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, 21 insertions, 55 deletions

diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f909a2dc8a5a..d25425b8d0c0 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -148,13 +148,8 @@ static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31;
 int __bootdata(noexec_disabled);
 unsigned long __bootdata(ident_map_size);
 struct physmem_info __bootdata(physmem_info);
-struct initrd_data __bootdata(initrd_data);
-unsigned long __bootdata(pgalloc_pos);
-unsigned long __bootdata(pgalloc_end);
-unsigned long __bootdata(pgalloc_low);
 
 unsigned long __bootdata_preserved(__kaslr_offset);
-unsigned long __bootdata(__amode31_base);
 unsigned int __bootdata_preserved(zlib_dfltcc_support);
 EXPORT_SYMBOL(zlib_dfltcc_support);
 u64 __bootdata_preserved(stfle_fac_list[16]);
@@ -635,7 +630,11 @@ static struct notifier_block kdump_mem_nb = {
  */
 static void __init reserve_pgtables(void)
 {
-	memblock_reserve(pgalloc_pos, pgalloc_end - pgalloc_pos);
+	unsigned long start, end;
+	struct reserved_range *range;
+
+	for_each_physmem_reserved_type_range(RR_VMEM, range, &start, &end)
+		memblock_reserve(start, end - start);
 }
 
 /*
@@ -712,13 +711,13 @@ static void __init reserve_crashkernel(void)
  */
 static void __init reserve_initrd(void)
 {
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (!initrd_data.start || !initrd_data.size)
+	unsigned long addr, size;
+
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD) || !get_physmem_reserved(RR_INITRD, &addr, &size))
 		return;
-	initrd_start = (unsigned long)__va(initrd_data.start);
-	initrd_end = initrd_start + initrd_data.size;
-	memblock_reserve(initrd_data.start, initrd_data.size);
-#endif
+	initrd_start = (unsigned long)__va(addr);
+	initrd_end = initrd_start + size;
+	memblock_reserve(addr, size);
 }
 
 /*
@@ -732,35 +731,18 @@ static void __init reserve_certificate_list(void)
 
 static void __init reserve_physmem_info(void)
 {
-	unsigned long start, size;
+	unsigned long addr, size;
 
-	get_physmem_reserved(&start, &size);
-	if (size)
-		memblock_reserve(start, size);
+	if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+		memblock_reserve(addr, size);
 }
 
 static void __init free_physmem_info(void)
 {
-	unsigned long start, size;
+	unsigned long addr, size;
 
-	get_physmem_reserved(&start, &size);
-	if (size)
-		memblock_phys_free(start, size);
-}
-
-static const char * __init get_mem_info_source(void)
-{
-	switch (physmem_info.info_source) {
-	case MEM_DETECT_SCLP_STOR_INFO:
-		return "sclp storage info";
-	case MEM_DETECT_DIAG260:
-		return "diag260";
-	case MEM_DETECT_SCLP_READ_INFO:
-		return "sclp read info";
-	case MEM_DETECT_BIN_SEARCH:
-		return "binary search";
-	}
-	return "none";
+	if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+		memblock_phys_free(addr, size);
 }
 
 static void __init memblock_add_physmem_info(void)
@@ -769,7 +751,7 @@ static void __init memblock_add_physmem_info(void)
 	int i;
 
 	pr_debug("physmem info source: %s (%hhd)\n",
-		 get_mem_info_source(), physmem_info.info_source);
+		 get_physmem_info_source(), physmem_info.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
 	for_each_physmem_usable_range(i, &start, &end)
@@ -781,21 +763,6 @@ static void __init memblock_add_physmem_info(void)
 }
 
 /*
- * Check for initrd being in usable memory
- */
-static void __init check_initrd(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	if (initrd_data.start && initrd_data.size &&
-	    !memblock_is_region_memory(initrd_data.start, initrd_data.size)) {
-		pr_err("The initial RAM disk does not fit into the memory\n");
-		memblock_phys_free(initrd_data.start, initrd_data.size);
-		initrd_start = initrd_end = 0;
-	}
-#endif
-}
-
-/*
  * Reserve memory used for lowcore/command line/kernel image.
  */
 static void __init reserve_kernel(void)
@@ -803,7 +770,7 @@ static void __init reserve_kernel(void)
 	memblock_reserve(0, STARTUP_NORMAL_OFFSET);
 	memblock_reserve(OLDMEM_BASE, sizeof(unsigned long));
 	memblock_reserve(OLDMEM_SIZE, sizeof(unsigned long));
-	memblock_reserve(__amode31_base, __eamode31 - __samode31);
+	memblock_reserve(physmem_info.reserved[RR_AMODE31].start, __eamode31 - __samode31);
 	memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP);
 	memblock_reserve(__pa(_stext), _end - _stext);
 }
@@ -825,13 +792,13 @@ static void __init setup_memory(void)
 static void __init relocate_amode31_section(void)
 {
 	unsigned long amode31_size = __eamode31 - __samode31;
-	long amode31_offset = __amode31_base - __samode31;
+	long amode31_offset = physmem_info.reserved[RR_AMODE31].start - __samode31;
 	long *ptr;
 
 	pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size);
 
 	/* Move original AMODE31 section to the new one */
-	memmove((void *)__amode31_base, (void *)__samode31, amode31_size);
+	memmove((void *)physmem_info.reserved[RR_AMODE31].start, (void *)__samode31, amode31_size);
 	/* Zero out the old AMODE31 section to catch invalid accesses within it */
 	memset((void *)__samode31, 0, amode31_size);
 
@@ -1017,7 +984,6 @@ void __init setup_arch(char **cmdline_p)
 	if (MACHINE_HAS_EDAT2)
 		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
 
-	check_initrd();
 	reserve_crashkernel();
 #ifdef CONFIG_CRASH_DUMP
 	/*