From 420f48f636b98fd685f44a3acc4c0a7c0840910d Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 14 Oct 2021 13:33:45 +0200 Subject: s390/setup: avoid reserving memory above identity mapping Such reserved memory region, if not cleaned up later causes problems when memblock_free_all() is called to release free pages to the buddy allocator and those reserved regions are carried over to reserve_bootmem_region() which marks the pages as PageReserved. Instead use memblock_set_current_limit() to make sure memblock allocations do not go over identity mapping (which could happen when "mem=" option is used or during kdump). Cc: stable@vger.kernel.org Fixes: 73045a08cf55 ("s390: unify identity mapping limits handling") Reported-by: Gerald Schaefer Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/setup.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 40405f2304f1..30aba0f21e85 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -637,14 +637,6 @@ static struct notifier_block kdump_mem_nb = { #endif -/* - * Make sure that the area above identity mapping is protected - */ -static void __init reserve_above_ident_map(void) -{ - memblock_reserve(ident_map_size, ULONG_MAX); -} - /* * Reserve memory for kdump kernel to be loaded with kexec */ @@ -999,11 +991,11 @@ void __init setup_arch(char **cmdline_p) setup_control_program_code(); /* Do some memory reservations *before* memory is added to memblock */ - reserve_above_ident_map(); reserve_kernel(); reserve_initrd(); reserve_certificate_list(); reserve_mem_detect_info(); + memblock_set_current_limit(ident_map_size); memblock_allow_resize(); /* Get information about *all* installed memory */ -- cgit v1.2.3 From 5dbc4cb4667457b0c53bcd7bff11500b3c362975 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 14 Oct 2021 13:38:17 +0200 Subject: s390/setup: avoid using memblock_enforce_memory_limit There is a difference in how architectures treat "mem=" option. For some that is an amount of online memory, for s390 and x86 this is the limiting max address. Some memblock api like memblock_enforce_memory_limit() take limit argument and explicitly treat it as the size of online memory, and use __find_max_addr to convert it to an actual max address. Current s390 usage: memblock_enforce_memory_limit(memblock_end_of_DRAM()); yields different results depending on presence of memory holes (offline memory blocks in between online memory). If there are no memory holes limit == max_addr in memblock_enforce_memory_limit() and it does trim online memory and reserved memory regions. With memory holes present it actually does nothing. Since we already use memblock_remove() explicitly to trim online memory regions to potential limit (think mem=, kdump, addressing limits, etc.) drop the usage of memblock_enforce_memory_limit() altogether. Trimming reserved regions should not be required, since we now use memblock_set_current_limit() to limit allocations and any explicit memory reservations above the limit is an actual problem we should not hide. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/setup.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 30aba0f21e85..349d24df37b8 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -818,9 +818,6 @@ static void __init setup_memory(void) storage_key_init_range(start, end); psw_set_key(PAGE_DEFAULT_KEY); - - /* Only cosmetics */ - memblock_enforce_memory_limit(memblock_end_of_DRAM()); } static void __init relocate_amode31_section(void) -- cgit v1.2.3 From 6ad5f024d1f5612b9e39ced9f1add6e8121a7afb Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 14 Oct 2021 13:45:35 +0200 Subject: s390/setup: re-arrange memblock setup - Avoid using ULONG_MAX in memblock_remove, it has no functional change but makes memblock_dbg output a range which makes sense. - Actually finish memblock memory setup before doing amode31/cr/uv setup. - Move memblock_dump_all() debug output after memblock memory setup is complete. This gives us final "memory" regions if they were trimmed due to addressing limits and still "physmem" regions as original info which came from mem_detect. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/setup.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 349d24df37b8..225ab2d0a4c6 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -606,7 +606,7 @@ static void __init setup_resources(void) static void __init setup_memory_end(void) { - memblock_remove(ident_map_size, ULONG_MAX); + memblock_remove(ident_map_size, PHYS_ADDR_MAX - ident_map_size); max_pfn = max_low_pfn = PFN_DOWN(ident_map_size); pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20); } @@ -777,7 +777,6 @@ static void __init memblock_add_mem_detect_info(void) } memblock_set_bottom_up(false); memblock_set_node(0, ULONG_MAX, &memblock.memory, 0); - memblock_dump_all(); } /* @@ -999,13 +998,13 @@ void __init setup_arch(char **cmdline_p) memblock_add_mem_detect_info(); free_mem_detect_info(); + setup_memory_end(); + memblock_dump_all(); + setup_memory(); relocate_amode31_section(); setup_cr(); - setup_uv(); - setup_memory_end(); - setup_memory(); dma_contiguous_reserve(ident_map_size); vmcp_cma_reserve(); if (MACHINE_HAS_EDAT2) -- cgit v1.2.3 From 7b737adc10d269e7fdf714ae2caa2281b6a801cf Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 8 Nov 2021 01:21:11 +0900 Subject: s390/vdso: remove -nostdlib compiler flag The -nostdlib option requests the compiler to not use the standard system startup files or libraries when linking. It is effective only when $(CC) is used as a linker driver. Since commit 2b2a25845d53 ("s390/vdso: Use $(LD) instead of $(CC) to link vDSO"), $(LD) is directly used, hence -nostdlib is unneeded. