Automatic merge of 'next' into merge (2024-05-13 23:14)

Documentation/ABI/testing/sysfs-kernel-fadump

@@ -49,3 +49,10 @@ Description:	read only
 		memory add/remove events because elfcorehdr is now prepared in
 		the second/fadump kernel.
 User:		kexec-tools
+
+What:		/sys/kernel/fadump/bootargs_append
+Date:		May 2024
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read/write
+		This is a special sysfs file available to setup additional
+		parameters to be passed to capture kernel.

Documentation/virt/kvm/api.rst

@@ -4300,7 +4300,7 @@ operating system that uses the PIT for timing (e.g. Linux 2.4.x).
 4.100 KVM_PPC_CONFIGURE_V3_MMU
 ------------------------------
 
-:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
+:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3
 :Architectures: ppc
 :Type: vm ioctl
 :Parameters: struct kvm_ppc_mmuv3_cfg (in)
@@ -4334,7 +4334,7 @@ the Power ISA V3.00, Book III section 5.7.6.1.
 4.101 KVM_PPC_GET_RMMU_INFO
 ---------------------------
 
-:Capability: KVM_CAP_PPC_RADIX_MMU
+:Capability: KVM_CAP_PPC_MMU_RADIX
 :Architectures: ppc
 :Type: vm ioctl
 :Parameters: struct kvm_ppc_rmmu_info (out)
@@ -8095,7 +8095,7 @@ capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
 will disable the use of APIC hardware virtualization even if supported
 by the CPU, as it's incompatible with SynIC auto-EOI behavior.
 
-8.3 KVM_CAP_PPC_RADIX_MMU
+8.3 KVM_CAP_PPC_MMU_RADIX
 -------------------------
 
 :Architectures: ppc
@@ -8105,7 +8105,7 @@ available, means that the kernel can support guests using the
 radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
 processor).
 
-8.4 KVM_CAP_PPC_HASH_MMU_V3
+8.4 KVM_CAP_PPC_MMU_HASH_V3
 ---------------------------
 
 :Architectures: ppc

arch/powerpc/Kconfig

@@ -686,6 +686,10 @@ config ARCH_SELECTS_CRASH_DUMP
 	depends on CRASH_DUMP
 	select RELOCATABLE if PPC64 || 44x || PPC_85xx
 
+config ARCH_SUPPORTS_CRASH_HOTPLUG
+	def_bool y
+	depends on PPC64
+
 config FA_DUMP
 	bool "Firmware-assisted dump"
 	depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV)

arch/powerpc/include/asm/fadump-internal.h

@@ -124,6 +124,8 @@ struct fw_dump {
 	unsigned long	cpu_notes_buf_vaddr;
 	unsigned long	cpu_notes_buf_size;
 
+	unsigned long	param_area;
+
 	/*
 	 * Maximum size supported by firmware to copy from source to
 	 * destination address per entry.
@@ -138,6 +140,7 @@ struct fw_dump {
 	unsigned long	dump_active:1;
 	unsigned long	dump_registered:1;
 	unsigned long	nocma:1;
+	unsigned long	param_area_supported:1;
 
 	struct fadump_ops	*ops;
 };
@@ -156,14 +159,14 @@ struct fadump_ops {
 				      struct seq_file *m);
 	void	(*fadump_trigger)(struct fadump_crash_info_header *fdh,
 				  const char *msg);
+	int	(*fadump_max_boot_mem_rgns)(void);
 };
 
 /* Helper functions */
 s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus);
 void fadump_free_cpu_notes_buf(void);
 u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
 void __init fadump_update_elfcore_header(char *bufp);
-bool is_fadump_boot_mem_contiguous(void);
 bool is_fadump_reserved_mem_contiguous(void);
 
 #else /* !CONFIG_PRESERVE_FA_DUMP */

arch/powerpc/include/asm/fadump.h

@@ -19,12 +19,14 @@ extern int is_fadump_active(void);
 extern int should_fadump_crash(void);
 extern void crash_fadump(struct pt_regs *, const char *);
 extern void fadump_cleanup(void);
+extern void fadump_append_bootargs(void);
 
 #else	/* CONFIG_FA_DUMP */
 static inline int is_fadump_active(void) { return 0; }
 static inline int should_fadump_crash(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
 static inline void fadump_cleanup(void) { }
+static inline void fadump_append_bootargs(void) { }
 #endif /* !CONFIG_FA_DUMP */
 
 #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)

arch/powerpc/include/asm/kexec.h

@@ -135,6 +135,17 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 		ppc_save_regs(newregs);
 }
 
