From: "Mike Rapoport (IBM)" <[email protected]>
powerpc overrides kprobes::alloc_insn_page() to remove writable
permissions when STRICT_MODULE_RWX is on.
Add definition of EXECMEM_KRPOBES to execmem_params to allow using the
generic kprobes::alloc_insn_page() with the desired permissions.
As powerpc uses breakpoint instructions to inject kprobes, it does not
need to constrain kprobe allocations to the modules area and can use the
entire vmalloc address space.
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
arch/powerpc/kernel/kprobes.c | 20 --------------------
arch/powerpc/kernel/module.c | 7 +++++++
2 files changed, 7 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 9fcd01bb2ce6..14c5ddec3056 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -126,26 +126,6 @@ kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offse
return (kprobe_opcode_t *)(addr + offset);
}
-void *alloc_insn_page(void)
-{
- void *page;
-
- page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
- if (!page)
- return NULL;
-
- if (strict_module_rwx_enabled()) {
- int err = set_memory_rox((unsigned long)page, 1);
-
- if (err)
- goto error;
- }
- return page;
-error:
- execmem_free(page);
- return NULL;
-}
-
int arch_prepare_kprobe(struct kprobe *p)
{
int ret = 0;
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index ac80559015a3..2a23cf7e141b 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -94,6 +94,7 @@ static struct execmem_info execmem_info __ro_after_init;
struct execmem_info __init *execmem_arch_setup(void)
{
+ pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
unsigned long fallback_start = 0, fallback_end = 0;
unsigned long start, end;
@@ -132,6 +133,12 @@ struct execmem_info __init *execmem_arch_setup(void)
.fallback_start = fallback_start,
.fallback_end = fallback_end,
},
+ [EXECMEM_KPROBES] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = kprobes_prot,
+ .alignment = 1,
+ },
[EXECMEM_MODULE_DATA] = {
.start = VMALLOC_START,
.end = VMALLOC_END,
--
2.43.0
From: "Mike Rapoport (IBM)" <[email protected]>
There are places where CONFIG_MODULES guards the code that depends on
memory allocation being done with module_alloc().
Replace CONFIG_MODULES with CONFIG_EXECMEM in such places.
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/kasan.h | 2 +-
arch/powerpc/kernel/head_8xx.S | 4 ++--
arch/powerpc/kernel/head_book3s_32.S | 6 +++---
arch/powerpc/lib/code-patching.c | 2 +-
arch/powerpc/mm/book3s32/mmu.c | 2 +-
6 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1c4be3373686..2e586733a464 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -285,7 +285,7 @@ config PPC
select IOMMU_HELPER if PPC64
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
- select KASAN_VMALLOC if KASAN && MODULES
+ select KASAN_VMALLOC if KASAN && EXECMEM
select LOCK_MM_AND_FIND_VMA
select MMU_GATHER_PAGE_SIZE
select MMU_GATHER_RCU_TABLE_FREE
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 365d2720097c..b5bbb94c51f6 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -19,7 +19,7 @@
#define KASAN_SHADOW_SCALE_SHIFT 3
-#if defined(CONFIG_MODULES) && defined(CONFIG_PPC32)
+#if defined(CONFIG_EXECMEM) && defined(CONFIG_PPC32)
#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M)
#else
#define KASAN_KERN_START PAGE_OFFSET
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 647b0b445e89..edc479a7c2bc 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -199,12 +199,12 @@ instruction_counter:
mfspr r10, SPRN_SRR0 /* Get effective address of fault */
INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
mtspr SPRN_MD_EPN, r10
-#ifdef CONFIG_MODULES
+#ifdef CONFIG_EXECMEM
mfcr r11
compare_to_kernel_boundary r10, r10
#endif
mfspr r10, SPRN_M_TWB /* Get level 1 table */
-#ifdef CONFIG_MODULES
+#ifdef CONFIG_EXECMEM
blt+ 3f
rlwinm r10, r10, 0, 20, 31
oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index c1d89764dd22..57196883a00e 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -419,14 +419,14 @@ InstructionTLBMiss:
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_IMISS
-#ifdef CONFIG_MODULES
+#ifdef CONFIG_EXECMEM
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SDR1
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
rlwinm r2, r2, 28, 0xfffff000
-#ifdef CONFIG_MODULES
+#ifdef CONFIG_EXECMEM
li r0, 3
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
@@ -442,7 +442,7 @@ InstructionTLBMiss:
andc. r1,r1,r2 /* check access & ~permission */
bne- InstructionAddressInvalid /* return if access not permitted */
/* Convert linux-style PTE to low word of PPC-style PTE */
-#ifdef CONFIG_MODULES
+#ifdef CONFIG_EXECMEM
rlwimi r2, r0, 0, 31, 31 /* userspace ? -> PP lsb */
#endif
ori r1, r1, 0xe06 /* clear out reserved bits */
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c6ab46156cda..7af791446ddf 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -225,7 +225,7 @@ void __init poking_init(void)
static unsigned long get_patch_pfn(void *addr)
{
- if (IS_ENABLED(CONFIG_MODULES) && is_vmalloc_or_module_addr(addr))
+ if (IS_ENABLED(CONFIG_EXECMEM) && is_vmalloc_or_module_addr(addr))
return vmalloc_to_pfn(addr);
else
return __pa_symbol(addr) >> PAGE_SHIFT;
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 100f999871bc..625fe7d08e06 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -184,7 +184,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
static bool is_module_segment(unsigned long addr)
{
- if (!IS_ENABLED(CONFIG_MODULES))
+ if (!IS_ENABLED(CONFIG_EXECMEM))
return false;
if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
return false;
--
2.43.0
From: "Mike Rapoport (IBM)" <[email protected]>
execmem does not depend on modules, on the contrary modules use
execmem.