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20211107162111.323701-1-masahiroy@kernel.org Signed-off-by: Heiko Carstens --- arch/s390/kernel/vdso32/Makefile | 2 +- arch/s390/kernel/vdso64/Makefile | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index e3e6ac5686df..245bddfe9bc0 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -22,7 +22,7 @@ KBUILD_AFLAGS_32 += -m31 -s KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -LDFLAGS_vdso32.so.dbg += -fPIC -shared -nostdlib -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 6568de236701..e7d911780935 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -25,7 +25,7 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin -ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \ +ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) -- cgit v1.2.3 From 00b55eaf45549ce26424224d069a091c7e5d8bac Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Thu, 11 Nov 2021 10:58:26 +0100 Subject: s390/vdso: filter out -mstack-guard and -mstack-size When CONFIG_VMAP_STACK is disabled, the user can enable CONFIG_STACK_CHECK, which adds a stack overflow check to each C function in the kernel. This is also done for functions in the vdso page. These functions are run in user context and user stack sizes are usually different to what the kernel uses. This might trigger the stack check although the stack size is valid. Therefore filter the -mstack-guard and -mstack-size flags when compiling vdso C files. Cc: stable@kernel.org # 5.10+ Fixes: 4bff8cb54502 ("s390: convert to GENERIC_VDSO") Reported-by: Janosch Frank Signed-off-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens --- arch/s390/Makefile | 10 ++++++---- arch/s390/kernel/vdso64/Makefile | 5 +++-- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 69c45f600273..609e3697324b 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -77,10 +77,12 @@ KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y) KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y) ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),) -cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE) -ifeq ($(call cc-option,-mstack-size=8192),) -cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD) -endif + CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE) + ifeq ($(call cc-option,-mstack-size=8192),) + CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD) + endif + export CC_FLAGS_CHECK_STACK + cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK) endif ifdef CONFIG_EXPOLINE diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index e7d911780935..9e2b95a222a9 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -8,8 +8,9 @@ ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT include $(srctree)/lib/vdso/Makefile obj-vdso64 = vdso_user_wrapper.o note.o obj-cvdso64 = vdso64_generic.o getcpu.o -CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) -CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) +VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK) +CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE) +CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE) # Build rules -- cgit v1.2.3 From 6c122360cf2f4c5a856fcbd79b4485b7baec942a Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Mon, 1 Nov 2021 14:38:18 +0100 Subject: s390: wire up sys_futex_waitv system call Tested with futex kselftests. Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/syscalls/syscall.tbl | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index df5261e5cfe1..ed9c5c2eafad 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv -- cgit v1.2.3 From 3b90954419d4c05651de9cce6d7632bcf6977678 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Mon, 15 Nov 2021 07:40:25 +0100 Subject: s390/dump: fix copying to user-space of swapped kdump oldmem This commit fixes a bug introduced by commit e9e7870f90e3 ("s390/dump: introduce boot data 'oldmem_data'"). OLDMEM_BASE was mistakenly replaced by oldmem_data.size instead of oldmem_data.start. This bug caused the following error during kdump: kdump.sh[878]: No program header covering vaddr 0x3434f5245found kexec bug? Fixes: e9e7870f90e3 ("s390/dump: introduce boot data 'oldmem_data'") Cc: stable@vger.kernel.org # 5.15+ Signed-off-by: Alexander Egorenkov Reviewed-by: Marc Hartmayer Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens --- arch/s390/kernel/crash_dump.