@@ -86,7 +86,7 @@
* x20 primary_entry() .. __primary_switch() CPU boot mode
* x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0
* x23 __primary_switch() .. relocate_kernel() physical misalignment/KASLR offset
- * x28 create_idmap() callee preserved temp register
+ * x28 create_idmap(), remap_kernel_text() callee preserved temp register
*/
SYM_CODE_START(primary_entry)
bl preserve_boot_args
@@ -372,10 +372,62 @@ SYM_FUNC_START_LOCAL(create_kernel_mapping)
mov x7, SWAPPER_RW_MMUFLAGS
map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14
-
ret
SYM_FUNC_END(create_kernel_mapping)
+SYM_FUNC_START_LOCAL(remap_kernel_text)
+ mov x28, lr
+
+ ldr x1, =_text
+ mov x2, x1
+ ldr x3, =__initdata_begin - 1
+ adrp x4, _text
+ bic x4, x4, #SWAPPER_BLOCK_SIZE - 1
+ mov x5, SWAPPER_RX_MMUFLAGS
+ mov x6, #SWAPPER_BLOCK_SHIFT
+ bl remap_region
+
+#if SWAPPER_BLOCK_SHIFT > PAGE_SHIFT
+ /*
+ * If the boundary between inittext and initdata happens to be aligned
+ * sufficiently, we are done here. Otherwise, we have to replace its block
+ * entry with a table entry, and populate the lower level table accordingly.
+ */
+ ldr x3, =__initdata_begin
+ tst x3, #SWAPPER_BLOCK_SIZE - 1
+ b.eq 0f
+
+ /* First, create a table mapping to replace the block mapping */
+ ldr x1, =_text
+ bic x2, x3, #SWAPPER_BLOCK_SIZE - 1
+ adrp x4, init_pg_end - PAGE_SIZE
+ mov x5, #PMD_TYPE_TABLE
+ mov x6, #SWAPPER_BLOCK_SHIFT
+ bl remap_region
+
+ /* Apply executable permissions to the first subregion */
+ adrp x0, init_pg_end - PAGE_SIZE
+ ldr x3, =__initdata_begin - 1
+ bic x1, x3, #SWAPPER_BLOCK_SIZE - 1
+ mov x2, x1
+ adrp x4, __initdata_begin
+ bic x4, x4, #SWAPPER_BLOCK_SIZE - 1
+ mov x5, SWAPPER_RX_MMUFLAGS | PTE_TYPE_PAGE
+ mov x6, #PAGE_SHIFT
+ bl remap_region
+
+ /* Apply writable permissions to the second subregion */
+ ldr x2, =__initdata_begin
+ bic x1, x2, #SWAPPER_BLOCK_SIZE - 1
+ orr x3, x1, #SWAPPER_BLOCK_SIZE - 1
+ adrp x4, __initdata_begin
+ mov x5, SWAPPER_RW_MMUFLAGS | PTE_TYPE_PAGE
+ mov x6, #PAGE_SHIFT
+ bl remap_region
+#endif
+0: ret x28
+SYM_FUNC_END(remap_kernel_text)
+
/*
* Initialize CPU registers with task-specific and cpu-specific context.
*
@@ -805,12 +857,25 @@ SYM_FUNC_START_LOCAL(__primary_switch)
#endif
bl clear_page_tables
bl create_kernel_mapping
+#ifdef CONFIG_RELOCATABLE
+ mov x29, x0 // preserve returned page table pointer
adrp x1, init_pg_dir
load_ttbr1 x1, x2
-#ifdef CONFIG_RELOCATABLE
bl __relocate_kernel
+ adrp x1, reserved_pg_dir
+ load_ttbr1 x1, x2
+
+ tlbi vmalle1
+ dsb nsh
+ isb
+
+ mov x0, x29 // pass page table pointer to remap_kernel_text
#endif
+ bl remap_kernel_text
+ adrp x1, init_pg_dir
+ load_ttbr1 x1, x2
+
ldr x8, =__primary_switched
adrp x0, __PHYS_OFFSET
br x8
@@ -298,7 +298,7 @@ SECTIONS
. = ALIGN(PAGE_SIZE);
init_pg_dir = .;
- . += INIT_DIR_SIZE;
+ . += INIT_DIR_SIZE + PAGE_SIZE;
init_pg_end = .;
. = ALIGN(SEGMENT_ALIGN);
In order to be able to run with WXN from boot (which could potentially be under a hypervisor regime that mandates this), update the temporary kernel page tables with read-only attributes for the text regions before attempting to execute from them. This is rather straight-forward for 16k and 64k granule configurations, as the split between executable and writable regions is guaranteed to be aligned to the granule used for the early kernel page tables. For 4k, it involves installing a single table entry and populating it accordingly. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> --- arch/arm64/kernel/head.S | 71 +++++++++++++++++++- arch/arm64/kernel/vmlinux.lds.S | 2 +- 2 files changed, 69 insertions(+), 4 deletions(-)