To make execmem available when CONFIG_MODULES=n, for instance for
kprobes, split execmem_params initialization out from
arch/*/kernel/module.c and compile it when CONFIG_EXECMEM=y
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
arch/arm/kernel/module.c | 43 ----------
arch/arm/mm/init.c | 45 +++++++++++
arch/arm64/kernel/module.c | 140 ---------------------------------
arch/arm64/mm/init.c | 140 +++++++++++++++++++++++++++++++++
arch/loongarch/kernel/module.c | 19 -----
arch/loongarch/mm/init.c | 21 +++++
arch/mips/kernel/module.c | 22 ------
arch/mips/mm/init.c | 23 ++++++
arch/nios2/kernel/module.c | 20 -----
arch/nios2/mm/init.c | 21 +++++
arch/parisc/kernel/module.c | 20 -----
arch/parisc/mm/init.c | 23 +++++-
arch/powerpc/kernel/module.c | 63 ---------------
arch/powerpc/mm/mem.c | 64 +++++++++++++++
arch/riscv/kernel/module.c | 44 -----------
arch/riscv/mm/init.c | 45 +++++++++++
arch/s390/kernel/module.c | 27 -------
arch/s390/mm/init.c | 30 +++++++
arch/sparc/kernel/module.c | 19 -----
arch/sparc/mm/Makefile | 2 +
arch/sparc/mm/execmem.c | 21 +++++
arch/x86/kernel/module.c | 27 -------
arch/x86/mm/init.c | 29 +++++++
23 files changed, 463 insertions(+), 445 deletions(-)
create mode 100644 arch/sparc/mm/execmem.c
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index a98fdf6ff26c..677f218f7e84 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -12,57 +12,14 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elf.h>
-#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/execmem.h>
#include <asm/sections.h>
#include <asm/smp_plat.h>
#include <asm/unwind.h>
#include <asm/opcodes.h>
-#ifdef CONFIG_XIP_KERNEL
-/*
- * The XIP kernel text is mapped in the module area for modules and
- * some other stuff to work without any indirect relocations.
- * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
- * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
- */
-#undef MODULES_VADDR
-#define MODULES_VADDR (((unsigned long)_exiprom + ~PMD_MASK) & PMD_MASK)
-#endif
-
-#ifdef CONFIG_MMU
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- unsigned long fallback_start = 0, fallback_end = 0;
-
- if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS)) {
- fallback_start = VMALLOC_START;
- fallback_end = VMALLOC_END;
- }
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = MODULES_VADDR,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL_EXEC,
- .alignment = 1,
- .fallback_start = fallback_start,
- .fallback_end = fallback_end,
- },
- },
- };
-
- return &execmem_info;
-}
-#endif
-
bool module_init_section(const char *name)
{
return strstarts(name, ".init") ||
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index e8c6f4be0ce1..5345d218899a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -22,6 +22,7 @@
#include <linux/sizes.h>
#include <linux/stop_machine.h>
#include <linux/swiotlb.h>
+#include <linux/execmem.h>
#include <asm/cp15.h>
#include <asm/mach-types.h>
@@ -486,3 +487,47 @@ void free_initrd_mem(unsigned long start, unsigned long end)
free_reserved_area((void *)start, (void *)end, -1, "initrd");
}
#endif
+
+#ifdef CONFIG_EXECMEM
+
+#ifdef CONFIG_XIP_KERNEL
+/*
+ * The XIP kernel text is mapped in the module area for modules and
+ * some other stuff to work without any indirect relocations.
+ * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
+ * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
+ */
+#undef MODULES_VADDR
+#define MODULES_VADDR (((unsigned long)_exiprom + ~PMD_MASK) & PMD_MASK)
+#endif
+
+#ifdef CONFIG_MMU
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long fallback_start = 0, fallback_end = 0;
+
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS)) {
+ fallback_start = VMALLOC_START;
+ fallback_end = VMALLOC_END;
+ }
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = MODULES_VADDR,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL_EXEC,
+ .alignment = 1,
+ .fallback_start = fallback_start,
+ .fallback_end = fallback_end,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_MMU */
+
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index a52240ea084b..36b25af56324 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -12,158 +12,18 @@
#include <linux/bitops.h>
#include <linux/elf.h>
#include <linux/ftrace.h>
-#include <linux/gfp.h>
#include <linux/kasan.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/moduleloader.h>
#include <linux/random.h>
#include <linux/scs.h>
-#include <linux/vmalloc.h>
-#include <linux/execmem.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/scs.h>
#include <asm/sections.h>
-static u64 module_direct_base __ro_after_init = 0;
-static u64 module_plt_base __ro_after_init = 0;
-
-/*
- * Choose a random page-aligned base address for a window of 'size' bytes which
- * entirely contains the interval [start, end - 1].
