s390/boot: rework decompressor reserved tracking

Currently several approaches for finding unused memory in decompressor
are utilized. While "safe_addr" grows towards higher addresses, vmem
code allocates paging structures top down. The former requires careful
ordering. In addition to that ipl report handling code verifies potential
intersections with secure boot certificates on its own. Neither of two
approaches are memory holes aware and consistent with each other in low
memory conditions.

To solve that, existing approaches are generalized and combined
together, as well as online memory ranges are now taken into
consideration.

physmem_info has been extended to contain reserved memory ranges. New
set of functions allow to handle reserves and find unused memory.
All reserves and memory allocations are "typed". In case of out of
memory condition decompressor fails with detailed info on current
reserved ranges and usable online memory.

Linux version 6.2.0 ...
Kernel command line: ... mem=100M
Our of memory allocating 100000 bytes 100000 aligned in range 0:5800000
Reserved memory ranges:
0000000000000000 0000000003e33000 DECOMPRESSOR
0000000003f00000 00000000057648a3 INITRD
00000000063e0000 00000000063e8000 VMEM
00000000063eb000 00000000063f4000 VMEM
00000000063f7800 0000000006400000 VMEM
0000000005800000 0000000006300000 KASAN
Usable online memory ranges (info source: sclp read info [3]):
0000000000000000 0000000006400000
Usable online memory total: 6400000 Reserved: 61b10a3 Free: 24ef5d
Call Trace:
(sp:000000000002bd58 [<0000000000012a70>] physmem_alloc_top_down+0x60/0x14c)
 sp:000000000002bdc8 [<0000000000013756>] _pa+0x56/0x6a
 sp:000000000002bdf0 [<0000000000013bcc>] pgtable_populate+0x45c/0x65e
 sp:000000000002be90 [<00000000000140aa>] setup_vmem+0x2da/0x424
 sp:000000000002bec8 [<0000000000011c20>] startup_kernel+0x428/0x8b4
 sp:000000000002bf60 [<00000000000100f4>] startup_normal+0xd4/0xd4

physmem_alloc_range allows to find free memory in specified range. It
should be used for one time allocations only like finding position for
amode31 and vmlinux.
physmem_alloc_top_down can be used just like physmem_alloc_range, but
it also allows multiple allocations per type and tries to merge sequential
allocations together. Which is useful for paging structures allocations.
If sequential allocations cannot be merged together they are "chained",
allowing easy per type reserved ranges enumeration and migration to
memblock later. Extra "struct reserved_range" allocated for chaining are
not tracked or reserved but rely on the fact that both
physmem_alloc_range and physmem_alloc_top_down search for free memory
only below current top down allocator position. All reserved ranges
should be transferred to memblock before memblock allocations are
enabled.

The startup code has been reordered to delay any memory allocations until
online memory ranges are detected and occupied memory ranges are marked as
reserved to be excluded from follow-up allocations.
Ipl report certificates are a special case, ipl report certificates list
is checked together with other memory reserves until certificates are
saved elsewhere.
KASAN required memory for shadow memory allocation and mapping is reserved
as 1 large chunk which is later passed to KASAN early initialization code.

Acked-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

1 files changed, 160 insertions, 28 deletions

diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c
index dc2e4d0abfab..4ee9b7381142 100644
--- a/arch/s390/boot/physmem_info.c
+++ b/arch/s390/boot/physmem_info.c
@@ -1,16 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/processor.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <asm/setup.h>
-#include <asm/processor.h>
-#include <asm/sclp.h>
-#include <asm/sections.h>
 #include <asm/physmem_info.h>
+#include <asm/stacktrace.h>
+#include <asm/boot_data.h>
 #include <asm/sparsemem.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sclp.h>
+#include <asm/uv.h>
 #include "decompressor.h"
 #include "boot.h"
 
 struct physmem_info __bootdata(physmem_info);
+static unsigned int physmem_alloc_ranges;
+static unsigned long physmem_alloc_pos;
 
 /* up to 256 storage elements, 1020 subincrements each */
 #define ENTRIES_EXTENDED_MAX						       \
@@ -20,6 +25,11 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n)
 {
 	if (n < MEM_INLINED_ENTRIES)
 		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,
+			physmem_alloc_pos, true);
+	}
 	return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES];
 }
 
@@ -143,49 +153,171 @@ static unsigned long search_mem_end(void)
 	return (offset + 1) << 20;
 }
 
-unsigned long detect_memory(unsigned long *safe_addr)
+unsigned long detect_max_physmem_end(void)
 {
 	unsigned long max_physmem_end = 0;
 
-	sclp_early_get_memsize(&max_physmem_end);
-	physmem_info.online_extended = (struct physmem_range *)ALIGN(*safe_addr, sizeof(u64));
+	if (!sclp_early_get_memsize(&max_physmem_end)) {
+		physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
+	} else {
+		max_physmem_end = search_mem_end();
+		physmem_info.info_source = MEM_DETECT_BIN_SEARCH;
+	}
+	return max_physmem_end;
+}
 
