[RFC PATCH v6 2/2] module: allocate codetag sections before the regular module layout

@@ -325,6 +325,8 @@ enum mod_mem_type {
 	MOD_INIT_RODATA,
 
 	MOD_MEM_NUM_TYPES,
+
+	MOD_STANDALONE = -2,
 	MOD_INVALID = -1,
 };
 

@@ -29,6 +29,10 @@
 #define SH_ENTSIZE_TYPE_MASK	((1UL << SH_ENTSIZE_TYPE_BITS) - 1)
 #define SH_ENTSIZE_OFFSET_MASK	((1UL << (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)) - 1)
 
+#define SH_ENTSIZE_STANDALONE					\
+	(((unsigned long)MOD_STANDALONE & SH_ENTSIZE_TYPE_MASK)	\
+	 << SH_ENTSIZE_TYPE_SHIFT)
+
 /* Maximum number of characters written by module_flags() */
 #define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4)
 

@@ -1625,7 +1625,7 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		 * ELF template and subsequently copy it to the per-CPU destinations.
 		 */
 		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC) &&
-		    (!infosec || infosec != info->index.pcpu))
+		    info->sechdrs[infosec].sh_entsize != SH_ENTSIZE_STANDALONE)
 			continue;
 
 		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)

@@ -1723,20 +1723,6 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
 			if (WARN_ON_ONCE(type == MOD_INVALID))
 				continue;
 
-			/*
-			 * Do not allocate codetag memory as we load it into
-			 * preallocated contiguous memory.
-			 */
-			if (codetag_needs_module_section(mod, sname, s->sh_size)) {
-				/*
-				 * s->sh_entsize won't be used but populate the
-				 * type field to avoid confusion.
-				 */
-				s->sh_entsize = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK)
-						<< SH_ENTSIZE_TYPE_SHIFT;
-				continue;
-			}
-
 			s->sh_entsize = module_get_offset_and_type(mod, type, s, i);
 			pr_debug("\t%s\n", sname);
 		}

@@ -1746,16 +1732,10 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i
 /*
  * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld
  * might -- code, read-only data, read-write data, small data.  Tally
- * sizes, and place the offsets into sh_entsize fields: high bit means it
- * belongs in init.
+ * sizes, and place the offsets into sh_entsize fields.
  */
 static void layout_sections(struct module *mod, struct load_info *info)
 {
-	unsigned int i;
-
-	for (i = 0; i < info->hdr->e_shnum; i++)
-		info->sechdrs[i].sh_entsize = ~0UL;
-
 	pr_debug("Core section allocation order for %s:\n", mod->name);
 	__layout_sections(mod, info, false);
 

@@ -2789,7 +2769,6 @@ static int move_module(struct module *mod, struct load_info *info)
 {
 	int i, ret;
 	enum mod_mem_type t = MOD_MEM_NUM_TYPES;
-	bool codetag_section_found = false;
 
 	for_each_mod_mem_type(type) {
 		if (!mod->mem[type].size) {

@@ -2807,36 +2786,14 @@ static int move_module(struct module *mod, struct load_info *info)
 	/* Transfer each section which specifies SHF_ALLOC */
 	pr_debug("Final section addresses for %s:\n", mod->name);
 	for (i = 0; i < info->hdr->e_shnum; i++) {
-		void *dest;
 		Elf_Shdr *shdr = &info->sechdrs[i];
-		const char *sname;
+		void *dest;
 
 		if (!(shdr->sh_flags & SHF_ALLOC))
 			continue;
 
-		sname = info->secstrings + shdr->sh_name;
-		/*
-		 * Load codetag sections separately as they might still be used
-		 * after module unload.
-		 */
-		if (codetag_needs_module_section(mod, sname, shdr->sh_size)) {
-			dest = codetag_alloc_module_section(mod, sname, shdr->sh_size,
-					arch_mod_section_prepend(mod, i), shdr->sh_addralign);
-			if (WARN_ON(!dest)) {
-				ret = -EINVAL;
-				goto out_err;
-			}
-			if (IS_ERR(dest)) {
-				ret = PTR_ERR(dest);
-				goto out_err;
-			}
-			codetag_section_found = true;
-		} else {
-			enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
-			unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK;
-
-			dest = mod->mem[type].base + offset;
-		}
+		dest = mod->mem[shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT].base +
+		       (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK);
 
 		if (shdr->sh_type != SHT_NOBITS) {
 			/*

@@ -2868,8 +2825,6 @@ static int move_module(struct module *mod, struct load_info *info)
 	module_memory_restore_rox(mod);
 	while (t--)
 		module_memory_free(mod, t);
-	if (codetag_section_found)
-		codetag_free_module_sections(mod);
 
 	return ret;
 }

@@ -2940,9 +2895,48 @@ static bool blacklisted(const char *module_name)
 }
 core_param(module_blacklist, module_blacklist, charp, 0400);
 
