arm64: efi: leave MMU and caches on at boot
Ard Biesheuvel
maintainerv5 cover arm64: efi: leave MMU and caches on at boot
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
Changes since v4:
- add patch to align the callers of finalise_el2()
- also clean HYP text to the PoC when booting at EL2 with the MMU on
- add a warning and a taint when doing non-EFI boot with the MMU and caches enabled
- rebase onto zboot changes in efi/next - this means that patches #6 and #7 will not apply onto arm64/for-next so a shared stable branch will be needed if we want to queue this up for v6.2
Changes since v3:
- drop EFI_LOADER_CODE memory type patch that has been queued in the mean time
- rebased onto [partial] series that moves efi-entry.S into the libstub/ source directory
- fixed a correctness issue in patch #2
Ard Biesheuvel (7):
arm64: head: Move all finalise_el2 calls to after __enable_mmu
arm64: kernel: move identity map out of .text mapping
arm64: head: record the MMU state at primary entry
arm64: head: avoid cache invalidation when entering with the MMU on
arm64: head: Clean the ID map and the HYP text to the PoC if needed
arm64: lds: reduce effective minimum image alignment to 64k
efi: arm64: enter with MMU and caches enabled
arch/arm64/include/asm/efi.h | 9 +- arch/arm64/kernel/head.S | 93 +++++++++++++++----- arch/arm64/kernel/image-vars.h | 5 +- arch/arm64/kernel/setup.c | 9 +- arch/arm64/kernel/sleep.S | 6 +- arch/arm64/kernel/vmlinux.lds.S | 13 ++- arch/arm64/mm/cache.S | 5 +- arch/arm64/mm/proc.S | 2 - drivers/firmware/efi/libstub/Makefile | 4 +- drivers/firmware/efi/libstub/arm64-entry.S | 67 -------------- drivers/firmware/efi/libstub/arm64-stub.c | 26 ++++-- drivers/firmware/efi/libstub/arm64.c | 41 +++++++-- include/linux/efi.h | 6 +- 13 files changed, 159 insertions(+), 127 deletions(-) delete mode 100644 drivers/firmware/efi/libstub/arm64-entry.S
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 2/7 arm64: kernel: move identity map out of .text mapping
Reorganize the ID map slightly so that only code that is executed with the MMU off or via the 1:1 mapping remains. This allows us to move the identity map out of the .text segment, as it will no longer need executable permissions via the kernel mapping.
--- arch/arm64/kernel/head.S | 28 +++++++++++--------- arch/arm64/kernel/vmlinux.lds.S | 2 +- arch/arm64/mm/proc.S | 2 -- 3 files changed, 16 insertions(+), 16 deletions(-)
arch/arm64/kernel/head.S +15 -13
@@ -540,19 +540,6 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) eret SYM_FUNC_END(init_kernel_el) -/* - * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed - * in w0. See arch/arm64/include/asm/virt.h for more info. - */ -SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) - adr_l x1, __boot_cpu_mode - cmp w0, #BOOT_CPU_MODE_EL2 - b.ne 1f - add x1, x1, #4 -1: str w0, [x1] // Save CPU boot mode - ret -SYM_FUNC_END(set_cpu_boot_mode_flag) - /* * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise.
@@ -596,6 +583,7 @@ SYM_FUNC_START_LOCAL(secondary_startup) br x8 SYM_FUNC_END(secondary_startup) + .text SYM_FUNC_START_LOCAL(__secondary_switched) mov x0, x20 bl set_cpu_boot_mode_flag
@@ -628,6 +616,19 @@ SYM_FUNC_START_LOCAL(__secondary_too_slow) b __secondary_too_slow SYM_FUNC_END(__secondary_too_slow) +/* + * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed + * in w0. See arch/arm64/include/asm/virt.h for more info. + */ +SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) + adr_l x1, __boot_cpu_mode + cmp w0, #BOOT_CPU_MODE_EL2 + b.ne 1f + add x1, x1, #4 +1: str w0, [x1] // Save CPU boot mode + ret +SYM_FUNC_END(set_cpu_boot_mode_flag) + /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off.
@@ -659,6 +660,7 @@ SYM_FUNC_END(__secondary_too_slow) * Checks if the selected granule size is supported by the CPU. * If it isn't, park the CPU */ + .section ".idmap.text","awx" SYM_FUNC_START(__enable_mmu) mrs x3, ID_AA64MMFR0_EL1 ubfx x3, x3, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4
arch/arm64/kernel/vmlinux.lds.S +1 -1
@@ -168,7 +168,6 @@ SECTIONS LOCK_TEXT KPROBES_TEXT HYPERVISOR_TEXT - IDMAP_TEXT *(.gnu.warning) . = ALIGN(16); *(.got) /* Global offset table */
@@ -195,6 +194,7 @@ SECTIONS TRAMP_TEXT HIBERNATE_TEXT KEXEC_TEXT + IDMAP_TEXT . = ALIGN(PAGE_SIZE); }
arch/arm64/mm/proc.S +0 -2
@@ -110,7 +110,6 @@ SYM_FUNC_END(cpu_do_suspend) * * x0: Address of context pointer */ - .pushsection ".idmap.text", "awx" SYM_FUNC_START(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16]
@@ -166,7 +165,6 @@ alternative_else_nop_endif isb ret SYM_FUNC_END(cpu_do_resume) - .popsection #endif .pushsection ".idmap.text", "awx"
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 3/7 arm64: head: record the MMU state at primary entry
In reply to Ard BiesheuvelPrepare for being able to deal with primary entry with the MMU and caches enabled, by recording whether or not we entered with the MMU on in register x19 and in a global variable. (Note that setting this variable to '1' does not require cache invalidation, nor is it required for storing the bootargs in that case, so omit the cache maintenance).
