[PATCH v2 0/5] Allocate module text and data separately

STALE1693d

Revision v2 of 6 in this series.

12 messages, 5 authors, 2022-02-09 · open the first message on its own page

[PATCH v2 0/5] Allocate module text and data separately

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:00

This series allow architectures to request having modules data in
vmalloc area instead of module area.

This is required on powerpc book3s/32 in order to set data non
executable, because it is not possible to set executability on page
basis, this is done per 256 Mbytes segments. The module area has exec
right, vmalloc area has noexec. Without this change module data
remains executable regardless of CONFIG_STRICT_MODULES_RWX.

This can also be useful on other powerpc/32 in order to maximize the
chance of code being close enough to kernel core to avoid branch
trampolines.

Changes in v2:
- Dropped first two patches which are not necessary. They may be added back later as a follow-up series.
- Fixed the printks in GDB

Christophe Leroy (5):
  modules: Always have struct mod_tree_root
  modules: Prepare for handling several RB trees
  modules: Introduce data_layout
  modules: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
  powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and
    8xx

 arch/Kconfig                |   6 ++
 arch/powerpc/Kconfig        |   1 +
 include/linux/module.h      |   8 ++
 kernel/debug/kdb/kdb_main.c |  10 +-
 kernel/module.c             | 193 +++++++++++++++++++++++++-----------
 5 files changed, 156 insertions(+), 62 deletions(-)

-- 
2.33.1

[PATCH v2 1/5] modules: Always have struct mod_tree_root

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:02

In order to separate text and data, we need to setup
two rb trees.

This also means that struct mod_tree_root is required even without
MODULES_TREE_LOOKUP.

Also remove module_addr_min and module_addr_max as there will
be one min and one max for each tree.

Signed-off-by: Christophe Leroy <redacted>
---
 kernel/module.c | 39 ++++++++++++++++++---------------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/kernel/module.c b/kernel/module.c
index 24dab046e16c..c0f9d63d3f05 100644
--- a/kernel/module.c
+++ b/kernel/module.c

@@ -85,7 +85,7 @@
  * Mutex protects:
  * 1) List of modules (also safely readable with preempt_disable),
  * 2) module_use links,
- * 3) module_addr_min/module_addr_max.
+ * 3) mod_tree.addr_min/mod_tree.addr_max.
  * (delete and add uses RCU list operations).
  */
 static DEFINE_MUTEX(module_mutex);

@@ -96,6 +96,16 @@ static void do_free_init(struct work_struct *w);
 static DECLARE_WORK(init_free_wq, do_free_init);
 static LLIST_HEAD(init_free_list);
 
+static struct mod_tree_root {
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+	struct latch_tree_root root;
+#endif
+	unsigned long addr_min;
+	unsigned long addr_max;
+} mod_tree __cacheline_aligned = {
+	.addr_min = -1UL,
+};
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*

@@ -149,17 +159,6 @@ static const struct latch_tree_ops mod_tree_ops = {
 	.comp = mod_tree_comp,
 };
 
-static struct mod_tree_root {
-	struct latch_tree_root root;
-	unsigned long addr_min;
-	unsigned long addr_max;
-} mod_tree __cacheline_aligned = {
-	.addr_min = -1UL,
-};
-
-#define module_addr_min mod_tree.addr_min
-#define module_addr_max mod_tree.addr_max
-
 static noinline void __mod_tree_insert(struct mod_tree_node *node)
 {
 	latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops);

@@ -209,8 +208,6 @@ static struct module *mod_find(unsigned long addr)
 
 #else /* MODULES_TREE_LOOKUP */
 
-static unsigned long module_addr_min = -1UL, module_addr_max = 0;
-
 static void mod_tree_insert(struct module *mod) { }
 static void mod_tree_remove_init(struct module *mod) { }
 static void mod_tree_remove(struct module *mod) { }

@@ -239,10 +236,10 @@ static void __mod_update_bounds(void *base, unsigned int size)
 	unsigned long min = (unsigned long)base;
 	unsigned long max = min + size;
 
-	if (min < module_addr_min)
-		module_addr_min = min;
-	if (max > module_addr_max)
-		module_addr_max = max;
+	if (min < mod_tree.addr_min)
+		mod_tree.addr_min = min;
+	if (max > mod_tree.addr_max)
+		mod_tree.addr_max = max;
 }
 
 static void mod_update_bounds(struct module *mod)

