Merge tag 's390-6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull more s390 updates from Alexander Gordeev:

 - The rework that uncoupled physical and virtual address spaces
   inadvertently prevented KASAN shadow mappings from using large pages.
   Restore large page mappings for KASAN shadows

 - Add decompressor routine physmem_alloc() that may fail, unlike
   physmem_alloc_or_die(). This allows callers to implement fallback
   paths

 - Allow falling back from large pages to smaller pages (1MB or 4KB) if
   the allocation of 2GB pages in the decompressor can not be fulfilled

 - Add to the decompressor boot print support of "%%" format string,
   width and padding hadnling, length modifiers and decimal conversion
   specifiers

 - Add to the decompressor message severity levels similar to kernel
   ones. Support command-line options that control console output
   verbosity

 - Replaces boot_printk() calls with appropriate loglevel- specific
   helpers such as boot_emerg(), boot_warn(), and boot_debug().

 - Collect all boot messages into a ring buffer independent of the
   current log level. This is particularly useful for early crash
   analysis

 - If 'earlyprintk' command line parameter is not specified, store
   decompressor boot messages in a ring buffer to be printed later by
   the kernel, once the console driver is registered

 - Add 'bootdebug' command line parameter to enable printing of
   decompressor debug messages when needed. That parameters allows
   message suppressing and filtering

 - Dump boot messages on a decompressor crash, but only if 'bootdebug'
   command line parameter is enabled

 - When CONFIG_PRINTK_TIME is enabled, add timestamps to boot messages
   in the same format as regular printk()

 - Dump physical memory tracking information on boot: online ranges,
   reserved areas and vmem allocations

 - Dump virtual memory layout and randomization details

 - Improve decompression error reporting and dump the message ring
   buffer in case the boot failed and system halted

 - Add an exception handler which handles exceptions when FPU control
   register is attempted to be set to an invalid value. Remove '.fixup'
   section as result of this change

 - Use 'A', 'O', and 'R' inline assembly format flags, which allows
   recent Clang compilers to generate better FPU code

 - Rework uaccess code so it reads better and generates more efficient
   code

 - Cleanup futex inline assembly code

 - Disable KMSAN instrumention for futex inline assemblies, which
   contain dereferenced user pointers. Otherwise, shadows for the user
   pointers would be accessed

 - PFs which are not initially configured but in standby create only a
   single-function PCI domain. If they are configured later on, sibling
   PFs and their child VFs will not be added to their PCI domain
   breaking SR-IOV expectations.

   Fix that by allowing initially configured but in standby PFs create
   multi-function PCI domains

 - Add '-std=gnu11' to decompressor and purgatory CFLAGS to avoid
   compile errors caused by kernel's own definitions of 'bool', 'false',
   and 'true' conflicting with the C23 reserved keywords

 - Fix sclp subsystem failure when a sclp console is not present

 - Fix misuse of non-NULL terminated strings in vmlogrdr driver

 - Various other small improvements, cleanups and fixes

* tag 's390-6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (53 commits)
  s390/vmlogrdr: Use array instead of string initializer
  s390/vmlogrdr: Use internal_name for error messages
  s390/sclp: Initialize sclp subsystem via arch_cpu_finalize_init()
  s390/tools: Use array instead of string initializer
  s390/vmem: Fix null-pointer-arithmetic warning in vmem_map_init()
  s390: Add '-std=gnu11' to decompressor and purgatory CFLAGS
  s390/bitops: Use correct constraint for arch_test_bit() inline assembly
  s390/pci: Fix SR-IOV for PFs initially in standby
  s390/futex: Avoid KMSAN instrumention for user pointers
  s390/uaccess: Rename get_put_user_noinstr_attributes to uaccess_kmsan_or_inline
  s390/futex: Cleanup futex_atomic_cmpxchg_inatomic()
  s390/futex: Generate futex atomic op functions
  s390/uaccess: Remove INLINE_COPY_FROM_USER and INLINE_COPY_TO_USER
  s390/uaccess: Use asm goto for put_user()/get_user()
  s390/uaccess: Remove usage of the oac specifier
  s390/uaccess: Replace EX_TABLE_UA_LOAD_MEM exception handling
  s390/uaccess: Cleanup noinstr __put_user()/__get_user() inline assembly constraints
  s390/uaccess: Remove __put_user_fn()/__get_user_fn() wrappers
  s390/uaccess: Move put_user() / __put_user() close to put_user() asm code
  s390/uaccess: Use asm goto for __mvc_kernel_nofault()
  ...