+/*
+ * Allocate codetag sections separately. They are loaded into preallocated
+ * contiguous memory because they may still be used after the module is
+ * unloaded.
+ *
+ * If the separate allocation overflows, allocate the section normally
+ * so that the module can still be loaded.
+ */
+static int allocate_codetag_sections(struct load_info *info)
+{
+	for (unsigned int i = 1; i < info->hdr->e_shnum; i++) {
+		Elf_Shdr *shdr = &info->sechdrs[i];
+		const char *sname = info->secstrings + shdr->sh_name;
+		void *dest;
+
+		if (!codetag_needs_module_section(info->mod, sname, shdr->sh_size))
+			continue;
+
+		dest = codetag_alloc_module_section(info->mod, sname, shdr->sh_size,
+				arch_mod_section_prepend(info->mod, i), shdr->sh_addralign);
+		if (WARN_ON(!dest))
+			return -EINVAL;
+		if (dest == ERR_PTR(-EAGAIN))
+			/* Allocate the section as a regular section. */
+			continue;
+		if (IS_ERR(dest))
+			return PTR_ERR(dest);
+
+		if (shdr->sh_type != SHT_NOBITS)
+			memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size);
+		shdr->sh_addr = (unsigned long)dest;
+		shdr->sh_flags &= ~(unsigned long)SHF_ALLOC;
+		shdr->sh_entsize = SH_ENTSIZE_STANDALONE;
+	}
+
+	return 0;
+}
+
 static struct module *layout_and_allocate(struct load_info *info, int flags)
 {
 	struct module *mod;
+	unsigned int i;
 	int err;
 
 	/* Allow arches to frob section contents and sizes.  */

@@ -2956,8 +2950,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	if (err < 0)
 		return ERR_PTR(err);
 
+	/* Repurpose sh_entsize to track where each section is allocated. */
+	for (i = 0; i < info->hdr->e_shnum; i++)
+		info->sechdrs[i].sh_entsize = ~0UL;
+
 	/* We will do a special allocation for per-cpu sections later. */
-	info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
+	if (info->index.pcpu) {
+		info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
+		info->sechdrs[info->index.pcpu].sh_entsize = SH_ENTSIZE_STANDALONE;
+	}
 
 	/*
 	 * Mark relevant sections as SHF_RO_AFTER_INIT so layout_sections() can

@@ -2966,18 +2967,23 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 	 */
 	module_mark_ro_after_init(info->hdr, info->sechdrs, info->secstrings);
 
-	/*
-	 * Determine total sizes, and put offsets in sh_entsize.  For now
-	 * this is done generically; there doesn't appear to be any
-	 * special cases for the architectures.
-	 */
+	/* Allow codetag sections to be allocated separately first. */
+	err = allocate_codetag_sections(info);
+	if (err) {
+		codetag_free_module_sections(info->mod);
+		return ERR_PTR(err);
+	}
+
+	/* Determine total sizes and put offsets in sh_entsize. */
 	layout_sections(info->mod, info);
 	layout_symtab(info->mod, info);
 
 	/* Allocate and move to the final place */
 	err = move_module(info->mod, info);
-	if (err)
+	if (err) {
+		codetag_free_module_sections(info->mod);
 		return ERR_PTR(err);
+	}
 
 	/* Module has been copied to its final place now: return it. */
 	mod = (void *)info->sechdrs[info->index.mod].sh_addr;

@@ -958,10 +958,12 @@ static void *reserve_module_tags(struct module *mod, unsigned long size,
 		int grow_res;
 
 		module_tags.size = offset + size;
-		if (mem_alloc_profiling_enabled() && !tags_addressable()) {
+		if (!tags_addressable()) {
 			shutdown_mem_profiling(true);
-			pr_warn("With module %s there are too many tags to fit in %d page flag bits. Memory allocation profiling is disabled!\n",
-				mod->name, NR_UNUSED_PAGEFLAG_BITS);
+			pr_warn_once("With module %s there are too many tags to fit in %d page flag bits. Memory allocation profiling is disabled!\n",
+				     mod->name, NR_UNUSED_PAGEFLAG_BITS);
+			release_module_tags(mod, false);
+			return ERR_PTR(-EAGAIN);
 		}
 
 		grow_res = vm_module_tags_populate();

@@ -969,6 +971,7 @@ static void *reserve_module_tags(struct module *mod, unsigned long size,
 			shutdown_mem_profiling(true);
 			pr_err("Failed to allocate memory for allocation tags in the module %s. Memory allocation profiling is disabled!\n",
 			       mod->name);
+			release_module_tags(mod, false);
 			return ERR_PTR(grow_res);
 		}
 	}