@@ -4546,14 +4543,14 @@ static void cfi_init(struct module *mod)
 		mod->exit = *exit;
 #endif
 
-	cfi_module_add(mod, module_addr_min);
+	cfi_module_add(mod, mod_tree.addr_min);
 #endif
 }
 
 static void cfi_cleanup(struct module *mod)
 {
 #ifdef CONFIG_CFI_CLANG
-	cfi_module_remove(mod, module_addr_min);
+	cfi_module_remove(mod, mod_tree.addr_min);
 #endif
 }

@@ -4737,7 +4734,7 @@ struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;
 
-	if (addr < module_addr_min || addr > module_addr_max)
+	if (addr < mod_tree.addr_min || addr > mod_tree.addr_max)
 		return NULL;
 
 	module_assert_mutex_or_preempt();

-- 
2.33.1

[PATCH v2 2/5] modules: Prepare for handling several RB trees

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:07

In order to separate text and data, we need to setup
two rb trees. So modify functions to give the tree
as a parameter.

Signed-off-by: Christophe Leroy <redacted>
---
 kernel/module.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/kernel/module.c b/kernel/module.c
index c0f9d63d3f05..2b9a3d9d3c0d 100644
--- a/kernel/module.c
+++ b/kernel/module.c

@@ -159,14 +159,14 @@ static const struct latch_tree_ops mod_tree_ops = {
 	.comp = mod_tree_comp,
 };
 
-static noinline void __mod_tree_insert(struct mod_tree_node *node)
+static noinline void __mod_tree_insert(struct mod_tree_node *node, struct mod_tree_root *tree)
 {
-	latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops);
+	latch_tree_insert(&node->node, &tree->root, &mod_tree_ops);
 }
 
-static void __mod_tree_remove(struct mod_tree_node *node)
+static void __mod_tree_remove(struct mod_tree_node *node, struct mod_tree_root *tree)
 {
-	latch_tree_erase(&node->node, &mod_tree.root, &mod_tree_ops);
+	latch_tree_erase(&node->node, &tree->root, &mod_tree_ops);
 }
 
 /*

@@ -178,28 +178,28 @@ static void mod_tree_insert(struct module *mod)
 	mod->core_layout.mtn.mod = mod;
 	mod->init_layout.mtn.mod = mod;
 
-	__mod_tree_insert(&mod->core_layout.mtn);
+	__mod_tree_insert(&mod->core_layout.mtn, &mod_tree);
 	if (mod->init_layout.size)
-		__mod_tree_insert(&mod->init_layout.mtn);
+		__mod_tree_insert(&mod->init_layout.mtn, &mod_tree);
 }
 
 static void mod_tree_remove_init(struct module *mod)
 {
 	if (mod->init_layout.size)
-		__mod_tree_remove(&mod->init_layout.mtn);
+		__mod_tree_remove(&mod->init_layout.mtn, &mod_tree);
 }
 
 static void mod_tree_remove(struct module *mod)
 {
-	__mod_tree_remove(&mod->core_layout.mtn);
+	__mod_tree_remove(&mod->core_layout.mtn, &mod_tree);
 	mod_tree_remove_init(mod);
 }
 
-static struct module *mod_find(unsigned long addr)
+static struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)
 {
 	struct latch_tree_node *ltn;
 
-	ltn = latch_tree_find((void *)addr, &mod_tree.root, &mod_tree_ops);
+	ltn = latch_tree_find((void *)addr, &tree->root, &mod_tree_ops);
 	if (!ltn)
 		return NULL;

@@ -212,7 +212,7 @@ static void mod_tree_insert(struct module *mod) { }
 static void mod_tree_remove_init(struct module *mod) { }
 static void mod_tree_remove(struct module *mod) { }
 
-static struct module *mod_find(unsigned long addr)
+static struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)
 {
 	struct module *mod;

@@ -231,22 +231,22 @@ static struct module *mod_find(unsigned long addr)
  * Bounds of module text, for speeding up __module_address.
  * Protected by module_mutex.
  */
-static void __mod_update_bounds(void *base, unsigned int size)
+static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_root *tree)
 {
 	unsigned long min = (unsigned long)base;
 	unsigned long max = min + size;
 
