Merge: Enable virtio-mem on s390x

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/540

JIRA: https://issues.redhat.com/browse/RHEL-72992

Enable virtio-mem on s390x. Sanity tested with a self-built QEMU in the host, and then checking in the guest that the amount of memory changes in the guest in /proc/meminfo when adding or removing memory.

Signed-off-by: Thomas Huth <thuth@redhat.com>

Approved-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Approved-by: Philipp Rudo <prudo@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

Documentation/virt/kvm/s390/s390-diag.rst

@@ -35,20 +35,24 @@ DIAGNOSE function codes not specific to KVM, please refer to the
 documentation for the s390 hypervisors defining them.
 
 
-DIAGNOSE function code 'X'500' - KVM virtio functions
------------------------------------------------------
+DIAGNOSE function code 'X'500' - KVM functions
+----------------------------------------------
 
-If the function code specifies 0x500, various virtio-related functions
-are performed.
+If the function code specifies 0x500, various KVM-specific functions
+are performed, including virtio functions.
 
-General register 1 contains the virtio subfunction code. Supported
-virtio subfunctions depend on KVM's userspace. Generally, userspace
-provides either s390-virtio (subcodes 0-2) or virtio-ccw (subcode 3).
+General register 1 contains the subfunction code. Supported subfunctions
+depend on KVM's userspace. Regarding virtio subfunctions, generally
+userspace provides either s390-virtio (subcodes 0-2) or virtio-ccw
+(subcode 3).
 
 Upon completion of the DIAGNOSE instruction, general register 2 contains
 the function's return code, which is either a return code or a subcode
 specific value.
 
+If the specified subfunction is not supported, a SPECIFICATION exception
+will be triggered.
+
 Subcode 0 - s390-virtio notification and early console printk
     Handled by userspace.
 
@@ -76,6 +80,23 @@ Subcode 3 - virtio-ccw notification
 
     See also the virtio standard for a discussion of this hypercall.
 
+Subcode 4 - storage-limit
+    Handled by userspace.
+
+    After completion of the DIAGNOSE call, general register 2 will
+    contain the storage limit: the maximum physical address that might be
+    used for storage throughout the lifetime of the VM.
+
+    The storage limit does not indicate currently usable storage, it may
+    include holes, standby storage and areas reserved for other means, such
+    as memory hotplug or virtio-mem devices. Other interfaces for detecting
+    actually usable storage, such as SCLP, must be used in conjunction with
+    this subfunction.
+
+    Note that the storage limit can be larger, but never smaller than the
+    maximum storage address indicated by SCLP via the "maximum storage
+    increment" and the "increment size".
+
 
 DIAGNOSE function code 'X'501 - KVM breakpoint
 ----------------------------------------------

arch/s390/Kconfig

@@ -239,6 +239,7 @@ config S390
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PROC_VMCORE_DEVICE_RAM if PROC_VMCORE
 	select NEED_SG_DMA_LENGTH	if PCI
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3

arch/s390/boot/physmem_info.c

@@ -112,6 +112,42 @@ static int diag260(void)
 	return 0;
 }
 
+#define DIAG500_SC_STOR_LIMIT 4
+
+static int diag500_storage_limit(unsigned long *max_physmem_end)
+{
+	unsigned long storage_limit;
+	unsigned long reg1, reg2;
+	psw_t old;
+
+	asm volatile(
+		"	mvc	0(16,%[psw_old]),0(%[psw_pgm])\n"
+		"	epsw	%[reg1],%[reg2]\n"
+		"	st	%[reg1],0(%[psw_pgm])\n"
+		"	st	%[reg2],4(%[psw_pgm])\n"
+		"	larl	%[reg1],1f\n"
+		"	stg	%[reg1],8(%[psw_pgm])\n"
+		"	lghi	1,%[subcode]\n"
+		"	lghi	2,0\n"
+		"	diag	2,4,0x500\n"
+		"1:	mvc	0(16,%[psw_pgm]),0(%[psw_old])\n"
+		"	lgr	%[slimit],2\n"
+		: [reg1] "=&d" (reg1),
+		  [reg2] "=&a" (reg2),
+		  [slimit] "=d" (storage_limit),
+		  "=Q" (get_lowcore()->program_new_psw),
+		  "=Q" (old)
+		: [psw_old] "a" (&old),
+		  [psw_pgm] "a" (&get_lowcore()->program_new_psw),
+		  [subcode] "i" (DIAG500_SC_STOR_LIMIT)
+		: "memory", "1", "2");
+	if (!storage_limit)
+		return -EINVAL;
+	/* Convert inclusive end to exclusive end */
+	*max_physmem_end = storage_limit + 1;
+	return 0;
+}
+
 static int tprot(unsigned long addr)
 {
 	unsigned long reg1, reg2;
@@ -163,7 +199,9 @@ unsigned long detect_max_physmem_end(void)
 {
 	unsigned long max_physmem_end = 0;
 
