Merge branch 'for-next/kexec' into for-next/core

* for-next/kexec:
  arm64: trans_pgd: remove trans_pgd_map_page()
  arm64: kexec: remove cpu-reset.h
  arm64: kexec: remove the pre-kexec PoC maintenance
  arm64: kexec: keep MMU enabled during kexec relocation
  arm64: kexec: install a copy of the linear-map
  arm64: kexec: use ld script for relocation function
  arm64: kexec: relocate in EL1 mode
  arm64: kexec: configure EL2 vectors for kexec
  arm64: kexec: pass kimage as the only argument to relocation function
  arm64: kexec: Use dcache ops macros instead of open-coding
  arm64: kexec: skip relocation code for inplace kexec
  arm64: kexec: flush image and lists during kexec load time
  arm64: hibernate: abstract ttrb0 setup function
  arm64: trans_pgd: hibernate: Add trans_pgd_copy_el2_vectors
  arm64: kernel: add helper for booted at EL2 and not VHE

Author: willdeacon

arch/arm64/Kconfig

@@ -1135,7 +1135,7 @@ config CRASH_DUMP
 
 config TRANS_TABLE
 	def_bool y
-	depends on HIBERNATION
+	depends on HIBERNATION || KEXEC_CORE
 
 config XEN_DOM0
 	def_bool y

arch/arm64/include/asm/assembler.h

@@ -380,19 +380,19 @@ alternative_endif
 
 /*
  * Macro to perform a data cache maintenance for the interval
- * [start, end)
+ * [start, end) with dcache line size explicitly provided.
  *
  * 	op:		operation passed to dc instruction
  * 	domain:		domain used in dsb instruciton
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
+ *	linesz:		dcache line size
  * 	fixup:		optional label to branch to on user fault
- * 	Corrupts:       start, end, tmp1, tmp2
+ * 	Corrupts:       start, end, tmp
  */
-	.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
-	dcache_line_size \tmp1, \tmp2
-	sub	\tmp2, \tmp1, #1
-	bic	\start, \start, \tmp2
+	.macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup
+	sub	\tmp, \linesz, #1
+	bic	\start, \start, \tmp
 .Ldcache_op\@:
 	.ifc	\op, cvau
 	__dcache_op_workaround_clean_cache \op, \start
@@ -411,14 +411,30 @@ alternative_endif
 	.endif
 	.endif
 	.endif
-	add	\start, \start, \tmp1
+	add	\start, \start, \linesz
 	cmp	\start, \end
 	b.lo	.Ldcache_op\@
 	dsb	\domain
 
 	_cond_extable .Ldcache_op\@, \fixup
 	.endm
 
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [start, end)
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	start:          starting virtual address of the region
+ * 	end:            end virtual address of the region
+ * 	fixup:		optional label to branch to on user fault
+ * 	Corrupts:       start, end, tmp1, tmp2
+ */
+	.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
+	dcache_line_size \tmp1, \tmp2
+	dcache_by_myline_op \op, \domain, \start, \end, \tmp1, \tmp2, \fixup
+	.endm
+
 /*
  * Macro to perform an instruction cache maintenance for the interval
  * [start, end)
@@ -442,6 +458,25 @@ alternative_endif
 	_cond_extable .Licache_op\@, \fixup
 	.endm
 
+/*
+ * To prevent the possibility of old and new partial table walks being visible
+ * in the tlb, switch the ttbr to a zero page when we invalidate the old
+ * records. D4.7.1 'General TLB maintenance requirements' in ARM DDI 0487A.i
+ * Even switching to our copied tables will cause a changed output address at
+ * each stage of the walk.
+ */
+	.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2
+	phys_to_ttbr \tmp, \zero_page
+	msr	ttbr1_el1, \tmp
+	isb
+	tlbi	vmalle1
+	dsb	nsh
+	phys_to_ttbr \tmp, \page_table
+	offset_ttbr1 \tmp, \tmp2
+	msr	ttbr1_el1, \tmp
+	isb
+	.endm
+
 /*
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */

arch/arm64/include/asm/kexec.h

@@ -90,12 +90,24 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
+#if defined(CONFIG_KEXEC_CORE)
+void cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
+		      unsigned long arg0, unsigned long arg1,
+		      unsigned long arg2);
+#endif
+
 #define ARCH_HAS_KIMAGE_ARCH
 
 struct kimage_arch {
 	void *dtb;
 	phys_addr_t dtb_mem;
 	phys_addr_t kern_reloc;
+	phys_addr_t el2_vectors;
+	phys_addr_t ttbr0;
+	phys_addr_t ttbr1;
+	phys_addr_t zero_page;
+	unsigned long phys_offset;
+	unsigned long t0sz;
 };
 
 #ifdef CONFIG_KEXEC_FILE

arch/arm64/include/asm/mmu_context.h

@@ -115,6 +115,30 @@ static inline void cpu_install_idmap(void)
 	cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
 }
 