-	if (min < mod_tree.addr_min)
-		mod_tree.addr_min = min;
-	if (max > mod_tree.addr_max)
-		mod_tree.addr_max = max;
+	if (min < tree->addr_min)
+		tree->addr_min = min;
+	if (max > tree->addr_max)
+		tree->addr_max = max;
 }
 
 static void mod_update_bounds(struct module *mod)
 {
-	__mod_update_bounds(mod->core_layout.base, mod->core_layout.size);
+	__mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree);
 	if (mod->init_layout.size)
-		__mod_update_bounds(mod->init_layout.base, mod->init_layout.size);
+		__mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree);
 }
 
 #ifdef CONFIG_KGDB_KDB

@@ -4739,7 +4739,7 @@ struct module *__module_address(unsigned long addr)
 
 	module_assert_mutex_or_preempt();
 
-	mod = mod_find(addr);
+	mod = mod_find(addr, &mod_tree);
 	if (mod) {
 		BUG_ON(!within_module(addr, mod));
 		if (mod->state == MODULE_STATE_UNFORMED)

-- 
2.33.1

[PATCH v2 3/5] modules: Introduce data_layout

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:12

In order to allow separation of data from text, add another layout,
called data_layout. For architectures requesting separation of text
and data, only text will go in core_layout and data will go in
data_layout.

For architectures which keep text and data together, make data_layout
an alias of core_layout, that way data_layout can be used for all
data manipulations, regardless of whether data is in core_layout or
data_layout.

Signed-off-by: Christophe Leroy <redacted>
---
 kernel/module.c | 52 ++++++++++++++++++++++++++++---------------------
 1 file changed, 30 insertions(+), 22 deletions(-)

diff --git a/kernel/module.c b/kernel/module.c
index 2b9a3d9d3c0d..2b70b997a36d 100644
--- a/kernel/module.c
+++ b/kernel/module.c

@@ -81,6 +81,8 @@
 /* If this is set, the section belongs in the init part of the module */
 #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))
 
+#define	data_layout core_layout
+
 /*
  * Mutex protects:
  * 1) List of modules (also safely readable with preempt_disable),

@@ -2011,19 +2013,20 @@ static void module_enable_ro(const struct module *mod, bool after_init)
 	set_vm_flush_reset_perms(mod->init_layout.base);
 	frob_text(&mod->core_layout, set_memory_ro);
 
-	frob_rodata(&mod->core_layout, set_memory_ro);
+	frob_rodata(&mod->data_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
-		frob_ro_after_init(&mod->core_layout, set_memory_ro);
+		frob_ro_after_init(&mod->data_layout, set_memory_ro);
 }
 
 static void module_enable_nx(const struct module *mod)
 {
-	frob_rodata(&mod->core_layout, set_memory_nx);
-	frob_ro_after_init(&mod->core_layout, set_memory_nx);
-	frob_writable_data(&mod->core_layout, set_memory_nx);
+	frob_rodata(&mod->data_layout, set_memory_nx);
+	frob_ro_after_init(&mod->data_layout, set_memory_nx);
+	frob_writable_data(&mod->data_layout, set_memory_nx);
 	frob_rodata(&mod->init_layout, set_memory_nx);
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }

@@ -2201,7 +2204,7 @@ static void free_module(struct module *mod)
 	percpu_modfree(mod);
 
 	/* Free lock-classes; relies on the preceding sync_rcu(). */
-	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
+	lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
 	module_memfree(mod->core_layout.base);

@@ -2448,7 +2451,10 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			    || s->sh_entsize != ~0UL
 			    || module_init_layout_section(sname))
 				continue;
-			s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i);
+			if (m)
+				s->sh_entsize = get_offset(mod, &mod->data_layout.size, s, i);
+			else
+				s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i);
 			pr_debug("\t%s\n", sname);
 		}
 		switch (m) {

