Merge pull request #744 from angolini/lf-6.12.20-2.0.0_up_6.12.49toradex_6.12-2.0.x-imx

Lf 6.12.20 2.0.0 up 6.12.49

12 files changed, 71 insertions, 24 deletions

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index a407f9cd549e..c07a58b96329 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -150,7 +150,7 @@ acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor)
 {}
 #endif
 
-static inline const char *acpi_get_enable_method(int cpu)
+static __always_inline const char *acpi_get_enable_method(int cpu)
 {
 	if (acpi_psci_present())
 		return "psci";
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 74e4aaccf9f3..67b56ad1ab82 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -41,6 +41,11 @@
 /*
  * Save/restore interrupts.
  */
+	.macro save_and_disable_daif, flags
+	mrs	\flags, daif
+	msr	daifset, #0xf
+	.endm
+
 	.macro	save_and_disable_irq, flags
 	mrs	\flags, daif
 	msr	daifset, #3
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 2a4e686e633c..d92a0203e5a9 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -81,6 +81,7 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_X1C		0xD4C
 #define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
@@ -131,6 +132,7 @@
 #define FUJITSU_CPU_PART_A64FX		0x001
 
 #define HISI_CPU_PART_TSV110		0xD01
+#define HISI_CPU_PART_HIP09			0xD02
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
 #define APPLE_CPU_PART_M1_FIRESTORM	0x023
@@ -166,6 +168,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
 #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
@@ -206,6 +209,7 @@
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
 #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index e0ffdf13a18b..bdbe9e08664a 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -215,6 +215,30 @@
 .Lskip_fgt_\@:
 .endm
 
+.macro __init_el2_fgt2
+	mrs	x1, id_aa64mmfr0_el1
+	ubfx	x1, x1, #ID_AA64MMFR0_EL1_FGT_SHIFT, #4
+	cmp	x1, #ID_AA64MMFR0_EL1_FGT_FGT2
+	b.lt	.Lskip_fgt2_\@
+
+	mov	x0, xzr
+	mrs	x1, id_aa64dfr0_el1
+	ubfx	x1, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x1, #ID_AA64DFR0_EL1_PMUVer_V3P9
+	b.lt	.Lskip_pmuv3p9_\@
+
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICNTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMICFILTR_EL0
+	orr	x0, x0, #HDFGRTR2_EL2_nPMUACR_EL1
+.Lskip_pmuv3p9_\@:
+	msr_s   SYS_HDFGRTR2_EL2, x0
+	msr_s   SYS_HDFGWTR2_EL2, x0
+	msr_s   SYS_HFGRTR2_EL2, xzr
+	msr_s   SYS_HFGWTR2_EL2, xzr
+	msr_s   SYS_HFGITR2_EL2, xzr
+.Lskip_fgt2_\@:
+.endm
+
 .macro __init_el2_nvhe_prepare_eret
 	mov	x0, #INIT_PSTATE_EL1
 	msr	spsr_el2, x0
@@ -240,6 +264,7 @@
 	__init_el2_nvhe_idregs
 	__init_el2_cptr
 	__init_el2_fgt
+	__init_el2_fgt2
 .endm
 
 #ifndef __KVM_NVHE_HYPERVISOR__
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index da6d2c1c0b03..5f4dc6364dbb 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -370,12 +370,14 @@
 /*
  * ISS values for SME traps
  */
-
-#define ESR_ELx_SME_ISS_SME_DISABLED	0
-#define ESR_ELx_SME_ISS_ILL		1
-#define ESR_ELx_SME_ISS_SM_DISABLED	2
-#define ESR_ELx_SME_ISS_ZA_DISABLED	3
-#define ESR_ELx_SME_ISS_ZT_DISABLED	4
+#define ESR_ELx_SME_ISS_SMTC_MASK		GENMASK(2, 0)
+#define ESR_ELx_SME_ISS_SMTC(esr)		((esr) & ESR_ELx_SME_ISS_SMTC_MASK)
+
+#define ESR_ELx_SME_ISS_SMTC_SME_DISABLED	0
+#define ESR_ELx_SME_ISS_SMTC_ILL		1
+#define ESR_ELx_SME_ISS_SMTC_SM_DISABLED	2
+#define ESR_ELx_SME_ISS_SMTC_ZA_DISABLED	3
+#define ESR_ELx_SME_ISS_SMTC_ZT_DISABLED	4
 