- */
-static u64 __init random_bounding_box(u64 size, u64 start, u64 end)
-{
- u64 max_pgoff, pgoff;
-
- if ((end - start) >= size)
- return 0;
-
- max_pgoff = (size - (end - start)) / PAGE_SIZE;
- pgoff = get_random_u32_inclusive(0, max_pgoff);
-
- return start - pgoff * PAGE_SIZE;
-}
-
-/*
- * Modules may directly reference data and text anywhere within the kernel
- * image and other modules. References using PREL32 relocations have a +/-2G
- * range, and so we need to ensure that the entire kernel image and all modules
- * fall within a 2G window such that these are always within range.
- *
- * Modules may directly branch to functions and code within the kernel text,
- * and to functions and code within other modules. These branches will use
- * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure
- * that the entire kernel text and all module text falls within a 128M window
- * such that these are always within range. With PLTs, we can expand this to a
- * 2G window.
- *
- * We chose the 128M region to surround the entire kernel image (rather than
- * just the text) as using the same bounds for the 128M and 2G regions ensures
- * by construction that we never select a 128M region that is not a subset of
- * the 2G region. For very large and unusual kernel configurations this means
- * we may fall back to PLTs where they could have been avoided, but this keeps
- * the logic significantly simpler.
- */
-static int __init module_init_limits(void)
-{
- u64 kernel_end = (u64)_end;
- u64 kernel_start = (u64)_text;
- u64 kernel_size = kernel_end - kernel_start;
-
- /*
- * The default modules region is placed immediately below the kernel
- * image, and is large enough to use the full 2G relocation range.
- */
- BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END);
- BUILD_BUG_ON(MODULES_VSIZE < SZ_2G);
-
- if (!kaslr_enabled()) {
- if (kernel_size < SZ_128M)
- module_direct_base = kernel_end - SZ_128M;
- if (kernel_size < SZ_2G)
- module_plt_base = kernel_end - SZ_2G;
- } else {
- u64 min = kernel_start;
- u64 max = kernel_end;
-
- if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) {
- pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n");
- } else {
- module_direct_base = random_bounding_box(SZ_128M, min, max);
- if (module_direct_base) {
- min = module_direct_base;
- max = module_direct_base + SZ_128M;
- }
- }
-
- module_plt_base = random_bounding_box(SZ_2G, min, max);
- }
-
- pr_info("%llu pages in range for non-PLT usage",
- module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0);
- pr_info("%llu pages in range for PLT usage",
- module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0);
-
- return 0;
-}
-
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- unsigned long fallback_start = 0, fallback_end = 0;
- unsigned long start = 0, end = 0;
-
- module_init_limits();
-
- /*
- * Where possible, prefer to allocate within direct branch range of the
- * kernel such that no PLTs are necessary.
- */
- if (module_direct_base) {
- start = module_direct_base;
- end = module_direct_base + SZ_128M;
-
- if (module_plt_base) {
- fallback_start = module_plt_base;
- fallback_end = module_plt_base + SZ_2G;
- }
- } else if (module_plt_base) {
- start = module_plt_base;
- end = module_plt_base + SZ_2G;
- }
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = start,
- .end = end,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- .fallback_start = fallback_start,
- .fallback_end = fallback_end,
- },
- [EXECMEM_KPROBES] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = PAGE_KERNEL_ROX,
- .alignment = 1,
- },
- [EXECMEM_BPF] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-
enum aarch64_reloc_op {
RELOC_OP_NONE,
RELOC_OP_ABS,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 03efd86dce0a..9b5ab6818f7f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -32,6 +32,7 @@
#include <linux/hugetlb.h>
#include <linux/acpi_iort.h>
#include <linux/kmemleak.h>
+#include <linux/execmem.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
@@ -432,3 +433,142 @@ void dump_mem_limit(void)
pr_emerg("Memory Limit: none\n");
}
}
+
+#ifdef CONFIG_EXECMEM
+static u64 module_direct_base __ro_after_init = 0;
+static u64 module_plt_base __ro_after_init = 0;
+
+/*
+ * Choose a random page-aligned base address for a window of 'size' bytes which
+ * entirely contains the interval [start, end - 1].
+ */
+static u64 __init random_bounding_box(u64 size, u64 start, u64 end)
+{
+ u64 max_pgoff, pgoff;
+
+ if ((end - start) >= size)
+ return 0;
+
+ max_pgoff = (size - (end - start)) / PAGE_SIZE;
+ pgoff = get_random_u32_inclusive(0, max_pgoff);
+
+ return start - pgoff * PAGE_SIZE;
+}
+
+/*
+ * Modules may directly reference data and text anywhere within the kernel
+ * image and other modules. References using PREL32 relocations have a +/-2G
+ * range, and so we need to ensure that the entire kernel image and all modules
+ * fall within a 2G window such that these are always within range.