@@ -2457,15 +2463,15 @@ static void layout_sections(struct module *mod, struct load_info *info)
 			mod->core_layout.text_size = mod->core_layout.size;
 			break;
 		case 1: /* RO: text and ro-data */
-			mod->core_layout.size = debug_align(mod->core_layout.size);
-			mod->core_layout.ro_size = mod->core_layout.size;
+			mod->data_layout.size = debug_align(mod->data_layout.size);
+			mod->data_layout.ro_size = mod->data_layout.size;
 			break;
 		case 2: /* RO after init */
-			mod->core_layout.size = debug_align(mod->core_layout.size);
-			mod->core_layout.ro_after_init_size = mod->core_layout.size;
+			mod->data_layout.size = debug_align(mod->data_layout.size);
+			mod->data_layout.ro_after_init_size = mod->data_layout.size;
 			break;
 		case 4: /* whole core */
-			mod->core_layout.size = debug_align(mod->core_layout.size);
+			mod->data_layout.size = debug_align(mod->data_layout.size);
 			break;
 		}
 	}

@@ -2718,12 +2724,12 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 	}
 
 	/* Append room for core symbols at end of core part. */
-	info->symoffs = ALIGN(mod->core_layout.size, symsect->sh_addralign ?: 1);
-	info->stroffs = mod->core_layout.size = info->symoffs + ndst * sizeof(Elf_Sym);
-	mod->core_layout.size += strtab_size;
-	info->core_typeoffs = mod->core_layout.size;
-	mod->core_layout.size += ndst * sizeof(char);
-	mod->core_layout.size = debug_align(mod->core_layout.size);
+	info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1);
+	info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym);
+	mod->data_layout.size += strtab_size;
+	info->core_typeoffs = mod->data_layout.size;
+	mod->data_layout.size += ndst * sizeof(char);
+	mod->data_layout.size = debug_align(mod->data_layout.size);
 
 	/* Put string table section at end of init part of module. */
 	strsect->sh_flags |= SHF_ALLOC;

@@ -2767,9 +2773,9 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 	 * Now populate the cut down core kallsyms for after init
 	 * and set types up while we still have access to sections.
 	 */
-	mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs;
-	mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs;
-	mod->core_kallsyms.typetab = mod->core_layout.base + info->core_typeoffs;
+	mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs;
+	mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs;
+	mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs;
 	src = mod->kallsyms->symtab;
 	for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
 		mod->kallsyms->typetab[i] = elf_type(src + i, info);

@@ -3465,6 +3471,8 @@ static int move_module(struct module *mod, struct load_info *info)
 		if (shdr->sh_entsize & INIT_OFFSET_MASK)
 			dest = mod->init_layout.base
 				+ (shdr->sh_entsize & ~INIT_OFFSET_MASK);
+		else if (!(shdr->sh_flags & SHF_EXECINSTR))
+			dest = mod->data_layout.base + shdr->sh_entsize;
 		else
 			dest = mod->core_layout.base + shdr->sh_entsize;

@@ -4170,7 +4178,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_unlock(&module_mutex);
  free_module:
 	/* Free lock-classes; relies on the preceding sync_rcu() */
-	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
+	lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size);
 
 	module_deallocate(mod, info);
  free_copy:

-- 
2.33.1

[PATCH v2 4/5] modules: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:15

Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC to allow architectures
to request having modules data in vmalloc area instead of module area.

This is required on powerpc book3s/32 in order to set data non
executable, because it is not possible to set executability on page
basis, this is done per 256 Mbytes segments. The module area has exec
right, vmalloc area has noexec.

This can also be useful on other powerpc/32 in order to maximize the
chance of code being close enough to kernel core to avoid branch
trampolines.

Signed-off-by: Christophe Leroy <redacted>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Daniel Thompson <redacted>
Cc: Douglas Anderson <dianders@chromium.org>
---
 arch/Kconfig                |  6 +++
 include/linux/module.h      |  8 ++++
 kernel/debug/kdb/kdb_main.c | 10 ++++-
 kernel/module.c             | 76 +++++++++++++++++++++++++++++++++++--
 4 files changed, 94 insertions(+), 6 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 678a80713b21..b5d1f2c19c27 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig

@@ -882,6 +882,12 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
+config ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	bool
+	help
+	  For architectures like powerpc/32 which have constraints on module
+	  allocation and need to allocate module data outside of module area.
+
 config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	bool
 	help

diff --git a/include/linux/module.h b/include/linux/module.h
index 1e135fd5c076..3a892bdcbb5f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h

@@ -422,6 +422,9 @@ struct module {
 	/* Core layout: rbtree is accessed frequently, so keep together. */
 	struct module_layout core_layout __module_layout_align;
 	struct module_layout init_layout;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	struct module_layout data_layout;
+#endif
 
