Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Support for arm64 SME 2 and 2.1. SME2 introduces a new 512-bit
   architectural register (ZT0, for the look-up table feature) that
   Linux needs to save/restore

 - Include TPIDR2 in the signal context and add the corresponding
   kselftests

 - Perf updates: Arm SPEv1.2 support, HiSilicon uncore PMU updates, ACPI
   support to the Marvell DDR and TAD PMU drivers, reset DTM_PMU_CONFIG
   (ARM CMN) at probe time

 - Support for DYNAMIC_FTRACE_WITH_CALL_OPS on arm64

 - Permit EFI boot with MMU and caches on. Instead of cleaning the
   entire loaded kernel image to the PoC and disabling the MMU and
   caches before branching to the kernel bare metal entry point, leave
   the MMU and caches enabled and rely on EFI's cacheable 1:1 mapping of
   all of system RAM to populate the initial page tables

 - Expose the AArch32 (compat) ELF_HWCAP features to user in an arm64
   kernel (the arm32 kernel only defines the values)

 - Harden the arm64 shadow call stack pointer handling: stash the shadow
   stack pointer in the task struct on interrupt, load it directly from
   this structure

 - Signal handling cleanups to remove redundant validation of size
   information and avoid reading the same data from userspace twice

 - Refactor the hwcap macros to make use of the automatically generated
   ID registers. It should make new hwcaps writing less error prone

 - Further arm64 sysreg conversion and some fixes

 - arm64 kselftest fixes and improvements

 - Pointer authentication cleanups: don't sign leaf functions, unify
   asm-arch manipulation

 - Pseudo-NMI code generation optimisations

 - Minor fixes for SME and TPIDR2 handling

 - Miscellaneous updates: ARCH_FORCE_MAX_ORDER is now selectable,
   replace strtobool() to kstrtobool() in the cpufeature.c code, apply
   dynamic shadow call stack in two passes, intercept pfn changes in
   set_pte_at() without the required break-before-make sequence, attempt
   to dump all instructions on unhandled kernel faults

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (130 commits)
  arm64: fix .idmap.text assertion for large kernels
  kselftest/arm64: Don't require FA64 for streaming SVE+ZA tests
  kselftest/arm64: Copy whole EXTRA context
  arm64: kprobes: Drop ID map text from kprobes blacklist
  perf: arm_spe: Print the version of SPE detected
  perf: arm_spe: Add support for SPEv1.2 inverted event filtering
  perf: Add perf_event_attr::config3
  arm64/sme: Fix __finalise_el2 SMEver check
  drivers/perf: fsl_imx8_ddr_perf: Remove set-but-not-used variable
  arm64/signal: Only read new data when parsing the ZT context
  arm64/signal: Only read new data when parsing the ZA context
  arm64/signal: Only read new data when parsing the SVE context
  arm64/signal: Avoid rereading context frame sizes
  arm64/signal: Make interface for restore_fpsimd_context() consistent
  arm64/signal: Remove redundant size validation from parse_user_sigframe()
  arm64/signal: Don't redundantly verify FPSIMD magic
  arm64/cpufeature: Use helper macros to specify hwcaps
  arm64/cpufeature: Always use symbolic name for feature value in hwcaps
  arm64/sysreg: Initial unsigned annotations for ID registers
  arm64/sysreg: Initial annotation of signed ID registers
  ...