+ *
+ * Modules may directly branch to functions and code within the kernel text,
+ * and to functions and code within other modules. These branches will use
+ * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure
+ * that the entire kernel text and all module text falls within a 128M window
+ * such that these are always within range. With PLTs, we can expand this to a
+ * 2G window.
+ *
+ * We chose the 128M region to surround the entire kernel image (rather than
+ * just the text) as using the same bounds for the 128M and 2G regions ensures
+ * by construction that we never select a 128M region that is not a subset of
+ * the 2G region. For very large and unusual kernel configurations this means
+ * we may fall back to PLTs where they could have been avoided, but this keeps
+ * the logic significantly simpler.
+ */
+static int __init module_init_limits(void)
+{
+ u64 kernel_end = (u64)_end;
+ u64 kernel_start = (u64)_text;
+ u64 kernel_size = kernel_end - kernel_start;
+
+ /*
+ * The default modules region is placed immediately below the kernel
+ * image, and is large enough to use the full 2G relocation range.
+ */
+ BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END);
+ BUILD_BUG_ON(MODULES_VSIZE < SZ_2G);
+
+ if (!kaslr_enabled()) {
+ if (kernel_size < SZ_128M)
+ module_direct_base = kernel_end - SZ_128M;
+ if (kernel_size < SZ_2G)
+ module_plt_base = kernel_end - SZ_2G;
+ } else {
+ u64 min = kernel_start;
+ u64 max = kernel_end;
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) {
+ pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n");
+ } else {
+ module_direct_base = random_bounding_box(SZ_128M, min, max);
+ if (module_direct_base) {
+ min = module_direct_base;
+ max = module_direct_base + SZ_128M;
+ }
+ }
+
+ module_plt_base = random_bounding_box(SZ_2G, min, max);
+ }
+
+ pr_info("%llu pages in range for non-PLT usage",
+ module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0);
+ pr_info("%llu pages in range for PLT usage",
+ module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0);
+
+ return 0;
+}
+
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long fallback_start = 0, fallback_end = 0;
+ unsigned long start = 0, end = 0;
+
+ module_init_limits();
+
+ /*
+ * Where possible, prefer to allocate within direct branch range of the
+ * kernel such that no PLTs are necessary.
+ */
+ if (module_direct_base) {
+ start = module_direct_base;
+ end = module_direct_base + SZ_128M;
+
+ if (module_plt_base) {
+ fallback_start = module_plt_base;
+ fallback_end = module_plt_base + SZ_2G;
+ }
+ } else if (module_plt_base) {
+ start = module_plt_base;
+ end = module_plt_base + SZ_2G;
+ }
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = start,
+ .end = end,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ .fallback_start = fallback_start,
+ .fallback_end = fallback_end,
+ },
+ [EXECMEM_KPROBES] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL_ROX,
+ .alignment = 1,
+ },
+ [EXECMEM_BPF] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index ca6dd7ea1610..36d6d9eeb7c7 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -18,7 +18,6 @@
#include <linux/ftrace.h>
#include <linux/string.h>
#include <linux/kernel.h>
-#include <linux/execmem.h>
#include <asm/alternative.h>
#include <asm/inst.h>
#include <asm/unwind.h>
@@ -491,24 +490,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
return 0;
}
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = MODULES_VADDR,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-
static void module_init_ftrace_plt(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs, struct module *mod)
{
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 4dd53427f657..bf789d114c2d 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -24,6 +24,7 @@
#include <linux/gfp.h>
#include <linux/hugetlb.h>
#include <linux/mmzone.h>
+#include <linux/execmem.h>
#include <asm/asm-offsets.h>
#include <asm/bootinfo.h>
@@ -248,3 +249,23 @@ EXPORT_SYMBOL(invalid_pmd_table);
#endif
pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
EXPORT_SYMBOL(invalid_pte_table);
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = MODULES_VADDR,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index 59225a3cf918..ba0f62d8eff5 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -13,14 +13,12 @@
#include <linux/elf.h>
#include <linux/mm.h>
#include <linux/numa.h>
-#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/spinlock.h>
#include <linux/jump_label.h>
-#include <linux/execmem.h>
#include <asm/jump_label.h>
struct mips_hi16 {
@@ -32,26 +30,6 @@ struct mips_hi16 {
static LIST_HEAD(dbe_list);
static DEFINE_SPINLOCK(dbe_lock);
-#ifdef MODULES_VADDR
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = MODULES_VADDR,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-#endif
-
static void apply_r_mips_32(u32 *location, u32 base, Elf_Addr v)
{
*location = base + v;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 39f129205b0c..4583d1a2a73e 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -31,6 +31,7 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/initrd.h>
+#include <linux/execmem.h>
#include <asm/bootinfo.h>
#include <asm/cachectl.h>