 	/* Arch-specific module values */
 	struct mod_arch_specific arch;

@@ -569,6 +572,11 @@ bool is_module_text_address(unsigned long addr);
 static inline bool within_module_core(unsigned long addr,
 				      const struct module *mod)
 {
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	if ((unsigned long)mod->data_layout.base <= addr &&
+	    addr < (unsigned long)mod->data_layout.base + mod->data_layout.size)
+		return true;
+#endif
 	return (unsigned long)mod->core_layout.base <= addr &&
 	       addr < (unsigned long)mod->core_layout.base + mod->core_layout.size;
 }

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 0852a537dad4..85d3fd40b7fe 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c

@@ -2022,8 +2022,11 @@ static int kdb_lsmod(int argc, const char **argv)
 		if (mod->state == MODULE_STATE_UNFORMED)
 			continue;
 
-		kdb_printf("%-20s%8u  0x%px ", mod->name,
-			   mod->core_layout.size, (void *)mod);
+		kdb_printf("%-20s%8u", mod->name, mod->core_layout.size);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+		kdb_printf("/%8u", mod->data_layout.size);
+#endif
+		kdb_printf("  0x%px ", (void *)mod);
 #ifdef CONFIG_MODULE_UNLOAD
 		kdb_printf("%4d ", module_refcount(mod));
 #endif

@@ -2034,6 +2037,9 @@ static int kdb_lsmod(int argc, const char **argv)
 		else
 			kdb_printf(" (Live)");
 		kdb_printf(" 0x%px", mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+		kdb_printf("/0x%px", mod->data_layout.base);
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 		{

diff --git a/kernel/module.c b/kernel/module.c
index 2b70b997a36d..884c9fb11813 100644
--- a/kernel/module.c
+++ b/kernel/module.c

@@ -81,7 +81,9 @@
 /* If this is set, the section belongs in the init part of the module */
 #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1))
 
+#ifndef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
 #define	data_layout core_layout
+#endif
 
 /*
  * Mutex protects:

@@ -108,6 +110,12 @@ static struct mod_tree_root {
 	.addr_min = -1UL,
 };
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+static struct mod_tree_root mod_data_tree __cacheline_aligned = {
+	.addr_min = -1UL,
+};
+#endif
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*

@@ -183,6 +191,11 @@ static void mod_tree_insert(struct module *mod)
 	__mod_tree_insert(&mod->core_layout.mtn, &mod_tree);
 	if (mod->init_layout.size)
 		__mod_tree_insert(&mod->init_layout.mtn, &mod_tree);
+
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	mod->data_layout.mtn.mod = mod;
+	__mod_tree_insert(&mod->data_layout.mtn, &mod_data_tree);
+#endif
 }
 
 static void mod_tree_remove_init(struct module *mod)

@@ -195,6 +208,9 @@ static void mod_tree_remove(struct module *mod)
 {
 	__mod_tree_remove(&mod->core_layout.mtn, &mod_tree);
 	mod_tree_remove_init(mod);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	__mod_tree_remove(&mod->core_layout.mtn, &mod_data_tree);
+#endif
 }
 
 static struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)

@@ -249,6 +265,9 @@ static void mod_update_bounds(struct module *mod)
 	__mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree);
 	if (mod->init_layout.size)
 		__mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	__mod_update_bounds(mod->data_layout.base, mod->data_layout.size, &mod_data_tree);
+#endif
 }
 
 #ifdef CONFIG_KGDB_KDB

@@ -1178,6 +1197,17 @@ static ssize_t show_coresize(struct module_attribute *mattr,
 static struct module_attribute modinfo_coresize =
 	__ATTR(coresize, 0444, show_coresize, NULL);
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+static ssize_t show_datasize(struct module_attribute *mattr,
+			     struct module_kobject *mk, char *buffer)
+{
+	return sprintf(buffer, "%u\n", mk->mod->data_layout.size);
+}
+
+static struct module_attribute modinfo_datasize =
+	__ATTR(datasize, 0444, show_datasize, NULL);
+#endif
+
 static ssize_t show_initsize(struct module_attribute *mattr,
 			     struct module_kobject *mk, char *buffer)
 {