-	if (!sclp_early_get_memsize(&max_physmem_end)) {
+	if (!diag500_storage_limit(&max_physmem_end)) {
+		physmem_info.info_source = MEM_DETECT_DIAG500_STOR_LIMIT;
+	} else if (!sclp_early_get_memsize(&max_physmem_end)) {
 		physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
 	} else {
 		max_physmem_end = search_mem_end();
@@ -176,6 +214,13 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end)
 {
 	if (!sclp_early_read_storage_info()) {
 		physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO;
+	} else if (physmem_info.info_source == MEM_DETECT_DIAG500_STOR_LIMIT) {
+		unsigned long online_end;
+
+		if (!sclp_early_get_memsize(&online_end)) {
+			physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
+			add_physmem_online_range(0, online_end);
+		}
 	} else if (!diag260()) {
 		physmem_info.info_source = MEM_DETECT_DIAG260;
 	} else if (max_physmem_end) {

arch/s390/boot/startup.c

@@ -182,12 +182,15 @@ static void kaslr_adjust_got(unsigned long offset)
  * Merge information from several sources into a single ident_map_size value.
  * "ident_map_size" represents the upper limit of physical memory we may ever
  * reach. It might not be all online memory, but also include standby (offline)
- * memory. "ident_map_size" could be lower then actual standby or even online
+ * memory or memory areas reserved for other means (e.g., memory devices such as
+ * virtio-mem).
+ *
+ * "ident_map_size" could be lower then actual standby/reserved or even online
  * memory present, due to limiting factors. We should never go above this limit.
  * It is the size of our identity mapping.
  *
  * Consider the following factors:
- * 1. max_physmem_end - end of physical memory online or standby.
+ * 1. max_physmem_end - end of physical memory online, standby or reserved.
  *    Always >= end of the last online memory range (get_physmem_online_end()).
  * 2. CONFIG_MAX_PHYSMEM_BITS - the maximum size of physical memory the
  *    kernel is able to support.

arch/s390/include/asm/physmem_info.h

@@ -9,6 +9,7 @@ enum physmem_info_source {
 	MEM_DETECT_NONE = 0,
 	MEM_DETECT_SCLP_STOR_INFO,
 	MEM_DETECT_DIAG260,
+	MEM_DETECT_DIAG500_STOR_LIMIT,
 	MEM_DETECT_SCLP_READ_INFO,
 	MEM_DETECT_BIN_SEARCH
 };
@@ -107,6 +108,8 @@ static inline const char *get_physmem_info_source(void)
 		return "sclp storage info";
 	case MEM_DETECT_DIAG260:
 		return "diag260";
+	case MEM_DETECT_DIAG500_STOR_LIMIT:
+		return "diag500 storage limit";
 	case MEM_DETECT_SCLP_READ_INFO:
 		return "sclp read info";
 	case MEM_DETECT_BIN_SEARCH:

arch/s390/include/asm/sparsemem.h

@@ -2,7 +2,15 @@
 #ifndef _ASM_S390_SPARSEMEM_H
 #define _ASM_S390_SPARSEMEM_H
 
-#define SECTION_SIZE_BITS	28
+#define SECTION_SIZE_BITS	27
 #define MAX_PHYSMEM_BITS	CONFIG_MAX_PHYSMEM_BITS
 
+#ifdef CONFIG_NUMA
+static inline int memory_add_physaddr_to_nid(u64 addr)
+{
+	return 0;
+}
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif /* CONFIG_NUMA */
+
 #endif /* _ASM_S390_SPARSEMEM_H */

arch/s390/kernel/crash_dump.c

@@ -497,6 +497,19 @@ static int get_mem_chunk_cnt(void)
 	return cnt;
 }
 
+static void fill_ptload(Elf64_Phdr *phdr, unsigned long paddr,
+		unsigned long vaddr, unsigned long size)
+{
+	phdr->p_type = PT_LOAD;
+	phdr->p_vaddr = vaddr;
+	phdr->p_offset = paddr;
+	phdr->p_paddr = paddr;
+	phdr->p_filesz = size;
+	phdr->p_memsz = size;
+	phdr->p_flags = PF_R | PF_W | PF_X;
+	phdr->p_align = PAGE_SIZE;
+}
+
 /*
  * Initialize ELF loads (new kernel)
  */
@@ -509,14 +522,8 @@ static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm)
 	if (os_info_has_vm)
 		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
 	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
-		phdr->p_type = PT_LOAD;
-		phdr->p_vaddr = old_identity_base + start;
-		phdr->p_offset = start;
-		phdr->p_paddr = start;
-		phdr->p_filesz = end - start;
-		phdr->p_memsz = end - start;
-		phdr->p_flags = PF_R | PF_W | PF_X;
-		phdr->p_align = PAGE_SIZE;
+		fill_ptload(phdr, start, old_identity_base + start,
+			    end - start);
 		phdr++;
 	}
 }
@@ -526,6 +533,22 @@ static bool os_info_has_vm(void)
 	return os_info_old_value(OS_INFO_KASLR_OFFSET);
 }
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+/*
+ * Fill PT_LOAD for a physical memory range owned by a device and detected by
+ * its device driver.
+ */
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size)
+{
+	unsigned long old_identity_base = 0;
+
+	if (os_info_has_vm())
+		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
+	fill_ptload(phdr, paddr, old_identity_base + paddr, size);
+}
+#endif
+
 /*
  * Prepare PT_LOAD type program header for kernel image region
  */

drivers/virtio/Kconfig

@@ -122,7 +122,7 @@ config VIRTIO_BALLOON
 
 config VIRTIO_MEM
 	tristate "Virtio mem driver"
-	depends on X86_64 || ARM64 || RISCV
+	depends on X86_64 || ARM64 || RISCV || S390
 	depends on VIRTIO
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
@@ -132,11 +132,11 @@ config VIRTIO_MEM
 	 This driver provides access to virtio-mem paravirtualized memory
 	 devices, allowing to hotplug and hotunplug memory.
 
-	 This driver currently only supports x86-64 and arm64. Although it
-	 should compile on other architectures that implement memory
-	 hot(un)plug, architecture-specific and/or common
-	 code changes may be required for virtio-mem, kdump and kexec to work as
-	 expected.
+	 This driver currently supports x86-64, arm64, riscv and s390.
+	 Although it should compile on other architectures that implement
+	 memory hot(un)plug, architecture-specific and/or common
+	 code changes may be required for virtio-mem, kdump and kexec to
+	 work as expected.
 
 	 If unsure, say M.