Since boot with the MMU enabled is not permitted by the bare metal boot protocol, ensure that a diagnostic is emitted and a taint bit set if the MMU was found to be enabled on a non-EFI boot. We will make an exception for EFI boot later, which has strict requirements for the mapping of system memory, permitting us to relax the boot protocol and hand over from the EFI stub to the core kernel with MMU and caches left enabled.
While at it, add 'pre_disable_mmu_workaround' macro invocations to init_kernel_el, as its manipulation of SCTLR_ELx may amount to disabling of the MMU after subsequent patches.
--- arch/arm64/kernel/head.S | 21 ++++++++++++++++++++ arch/arm64/kernel/setup.c | 9 +++++++-- 2 files changed, 28 insertions(+), 2 deletions(-)
arch/arm64/kernel/head.S +21 -0
@@ -77,6 +77,7 @@ * primary lowlevel boot path: * * Register Scope Purpose + * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 * x22 create_idmap() .. start_kernel() ID map VA of the DT blob
@@ -86,6 +87,7 @@ * x28 create_idmap() callee preserved temp register */ SYM_CODE_START(primary_entry) + bl record_mmu_state bl preserve_boot_args bl init_kernel_el // w0=cpu_boot_mode mov x20, x0
@@ -109,6 +111,19 @@ SYM_CODE_START(primary_entry) b __primary_switch SYM_CODE_END(primary_entry) +SYM_CODE_START_LOCAL(record_mmu_state) + mrs x19, CurrentEL + cmp x19, #CurrentEL_EL2 + mrs x19, sctlr_el1 + b.ne 0f + mrs x19, sctlr_el2 +0: tst x19, #SCTLR_ELx_C // Z := (C == 0) + and x19, x19, #SCTLR_ELx_M // isolate M bit + ccmp x19, xzr, #4, ne // Z |= (M == 0) + cset x19, ne // set x19 if !Z + ret +SYM_CODE_END(record_mmu_state) + /* * Preserve the arguments passed by the bootloader in x0 .. x3 */
@@ -119,11 +134,14 @@ SYM_CODE_START_LOCAL(preserve_boot_args) stp x21, x1, [x0] // x0 .. x3 at kernel entry stp x2, x3, [x0, #16] + cbnz x19, 0f // skip cache invalidation if MMU is on dmb sy // needed before dc ivac with // MMU off add x1, x0, #0x20 // 4 x 8 bytes b dcache_inval_poc // tail call +0: str_l x19, mmu_enabled_at_boot, x0 + ret SYM_CODE_END(preserve_boot_args) SYM_FUNC_START_LOCAL(clear_page_tables)
@@ -494,6 +512,7 @@ SYM_FUNC_START(init_kernel_el) SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) mov_q x0, INIT_SCTLR_EL1_MMU_OFF + pre_disable_mmu_workaround msr sctlr_el1, x0 isb mov_q x0, INIT_PSTATE_EL1
@@ -526,11 +545,13 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) cbz x0, 1f /* Set a sane SCTLR_EL1, the VHE way */ + pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 mov x2, #BOOT_CPU_FLAG_E2H b 2f 1: + pre_disable_mmu_workaround msr sctlr_el1, x1 mov x2, xzr 2:
arch/arm64/kernel/setup.c +7 -2
@@ -56,6 +56,7 @@ static int num_standard_resources;static struct resource *standard_resources;phys_addr_t __fdt_pointer__initdata ; +u64 mmu_enabled_at_boot__initdata ;/* * Standard memory resources
@@ -328,8 +329,12 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)xen_early_init ();efi_init (); -if (!efi_enabled (EFI_BOOT ) && ((u64 )_text %MIN_KIMG_ALIGN ) !=0 ) -pr_warn (FW_BUG "Kernel image misaligned at boot, please fix your bootloader!" ); +if (!efi_enabled (EFI_BOOT )) { +if ((u64 )_text %MIN_KIMG_ALIGN ) +pr_warn (FW_BUG "Kernel image misaligned at boot, please fix your bootloader!" ); +WARN_TAINT (mmu_enabled_at_boot,TAINT_FIRMWARE_WORKAROUND , +FW_BUG "Booted with MMU enabled!" ); + }arm64_memblock_init ();
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 4/7 arm64: head: avoid cache invalidation when entering with the MMU on
In reply to Ard BiesheuvelIf we enter with the MMU on, there is no need for explicit cache invalidation for stores to memory, as they will be coherent with the caches.