@@ -1206,6 +1236,9 @@ static struct module_attribute *modinfo_attrs[] = {
 	&modinfo_srcversion,
 	&modinfo_initstate,
 	&modinfo_coresize,
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	&modinfo_datasize,
+#endif
 	&modinfo_initsize,
 	&modinfo_taint,
 #ifdef CONFIG_MODULE_UNLOAD

@@ -2208,6 +2241,9 @@ static void free_module(struct module *mod)
 
 	/* Finally, free the core (containing the module structure) */
 	module_memfree(mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	vfree(mod->data_layout.base);
+#endif
 }
 
 void *__symbol_get(const char *symbol)

@@ -3459,6 +3495,24 @@ static int move_module(struct module *mod, struct load_info *info)
 	} else
 		mod->init_layout.base = NULL;
 
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	/* Do the allocs. */
+	ptr = vmalloc(mod->data_layout.size);
+	/*
+	 * The pointer to this block is stored in the module structure
+	 * which is inside the block. Just mark it as not being a
+	 * leak.
+	 */
+	kmemleak_not_leak(ptr);
+	if (!ptr) {
+		module_memfree(mod->core_layout.base);
+		module_memfree(mod->init_layout.base);
+		return -ENOMEM;
+	}
+
+	memset(ptr, 0, mod->data_layout.size);
+	mod->data_layout.base = ptr;
+#endif
 	/* Transfer each section which specifies SHF_ALLOC */
 	pr_debug("final section addresses:\n");
 	for (i = 0; i < info->hdr->e_shnum; i++) {

@@ -3634,6 +3688,9 @@ static void module_deallocate(struct module *mod, struct load_info *info)
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	module_memfree(mod->core_layout.base);
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	vfree(mod->data_layout.base);
+#endif
 }
 
 int __weak module_finalize(const Elf_Ehdr *hdr,

@@ -4612,13 +4669,17 @@ static int m_show(struct seq_file *m, void *p)
 	struct module *mod = list_entry(p, struct module, list);
 	char buf[MODULE_FLAGS_BUF_SIZE];
 	void *value;
+	unsigned int size;
 
 	/* We always ignore unformed modules. */
 	if (mod->state == MODULE_STATE_UNFORMED)
 		return 0;
 
-	seq_printf(m, "%s %u",
-		   mod->name, mod->init_layout.size + mod->core_layout.size);
+	size = mod->init_layout.size + mod->core_layout.size;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	size += mod->data_layout.size;
+#endif
+	seq_printf(m, "%s %u", mod->name, size);
 	print_unload_info(m, mod);
 
 	/* Informative for users. */

@@ -4741,13 +4802,20 @@ bool is_module_address(unsigned long addr)
 struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;
+	struct mod_tree_root *tree;
 
-	if (addr < mod_tree.addr_min || addr > mod_tree.addr_max)
+	if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max)
+		tree = &mod_tree;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	else if (addr >= mod_data_tree.addr_min && addr <= mod_data_tree.addr_max)
+		tree = &mod_data_tree;
+#endif
+	else
 		return NULL;
 
 	module_assert_mutex_or_preempt();
 
-	mod = mod_find(addr, &mod_tree);
+	mod = mod_find(addr, tree);
 	if (mod) {
 		BUG_ON(!within_module(addr, mod));
 		if (mod->state == MODULE_STATE_UNFORMED)

-- 
2.33.1

[PATCH v2 5/5] powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx

From: Christophe Leroy <hidden>
Date: 2022-01-27 11:28:20

book3s/32 and 8xx have a separate area for allocating modules,
defined by MODULES_VADDR / MODULES_END.

On book3s/32, it is not possible to protect against execution
on a page basis. A full 256M segment is either Exec or NoExec.
The module area is in an Exec segment while vmalloc area is
in a NoExec segment.

In order to protect module data against execution, select
ARCH_WANTS_MODULES_DATA_IN_VMALLOC.

For the 8xx (and possibly other 32 bits platform in the future),
there is no such constraint on Exec/NoExec protection, however
there is a critical distance between kernel functions and callers
that needs to remain below 32Mbytes in order to avoid costly
trampolines. By allocating data outside of module area, we
increase the chance for module text to remain within acceptable
distance from kernel core text.

So select ARCH_WANTS_MODULES_DATA_IN_VMALLOC for 8xx as well.

