-		if (k > elf_bss)
-			elf_bss = k;
 		if ((elf_ppnt->p_flags & PF_X) && end_code < k)
 			end_code = k;
 		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;
 	phdr_addr += load_bias;
-	elf_bss += load_bias;
 	elf_brk += load_bias;
 	start_code += load_bias;
 	end_code += load_bias;
 	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;
-	}
-
 	if (interpreter) {
 		elf_entry = load_elf_interp(interp_elf_ex,
 					    interpreter,
@@ -1302,24 +1323,44 @@ out_free_interp:
 	mm->end_data = end_data;
 	mm->start_stack = bprm->p;
 
-	if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) {
+	/**
+	 * DOC: "brk" handling
+	 *
+	 * For architectures with ELF randomization, when executing a
+	 * loader directly (i.e. static PIE: ET_DYN without PT_INTERP),
+	 * move the brk area out of the mmap region and into the unused
+	 * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide
+	 * early with the stack growing down or other regions being put
+	 * into the mmap region by the kernel (e.g. vdso).
+	 *
+	 * In the CONFIG_COMPAT_BRK case, though, everything is turned
+	 * off because we're not allowed to move the brk at all.
+	 */
+	if (!IS_ENABLED(CONFIG_COMPAT_BRK) &&
+	    IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
+	    elf_ex->e_type == ET_DYN && !interpreter) {
+		elf_brk = ELF_ET_DYN_BASE;
+		/* This counts as moving the brk, so let brk(2) know. */
+		brk_moved = true;
+	}
+	mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk);
+
+	if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) {
 		/*
-		 * For architectures with ELF randomization, when executing
-		 * a loader directly (i.e. no interpreter listed in ELF
-		 * headers), move the brk area out of the mmap region
-		 * (since it grows up, and may collide early with the stack
-		 * growing down), and into the unused ELF_ET_DYN_BASE region.
+		 * If we didn't move the brk to ELF_ET_DYN_BASE (above),
+		 * leave a gap between .bss and brk.
 		 */
-		if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
-		    elf_ex->e_type == ET_DYN && !interpreter) {
-			mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
-		}
+		if (!brk_moved)
+			mm->brk = mm->start_brk = mm->brk + PAGE_SIZE;
 
 		mm->brk = mm->start_brk = arch_randomize_brk(mm);
+		brk_moved = true;
+	}
+
 #ifdef compat_brk_randomized
+	if (brk_moved)
 		current->brk_randomized = 1;
 #endif
-	}
 
 	if (current->personality & MMAP_PAGE_ZERO) {
 		/* Why this, you ask???  Well SVr4 maps page 0 as read-only,
@@ -1522,7 +1563,7 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset)
 	phdr->p_align = 0;
 }
 
-static void fill_note(struct memelfnote *note, const char *name, int type, 
+static void fill_note(struct memelfnote *note, const char *name, int type,
 		unsigned int sz, void *data)
 {
 	note->name = name;
@@ -2005,8 +2046,8 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
 	t->num_notes = 0;
 
 	fill_prstatus(&t->prstatus.common, p, signr);
-	elf_core_copy_task_regs(p, &t->prstatus.pr_reg);	
-	
+	elf_core_copy_task_regs(p, &t->prstatus.pr_reg);
+
 	fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus),
 		  &(t->prstatus));
 	t->num_notes++;
@@ -2296,7 +2337,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!elf_core_write_extra_phdrs(cprm, offset))
 		goto end_coredump;
 
- 	/* write out the notes section */
+	/* write out the notes section */
 	if (!write_note_info(&info, cprm))
 		goto end_coredump;