+#ifdef CONFIG_CRASH_HOTPLUG
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
+#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
+
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
+
+unsigned int arch_crash_get_elfcorehdr_size(void);
+#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
+#endif /* CONFIG_CRASH_HOTPLUG */
+
 extern int crashing_cpu;
 extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
 extern void crash_ipi_callback(struct pt_regs *regs);
@@ -185,6 +196,10 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 
 #endif /* CONFIG_CRASH_DUMP */
 
+#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP)
+int update_cpus_node(void *fdt);
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/book3s/64/kexec.h>
 #endif

arch/powerpc/include/asm/kexec_ranges.h

@@ -7,19 +7,9 @@
 void sort_memory_ranges(struct crash_mem *mrngs, bool merge);
 struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges);
 int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
-int add_tce_mem_ranges(struct crash_mem **mem_ranges);
-int add_initrd_mem_range(struct crash_mem **mem_ranges);
-#ifdef CONFIG_PPC_64S_HASH_MMU
-int add_htab_mem_range(struct crash_mem **mem_ranges);
-#else
-static inline int add_htab_mem_range(struct crash_mem **mem_ranges)
-{
-	return 0;
-}
-#endif
-int add_kernel_mem_range(struct crash_mem **mem_ranges);
-int add_rtas_mem_range(struct crash_mem **mem_ranges);
-int add_opal_mem_range(struct crash_mem **mem_ranges);
-int add_reserved_mem_ranges(struct crash_mem **mem_ranges);
-
+int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size);
+int get_exclude_memory_ranges(struct crash_mem **mem_ranges);
+int get_reserved_memory_ranges(struct crash_mem **mem_ranges);
+int get_crash_memory_ranges(struct crash_mem **mem_ranges);
+int get_usable_memory_ranges(struct crash_mem **mem_ranges);
 #endif /* _ASM_POWERPC_KEXEC_RANGES_H */

arch/powerpc/kernel/fadump.c

@@ -131,6 +131,41 @@ static int __init fadump_cma_init(void)
 static int __init fadump_cma_init(void) { return 1; }
 #endif /* CONFIG_CMA */
 
+/*
+ * Additional parameters meant for capture kernel are placed in a dedicated area.
+ * If this is capture kernel boot, append these parameters to bootargs.
+ */
+void __init fadump_append_bootargs(void)
+{
+	char *append_args;
+	size_t len;
+
+	if (!fw_dump.dump_active || !fw_dump.param_area_supported || !fw_dump.param_area)
+		return;
+
+	if (fw_dump.param_area >= fw_dump.boot_mem_top) {
+		if (memblock_reserve(fw_dump.param_area, COMMAND_LINE_SIZE)) {
+			pr_warn("WARNING: Can't use additional parameters area!\n");
+			fw_dump.param_area = 0;
+			return;
+		}
+	}
+
+	append_args = (char *)fw_dump.param_area;
+	len = strlen(boot_command_line);
+
+	/*
+	 * Too late to fail even if cmdline size exceeds. Truncate additional parameters
+	 * to cmdline size and proceed anyway.
+	 */
+	if (len + strlen(append_args) >= COMMAND_LINE_SIZE - 1)
+		pr_warn("WARNING: Appending parameters exceeds cmdline size. Truncating!\n");
+
+	pr_debug("Cmdline: %s\n", boot_command_line);
+	snprintf(boot_command_line + len, COMMAND_LINE_SIZE - len, " %s", append_args);
+	pr_info("Updated cmdline: %s\n", boot_command_line);
+}
+
 /* Scan the Firmware Assisted dump configuration details. */
 int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 				      int depth, void *data)
@@ -220,28 +255,6 @@ static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
 	return ret;
 }
 
-/*
- * Returns true, if there are no holes in boot memory area,
- * false otherwise.
- */
-bool is_fadump_boot_mem_contiguous(void)
-{
-	unsigned long d_start, d_end;
-	bool ret = false;
-	int i;
-
-	for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
-		d_start = fw_dump.boot_mem_addr[i];
-		d_end   = d_start + fw_dump.boot_mem_sz[i];
-
-		ret = is_fadump_mem_area_contiguous(d_start, d_end);
-		if (!ret)
-			break;
-	}
-
-	return ret;
-}
-
 /*
  * Returns true, if there are no holes in reserved memory area,
  * false otherwise.
@@ -381,10 +394,11 @@ static unsigned long __init get_fadump_area_size(void)
 static int __init add_boot_mem_region(unsigned long rstart,
 				      unsigned long rsize)
 {
+	int max_boot_mem_rgns = fw_dump.ops->fadump_max_boot_mem_rgns();
 	int i = fw_dump.boot_mem_regs_cnt++;
 
-	if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
-		fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+	if (fw_dump.boot_mem_regs_cnt > max_boot_mem_rgns) {
+		fw_dump.boot_mem_regs_cnt = max_boot_mem_rgns;
 		return 0;
 	}
 