1 files changed, 77 insertions, 26 deletions

diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c
index 7617aa2d2f7e..aa096ef68e8c 100644
--- a/arch/s390/boot/physmem_info.c
+++ b/arch/s390/boot/physmem_info.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt) "physmem: " fmt
 #include <linux/processor.h>
 #include <linux/errno.h>
 #include <linux/init.h>
@@ -28,7 +29,7 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n)
 		return &physmem_info.online[n];
 	if (unlikely(!physmem_info.online_extended)) {
 		physmem_info.online_extended = (struct physmem_range *)physmem_alloc_range(
-			RR_MEM_DETECT_EXTENDED, ENTRIES_EXTENDED_MAX, sizeof(long), 0,
+			RR_MEM_DETECT_EXT, ENTRIES_EXTENDED_MAX, sizeof(long), 0,
 			physmem_alloc_pos, true);
 	}
 	return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES];
@@ -207,11 +208,16 @@ unsigned long detect_max_physmem_end(void)
 		max_physmem_end = search_mem_end();
 		physmem_info.info_source = MEM_DETECT_BIN_SEARCH;
 	}
+	boot_debug("Max physical memory: 0x%016lx (info source: %s)\n", max_physmem_end,
+		   get_physmem_info_source());
 	return max_physmem_end;
 }
 
 void detect_physmem_online_ranges(unsigned long max_physmem_end)
 {
+	unsigned long start, end;
+	int i;
+
 	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) {
@@ -226,12 +232,16 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end)
 	} else if (max_physmem_end) {
 		add_physmem_online_range(0, max_physmem_end);
 	}
+	boot_debug("Online memory ranges (info source: %s):\n", get_physmem_info_source());
+	for_each_physmem_online_range(i, &start, &end)
+		boot_debug(" online [%d]:   0x%016lx-0x%016lx\n", i, start, end);
 }
 
 void physmem_set_usable_limit(unsigned long limit)
 {
 	physmem_info.usable = limit;
 	physmem_alloc_pos = limit;
+	boot_debug("Usable memory limit: 0x%016lx\n", limit);
 }
 
 static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max)
@@ -241,38 +251,47 @@ static void die_oom(unsigned long size, unsigned long align, unsigned long min,
 	enum reserved_range_type t;
 	int i;
 
-	boot_printk("Linux version %s\n", kernel_version);
+	boot_emerg("Linux version %s\n", kernel_version);
 	if (!is_prot_virt_guest() && early_command_line[0])
-		boot_printk("Kernel command line: %s\n", early_command_line);
-	boot_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n",
-		    size, align, min, max);
-	boot_printk("Reserved memory ranges:\n");
+		boot_emerg("Kernel command line: %s\n", early_command_line);
+	boot_emerg("Out of memory allocating %lu bytes 0x%lx aligned in range %lx:%lx\n",
+		   size, align, min, max);
+	boot_emerg("Reserved memory ranges:\n");
 	for_each_physmem_reserved_range(t, range, &start, &end) {
-		boot_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t));
+		boot_emerg("%016lx %016lx %s\n", start, end, get_rr_type_name(t));
 		total_reserved_mem += end - start;
 	}
-	boot_printk("Usable online memory ranges (info source: %s [%x]):\n",
-		    get_physmem_info_source(), physmem_info.info_source);
+	boot_emerg("Usable online memory ranges (info source: %s [%d]):\n",
+		   get_physmem_info_source(), physmem_info.info_source);
 	for_each_physmem_usable_range(i, &start, &end) {
-		boot_printk("%016lx %016lx\n", start, end);
+		boot_emerg("%016lx %016lx\n", start, end);
 		total_mem += end - start;
 	}
-	boot_printk("Usable online memory total: %lx Reserved: %lx Free: %lx\n",
-		    total_mem, total_reserved_mem,
-		    total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0);
+	boot_emerg("Usable online memory total: %lu Reserved: %lu Free: %lu\n",
+		   total_mem, total_reserved_mem,
+		   total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0);
 	print_stacktrace(current_frame_address());
-	boot_printk("\n\n -- System halted\n");
+	boot_emerg(" -- System halted\n");
 	disabled_wait();
 }
 