Let's take advantage of this, and create the ID map with the MMU still enabled if that is how we entered, and avoid any cache invalidation calls in that case.
--- arch/arm64/kernel/head.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
arch/arm64/kernel/head.S +3 -2
@@ -89,9 +89,9 @@ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args + bl create_idmap bl init_kernel_el // w0=cpu_boot_mode mov x20, x0 - bl create_idmap /* * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -378,12 +378,13 @@ SYM_FUNC_START_LOCAL(create_idmap) * accesses (MMU disabled), invalidate those tables again to * remove any speculatively loaded cache lines. */ + cbnz x19, 0f // skip cache invalidation if MMU is on dmb sy adrp x0, init_idmap_pg_dir adrp x1, init_idmap_pg_end bl dcache_inval_poc - ret x28 +0: ret x28 SYM_FUNC_END(create_idmap) SYM_FUNC_START_LOCAL(create_kernel_mapping)
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 5/7 arm64: head: Clean the ID map and the HYP text to the PoC if needed
In reply to Ard BiesheuvelIf we enter with the MMU and caches enabled, the bootloader may not have performed any cache maintenance to the PoC. So clean the ID mapped page to the PoC, to ensure that instruction and data accesses with the MMU off see the correct data. For similar reasons, clean all the HYP text to the PoC as well when entering at EL2 with the MMU and caches enabled.
Note that this means primary_entry() itself needs to be moved into the ID map as well, as we will return from init_kernel_el() with the MMU and caches off.
--- arch/arm64/kernel/head.S | 31 +++++++++++++++++--- arch/arm64/kernel/sleep.S | 1 + 2 files changed, 28 insertions(+), 4 deletions(-)
arch/arm64/kernel/head.S +27 -4
@@ -70,7 +70,7 @@ __EFI_PE_HEADER - __INIT + .section ".idmap.text","awx" /* * The following callee saved general purpose registers are used on the
@@ -90,6 +90,17 @@ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args bl create_idmap + + /* + * If we entered with the MMU and caches on, clean the ID mapped part + * of the primary boot code to the PoC so we can safely execute it with + * the MMU off. + */ + cbz x19, 0f + adrp x0, __idmap_text_start + adr_l x1, __idmap_text_end + bl dcache_clean_poc +0: mov x19, x0 bl init_kernel_el // w0=cpu_boot_mode mov x20, x0
@@ -111,6 +122,7 @@ SYM_CODE_START(primary_entry) b __primary_switch SYM_CODE_END(primary_entry) + __INIT SYM_CODE_START_LOCAL(record_mmu_state) mrs x19, CurrentEL cmp x19, #CurrentEL_EL2
@@ -505,10 +517,12 @@ SYM_FUNC_END(__primary_switched) * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x0 if * booted in EL1 or EL2 respectively, with the top 32 bits containing * potential context flags. These flags are *not* stored in __boot_cpu_mode. + * + * x0: whether we are being called from the primary boot path with the MMU on */ SYM_FUNC_START(init_kernel_el) - mrs x0, CurrentEL - cmp x0, #CurrentEL_EL2 + mrs x1, CurrentEL + cmp x1, #CurrentEL_EL2 b.eq init_el2 SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
@@ -523,6 +537,14 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) eret SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) + msr elr_el2, lr + + // clean all HYP code to the PoC if we booted at EL2 with the MMU on + cbz x0, 0f + adrp x0, __hyp_idmap_text_start + adr_l x1, __hyp_text_end + bl dcache_clean_poc +0: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0 isb
@@ -556,7 +578,6 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) msr sctlr_el1, x1 mov x2, xzr 2: - msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 orr x0, x0, x2 eret
@@ -567,6 +588,7 @@ SYM_FUNC_END(init_kernel_el) * cores are held until we're ready for them to initialise. */ SYM_FUNC_START(secondary_holding_pen) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode mrs x2, mpidr_el1 mov_q x1, MPIDR_HWID_BITMASK
@@ -584,6 +606,7 @@ SYM_FUNC_END(secondary_holding_pen) * be used where CPUs are brought online dynamically by the kernel. */ SYM_FUNC_START(secondary_entry) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode b secondary_startup SYM_FUNC_END(secondary_entry)
arch/arm64/kernel/sleep.S +1 -0
@@ -99,6 +99,7 @@ SYM_FUNC_END(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" SYM_CODE_START(cpu_resume) + mov x0, xzr bl init_kernel_el mov x19, x0 // preserve boot mode #if VA_BITS > 48
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 1/7 arm64: head: Move all finalise_el2 calls to after __enable_mmu
In reply to Ard BiesheuvelIn the primary boot path, finalise_el2() is called much later than on the secondary boot or resume-from-suspend paths, and this does not appear to be intentional.
