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

* for-next/misc:
  arm64: mm: Drop 'const' from conditional arm64_dma_phys_limit definition
  arm64: clean up tools Makefile
  arm64: drop unused includes of <linux/personality.h>
  arm64: Do not defer reserve_crashkernel() for platforms with no DMA memory zones
  arm64: prevent instrumentation of bp hardening callbacks
  arm64: cpufeature: Remove cpu_has_fwb() check
  arm64: atomics: remove redundant static branch
  arm64: entry: Save some nops when CONFIG_ARM64_PSEUDO_NMI is not set

arch/arm64/include/asm/lse.h

@@ -17,12 +17,10 @@
 #include <asm/cpucaps.h>
 
 extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
-extern struct static_key_false arm64_const_caps_ready;
 
-static inline bool system_uses_lse_atomics(void)
+static __always_inline bool system_uses_lse_atomics(void)
 {
-	return (static_branch_likely(&arm64_const_caps_ready)) &&
-		static_branch_likely(&cpu_hwcap_keys[ARM64_HAS_LSE_ATOMICS]);
+	return static_branch_likely(&cpu_hwcap_keys[ARM64_HAS_LSE_ATOMICS]);
 }
 
 #define __lse_ll_sc_body(op, ...)					\

arch/arm64/include/asm/spectre.h

@@ -67,7 +67,8 @@ struct bp_hardening_data {
 
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
-static inline void arm64_apply_bp_hardening(void)
+/* Called during entry so must be __always_inline */
+static __always_inline void arm64_apply_bp_hardening(void)
 {
 	struct bp_hardening_data *d;
 

arch/arm64/kernel/cpufeature.c

@@ -1775,14 +1775,6 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
 		write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
 }
 
-static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
-{
-	u64 val = read_sysreg_s(SYS_CLIDR_EL1);
-
-	/* Check that CLIDR_EL1.LOU{U,IS} are both 0 */
-	WARN_ON(CLIDR_LOUU(val) || CLIDR_LOUIS(val));
-}
-
 #ifdef CONFIG_ARM64_PAN
 static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 {
@@ -2144,7 +2136,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64MMFR2_FWB_SHIFT,
 		.min_field_value = 1,
 		.matches = has_cpuid_feature,
-		.cpu_enable = cpu_has_fwb,
 	},
 	{
 		.desc = "ARMv8.4 Translation Table Level",

arch/arm64/kernel/entry.S

@@ -300,6 +300,7 @@ alternative_else_nop_endif
 	str	w21, [sp, #S_SYSCALLNO]
 	.endif
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
 	/* Save pmr */
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	mrs_s	x20, SYS_ICC_PMR_EL1
@@ -307,6 +308,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	mov	x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET
 	msr_s	SYS_ICC_PMR_EL1, x20
 alternative_else_nop_endif
+#endif
 
 	/* Re-enable tag checking (TCO set on exception entry) */
 #ifdef CONFIG_ARM64_MTE
@@ -330,6 +332,7 @@ alternative_else_nop_endif
 	disable_daif
 	.endif
 
+#ifdef CONFIG_ARM64_PSEUDO_NMI
 	/* Restore pmr */
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	ldr	x20, [sp, #S_PMR_SAVE]
@@ -339,6 +342,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	dsb	sy				// Ensure priority change is seen by redistributor
 .L__skip_pmr_sync\@:
 alternative_else_nop_endif
+#endif
 
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 

arch/arm64/kernel/proton-pack.c

@@ -193,17 +193,20 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn)
 	__this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT);
 }
 