@@ -576,3 +577,25 @@ EXPORT_SYMBOL_GPL(invalid_pmd_table);
#endif
pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;
EXPORT_SYMBOL(invalid_pte_table);
+
+#ifdef CONFIG_EXECMEM
+#ifdef MODULES_VADDR
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = MODULES_VADDR,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c
index 0d1ee86631fc..f4483243578d 100644
--- a/arch/nios2/kernel/module.c
+++ b/arch/nios2/kernel/module.c
@@ -13,33 +13,13 @@
#include <linux/moduleloader.h>
#include <linux/elf.h>
#include <linux/mm.h>
-#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/kernel.h>
-#include <linux/execmem.h>
#include <asm/cacheflush.h>
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = MODULES_VADDR,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL_EXEC,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-
int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
unsigned int symindex, unsigned int relsec,
struct module *mod)
diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c
index 7bc82ee889c9..3459df28afee 100644
--- a/arch/nios2/mm/init.c
+++ b/arch/nios2/mm/init.c
@@ -26,6 +26,7 @@
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/binfmts.h>
+#include <linux/execmem.h>
#include <asm/setup.h>
#include <asm/page.h>
@@ -143,3 +144,23 @@ static const pgprot_t protection_map[16] = {
[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = MKP(1, 1, 1)
};
DECLARE_VM_GET_PAGE_PROT
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = MODULES_VADDR,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL_EXEC,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index bdfa85e10c1b..4e5d991b2b65 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -41,7 +41,6 @@
#include <linux/moduleloader.h>
#include <linux/elf.h>
-#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/ftrace.h>
#include <linux/string.h>
@@ -49,7 +48,6 @@
#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/slab.h>
-#include <linux/execmem.h>
#include <asm/unwind.h>
#include <asm/sections.h>
@@ -174,24 +172,6 @@ static inline int reassemble_22(int as22)
((as22 & 0x0003ff) << 3));
}
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = PAGE_KERNEL_RWX,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-
#ifndef CONFIG_64BIT
static inline unsigned long count_gots(const Elf_Rela *rela, unsigned long n)
{
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index f876af56e13f..34d91cb8b259 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -24,6 +24,7 @@
#include <linux/nodemask.h> /* for node_online_map */
#include <linux/pagemap.h> /* for release_pages */
#include <linux/compat.h>
+#include <linux/execmem.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
@@ -481,7 +482,7 @@ void free_initmem(void)
/* finally dump all the instructions which were cached, since the
* pages are no-longer executable */
flush_icache_range(init_begin, init_end);
-
+
free_initmem_default(POISON_FREE_INITMEM);
/* set up a new led state on systems shipped LED State panel */
@@ -992,3 +993,23 @@ static const pgprot_t protection_map[16] = {
[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX
};
DECLARE_VM_GET_PAGE_PROT
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL_RWX,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index 2a23cf7e141b..77ea82e9dc5f 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -7,10 +7,8 @@
#include <linux/elf.h>
#include <linux/moduleloader.h>
#include <linux/err.h>
-#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/bug.h>
-#include <linux/execmem.h>
#include <asm/module.h>
#include <linux/uaccess.h>
#include <asm/firmware.h>
@@ -89,64 +87,3 @@ int module_finalize(const Elf_Ehdr *hdr,
return 0;
}
-
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
- pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
- unsigned long fallback_start = 0, fallback_end = 0;
- unsigned long start, end;
-
- /*
- * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
- * allow allocating data in the entire vmalloc space
- */
-#ifdef MODULES_VADDR
- unsigned long limit = (unsigned long)_etext - SZ_32M;
-
- BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
-
- /* First try within 32M limit from _etext to avoid branch trampolines */
- if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) {
- start = limit;
- fallback_start = MODULES_VADDR;
- fallback_end = MODULES_END;
- } else {
- start = MODULES_VADDR;
- }
-
- end = MODULES_END;
-#else
- start = VMALLOC_START;
- end = VMALLOC_END;
-#endif
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = start,
- .end = end,
- .pgprot = prot,
- .alignment = 1,
- .fallback_start = fallback_start,
- .fallback_end = fallback_end,
- },
- [EXECMEM_KPROBES] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = kprobes_prot,
- .alignment = 1,
- },
- [EXECMEM_MODULE_DATA] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 3a440004b97d..5de62a3c1d4b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -16,6 +16,7 @@
#include <linux/highmem.h>
#include <linux/suspend.h>
#include <linux/dma-direct.h>
+#include <linux/execmem.h>
#include <asm/swiotlb.h>
#include <asm/machdep.h>
@@ -406,3 +407,66 @@ int devmem_is_allowed(unsigned long pfn)
* the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed.