Since we aim to do as little as possible before enabling the MMU and caches, align secondary and resume with primary boot, and defer the call to after the MMU is turned on. This also removes the need to clean finalise_el2() to the PoC once we enable support for booting with the MMU on.
--- arch/arm64/kernel/head.S | 5 ++++- arch/arm64/kernel/sleep.S | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-)
arch/arm64/kernel/head.S +4 -1
@@ -584,7 +584,6 @@ SYM_FUNC_START_LOCAL(secondary_startup) * Common entry point for secondary CPUs. */ mov x20, x0 // preserve boot mode - bl finalise_el2 bl __cpu_secondary_check52bitva #if VA_BITS > 48 ldr_l x0, vabits_actual
@@ -600,6 +599,10 @@ SYM_FUNC_END(secondary_startup) SYM_FUNC_START_LOCAL(__secondary_switched) mov x0, x20 bl set_cpu_boot_mode_flag + + mov x0, x20 + bl finalise_el2 + str_l xzr, __early_cpu_boot_status, x3 adr_l x5, vectors msr vbar_el1, x5
arch/arm64/kernel/sleep.S +4 -1
@@ -100,7 +100,7 @@ SYM_FUNC_END(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" SYM_CODE_START(cpu_resume) bl init_kernel_el - bl finalise_el2 + mov x19, x0 // preserve boot mode #if VA_BITS > 48 ldr_l x0, vabits_actual #endif
@@ -116,6 +116,9 @@ SYM_CODE_END(cpu_resume) .popsection SYM_FUNC_START(_cpu_resume) + mov x0, x19 + bl finalise_el2 + mrs x1, mpidr_el1 adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 6/7 arm64: lds: reduce effective minimum image alignment to 64k
In reply to Ard BiesheuvelOur segment alignment is 64k for all configurations, and coincidentally, this is the largest alignment supported by the PE/COFF executable format used by EFI. This means that generally, there is no need to move the image around in memory after it has been loaded by the firmware, which can be advantageous as it also permits us to rely on the memory attributes set by the firmware (R-X for [_text, __inittext_end] and RW- for [__initdata_begin, _end].
However, the minimum alignment of the image is actually 128k on 64k pages configurations with CONFIG_VMAP_STACK=y, due to the existence of a single 128k aligned object in the image, which is the stack of the init task.
Let's work around this by adding some padding before the init stack allocation, so we can round down the stack pointer to a suitably aligned value if the image is not aligned to 128k in memory.
Note that this does not affect the boot protocol, which still requires 2 MiB alignment for bare metal boot, but is only part of the internal contract between the EFI stub and the kernel proper.
--- arch/arm64/include/asm/efi.h | 9 +-------- arch/arm64/kernel/head.S | 3 +++ arch/arm64/kernel/vmlinux.lds.S | 11 ++++++++++- include/linux/efi.h | 6 +----- 4 files changed, 15 insertions(+), 14 deletions(-)
arch/arm64/include/asm/efi.h +1 -8
@@ -54,13 +54,6 @@ efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);/* arch specific definitions used by the stub code */ -/* -* In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the -* kernel need greater alignment than we require the segments to be padded to. -*/ -#define EFI_KIMG_ALIGN \ - (SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : THREAD_ALIGN) -/* * On arm64, we have to ensure that the initrd ends up in the linear region, * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is
@@ -88,7 +81,7 @@ static inline unsigned long efi_get_kimg_min_align(void)* 2M alignment if KASLR was explicitly disabled, even if it was not * going to be activated to begin with. */ -return efi_nokaslr ?MIN_KIMG_ALIGN :EFI_KIMG_ALIGN ; +return efi_nokaslr ?MIN_KIMG_ALIGN :SEGMENT_ALIGN ; }#define EFI_ALLOC_ALIGN SZ_64K
arch/arm64/kernel/head.S +3 -0
@@ -429,6 +429,9 @@ SYM_FUNC_END(create_kernel_mapping) msr sp_el0, \tsk ldr \tmp1, [\tsk, #TSK_STACK] +#if THREAD_ALIGN > SEGMENT_ALIGN + bic \tmp1, \tmp1, #THREAD_ALIGN - 1 +#endif add sp, \tmp1, #THREAD_SIZE sub sp, sp, #PT_REGS_SIZE
arch/arm64/kernel/vmlinux.lds.S +10 -1
@@ -274,7 +274,16 @@ SECTIONS _data = .; _sdata = .; - RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) +#if THREAD_ALIGN > SEGMENT_ALIGN + /* + * Add some padding for the init stack so we can fix up any potential + * misalignment at runtime. In practice, this can only occur on 64k + * pages configurations with CONFIG_VMAP_STACK=y. + */ + . += THREAD_ALIGN - SEGMENT_ALIGN; + ASSERT(. == init_stack, "init_stack not at start of RW_DATA as expected") +#endif + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, SEGMENT_ALIGN) /* * Data written with the MMU off but read with the MMU on requires
include/linux/efi.h +1 -5
@@ -421,11 +421,7 @@ void efi_native_runtime_setup(void);/* * This GUID may be installed onto the kernel image's handle as a NULL protocol * to signal to the stub that the placement of the image should be respected, -* and moving the image in physical memory is undesirable. To ensure -* compatibility with 64k pages kernels with virtually mapped stacks, and to -* avoid defeating physical randomization, this protocol should only be -* installed if the image was placed at a randomized 128k aligned address in -* memory. +* and moving the image in physical memory is undesirable. */ #define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a)
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerPATCH v5 7/7 efi: arm64: enter with MMU and caches enabled
In reply to Ard BiesheuvelInstead of cleaning the entire loaded kernel image to the PoC and disabling the MMU and caches before branching to the kernel's bare metal entry point, we can leave the MMU and caches enabled, and rely on EFI's cacheable 1:1 mapping of all of system RAM (which is mandated by the spec) to populate the initial page tables.