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index d72a6df058d7..785d54c9350c 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -191,8 +191,8 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count) return rc; } else { /* Check for swapped kdump oldmem areas */ - if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) { - from -= oldmem_data.size; + if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) { + from -= oldmem_data.start; len = min(count, oldmem_data.size - from); } else if (oldmem_data.start && from < oldmem_data.size) { len = min(count, oldmem_data.size - from); -- cgit v1.2.3 From 20c76e242e7025bd355619ba67beb243ba1a1e95 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 16 Nov 2021 11:06:38 +0100 Subject: s390/kexec: fix return code handling kexec_file_add_ipl_report ignores that ipl_report_finish may fail and can return an error pointer instead of a valid pointer. Fix this and simplify by returning NULL in case of an error and let the only caller handle this case. Fixes: 99feaa717e55 ("s390/kexec_file: Create ipl report and pass to next kernel") Signed-off-by: Heiko Carstens --- arch/s390/kernel/ipl.c | 3 ++- arch/s390/kernel/machine_kexec_file.c | 8 +++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'arch/s390/kernel') diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index e2cc35775b99..5ad1dde23dc5 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2156,7 +2156,7 @@ void *ipl_report_finish(struct ipl_report *report) buf = vzalloc(report->size); if (!buf) - return ERR_PTR(-ENOMEM); + goto out; ptr = buf; memcpy(ptr, report->ipib, report->ipib->hdr.len); @@ -2195,6 +2195,7 @@ void *ipl_report_finish(struct ipl_report *report) } BUG_ON(ptr > buf + report->size); +out: return buf; } diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 528edff085d9..f0200b503f94 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -170,6 +170,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, struct kexec_buf buf; unsigned long addr; void *ptr, *end; + int ret; buf.image = image; @@ -199,7 +200,10 @@ static int kexec_file_add_ipl_report(struct kimage *image, ptr += len; } + ret = -ENOMEM; buf.buffer = ipl_report_finish(data->report); + if (!buf.buffer) + goto out; buf.bufsz = data->report->size; buf.memsz = buf.bufsz; @@ -209,7 +213,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; - return kexec_add_buffer(&buf); + ret = kexec_add_buffer(&buf); +out: + return ret; } void *kexec_file_add_components(struct kimage *image, -- cgit v1.2.3 From 4aa9340584e37debef06fa99b56d064beb723891 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 16 Nov 2021 11:31:01 +0800 Subject: s390/kexec: fix memory leak of ipl report buffer unreferenced object 0x38000195000 (size 4096): comm "kexec", pid 8548, jiffies 4294953647 (age 32443.270s) hex dump (first 32 bytes): 00 00 00 c8 20 00 00 00 00 00 00 c0 02 80 00 00 .... ........... 40 40 40 40 40 40 40 40 00 00 00 00 00 00 00 00 @@@@@@@@........ backtrace: [<0000000011a2f199>] __vmalloc_node_range+0xc0/0x140 [<0000000081fa2752>] vzalloc+0x5a/0x70 [<0000000063a4c92d>] ipl_report_finish+0x2c/0x180 [<00000000553304da>] kexec_file_add_ipl_report+0xf4/0x150 [<00000000862d033f>] kexec_file_add_components+0x124/0x160 [<000000000d2717bb>] arch_kexec_kernel_image_load+0x62/0x90 [<000000002e0373b6>] kimage_file_alloc_init+0x1aa/0x2e0 [<0000000060f2d14f>] __do_sys_kexec_file_load+0x17c/0x2c0 [<000000008c86fe5a>] __s390x_sys_kexec_file_load+0x40/0x50 [<000000001fdb9dac>] __do_syscall+0x1bc/0x1f0 [<000000003ee4258d>] system_call+0x78/0xa0 Signed-off-by: Baoquan He Reviewed-by: Philipp Rudo Fixes: 99feaa717e55 ("s390/kexec_file: Create ipl report and pass to next kernel") Cc: # v5.2: 20c76e242e70: s390/kexec: fix return code handling Cc: # v5.2 Link: https://lore.kernel.org/r/20211116033101.GD21646@MiWiFi-R3L-srv Signed-off-by: Heiko Carstens --- arch/s390/include/asm/kexec.h | 6 ++++++ arch/s390/kernel/machine_kexec_file.c | 10 ++++++++++ 2 files changed, 16 insertions(+) (limited to 'arch/s390/kernel') diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index ea398a05f643..7f3c9ac34bd8 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -74,6 +74,12 @@ void *kexec_file_add_components(struct kimage *image, int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, unsigned long addr); +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *ipl_buf; +}; + extern const struct kexec_file_ops s390_kexec_image_ops; extern const struct kexec_file_ops s390_kexec_elf_ops; diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index f0200b503f94..9975ad200d74 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -206,6 +207,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, goto out; buf.bufsz = data->report->size; buf.memsz = buf.bufsz; + image->arch.ipl_buf = buf.buffer; data->memsz += buf.memsz; @@ -328,3 +330,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, } return 0; } + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->arch.ipl_buf); + image->arch.ipl_buf = NULL; + + return kexec_image_post_load_cleanup_default(image); +} -- cgit v1.2.3