*/
EXPORT_SYMBOL_GPL(walk_system_ram_range);
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ pgprot_t kprobes_prot = strict_module_rwx_enabled() ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+ pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
+ unsigned long fallback_start = 0, fallback_end = 0;
+ unsigned long start, end;
+
+ /*
+ * BOOK3S_32 and 8xx define MODULES_VADDR for text allocations and
+ * allow allocating data in the entire vmalloc space
+ */
+#ifdef MODULES_VADDR
+ unsigned long limit = (unsigned long)_etext - SZ_32M;
+
+ BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+ /* First try within 32M limit from _etext to avoid branch trampolines */
+ if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit) {
+ start = limit;
+ fallback_start = MODULES_VADDR;
+ fallback_end = MODULES_END;
+ } else {
+ start = MODULES_VADDR;
+ }
+
+ end = MODULES_END;
+#else
+ start = VMALLOC_START;
+ end = VMALLOC_END;
+#endif
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = start,
+ .end = end,
+ .pgprot = prot,
+ .alignment = 1,
+ .fallback_start = fallback_start,
+ .fallback_end = fallback_end,
+ },
+ [EXECMEM_KPROBES] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = kprobes_prot,
+ .alignment = 1,
+ },
+ [EXECMEM_MODULE_DATA] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 2ecbacbc9993..906f9a3a5d65 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -11,10 +11,8 @@
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/moduleloader.h>
-#include <linux/vmalloc.h>
#include <linux/sizes.h>
#include <linux/pgtable.h>
-#include <linux/execmem.h>
#include <asm/alternative.h>
#include <asm/sections.h>
@@ -906,48 +904,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
return 0;
}
-#ifdef CONFIG_MMU
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- unsigned long start, end;
-
- if (IS_ENABLED(CONFIG_64BIT)) {
- start = MODULES_VADDR;
- end = MODULES_END;
- } else {
- start = VMALLOC_START;
- end = VMALLOC_END;
- }
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = start,
- .end = end,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- [EXECMEM_KPROBES] = {
- .start = VMALLOC_START,
- .end = VMALLOC_END,
- .pgprot = PAGE_KERNEL_READ_EXEC,
- .alignment = 1,
- },
- [EXECMEM_BPF] = {
- .start = BPF_JIT_REGION_START,
- .end = BPF_JIT_REGION_END,
- .pgprot = PAGE_KERNEL,
- .alignment = PAGE_SIZE,
- },
- },
- };
-
- return &execmem_info;
-}
-#endif
-
int module_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *me)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index fe8e159394d8..902a4827a0a8 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -24,6 +24,7 @@
#include <linux/elf.h>
#endif
#include <linux/kfence.h>
+#include <linux/execmem.h>
#include <asm/fixmap.h>
#include <asm/io.h>
@@ -1481,3 +1482,47 @@ void __init pgtable_cache_init(void)
preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules");
}
#endif
+
+#ifdef CONFIG_EXECMEM
+#ifdef CONFIG_MMU
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long start, end;
+
+ if (IS_ENABLED(CONFIG_64BIT)) {
+ start = MODULES_VADDR;
+ end = MODULES_END;
+ } else {
+ start = VMALLOC_START;
+ end = VMALLOC_END;
+ }
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = start,
+ .end = end,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ [EXECMEM_KPROBES] = {
+ .start = VMALLOC_START,
+ .end = VMALLOC_END,
+ .pgprot = PAGE_KERNEL_READ_EXEC,
+ .alignment = 1,
+ },
+ [EXECMEM_BPF] = {
+ .start = BPF_JIT_REGION_START,
+ .end = BPF_JIT_REGION_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = PAGE_SIZE,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_MMU */
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index 7fee64fdc1bb..91e207b50394 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -37,33 +37,6 @@
#define PLT_ENTRY_SIZE 22
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- unsigned long module_load_offset = 0;
- unsigned long start;
-
- if (kaslr_enabled())
- module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
-
- start = MODULES_VADDR + module_load_offset;
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .flags = EXECMEM_KASAN_SHADOW,
- .start = start,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL,
- .alignment = MODULE_ALIGN,
- },
- },
- };
-
- return &execmem_info;
-}
-
#ifdef CONFIG_FUNCTION_TRACER
void module_arch_cleanup(struct module *mod)
{
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f6391442c0c2..e769d2726f4e 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,7 @@
#include <asm/uv.h>
#include <linux/virtio_anchor.h>
#include <linux/virtio_config.h>
+#include <linux/execmem.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
@@ -302,3 +303,32 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
vmem_remove_mapping(start, size);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long module_load_offset = 0;
+ unsigned long start;
+
+ if (kaslr_enabled())
+ module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + module_load_offset;
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index 8b7ee45defc3..b8c51cc23d96 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -14,7 +14,6 @@
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/mm.h>
-#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/spitfire.h>
@@ -22,24 +21,6 @@
#include "entry.h"
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .start = MODULES_VADDR,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL,
- .alignment = 1,
- },
- },
- };
-
- return &execmem_info;
-}
-
/* Make generic code ignore STT_REGISTER dummy undefined symbols. */
int module_frob_arch_sections(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 809d993f6d88..2d1752108d77 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -14,3 +14,5 @@ obj-$(CONFIG_SPARC32) += leon_mm.o
# Only used by sparc64
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+
+obj-$(CONFIG_EXECMEM) += execmem.o
diff --git a/arch/sparc/mm/execmem.c b/arch/sparc/mm/execmem.c
new file mode 100644
index 000000000000..0fac97dd5728
--- /dev/null
+++ b/arch/sparc/mm/execmem.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/execmem.h>
+
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .start = MODULES_VADDR,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = 1,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 45b1a7c03379..837450b6e882 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,7 +19,6 @@
#include <linux/jump_label.h>
#include <linux/random.h>
#include <linux/memory.h>
-#include <linux/execmem.h>
#include <asm/text-patching.h>
#include <asm/page.h>
@@ -37,32 +36,6 @@ do { \
} while (0)
#endif
-static struct execmem_info execmem_info __ro_after_init;
-
-struct execmem_info __init *execmem_arch_setup(void)
-{
- unsigned long start, offset = 0;
-
- if (kaslr_enabled())
- offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
-
- start = MODULES_VADDR + offset;
-
- execmem_info = (struct execmem_info){
- .ranges = {
- [EXECMEM_DEFAULT] = {
- .flags = EXECMEM_KASAN_SHADOW,
- .start = start,
- .end = MODULES_END,
- .pgprot = PAGE_KERNEL,
- .alignment = MODULE_ALIGN,
- },
- },
- };
-
- return &execmem_info;
-}
-
#ifdef CONFIG_X86_32
int apply_relocate(Elf32_Shdr *sechdrs,
const char *strtab,
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 679893ea5e68..be4fee17b717 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
#include <linux/swapops.h>
#include <linux/kmemleak.h>
#include <linux/sched/task.h>
+#include <linux/execmem.h>
#include <asm/set_memory.h>
#include <asm/cpu_device_id.h>
@@ -1099,3 +1100,31 @@ unsigned long arch_max_swapfile_size(void)
return pages;
}
#endif
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long start, offset = 0;
+
+ if (kaslr_enabled())
+ offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + offset;
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
--
2.43.0
From: "Mike Rapoport (IBM)" <[email protected]>
Dynamic ftrace must allocate memory for code and this was impossible
without CONFIG_MODULES.