-static void call_smc_arch_workaround_1(void)
+/* Called during entry so must be noinstr */
+static noinstr void call_smc_arch_workaround_1(void)
 {
 	arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void call_hvc_arch_workaround_1(void)
+/* Called during entry so must be noinstr */
+static noinstr void call_hvc_arch_workaround_1(void)
 {
 	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void qcom_link_stack_sanitisation(void)
+/* Called during entry so must be noinstr */
+static noinstr void qcom_link_stack_sanitisation(void)
 {
 	u64 tmp;
 

arch/arm64/kernel/signal.c

@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
-#include <linux/personality.h>
 #include <linux/freezer.h>
 #include <linux/stddef.h>
 #include <linux/uaccess.h>

arch/arm64/kernel/sys_compat.c

@@ -9,7 +9,6 @@
 
 #include <linux/compat.h>
 #include <linux/cpufeature.h>
-#include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>

arch/arm64/kernel/traps.c

@@ -9,7 +9,6 @@
 #include <linux/bug.h>
 #include <linux/context_tracking.h>
 #include <linux/signal.h>
-#include <linux/personality.h>
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
 #include <linux/spinlock.h>

arch/arm64/mm/init.c

@@ -61,8 +61,34 @@ EXPORT_SYMBOL(memstart_addr);
  * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
+ *
+ * Memory reservation for crash kernel either done early or deferred
+ * depending on DMA memory zones configs (ZONE_DMA) --
+ *
+ * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
+ * here instead of max_zone_phys().  This lets early reservation of
+ * crash kernel memory which has a dependency on arm64_dma_phys_limit.
+ * Reserving memory early for crash kernel allows linear creation of block
+ * mappings (greater than page-granularity) for all the memory bank rangs.
+ * In this scheme a comparatively quicker boot is observed.
+ *
+ * If ZONE_DMA configs are defined, crash kernel memory reservation
+ * is delayed until DMA zone memory range size initilazation performed in
+ * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
+ * memory range to avoid overlap allocation.  So crash kernel memory boundaries
+ * are not known when mapping all bank memory ranges, which otherwise means
+ * not possible to exclude crash kernel range from creating block mappings
+ * so page-granularity mappings are created for the entire memory range.
+ * Hence a slightly slower boot is observed.
+ *
+ * Note: Page-granularity mapppings are necessary for crash kernel memory
+ * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
  */
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
+#endif
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -153,8 +179,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
-	if (!arm64_dma_phys_limit)
-		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -315,6 +339,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
+	if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
+
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -361,7 +388,8 @@ void __init bootmem_init(void)
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
-	reserve_crashkernel();
+	if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
 
 	memblock_dump_all();
 }

arch/arm64/mm/mmu.c

@@ -517,7 +517,7 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
 
-	if (can_set_direct_map() || crash_mem_map || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
@@ -528,6 +528,17 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
 
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA) ||
+		    IS_ENABLED(CONFIG_ZONE_DMA32))
+			flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+		else if (crashk_res.end)
+			memblock_mark_nomap(crashk_res.start,
+			    resource_size(&crashk_res));
+	}
+#endif
+
 	/* map all the memory banks */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -554,6 +565,25 @@ static void __init map_mem(pgd_t *pgdp)
 	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map &&
+	    !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
+		if (crashk_res.end) {
+			__map_memblock(pgdp, crashk_res.start,
+				       crashk_res.end + 1,
+				       PAGE_KERNEL,
+				       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+			memblock_clear_nomap(crashk_res.start,
+					     resource_size(&crashk_res));
+		}
+	}
+#endif
 }
 
 void mark_rodata_ro(void)

arch/arm64/tools/Makefile

@@ -5,18 +5,14 @@ kapi := $(gen)/asm
 
 kapi-hdrs-y := $(kapi)/cpucaps.h
 
-targets += $(addprefix ../../../,$(gen-y) $(kapi-hdrs-y))
+targets += $(addprefix ../../../, $(kapi-hdrs-y))
 
 PHONY += kapi
 
-kapi:   $(kapi-hdrs-y) $(gen-y)
-
-# Create output directory if not already present
-_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
+kapi:   $(kapi-hdrs-y)
 
 quiet_cmd_gen_cpucaps = GEN     $@
-      cmd_gen_cpucaps = mkdir -p $(dir $@) && \
-                     $(AWK) -f $(filter-out $(PHONY),$^) > $@
+      cmd_gen_cpucaps = mkdir -p $(dir $@); $(AWK) -f $(real-prereqs) > $@
 
 $(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE
 	$(call if_changed,gen_cpucaps)