This removes the need for managing coherency in software, which is tedious and error prone.
Note that we still need to clean the executable region of the image to the PoU if this is required for I/D coherency, but only if we actually decided to move the image in memory, as otherwise, this will have been taken care of by the loader.
This change affects both the builtin EFI stub as well as the zboot decompressor, which now carries the entire EFI stub along with the decompression code and the compressed image.
--- arch/arm64/kernel/image-vars.h | 5 +- arch/arm64/mm/cache.S | 5 +- drivers/firmware/efi/libstub/Makefile | 4 +- drivers/firmware/efi/libstub/arm64-entry.S | 67 -------------------- drivers/firmware/efi/libstub/arm64-stub.c | 26 +++++--- drivers/firmware/efi/libstub/arm64.c | 41 ++++++++++-- 6 files changed, 61 insertions(+), 87 deletions(-)
arch/arm64/kernel/image-vars.h +3 -2
@@ -10,7 +10,7 @@#error This file should only be included in vmlinux.lds.S#endif -PROVIDE (__efistub_primary_entry_offset = primary_entry - _text); +PROVIDE (__efistub_primary_entry = primary_entry);/* * The EFI stub has its own symbol namespace prefixed by __efistub_, to
@@ -21,10 +21,11 @@ PROVIDE(__efistub_primary_entry_offset = primary_entry - _text);* linked at. The routines below are all implemented in assembler in a * position independent manner */ -PROVIDE (__efistub_dcache_clean_poc = __pi_dcache_clean_poc); +PROVIDE (__efistub_caches_clean_inval_pou = __pi_caches_clean_inval_pou);PROVIDE (__efistub__text = _text);PROVIDE (__efistub__end = _end); +PROVIDE (__efistub___inittext_end = __inittext_end);PROVIDE (__efistub__edata = _edata);PROVIDE (__efistub_screen_info = screen_info);PROVIDE (__efistub__ctype = _ctype);
arch/arm64/mm/cache.S +3 -2
@@ -52,10 +52,11 @@ alternative_else_nop_endif * - start - virtual start address of region * - end - virtual end address of region */ -SYM_FUNC_START(caches_clean_inval_pou) +SYM_FUNC_START(__pi_caches_clean_inval_pou) caches_clean_inval_pou_macro ret -SYM_FUNC_END(caches_clean_inval_pou) +SYM_FUNC_END(__pi_caches_clean_inval_pou) +SYM_FUNC_ALIAS(caches_clean_inval_pou, __pi_caches_clean_inval_pou) /* * caches_clean_inval_user_pou(start,end)
drivers/firmware/efi/libstub/Makefile +2 -2
@@ -86,7 +86,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o \ screen_info.o efi-stub-entry.o lib-$(CONFIG_ARM) += arm32-stub.o -lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o arm64-entry.o +lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o lib-$(CONFIG_X86) += x86-stub.o lib-$(CONFIG_RISCV) += riscv.o riscv-stub.o lib-$(CONFIG_LOONGARCH) += loongarch.o loongarch-stub.o
@@ -140,7 +140,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS # STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \ --prefix-symbols=__efistub_ -STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS64 +STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS # For RISC-V, we don't need anything special other than arm64. Keep all the # symbols in .init section and make sure that no absolute symbols references
drivers/firmware/efi/libstub/arm64-entry.S deleted +0 -67
67 lines not on this page · raw message
drivers/firmware/efi/libstub/arm64-stub.c +17 -9
@@ -58,7 +58,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, efi_handle_t image_handle) {efi_status_t status; -unsigned long kernel_size, kernel_memsize =0 ; +unsigned long kernel_size, kernel_codesize, kernel_memsize;u32 phys_seed =0 ;u64 min_kimg_align =efi_get_kimg_min_align ();
@@ -93,6 +93,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, SEGMENT_ALIGN >> 10); kernel_size = _edata - _text; + kernel_codesize = __inittext_end - _text; kernel_memsize = kernel_size + (_end - _edata); *reserve_size = kernel_memsize;
@@ -120,7 +121,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,*/ *image_addr = (u64 )_text; *reserve_size =0 ; - goto clean_image_to_poc; +return EFI_SUCCESS ; } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