With execmem separated from the modules code, execmem_text_alloc() is
available regardless of CONFIG_MODULES.
Remove dependency of dynamic ftrace on CONFIG_MODULES and make
CONFIG_DYNAMIC_FTRACE select CONFIG_EXECMEM in Kconfig.
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
arch/x86/Kconfig | 1 +
arch/x86/kernel/ftrace.c | 10 ----------
2 files changed, 1 insertion(+), 10 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3f5ba72c9480..cd8addb96a0b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86_64
select SWIOTLB
select ARCH_HAS_ELFCORE_COMPAT
select ZONE_DMA32
+ select EXECMEM if DYNAMIC_FTRACE
config FORCE_DYNAMIC_FTRACE
def_bool y
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c8ddb7abda7c..8da0e66ca22d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -261,8 +261,6 @@ void arch_ftrace_update_code(int command)
/* Currently only x86_64 supports dynamic trampolines */
#ifdef CONFIG_X86_64
-#ifdef CONFIG_MODULES
-/* Module allocation simplifies allocating memory for code */
static inline void *alloc_tramp(unsigned long size)
{
return execmem_alloc(EXECMEM_FTRACE, size);
@@ -271,14 +269,6 @@ static inline void tramp_free(void *tramp)
{
execmem_free(tramp);
}
-#else
-/* Trampolines can only be created if modules are supported */
-static inline void *alloc_tramp(unsigned long size)
-{
- return NULL;
-}
-static inline void tramp_free(void *tramp) { }
-#endif
/* Defined as markers to the end of the ftrace default trampolines */
extern void ftrace_regs_caller_end(void);
--
2.43.0
From: "Mike Rapoport (IBM)" <[email protected]>
kprobes depended on CONFIG_MODULES because it has to allocate memory for
code.
Since code allocations are now implemented with execmem, kprobes can be
enabled in non-modular kernels.
Add #ifdef CONFIG_MODULE guards for the code dealing with kprobes inside
modules, make CONFIG_KPROBES select CONFIG_EXECMEM and drop the
dependency of CONFIG_KPROBES on CONFIG_MODULES.
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
arch/Kconfig | 2 +-
include/linux/module.h | 9 ++++++
kernel/kprobes.c | 55 +++++++++++++++++++++++--------------
kernel/trace/trace_kprobe.c | 20 +++++++++++++-
4 files changed, 63 insertions(+), 23 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 7006f71f0110..a48ce6a488b3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -52,9 +52,9 @@ config GENERIC_ENTRY
config KPROBES
bool "Kprobes"
- depends on MODULES
depends on HAVE_KPROBES
select KALLSYMS
+ select EXECMEM
select TASKS_RCU if PREEMPTION
help
Kprobes allows you to trap at almost any kernel address and
diff --git a/include/linux/module.h b/include/linux/module.h
index 1153b0d99a80..ffa1c603163c 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -605,6 +605,11 @@ static inline bool module_is_live(struct module *mod)
return mod->state != MODULE_STATE_GOING;
}
+static inline bool module_is_coming(struct module *mod)
+{
+ return mod->state == MODULE_STATE_COMING;
+}
+
struct module *__module_text_address(unsigned long addr);
struct module *__module_address(unsigned long addr);
bool is_module_address(unsigned long addr);
@@ -857,6 +862,10 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr)
return ptr;
}
+static inline bool module_is_coming(struct module *mod)
+{
+ return false;
+}
#endif /* CONFIG_MODULES */
#ifdef CONFIG_SYSFS
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ddd7cdc16edf..ca2c6cbd42d2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1588,7 +1588,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
}
/* Get module refcount and reject __init functions for loaded modules. */
- if (*probed_mod) {
+ if (IS_ENABLED(CONFIG_MODULES) && *probed_mod) {
/*
* We must hold a refcount of the probed module while updating
* its code to prohibit unexpected unloading.