@@ -1452,6 +1466,43 @@ static ssize_t registered_show(struct kobject *kobj,
 	return sprintf(buf, "%d\n", fw_dump.dump_registered);
 }
 
+static ssize_t bootargs_append_show(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   char *buf)
+{
+	return sprintf(buf, "%s\n", (char *)__va(fw_dump.param_area));
+}
+
+static ssize_t bootargs_append_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	char *params;
+
+	if (!fw_dump.fadump_enabled || fw_dump.dump_active)
+		return -EPERM;
+
+	if (count >= COMMAND_LINE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Fail here instead of handling this scenario with
+	 * some silly workaround in capture kernel.
+	 */
+	if (saved_command_line_len + count >= COMMAND_LINE_SIZE) {
+		pr_err("Appending parameters exceeds cmdline size!\n");
+		return -ENOSPC;
+	}
+
+	params = __va(fw_dump.param_area);
+	strscpy_pad(params, buf, COMMAND_LINE_SIZE);
+	/* Remove newline character at the end. */
+	if (params[count-1] == '\n')
+		params[count-1] = '\0';
+
+	return count;
+}
+
 static ssize_t registered_store(struct kobject *kobj,
 				struct kobj_attribute *attr,
 				const char *buf, size_t count)
@@ -1511,6 +1562,7 @@ static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
 static struct kobj_attribute register_attr = __ATTR_RW(registered);
 static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
 static struct kobj_attribute hotplug_ready_attr = __ATTR_RO(hotplug_ready);
+static struct kobj_attribute bootargs_append_attr = __ATTR_RW(bootargs_append);
 
 static struct attribute *fadump_attrs[] = {
 	&enable_attr.attr,
@@ -1684,6 +1736,54 @@ static void __init fadump_process(void)
 	fadump_invalidate_release_mem();
 }
 
+/*
+ * Reserve memory to store additional parameters to be passed
+ * for fadump/capture kernel.
+ */
+static void fadump_setup_param_area(void)
+{
+	phys_addr_t range_start, range_end;
+
+	if (!fw_dump.param_area_supported || fw_dump.dump_active)
+		return;
+
+	/* This memory can't be used by PFW or bootloader as it is shared across kernels */
+	if (radix_enabled()) {
+		/*
+		 * Anywhere in the upper half should be good enough as all memory
+		 * is accessible in real mode.
+		 */
+		range_start = memblock_end_of_DRAM() / 2;
+		range_end = memblock_end_of_DRAM();
+	} else {
+		/*
+		 * Passing additional parameters is supported for hash MMU only
+		 * if the first memory block size is 768MB or higher.
+		 */
+		if (ppc64_rma_size < 0x30000000)
+			return;
+
+		/*
+		 * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving
+		 * memory for passing additional parameters in this range to avoid
+		 * being stomped on by PFW/bootloader.
+		 */
+		range_start = 0x2A000000;
+		range_end = range_start + 0x4000000;
+	}
+
+	fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE,
+						       COMMAND_LINE_SIZE,
+						       range_start,
+						       range_end);
+	if (!fw_dump.param_area || sysfs_create_file(fadump_kobj, &bootargs_append_attr.attr)) {
+		pr_warn("WARNING: Could not setup area to pass additional parameters!\n");
+		return;
+	}
+
+	memset(phys_to_virt(fw_dump.param_area), 0, COMMAND_LINE_SIZE);
+}
+
 /*
  * Prepare for firmware-assisted dump.
  */
@@ -1707,6 +1807,7 @@ int __init setup_fadump(void)
 	}
 	/* Initialize the kernel dump memory structure and register with f/w */
 	else if (fw_dump.reserve_dump_area_size) {
+		fadump_setup_param_area();
 		fw_dump.ops->fadump_init_mem_struct(&fw_dump);
 		register_fadump();
 	}

arch/powerpc/kernel/prom.c

@@ -813,6 +813,9 @@ void __init early_init_devtree(void *params)
 	 */
 	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
 
+	/* Append additional parameters passed for fadump capture kernel */
+	fadump_append_bootargs();
+
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	early_init_dt_scan_root();
 	early_init_dt_scan_memory_ppc();

arch/powerpc/kexec/Makefile

@@ -3,11 +3,11 @@
 # Makefile for the linux kernel.
 #
 
-obj-y				+= core.o core_$(BITS).o
+obj-y				+= core.o core_$(BITS).o ranges.o
 
 obj-$(CONFIG_PPC32)		+= relocate_32.o
 
-obj-$(CONFIG_KEXEC_FILE)	+= file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o
+obj-$(CONFIG_KEXEC_FILE)	+= file_load.o file_load_$(BITS).o elf_$(BITS).o
 obj-$(CONFIG_VMCORE_INFO)	+= vmcore_info.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash.o