Signed-off-by: Christophe Leroy <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>
---
 arch/powerpc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b779603978e1..242eed8cedf8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig

@@ -152,6 +152,7 @@ config PPC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANTS_MODULES_DATA_IN_VMALLOC	if PPC_BOOK3S_32 || PPC_8xx
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
 	select BUILDTIME_TABLE_SORT

-- 
2.33.1

Re: [PATCH v2 4/5] modules: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC

From: Daniel Thompson <hidden>
Date: 2022-01-28 14:09:53

On Thu, Jan 27, 2022 at 11:28:09AM +0000, Christophe Leroy wrote:

Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC to allow architectures
to request having modules data in vmalloc area instead of module area.

This is required on powerpc book3s/32 in order to set data non
executable, because it is not possible to set executability on page
basis, this is done per 256 Mbytes segments. The module area has exec
right, vmalloc area has noexec.

This can also be useful on other powerpc/32 in order to maximize the
chance of code being close enough to kernel core to avoid branch
trampolines.

Signed-off-by: Christophe Leroy <redacted>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Daniel Thompson <redacted>
Cc: Douglas Anderson <dianders@chromium.org>

Thanks for diligence in making sure kdb is up to date!

Acked-by: Daniel Thompson <redacted>


Daniel.

Re: [PATCH v2 5/5] powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx

From: Luis Chamberlain <mcgrof@kernel.org>
Date: 2022-02-02 23:36:43

On Thu, Jan 27, 2022 at 11:28:12AM +0000, Christophe Leroy wrote:

book3s/32 and 8xx have a separate area for allocating modules,
defined by MODULES_VADDR / MODULES_END.

On book3s/32, it is not possible to protect against execution
on a page basis. A full 256M segment is either Exec or NoExec.
The module area is in an Exec segment while vmalloc area is
in a NoExec segment.

In order to protect module data against execution, select
ARCH_WANTS_MODULES_DATA_IN_VMALLOC.

For the 8xx (and possibly other 32 bits platform in the future),
there is no such constraint on Exec/NoExec protection, however
there is a critical distance between kernel functions and callers
that needs to remain below 32Mbytes in order to avoid costly
trampolines. By allocating data outside of module area, we
increase the chance for module text to remain within acceptable
distance from kernel core text.

So select ARCH_WANTS_MODULES_DATA_IN_VMALLOC for 8xx as well.

Signed-off-by: Christophe Leroy <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>

Cc list first and then the SOB.

  Luis

Re: [PATCH v2 5/5] powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2022-02-03 05:39:12

Luis Chamberlain [off-list ref] writes:

On Thu, Jan 27, 2022 at 11:28:12AM +0000, Christophe Leroy wrote:

quoted

book3s/32 and 8xx have a separate area for allocating modules,
defined by MODULES_VADDR / MODULES_END.

On book3s/32, it is not possible to protect against execution
on a page basis. A full 256M segment is either Exec or NoExec.
The module area is in an Exec segment while vmalloc area is
in a NoExec segment.

In order to protect module data against execution, select
ARCH_WANTS_MODULES_DATA_IN_VMALLOC.

For the 8xx (and possibly other 32 bits platform in the future),
there is no such constraint on Exec/NoExec protection, however
there is a critical distance between kernel functions and callers
that needs to remain below 32Mbytes in order to avoid costly
trampolines. By allocating data outside of module area, we
increase the chance for module text to remain within acceptable
distance from kernel core text.

So select ARCH_WANTS_MODULES_DATA_IN_VMALLOC for 8xx as well.

Signed-off-by: Christophe Leroy <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>

Cc list first and then the SOB.

Just delete the Cc: list, it's meaningless.

cheers

Re: [PATCH v2 5/5] powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx

From: Christophe Leroy <hidden>
Date: 2022-02-03 07:07:30


Le 03/02/2022 à 06:39, Michael Ellerman a écrit :

Luis Chamberlain [off-list ref] writes:

quoted

On Thu, Jan 27, 2022 at 11:28:12AM +0000, Christophe Leroy wrote:

quoted

book3s/32 and 8xx have a separate area for allocating modules,
defined by MODULES_VADDR / MODULES_END.