@@ -1603,12 +1603,13 @@ static int check_kprobe_address_safe(struct kprobe *p,
* kprobes in there.
*/
if (within_module_init((unsigned long)p->addr, *probed_mod) &&
- (*probed_mod)->state != MODULE_STATE_COMING) {
+ !module_is_coming(*probed_mod)) {
module_put(*probed_mod);
*probed_mod = NULL;
ret = -ENOENT;
}
}
+
out:
preempt_enable();
jump_label_unlock();
@@ -2488,24 +2489,6 @@ int kprobe_add_area_blacklist(unsigned long start, unsigned long end)
return 0;
}
-/* Remove all symbols in given area from kprobe blacklist */
-static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
-{
- struct kprobe_blacklist_entry *ent, *n;
-
- list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
- if (ent->start_addr < start || ent->start_addr >= end)
- continue;
- list_del(&ent->list);
- kfree(ent);
- }
-}
-
-static void kprobe_remove_ksym_blacklist(unsigned long entry)
-{
- kprobe_remove_area_blacklist(entry, entry + 1);
-}
-
int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
char *type, char *sym)
{
@@ -2570,6 +2553,25 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
return ret ? : arch_populate_kprobe_blacklist();
}
+#ifdef CONFIG_MODULES
+/* Remove all symbols in given area from kprobe blacklist */
+static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end)
+{
+ struct kprobe_blacklist_entry *ent, *n;
+
+ list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) {
+ if (ent->start_addr < start || ent->start_addr >= end)
+ continue;
+ list_del(&ent->list);
+ kfree(ent);
+ }
+}
+
+static void kprobe_remove_ksym_blacklist(unsigned long entry)
+{
+ kprobe_remove_area_blacklist(entry, entry + 1);
+}
+
static void add_module_kprobe_blacklist(struct module *mod)
{
unsigned long start, end;
@@ -2672,6 +2674,17 @@ static struct notifier_block kprobe_module_nb = {
.priority = 0
};
+static int kprobe_register_module_notifier(void)
+{
+ return register_module_notifier(&kprobe_module_nb);
+}
+#else
+static int kprobe_register_module_notifier(void)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
void kprobe_free_init_mem(void)
{
void *start = (void *)(&__init_begin);
@@ -2731,7 +2744,7 @@ static int __init init_kprobes(void)
if (!err)
err = register_die_notifier(&kprobe_exceptions_nb);
if (!err)
- err = register_module_notifier(&kprobe_module_nb);
+ err = kprobe_register_module_notifier();
kprobes_initialized = (err == 0);
kprobe_sysctls_init();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 14099cc17fc9..2cb2a3951b4f 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -111,6 +111,7 @@ static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
return strncmp(module_name(mod), name, len) == 0 && name[len] == ':';
}
+#ifdef CONFIG_MODULES
static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
{
char *p;
@@ -129,6 +130,12 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
return ret;
}
+#else
+static inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
+{
+ return false;
+}
+#endif
static bool trace_kprobe_is_busy(struct dyn_event *ev)
{
@@ -670,6 +677,7 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
return ret;
}
+#ifdef CONFIG_MODULES
/* Module notifier call back, checking event on the module */
static int trace_kprobe_module_callback(struct notifier_block *nb,
unsigned long val, void *data)
@@ -704,6 +712,16 @@ static struct notifier_block trace_kprobe_module_nb = {
.notifier_call = trace_kprobe_module_callback,
.priority = 1 /* Invoked after kprobe module callback */
};
+static int trace_kprobe_register_module_notifier(void)
+{
+ return register_module_notifier(&trace_kprobe_module_nb);
+}
+#else
+static int trace_kprobe_register_module_notifier(void)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
static int count_symbols(void *data, unsigned long unused)
{
@@ -1933,7 +1951,7 @@ static __init int init_kprobe_trace_early(void)
if (ret)
return ret;
- if (register_module_notifier(&trace_kprobe_module_nb))
+ if (trace_kprobe_register_module_notifier())
return -EINVAL;
return 0;
--
2.43.0
From: "Mike Rapoport (IBM)" <[email protected]>
BPF just-in-time compiler depended on CONFIG_MODULES because it used
module_alloc() to allocate memory for the generated code.
Since code allocations are now implemented with execmem, drop dependency of
CONFIG_BPF_JIT on CONFIG_MODULES and make it select CONFIG_EXECMEM.
Suggested-by: Björn Töpel <[email protected]>
Signed-off-by: Mike Rapoport (IBM) <[email protected]>
---
kernel/bpf/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig
index bc25f5098a25..f999e4e0b344 100644
--- a/kernel/bpf/Kconfig
+++ b/kernel/bpf/Kconfig
@@ -43,7 +43,7 @@ config BPF_JIT
bool "Enable BPF Just In Time compiler"
depends on BPF
depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT
- depends on MODULES
+ select EXECMEM
help
BPF programs are normally handled by a BPF interpreter. This option
allows the kernel to generate native code when a program is loaded
--
2.43.0