+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 (!diag260()) {
 		physmem_info.info_source = MEM_DETECT_DIAG260;
-		max_physmem_end = max_physmem_end ?: get_physmem_usable_end();
 	} else if (max_physmem_end) {
 		add_physmem_online_range(0, max_physmem_end);
-		physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO;
-	} else {
-		max_physmem_end = search_mem_end();
-		add_physmem_online_range(0, max_physmem_end);
-		physmem_info.info_source = MEM_DETECT_BIN_SEARCH;
 	}
+}
 
-	if (physmem_info.range_count > MEM_INLINED_ENTRIES) {
-		*safe_addr += (physmem_info.range_count - MEM_INLINED_ENTRIES) *
-			      sizeof(struct physmem_range);
+void physmem_set_usable_limit(unsigned long limit)
+{
+	physmem_info.usable = limit;
+	physmem_alloc_pos = limit;
+}
+
+static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max)
+{
+	unsigned long start, end, total_mem = 0, total_reserved_mem = 0;
+	struct reserved_range *range;
+	enum reserved_range_type t;
+	int i;
+
+	decompressor_printk("Linux version %s\n", kernel_version);
+	if (!is_prot_virt_guest() && early_command_line[0])
+		decompressor_printk("Kernel command line: %s\n", early_command_line);
+	decompressor_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n",
+			    size, align, min, max);
+	decompressor_printk("Reserved memory ranges:\n");
+	for_each_physmem_reserved_range(t, range, &start, &end) {
+		decompressor_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t));
+		total_reserved_mem += end - start;
+	}
+	decompressor_printk("Usable online memory ranges (info source: %s [%x]):\n",
+			    get_physmem_info_source(), physmem_info.info_source);
+	for_each_physmem_usable_range(i, &start, &end) {
+		decompressor_printk("%016lx %016lx\n", start, end);
+		total_mem += end - start;
 	}
+	decompressor_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);
+	print_stacktrace(current_frame_address());
+	sclp_early_printk("\n\n -- System halted\n");
+	disabled_wait();
+}
 
-	return max_physmem_end;
+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_set_usable_limit(unsigned long limit)
+void physmem_free(enum reserved_range_type type)
 {
-	struct physmem_range *range;
-	int i;
+	physmem_info.reserved[type].start = 0;
+	physmem_info.reserved[type].end = 0;
+}
 
-	/* make sure mem_detect.usable ends up within online memory block */
-	for (i = 0; i < physmem_info.range_count; i++) {
-		range = __get_physmem_range_ptr(i);
-		if (range->start >= limit)
-			break;
-		if (range->end >= limit) {
-			physmem_info.usable = limit;
+static bool __physmem_alloc_intersects(unsigned long addr, unsigned long size,
+				       unsigned long *intersection_start)
+{
+	unsigned long res_addr, res_size;
+	int t;
+
+	for (t = 0; t < RR_MAX; t++) {
+		if (!get_physmem_reserved(t, &res_addr, &res_size))
+			continue;
+		if (intersects(addr, size, res_addr, res_size)) {
+			*intersection_start = res_addr;
+			return true;
+		}
+	}
+	return ipl_report_certs_intersects(addr, size, intersection_start);
+}
+
+static unsigned long __physmem_alloc_range(unsigned long size, unsigned long align,
+					   unsigned long min, unsigned long max,
+					   unsigned int from_ranges, unsigned int *ranges_left,
+					   bool die_on_oom)
+{
+	unsigned int nranges = from_ranges ?: physmem_info.range_count;
+	unsigned long range_start, range_end;
+	unsigned long intersection_start;
+	unsigned long addr, pos = max;
+
+	align = max(align, 8UL);
+	while (nranges) {
+		__get_physmem_range(nranges - 1, &range_start, &range_end, false);
+		pos = min(range_end, pos);
+
+		if (round_up(min, align) + size > pos)
 			break;
+		addr = round_down(pos - size, align);
+		if (range_start > addr) {
+			nranges--;
+			continue;
+		}
+		if (__physmem_alloc_intersects(addr, size, &intersection_start)) {
+			pos = intersection_start;
+			continue;
+		}
+
+		if (ranges_left)
+			*ranges_left = nranges;
+		return addr;
+	}
+	if (die_on_oom)
+		die_oom(size, align, min, max);
+	return 0;
+}
+
+unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size,
+				  unsigned long align, unsigned long min, unsigned long max,
+				  bool die_on_oom)
+{
+	unsigned long addr;
+
+	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);
+	return addr;
+}
+
+unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size,
+				     unsigned long align)
+{
+	struct reserved_range *range = &physmem_info.reserved[type];
+	struct reserved_range *new_range;
+	unsigned int ranges_left;
+	unsigned long addr;
+
+	addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges,
+				     &ranges_left, true);
+	/* 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;
+			*new_range = *range;
+			range->chain = new_range;
+			addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos,
+						     ranges_left, &ranges_left, true);
 		}
-		physmem_info.usable = range->end;
+		range->end = addr + size;
 	}
+	range->start = addr;
+	physmem_alloc_pos = addr;
+	physmem_alloc_ranges = ranges_left;
+	return addr;
 }