 /* ISS field definitions for MOPS exceptions */
 #define ESR_ELx_MOPS_ISS_MEM_INST	(UL(1) << 24)
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index f2a84efc3618..c8dcb67b81a7 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -6,6 +6,7 @@
 #define __ASM_FP_H
 
 #include <asm/errno.h>
+#include <asm/percpu.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
@@ -94,6 +95,8 @@ struct cpu_fp_state {
 	enum fp_type to_save;
 };
 
+DECLARE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+
 extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index bc77869dbd43..509c874de5c7 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -693,6 +693,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
 }
 #endif
 u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
+u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type);
 u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
 			 enum aarch64_insn_system_register sysreg);
 
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 79550b22ba19..fb9b88eebeb1 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -19,6 +19,7 @@ struct mod_arch_specific {
 
 	/* for CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry	*ftrace_trampolines;
+	struct plt_entry	*init_ftrace_trampolines;
 };
 
 u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index b9ae8349e35d..fb944b46846d 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -2,6 +2,7 @@ SECTIONS {
 	.plt 0 : { BYTE(0) }
 	.init.plt 0 : { BYTE(0) }
 	.text.ftrace_trampoline 0 : { BYTE(0) }
+	.init.text.ftrace_trampoline 0 : { BYTE(0) }
 
 #ifdef CONFIG_KASAN_SW_TAGS
 	/*
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bdf136f38656..78d188d3d721 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -554,18 +554,6 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif
 
 #define pmd_present(pmd)	pte_present(pmd_pte(pmd))
-
-/*
- * THP definitions.
- */
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pmd_trans_huge(pmd_t pmd)
-{
-	return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
@@ -730,6 +718,18 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
 #define pte_leaf_size(pte)	(pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE)
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int pmd_trans_huge(pmd_t pmd)
+{
+	/*
+	 * If pmd is present-invalid, pmd_table() won't detect it
+	 * as a table, so force the valid bit for the comparison.
+	 */
+	return pmd_val(pmd) && pmd_present(pmd) &&
+	       !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
 static inline bool pud_sect(pud_t pud) { return false; }
 static inline bool pud_table(pud_t pud) { return true; }
@@ -811,7 +811,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 	pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
 
 #define pud_none(pud)		(!pud_val(pud))
-#define pud_bad(pud)		(!pud_table(pud))
+#define pud_bad(pud)		((pud_val(pud) & PUD_TYPE_MASK) != \
+				 PUD_TYPE_TABLE)
 #define pud_present(pud)	pte_present(pud_pte(pud))
 #ifndef __PAGETABLE_PMD_FOLDED
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index f527b1cb7d1b..1b08cf620dc2 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -98,6 +98,9 @@ enum mitigation_state arm64_get_meltdown_state(void);
 enum mitigation_state arm64_get_spectre_bhb_state(void);
 enum mitigation_state arm64_get_spectre_bse_state(void);
 bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+extern bool __nospectre_bhb;
+u8 get_spectre_bhb_loop_value(void);
+bool is_spectre_bhb_fw_mitigated(void);
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
 
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 8d705ff95a59..9eb76e87641f 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -346,13 +346,14 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 }
 
 /*
- * If mprotect/munmap/etc occurs during TLB batched flushing, we need to
- * synchronise all the TLBI issued with a DSB to avoid the race mentioned in
- * flush_tlb_batched_pending().
+ * If mprotect/munmap/etc occurs during TLB batched flushing, we need to ensure
+ * all the previously issued TLBIs targeting mm have completed. But since we
+ * can be executing on a remote CPU, a DSB cannot guarantee this like it can
+ * for arch_tlbbatch_flush(). Our only option is to flush the entire mm.
  */
 static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
 {
-	dsb(ish);
+	flush_tlb_mm(mm);
 }
 
 /*