4 files changed, 55 insertions, 83 deletions

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index be8b8c6e8b40..80d85a5169fb 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -87,7 +87,7 @@ 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 smbios.o
+lib-$(CONFIG_ARM64)		+= arm64.o arm64-stub.o smbios.o
 lib-$(CONFIG_X86)		+= x86-stub.o
 lib-$(CONFIG_RISCV)		+= riscv.o riscv-stub.o
 lib-$(CONFIG_LOONGARCH)		+= loongarch.o loongarch-stub.o
@@ -141,7 +141,7 @@ 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
diff --git a/drivers/firmware/efi/libstub/arm64-entry.S b/drivers/firmware/efi/libstub/arm64-entry.S
deleted file mode 100644
index b5c17e89a4fc..000000000000
--- a/drivers/firmware/efi/libstub/arm64-entry.S
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * EFI entry point.
- *
- * Copyright (C) 2013, 2014 Red Hat, Inc.
- * Author: Mark Salter <msalter@redhat.com>
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-	/*
-	 * The entrypoint of a arm64 bare metal image is at offset #0 of the
-	 * image, so this is a reasonable default for primary_entry_offset.
-	 * Only when the EFI stub is integrated into the core kernel, it is not
-	 * guaranteed that the PE/COFF header has been copied to memory too, so
-	 * in this case, primary_entry_offset should be overridden by the
-	 * linker and point to primary_entry() directly.
-	 */
-	.weak	primary_entry_offset
-
-SYM_CODE_START(efi_enter_kernel)
-	/*
-	 * efi_pe_entry() will have copied the kernel image if necessary and we
-	 * end up here with device tree address in x1 and the kernel entry
-	 * point stored in x0. Save those values in registers which are
-	 * callee preserved.
-	 */
-	ldr	w2, =primary_entry_offset
-	add	x19, x0, x2		// relocated Image entrypoint
-
-	mov	x0, x1			// DTB address
-	mov	x1, xzr
-	mov	x2, xzr
-	mov	x3, xzr
-
-	/*
-	 * Clean the remainder of this routine to the PoC
-	 * so that we can safely disable the MMU and caches.
-	 */
-	adr	x4, 1f
-	dc	civac, x4
-	dsb	sy
-
-	/* Turn off Dcache and MMU */
-	mrs	x4, CurrentEL
-	cmp	x4, #CurrentEL_EL2
-	mrs	x4, sctlr_el1
-	b.ne	0f
-	mrs	x4, sctlr_el2
-0:	bic	x4, x4, #SCTLR_ELx_M
-	bic	x4, x4, #SCTLR_ELx_C
-	b.eq	1f
-	b	2f
-
-	.balign	32
-1:	pre_disable_mmu_workaround
-	msr	sctlr_el2, x4
-	isb
-	br	x19		// jump to kernel entrypoint
-
-2:	pre_disable_mmu_workaround
-	msr	sctlr_el1, x4
-	isb
-	br	x19		// jump to kernel entrypoint
-
-	.org	1b + 32
-SYM_CODE_END(efi_enter_kernel)
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 7327b98d8e3f..d4a6b12a8741 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -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;
 
@@ -121,7 +122,7 @@ 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,
@@ -137,14 +138,21 @@ 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;
 }
diff --git a/drivers/firmware/efi/libstub/arm64.c b/drivers/firmware/efi/libstub/arm64.c
index 4501652e11ab..399770266372 100644
--- a/drivers/firmware/efi/libstub/arm64.c
+++ b/drivers/firmware/efi/libstub/arm64.c
@@ -59,6 +59,12 @@ efi_status_t check_platform_features(void)
 	return EFI_SUCCESS;
 }
 
+#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
+#define DCTYPE	"civac"
+#else
+#define DCTYPE	"cvau"
+#endif
+
 void efi_cache_sync_image(unsigned long image_base,
 			  unsigned long alloc_size,
 			  unsigned long code_size)
@@ -67,13 +73,38 @@ void efi_cache_sync_image(unsigned long image_base,
 	u64 lsize = 4 << cpuid_feature_extract_unsigned_field(ctr,
 						CTR_EL0_DminLine_SHIFT);
 
-	do {
-		asm("dc civac, %0" :: "r"(image_base));
-		image_base += lsize;
-		alloc_size -= lsize;
-	} while (alloc_size >= lsize);
+	/* only perform the cache maintenance if needed for I/D coherency */
+	if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) {
+		do {
+			asm("dc " DCTYPE ", %0" :: "r"(image_base));
+			image_base += lsize;
+			code_size -= lsize;
+		} while (code_size >= lsize);
+	}
 
 	asm("ic ialluis");
 	dsb(ish);
 	isb();
 }
+
+unsigned long __weak primary_entry_offset(void)
+{
+	/*
+	 * By default, we can invoke the kernel via the branch instruction in
+	 * the image header, so offset #0. This will be overridden by the EFI
+	 * stub build that is linked into the core kernel, as in that case, the
+	 * image header may not have been loaded into memory, or may be mapped
+	 * with non-executable permissions.
+	 */
+       return 0;
+}
+
+void __noreturn efi_enter_kernel(unsigned long entrypoint,
+				 unsigned long fdt_addr,
+				 unsigned long fdt_size)
+{
+	void (* __noreturn enter_kernel)(u64, u64, u64, u64);
+
+	enter_kernel = (void *)entrypoint + primary_entry_offset();
+	enter_kernel(fdt_addr, 0, 0, 0);
+}