On book3s/32, it is not possible to protect against execution
on a page basis. A full 256M segment is either Exec or NoExec.
The module area is in an Exec segment while vmalloc area is
in a NoExec segment.

In order to protect module data against execution, select
ARCH_WANTS_MODULES_DATA_IN_VMALLOC.

For the 8xx (and possibly other 32 bits platform in the future),
there is no such constraint on Exec/NoExec protection, however
there is a critical distance between kernel functions and callers
that needs to remain below 32Mbytes in order to avoid costly
trampolines. By allocating data outside of module area, we
increase the chance for module text to remain within acceptable
distance from kernel core text.

So select ARCH_WANTS_MODULES_DATA_IN_VMALLOC for 8xx as well.

Signed-off-by: Christophe Leroy <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>

Cc list first and then the SOB.

Just delete the Cc: list, it's meaningless.

Was an easy way to copy you automatically with 'git send-email', but 
getting it through linuxppc-dev list is enough I guess ?

Christophe

Re: [PATCH v2 5/5] powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx

From: Michael Ellerman <mpe@ellerman.id.au>
Date: 2022-02-07 01:27:39

Christophe Leroy [off-list ref] writes:

Le 03/02/2022 à 06:39, Michael Ellerman a écrit :

quoted

Luis Chamberlain [off-list ref] writes:

quoted

On Thu, Jan 27, 2022 at 11:28:12AM +0000, Christophe Leroy wrote:

quoted

book3s/32 and 8xx have a separate area for allocating modules,
defined by MODULES_VADDR / MODULES_END.

On book3s/32, it is not possible to protect against execution
on a page basis. A full 256M segment is either Exec or NoExec.
The module area is in an Exec segment while vmalloc area is
in a NoExec segment.

In order to protect module data against execution, select
ARCH_WANTS_MODULES_DATA_IN_VMALLOC.

For the 8xx (and possibly other 32 bits platform in the future),
there is no such constraint on Exec/NoExec protection, however
there is a critical distance between kernel functions and callers
that needs to remain below 32Mbytes in order to avoid costly
trampolines. By allocating data outside of module area, we
increase the chance for module text to remain within acceptable
distance from kernel core text.

So select ARCH_WANTS_MODULES_DATA_IN_VMALLOC for 8xx as well.

Signed-off-by: Christophe Leroy <redacted>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>

Cc list first and then the SOB.

Just delete the Cc: list, it's meaningless.

Was an easy way to copy you automatically with 'git send-email', but 
getting it through linuxppc-dev list is enough I guess ?

It's useful for making the tooling Cc the right people, it's fine to use
them for that.

But there's no value in committing them to the git history, I actively
strip them when applying. The fact that someone is Cc'ed on a patch
tells you nothing, given the volume of mail maintainers receive.

The link tag back to the original submission gives you the Cc list
anyway.

cheers

Re: [PATCH v2 0/5] Allocate module text and data separately

From: Miroslav Benes <mbenes@suse.cz>
Date: 2022-02-09 15:43:11

On Thu, 27 Jan 2022, Christophe Leroy wrote:

This series allow architectures to request having modules data in
vmalloc area instead of module area.

This is required on powerpc book3s/32 in order to set data non
executable, because it is not possible to set executability on page
basis, this is done per 256 Mbytes segments. The module area has exec
right, vmalloc area has noexec. Without this change module data
remains executable regardless of CONFIG_STRICT_MODULES_RWX.

This can also be useful on other powerpc/32 in order to maximize the
chance of code being close enough to kernel core to avoid branch
trampolines.

Changes in v2:
- Dropped first two patches which are not necessary. They may be added back later as a follow-up series.
- Fixed the printks in GDB

Christophe Leroy (5):
  modules: Always have struct mod_tree_root
  modules: Prepare for handling several RB trees
  modules: Introduce data_layout
  modules: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
  powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and
    8xx

 arch/Kconfig                |   6 ++
 arch/powerpc/Kconfig        |   1 +
 include/linux/module.h      |   8 ++
 kernel/debug/kdb/kdb_main.c |  10 +-
 kernel/module.c             | 193 +++++++++++++++++++++++++-----------
 5 files changed, 156 insertions(+), 62 deletions(-)

Looks good to me apart from the typo I mentioned at v1. I will review 
again once it is rebased on Aaron's patch set.

Regards,
Miroslav

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help