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, 25 insertions, 5 deletions

diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index d39895d5796e..2b4048106418 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -8,6 +8,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/physmem_info.h>
+
 struct machine_info {
 	unsigned char has_edat1 : 1;
 	unsigned char has_edat2 : 1;
@@ -33,21 +35,34 @@ struct vmlinux_info {
 };
 
 void startup_kernel(void);
-unsigned long detect_memory(unsigned long *safe_addr);
+unsigned long detect_max_physmem_end(void);
+void detect_physmem_online_ranges(unsigned long max_physmem_end);
 void physmem_set_usable_limit(unsigned long limit);
+void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size);
+void physmem_free(enum reserved_range_type type);
+/* for continuous/multiple allocations per type */
+unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size,
+				     unsigned long align);
+/* for single allocations, 1 per type */
+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);
+bool ipl_report_certs_intersects(unsigned long addr, unsigned long size,
+				 unsigned long *intersection_start);
 bool is_ipl_block_dump(void);
 void store_ipl_parmblock(void);
-unsigned long read_ipl_report(unsigned long safe_addr);
+int read_ipl_report(void);
+void save_ipl_cert_comp_list(void);
 void setup_boot_command_line(void);
 void parse_boot_command_line(void);
 void verify_facilities(void);
 void print_missing_facilities(void);
 void sclp_early_setup_buffer(void);
 void print_pgm_check_info(void);
-unsigned long get_random_base(unsigned long safe_addr);
+unsigned long get_random_base(void);
 void setup_vmem(unsigned long asce_limit);
-unsigned long vmem_estimate_memory_needs(unsigned long online_mem_total);
 void __printf(1, 2) decompressor_printk(const char *fmt, ...);
+void print_stacktrace(unsigned long sp);
 void error(char *m);
 
 extern struct machine_info machine;
@@ -62,7 +77,7 @@ extern char __boot_data_start[], __boot_data_end[];
 extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
 extern char _decompressor_syms_start[], _decompressor_syms_end[];
 extern char _stack_start[], _stack_end[];
-extern char _end[];
+extern char _end[], _decompressor_end[];
 extern unsigned char _compressed_start[];
 extern unsigned char _compressed_end[];
 extern struct vmlinux_info _vmlinux_info;
@@ -70,5 +85,10 @@ extern struct vmlinux_info _vmlinux_info;
 
 #define __abs_lowcore_pa(x)	(((unsigned long)(x) - __abs_lowcore) % sizeof(struct lowcore))
 
+static inline bool intersects(unsigned long addr0, unsigned long size0,
+			      unsigned long addr1, unsigned long size1)
+{
+	return addr0 + size0 > addr1 && addr1 + size1 > addr0;
+}
 #endif /* __ASSEMBLY__ */
 #endif /* BOOT_BOOT_H */