@@ -136,14 +137,21 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, *image_addr = *reserve_addr;memcpy ((void *)*image_addr, _text, kernel_size); +caches_clean_inval_pou (*image_addr, *image_addr + kernel_codesize); -clean_image_to_poc: +return EFI_SUCCESS ; +} + +asmlinkage void primary_entry(void); + +unsigned long primary_entry_offset (void ) +{/* -* Clean the copied Image to the PoC, and ensure it is not shadowed by -* stale icache entries from before relocation. +* When built as part of the kernel, the EFI stub cannot branch to the +* kernel proper via the image header, as the PE/COFF header is +* strictly not part of the in-memory presentation of the image, only +* of the file representation. So instead, we need to jump to the +* actual entrypoint in the .text region of the image. */ -dcache_clean_poc (*image_addr, *image_addr + kernel_size); - asm("ic ialluis" ); - -return EFI_SUCCESS ; +return (char *)primary_entry - _text; }
drivers/firmware/efi/libstub/arm64.c +36 -5
55 lines not on this page · raw message
Signature · 1 line
2.35.1
Ard Biesheuvel
maintainerRe: [PATCH v5 5/7] arm64: head: Clean the ID map and the HYP text to the PoC if needed
In reply to Ard BiesheuvelQuoted 35 lines · Ard Biesheuvel
If we enter with the MMU and caches enabled, the bootloader may not have performed any cache maintenance to the PoC. So clean the ID mapped page to the PoC, to ensure that instruction and data accesses with the MMU off see the correct data. For similar reasons, clean all the HYP text to the PoC as well when entering at EL2 with the MMU and caches enabled.
Note that this means
primary_entry()itself needs to be moved into the ID map as well, as we will return frominit_kernel_el()with the MMU and caches off.Signed-off-by Ard Biesheuvel <[email protected]>--- arch/arm64/kernel/head.S | 31 +++++++++++++++++--- arch/arm64/kernel/sleep.S | 1 + 2 files changed, 28 insertions(+), 4 deletions(-)arch/arm64/kernel/head.S +2
-1@@ -70,7 +70,7 @@ __EFI_PE_HEADER - __INIT + .section ".idmap.text","awx" /* * The following callee saved general purpose registers are used on the@@ -90,6 +90,17 @@ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args bl create_idmap +
arch/arm64/kernel/head.S SYM_CODE_START(primary_entry) · line 103
Quoted 10 lines
arch/arm64/kernel/head.S +10
-0+ /* + * If we entered with the MMU and caches on, clean the ID mapped part + * of the primary boot code to the PoC so we can safely execute it with + * the MMU off. + */ + cbz x19, 0f + adrp x0, __idmap_text_start + adr_l x1, __idmap_text_end + bl dcache_clean_poc +0: mov x19, x0
This is wrong, it should be
mov x0, x19
Quoted 80 lines
arch/arm64/kernel/head.S +15
-3bl init_kernel_el // w0=cpu_boot_mode mov x20, x0@@ -111,6 +122,7 @@ SYM_CODE_START(primary_entry) b __primary_switch SYM_CODE_END(primary_entry) + __INIT SYM_CODE_START_LOCAL(record_mmu_state) mrs x19, CurrentEL cmp x19, #CurrentEL_EL2@@ -505,10 +517,12 @@ SYM_FUNC_END(__primary_switched) * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x0 if * booted in EL1 or EL2 respectively, with the top 32 bits containing * potential context flags. These flags are *not* stored in __boot_cpu_mode. + * + * x0: whether we are being called from the primary boot path with the MMU on */ SYM_FUNC_START(init_kernel_el) - mrs x0, CurrentEL - cmp x0, #CurrentEL_EL2 + mrs x1, CurrentEL + cmp x1, #CurrentEL_EL2 b.eq init_el2 SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)@@ -523,6 +537,14 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) eret SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) + msr elr_el2, lr + + // clean all HYP code to the PoC if we booted at EL2 with the MMU on + cbz x0, 0f + adrp x0, __hyp_idmap_text_start + adr_l x1, __hyp_text_end + bl dcache_clean_poc +0: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0 isb@@ -556,7 +578,6 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) msr sctlr_el1, x1 mov x2, xzr 2: - msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 orr x0, x0, x2 eret@@ -567,6 +588,7 @@ SYM_FUNC_END(init_kernel_el) * cores are held until we're ready for them to initialise. */ SYM_FUNC_START(secondary_holding_pen) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode mrs x2, mpidr_el1 mov_q x1, MPIDR_HWID_BITMASK@@ -584,6 +606,7 @@ SYM_FUNC_END(secondary_holding_pen) * be used where CPUs are brought online dynamically by the kernel. */ SYM_FUNC_START(secondary_entry) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode b secondary_startup SYM_FUNC_END(secondary_entry)arch/arm64/kernel/sleep.S +1
-1@@ -99,6 +99,7 @@ SYM_FUNC_END(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" SYM_CODE_START(cpu_resume) + mov x0, xzr bl init_kernel_el mov x19, x0 // preserve boot mode #if VA_BITS > 48 --2.35.1
Mark Rutland
reviewerHi Ard,
Sorry for the late-in-the-day reply here...