+/*
+ * Load our new page tables. A strict BBM approach requires that we ensure that
+ * TLBs are free of any entries that may overlap with the global mappings we are
+ * about to install.
+ *
+ * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero
+ * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime
+ * services), while for a userspace-driven test_resume cycle it points to
+ * userspace page tables (and we must point it at a zero page ourselves).
+ *
+ * We change T0SZ as part of installing the idmap. This is undone by
+ * cpu_uninstall_idmap() in __cpu_suspend_exit().
+ */
+static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
+{
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	__cpu_set_tcr_t0sz(t0sz);
+
+	/* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */
+	write_sysreg(ttbr0, ttbr0_el1);
+	isb();
+}
+
 /*
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.

arch/arm64/include/asm/sections.h

@@ -21,5 +21,6 @@ extern char __exittext_begin[], __exittext_end[];
 extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
+extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[];
 
 #endif /* __ASM_SECTIONS_H */

arch/arm64/include/asm/trans_pgd.h

@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 /*
- * Copyright (c) 2020, Microsoft Corporation.
- * Pavel Tatashin <[email protected]>
+ * Copyright (c) 2021, Microsoft Corporation.
+ * Pasha Tatashin <[email protected]>
  */
 
 #ifndef _ASM_TRANS_TABLE_H
@@ -15,7 +15,7 @@
 /*
  * trans_alloc_page
  *	- Allocator that should return exactly one zeroed page, if this
- *	  allocator fails, trans_pgd_create_copy() and trans_pgd_map_page()
+ *	  allocator fails, trans_pgd_create_copy() and trans_pgd_idmap_page()
  *	  return -ENOMEM error.
  *
  * trans_alloc_arg
@@ -30,10 +30,12 @@ struct trans_pgd_info {
 int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **trans_pgd,
 			  unsigned long start, unsigned long end);
 
-int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
-		       void *page, unsigned long dst_addr, pgprot_t pgprot);
-
 int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0,
 			 unsigned long *t0sz, void *page);
 
+int trans_pgd_copy_el2_vectors(struct trans_pgd_info *info,
+			       phys_addr_t *el2_vectors);
+
+extern char trans_pgd_stub_vectors[];
+
 #endif /* _ASM_TRANS_TABLE_H */

arch/arm64/include/asm/virt.h

@@ -67,6 +67,8 @@
  */
 extern u32 __boot_cpu_mode[2];
 
+#define ARM64_VECTOR_TABLE_LEN	SZ_2K
+
 void __hyp_set_vectors(phys_addr_t phys_vector_base);
 void __hyp_reset_vectors(void);
 
@@ -128,6 +130,11 @@ static __always_inline bool is_protected_kvm_enabled(void)
 		return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE);
 }
 
+static inline bool is_hyp_nvhe(void)
+{
+	return is_hyp_mode_available() && !is_kernel_in_hyp_mode();
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */

arch/arm64/kernel/asm-offsets.c

@@ -9,6 +9,7 @@
 
 #include <linux/arm_sdei.h>
 #include <linux/sched.h>
+#include <linux/kexec.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/kvm_host.h>
@@ -170,6 +171,16 @@ int main(void)
   DEFINE(PTRAUTH_KERNEL_KEY_APIA,	offsetof(struct ptrauth_keys_kernel, apia));
 #endif
   BLANK();
+#endif
+#ifdef CONFIG_KEXEC_CORE
+  DEFINE(KIMAGE_ARCH_DTB_MEM,		offsetof(struct kimage, arch.dtb_mem));
+  DEFINE(KIMAGE_ARCH_EL2_VECTORS,	offsetof(struct kimage, arch.el2_vectors));
+  DEFINE(KIMAGE_ARCH_ZERO_PAGE,		offsetof(struct kimage, arch.zero_page));
+  DEFINE(KIMAGE_ARCH_PHYS_OFFSET,	offsetof(struct kimage, arch.phys_offset));
+  DEFINE(KIMAGE_ARCH_TTBR1,		offsetof(struct kimage, arch.ttbr1));
+  DEFINE(KIMAGE_HEAD,			offsetof(struct kimage, head));
+  DEFINE(KIMAGE_START,			offsetof(struct kimage, start));
+  BLANK();
 #endif
   return 0;
 }

arch/arm64/kernel/cpu-reset.S

@@ -16,8 +16,7 @@
 .pushsection    .idmap.text, "awx"
 
 /*
- * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
- * cpu_soft_restart.
+ * cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2)
  *
  * @el2_switch: Flag to indicate a switch to EL2 is needed.
  * @entry: Location to jump to for soft reset.
@@ -29,7 +28,7 @@
  * branch to what would be the reset vector. It must be executed with the
  * flat identity mapping.
  */
-SYM_CODE_START(__cpu_soft_restart)
+SYM_CODE_START(cpu_soft_restart)
 	mov_q	x12, INIT_SCTLR_EL1_MMU_OFF
 	pre_disable_mmu_workaround
 	/*
@@ -48,6 +47,6 @@ SYM_CODE_START(__cpu_soft_restart)
 	mov	x1, x3				// arg1
 	mov	x2, x4				// arg2
 	br	x8
-SYM_CODE_END(__cpu_soft_restart)
+SYM_CODE_END(cpu_soft_restart)
 
 .popsection