-void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
+static void _physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
 {
 	physmem_info.reserved[type].start = addr;
 	physmem_info.reserved[type].end = addr + size;
 }
 
+void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
+{
+	_physmem_reserve(type, addr, size);
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Reserve:", addr, addr + size,
+		   get_rr_type_name(type));
+}
+
 void physmem_free(enum reserved_range_type type)
 {
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Free:", physmem_info.reserved[type].start,
+		   physmem_info.reserved[type].end, get_rr_type_name(type));
 	physmem_info.reserved[type].start = 0;
 	physmem_info.reserved[type].end = 0;
 }
@@ -339,41 +358,73 @@ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long s
 	max = min(max, physmem_alloc_pos);
 	addr = __physmem_alloc_range(size, align, min, max, 0, NULL, die_on_oom);
 	if (addr)
-		physmem_reserve(type, addr, size);
+		_physmem_reserve(type, addr, size);
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Alloc range:", addr, addr + size,
+		   get_rr_type_name(type));
 	return addr;
 }
 
-unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size,
-				     unsigned long align)
+unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size,
+			    unsigned long align, bool die_on_oom)
 {
 	struct reserved_range *range = &physmem_info.reserved[type];
-	struct reserved_range *new_range;
+	struct reserved_range *new_range = NULL;
 	unsigned int ranges_left;
 	unsigned long addr;
 
 	addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges,
-				     &ranges_left, true);
+				     &ranges_left, die_on_oom);
+	if (!addr)
+		return 0;
 	/* if not a consecutive allocation of the same type or first allocation */
 	if (range->start != addr + size) {
 		if (range->end) {
-			physmem_alloc_pos = __physmem_alloc_range(
-				sizeof(struct reserved_range), 0, 0, physmem_alloc_pos,
-				physmem_alloc_ranges, &ranges_left, true);
-			new_range = (struct reserved_range *)physmem_alloc_pos;
+			addr = __physmem_alloc_range(sizeof(struct reserved_range), 0, 0,
+						     physmem_alloc_pos, physmem_alloc_ranges,
+						     &ranges_left, true);
+			new_range = (struct reserved_range *)addr;
+			addr = __physmem_alloc_range(size, align, 0, addr, ranges_left,
+						     &ranges_left, die_on_oom);
+			if (!addr)
+				return 0;
 			*new_range = *range;
 			range->chain = new_range;
-			addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos,
-						     ranges_left, &ranges_left, true);
 		}
 		range->end = addr + size;
 	}
+	if (type != RR_VMEM) {
+		boot_debug("%-14s 0x%016lx-0x%016lx %-20s align 0x%lx split %d\n", "Alloc topdown:",
+			   addr, addr + size, get_rr_type_name(type), align, !!new_range);
+	}
 	range->start = addr;
 	physmem_alloc_pos = addr;
 	physmem_alloc_ranges = ranges_left;
 	return addr;
 }
 
+unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size,
+				   unsigned long align)
+{
+	return physmem_alloc(type, size, align, true);
+}
+
 unsigned long get_physmem_alloc_pos(void)
 {
 	return physmem_alloc_pos;
 }
+
+void dump_physmem_reserved(void)
+{
+	struct reserved_range *range;
+	enum reserved_range_type t;
+	unsigned long start, end;
+
+	boot_debug("Reserved memory ranges:\n");
+	for_each_physmem_reserved_range(t, range, &start, &end) {
+		if (end) {
+			boot_debug("%-14s 0x%016lx-0x%016lx @%012lx chain %012lx\n",
+				   get_rr_type_name(t), start, end, (unsigned long)range,
+				   (unsigned long)range->chain);
+		}
+	}
+}