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to head.S), and adds more scope for error, even if it simplifies the EFI stub itself.
I reckon that (sticking with entering with the MMU off), there's more that we can do to split the table creation into more stages, and to minimize the early portion of that which has to run with the MMU off. That would benefit non-EFI boot and kexec, and retain the single-boot-flow that we currently have.
My rough thinking was:
1) Reduce the idmap down to a single page, such that we only need to clear NR_PAGETABLE_LEVELS pages to initialize this.
2) Create a small stub at a fixed TTBR1 VA which we use to create a new initial mapping of the kernel image (either in TTBR0 as with the currently idmap, or in TTBR1 directly). The stub logic could be small enough that it could be mapped at page granularity, and we'd only need to initialize NR_PAGETABLE_LEVELS pages before enabling the MMU.
This would then bounce onto the next stage, either in TTBR0 directly, or bouncing through there as with the TTBR1 replacement logic.
We could plausibly write that in C, and the early page table asm logic could be simplified.
Thanks,
Mark.
Quoted 49 lines
Changes since v4:
- add patch to align the callers offinalise_el2()
- also clean HYP text to the PoC when booting at EL2 with the MMU on
- add a warning and a taint when doing non-EFI boot with the MMU and caches enabled
- rebase onto zboot changes in efi/next - this means that patches #6 and #7 will not apply onto arm64/for-next so a shared stable branch will be needed if we want to queue this up for v6.2Changes since v3:
- dropEFI_LOADER_CODEmemory type patch that has been queued in the mean time
- rebased onto [partial] series that movesefi-entry.Sinto the libstub/ source directory
- fixed a correctness issue in patch #2Cc Will Deacon <[email protected]>Cc Catalin Marinas <[email protected]>Cc Marc Zyngier <[email protected]>Cc Mark Rutland <[email protected]>Ard Biesheuvel (7):
arm64: head: Move allfinalise_el2calls to after__enable_mmu
arm64: kernel: move identity map out of .text mapping
arm64: head: record the MMU state at primary entry
arm64: head: avoid cache invalidation when entering with the MMU on
arm64: head: Clean the ID map and the HYP text to the PoC if needed
arm64: lds: reduce effective minimum image alignment to 64k
efi: arm64: enter with MMU and caches enabledarch/arm64/include/asm/efi.h | 9 +- arch/arm64/kernel/head.S | 93 +++++++++++++++----- arch/arm64/kernel/image-vars.h | 5 +- arch/arm64/kernel/setup.c | 9 +- arch/arm64/kernel/sleep.S | 6 +- arch/arm64/kernel/vmlinux.lds.S | 13 ++- arch/arm64/mm/cache.S | 5 +- arch/arm64/mm/proc.S | 2 - drivers/firmware/efi/libstub/Makefile | 4 +- drivers/firmware/efi/libstub/arm64-entry.S | 67 -------------- drivers/firmware/efi/libstub/arm64-stub.c | 26 ++++-- drivers/firmware/efi/libstub/arm64.c | 41 +++++++-- include/linux/efi.h | 6 +- 13 files changed, 159 insertions(+), 127 deletions(-) delete mode 100644 drivers/firmware/efi/libstub/arm64-entry.SSignature · 1 line
2.35.1
Will Deacon
maintainerQuoted 15 lines · Mark Rutland
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
Quoted 6 lines
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to
head.S), and adds more scope for error, even if it simplifies the EFI stub itself.
As discussed offline, two things that would help the current series are:
(1) Some performance numbers comparing MMU off vs MMU on boot
(2) Use of a separate entry point for the MMU on case, potentially failing the boot if the MMU is on and we're not using EFI
Will
Ard Biesheuvel
maintainerQuoted 24 lines · Will Deacon
Quoted 15 lines · Mark Rutland
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
Quoted 6 lines
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to
head.S), and adds more scope for error, even if it simplifies the EFI stub itself.
Quoted 7 lines
As discussed offline, two things that would help the current series are:
(1) Some performance numbers comparing MMU off vs MMU on boot
(2) Use of a separate entry point for the MMU on case, potentially failing the boot if the MMU is on and we're not using EFI
Ack.
But thinking about (2) again, failing the boot is better done at a time when you can inform the user about it, no?
IOW, just going into a deadloop really early if you enter the bare metal entry point with the MMU on is going to be hard to distinguish from other issues, whereas panicking after the console up is more likely to help getting the actual issue diagnosed.
So perhaps we should panic() instead of warn+taint when this condition occurs, and do it from an early initcall instead of from setup_arch().
Will Deacon
maintainerQuoted 35 lines · Ard Biesheuvel
Quoted 24 lines · Will Deacon
Quoted 15 lines · Mark Rutland
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
Quoted 6 lines
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to
head.S), and adds more scope for error, even if it simplifies the EFI stub itself.Quoted 7 lines
As discussed offline, two things that would help the current series are:
(1) Some performance numbers comparing MMU off vs MMU on boot
(2) Use of a separate entry point for the MMU on case, potentially failing the boot if the MMU is on and we're not using EFI
Ack.
