1 files changed, 197 insertions, 194 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index fb2c8d14327a..47335a0f4a61 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -110,38 +110,19 @@ 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
-   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;
@@ -367,6 +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)
@@ -406,6 +392,60 @@ 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)
+{
+	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 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);
+		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;
@@ -596,8 +636,6 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	struct elf_phdr *eppnt;
 	unsigned long load_addr = 0;
 	int load_addr_set = 0;
-	unsigned long last_bss = 0, elf_bss = 0;
-	int bss_prot = 0;
 	unsigned long error = ~0UL;
 	unsigned long total_size;
 	int i;
@@ -634,7 +672,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 			else if (no_base && interp_elf_ex->e_type == ET_DYN)
 				load_addr = -vaddr;
 
-			map_addr = elf_map(interpreter, load_addr + vaddr,
+			map_addr = elf_load(interpreter, load_addr + vaddr,
 					eppnt, elf_prot, elf_type, total_size);
 			total_size = 0;
 			error = map_addr;
@@ -660,51 +698,9 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 				error = -ENOMEM;
 				goto out;
 			}
-
-			/*
-			 * Find the end of the file mapping for this phdr, and
-			 * keep track of the largest address we see for this.
-			 */
-			k = load_addr + eppnt->p_vaddr + eppnt->p_filesz;
-			if (k > elf_bss)
-				elf_bss = k;
-
-			/*
-			 * Do the same thing for the memory mapping - between
-			 * elf_bss and last_bss is the bss section.
-			 */
-			k = load_addr + eppnt->p_vaddr + eppnt->p_memsz;
-			if (k > last_bss) {
-				last_bss = k;
-				bss_prot = elf_prot;
-			}
 		}
 	}
 
-	/*
-	 * Now fill out the bss section: first pad the last page from
-	 * the file up to the page boundary, and zero it from elf_bss
-	 * up to the end of the page.
-	 */
-	if (padzero(elf_bss)) {
-		error = -EFAULT;
-		goto out;
-	}
-	/*
-	 * Next, align both the file and mem bss up to the page size,
-	 * since this is where elf_bss was just zeroed up to, and where
-	 * last_bss will end after the vm_brk_flags() below.
-	 */
-	elf_bss = ELF_PAGEALIGN(elf_bss);
-	last_bss = ELF_PAGEALIGN(last_bss);
-	/* Finally, if there is still more bss to allocate, do it. */
-	if (last_bss > elf_bss) {
-		error = vm_brk_flags(elf_bss, last_bss - elf_bss,
-				bss_prot & PROT_EXEC ? VM_EXEC : 0);
-		if (error)
-			goto out;
-	}
-
 	error = load_addr;
 out:
 	return error;
@@ -828,8 +824,8 @@ 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;
@@ -1021,7 +1017,6 @@ out_free_interp:
 	if (retval < 0)
 		goto out_free_dentry;
 
-	elf_bss = 0;
 	elf_brk = 0;
 
 	start_code = ~0UL;
@@ -1041,33 +1036,6 @@ 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);
 
@@ -1095,15 +1063,49 @@ 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
@@ -1116,17 +1118,49 @@ 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
@@ -1136,34 +1170,9 @@ 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_VALUE(error) ?
@@ -1211,41 +1220,23 @@ 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,
@@ -1301,24 +1292,44 @@ 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,
@@ -1327,6 +1338,11 @@ out_free_interp:
 		   emulate the SVr4 behavior. Sigh. */
 		error = vm_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE, 0);
+
+		retval = do_mseal(0, PAGE_SIZE, 0);
+		if (retval)
+			pr_warn_ratelimited("pid=%d, couldn't seal address 0, ret=%d.\n",
+					    task_pid_nr(current), retval);
 	}
 
 	regs = current_pt_regs();
@@ -1370,7 +1386,6 @@ static int load_elf_library(struct file *file)
 {
 	struct elf_phdr *elf_phdata;
 	struct elf_phdr *eppnt;
-	unsigned long elf_bss, bss, len;
 	int retval, error, i, j;
 	struct elfhdr elf_ex;
 
@@ -1415,30 +1430,15 @@ static int load_elf_library(struct file *file)
 		eppnt++;
 
 	/* Now use mmap to map the library into memory. */
-	error = vm_mmap(file,
-			ELF_PAGESTART(eppnt->p_vaddr),
-			(eppnt->p_filesz +
-			 ELF_PAGEOFFSET(eppnt->p_vaddr)),
+	error = elf_load(file, ELF_PAGESTART(eppnt->p_vaddr),
+			eppnt,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
 			MAP_FIXED_NOREPLACE | MAP_PRIVATE,
-			(eppnt->p_offset -
-			 ELF_PAGEOFFSET(eppnt->p_vaddr)));
-	if (error != ELF_PAGESTART(eppnt->p_vaddr))
-		goto out_free_ph;
+			0);
 
-	elf_bss = eppnt->p_vaddr + eppnt->p_filesz;
-	if (padzero(elf_bss)) {
-		error = -EFAULT;
+	if (error != ELF_PAGESTART(eppnt->p_vaddr))
 		goto out_free_ph;
-	}
 
-	len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr);
-	bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr);
-	if (bss > len) {
-		error = vm_brk(len, bss - len);
-		if (error)
-			goto out_free_ph;
-	}
 	error = 0;
 
 out_free_ph:
@@ -1630,7 +1630,6 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
 	fill_note(note, "CORE", NT_SIGINFO, sizeof(*csigdata), csigdata);
 }
 
-#define MAX_FILE_NOTE_SIZE (4*1024*1024)
 /*
  * Format of NT_FILE note:
  *
@@ -1658,8 +1657,12 @@ static int fill_files_note(struct memelfnote *note, struct coredump_params *cprm
 
 	names_ofs = (2 + 3 * count) * sizeof(data[0]);
  alloc:
-	if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
+	/* paranoia check */
+	if (size >= core_file_note_size_limit) {
+		pr_warn_once("coredump Note size too large: %u (does kernel.core_file_note_size_limit sysctl need adjustment?\n",
+			      size);
 		return -EINVAL;
+	}
 	size = round_up(size, PAGE_SIZE);
 	/*
 	 * "size" can be 0 here legitimately.
@@ -1994,7 +1997,7 @@ static void free_note_info(struct elf_note_info *info)
 		threads = t->next;
 		WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus);
 		for (i = 1; i < info->thread_notes; ++i)
-			kfree(t->notes[i].data);
+			kvfree(t->notes[i].data);
 		kfree(t);
 	}
 	kfree(info->psinfo.data);
@@ -2066,7 +2069,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	{
 		size_t sz = info.size;
 
-		/* For cell spufs */
+		/* For cell spufs and x86 xstate */
 		sz += elf_coredump_extra_notes_size();
 
 		phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL);
@@ -2130,7 +2133,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!write_note_info(&info, cprm))
 		goto end_coredump;
 
-	/* For cell spufs */
+	/* For cell spufs and x86 xstate */
 	if (elf_coredump_extra_notes_write(cprm))
 		goto end_coredump;
 
@@ -2177,5 +2180,5 @@ core_initcall(init_elf_binfmt);
 module_exit(exit_elf_binfmt);
 
 #ifdef CONFIG_BINFMT_ELF_KUNIT_TEST
-#include "binfmt_elf_test.c"
+#include "tests/binfmt_elf_kunit.c"
 #endif