Quoted 7 lines
But thinking about (2) again, failing the boot is better done at a time when you can inform the user about it, no?
IOW, just going into a deadloop really early if you enter the bare metal entry point with the MMU on is going to be hard to distinguish from other issues, whereas panicking after the console up is more likely to help getting the actual issue diagnosed.
Agreed.
Quoted 2 lines
So perhaps we should
panic()instead of warn+taint when this condition occurs, and do it from an early initcall instead of fromsetup_arch().
To be honest, and I appreciate that this is unhelpful, but I'm fine with the warn+taint and prefer that to a fatal stop.
Will
_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Ard Biesheuvel
maintainerQuoted 27 lines · Will Deacon
Quoted 25 lines · Ard Biesheuvel
Quoted 24 lines · Will Deacon
Quoted 21 lines · Mark Rutland
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to
head.S), and adds more scope for error, even if it simplifies the EFI stub itself.
Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
As discussed offline, two things that would help the current series are:
(1) Some performance numbers comparing MMU off vs MMU on boot
Finally got around to measuring this - I lost access to my TX2 machine for a couple of days during the past week,
With the patch below applied to mainline, I measure ~6 ms spent cleaning the entire image to the PoC (which is the bulk of it) and subsequently populating the initial ID map and activating it.
This drops to about 0.6 ms with my changes applied. This is unlikely to ever matter in practice, perhaps, but I will note that booting a VM in EFI mode using Tianocore/EDK2 from the point where KVM clears the counter to the point where we start user space can be done (on the same machine) in 500-700 ms so it is not entirely insignificant either.
I could try and measure it on bare metal as well, but I suppose that launch times are even less relevant there so I didn't bother.
Ard Biesheuvel
maintainerQuoted 48 lines · Ard Biesheuvel
Quoted 27 lines · Will Deacon
Quoted 25 lines · Ard Biesheuvel
Quoted 24 lines · Will Deacon
Quoted 21 lines · Mark Rutland
Quoted 8 lines · Ard Biesheuvel
The purpose of this series is to remove any explicit cache maintenance for coherency during early boot that becomes unnecessary if we simply retain the cacheable 1:1 mapping of all of system RAM provided by EFI, and use it to populate the ID map page tables. After setting up this preliminary ID map, we disable the MMU, drop to EL1, reprogram the MAIR, TCR and SCTLR registers as before, and proceed as usual, avoiding the need for any manipulations of memory while the MMU and caches are off.
Quoted 5 lines
The only properties of the firmware provided 1:1 map we rely on is that it does not require any explicit cache maintenance for coherency, and that it covers the entire memory footprint of the image, including the BSS and padding at the end - all else is under control of the kernel itself, as before.
As a high-level thing, I'm still very much not keen on entering the kernel with the MMU on. Given that we have to support booting with the MMU off for !EFI boot (including kexec when EFI is in use), I think this makes it harder to reason about the boot code overall (e.g. due to the conditional maintenance added to
head.S), and adds more scope for error, even if it simplifies the EFI stub itself.Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
As discussed offline, two things that would help the current series are:
(1) Some performance numbers comparing MMU off vs MMU on boot
Finally got around to measuring this - I lost access to my TX2 machine for a couple of days during the past week,
With the patch below applied to mainline, I measure ~6 ms spent cleaning the entire image to the PoC (which is the bulk of it) and subsequently populating the initial ID map and activating it.
This drops to about 0.6 ms with my changes applied. This is unlikely to ever matter in practice, perhaps, but I will note that booting a VM in EFI mode using Tianocore/EDK2 from the point where KVM clears the counter to the point where we start user space can be done (on the same machine) in 500-700 ms so it is not entirely insignificant either.
Quoted 2 lines
I could try and measure it on bare metal as well, but I suppose that launch times are even less relevant there so I didn't bother.
arch/arm64/kernel/efi-entry.S +1 -0
@@ -22,6 +22,7 @@ SYM_CODE_START(efi_enter_kernel) ldr w2, =primary_entry_offset add x19, x0, x2 // relocated Image entrypoint mov x20, x1 // DTB address + mrs x27, cntvct_el0 /* * Clean the copied Image to the PoC, and ensure it is not shadowed by
arch/arm64/kernel/head.S +6 -0
@@ -430,6 +430,8 @@ SYM_FUNC_START_LOCAL(__primary_switched) str_l x21, __fdt_pointer, x5 // Save FDT pointer + str_l x27, boot_args + 8, x5 + ldr_l x4, kimage_vaddr // Save the offset between sub x4, x4, x0 // the kernel virtual and str_l x4, kimage_voffset, x5 // physical mappings
@@ -797,6 +799,10 @@ SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu + + mrs x0, cntvct_el0 + sub x27, x0, x27 + #ifdef CONFIG_RELOCATABLE adrp x23, KERNEL_START and x23, x23, MIN_KIMG_ALIGN - 1