From 58498ee3e573dc03be651b6839dbdf865ae7ee38 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 9 Dec 2014 10:18:49 +0100 Subject: s390/ftrace: add code replacement sanity checks Always verify that the to be replaced code matches what we expect to see. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/ftrace.c | 95 ++++++++++++++++++++++++----------------------- 1 file changed, 49 insertions(+), 46 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index b86bb8823f15..3dabcae40e04 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -59,62 +59,65 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn insn; - unsigned short op; - void *from, *to; - size_t size; - - ftrace_generate_nop_insn(&insn); - size = sizeof(insn); - from = &insn; - to = (void *) rec->ip; - if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + struct ftrace_insn orig, new, old; + + if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - /* - * If we find a breakpoint instruction, a kprobe has been placed - * at the beginning of the function. We write the constant - * KPROBE_ON_FTRACE_NOP into the remaining four bytes of the original - * instruction so that the kprobes handler can execute a nop, if it - * reaches this breakpoint. - */ - if (op == BREAKPOINT_INSTRUCTION) { - size -= 2; - from += 2; - to += 2; - insn.disp = KPROBE_ON_FTRACE_NOP; + if (addr == MCOUNT_ADDR) { + /* Initial code replacement; we expect to see stg r14,8(r15) */ + orig.opc = 0xe3e0; + orig.disp = 0xf0080024; + ftrace_generate_nop_insn(&new); + } else if (old.opc == BREAKPOINT_INSTRUCTION) { + /* + * If we find a breakpoint instruction, a kprobe has been + * placed at the beginning of the function. We write the + * constant KPROBE_ON_FTRACE_NOP into the remaining four + * bytes of the original instruction so that the kprobes + * handler can execute a nop, if it reaches this breakpoint. + */ + new.opc = orig.opc = BREAKPOINT_INSTRUCTION; + orig.disp = KPROBE_ON_FTRACE_CALL; + new.disp = KPROBE_ON_FTRACE_NOP; + } else { + /* Replace ftrace call with a nop. */ + ftrace_generate_call_insn(&orig, rec->ip); + ftrace_generate_nop_insn(&new); } - if (probe_kernel_write(to, from, size)) + /* Verify that the to be replaced code matches what we expect. */ + if (memcmp(&orig, &old, sizeof(old))) + return -EINVAL; + if (probe_kernel_write((void *) rec->ip, &new, sizeof(new))) return -EPERM; return 0; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - struct ftrace_insn insn; - unsigned short op; - void *from, *to; - size_t size; - - ftrace_generate_call_insn(&insn, rec->ip); - size = sizeof(insn); - from = &insn; - to = (void *) rec->ip; - if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + struct ftrace_insn orig, new, old; + + if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; - /* - * If we find a breakpoint instruction, a kprobe has been placed - * at the beginning of the function. We write the constant - * KPROBE_ON_FTRACE_CALL into the remaining four bytes of the original - * instruction so that the kprobes handler can execute a brasl if it - * reaches this breakpoint. - */ - if (op == BREAKPOINT_INSTRUCTION) { - size -= 2; - from += 2; - to += 2; - insn.disp = KPROBE_ON_FTRACE_CALL; + if (old.opc == BREAKPOINT_INSTRUCTION) { + /* + * If we find a breakpoint instruction, a kprobe has been + * placed at the beginning of the function. We write the + * constant KPROBE_ON_FTRACE_CALL into the remaining four + * bytes of the original instruction so that the kprobes + * handler can execute a brasl if it reaches this breakpoint. + */ + new.opc = orig.opc = BREAKPOINT_INSTRUCTION; + orig.disp = KPROBE_ON_FTRACE_NOP; + new.disp = KPROBE_ON_FTRACE_CALL; + } else { + /* Replace nop with an ftrace call. */ + ftrace_generate_nop_insn(&orig); + ftrace_generate_call_insn(&new, rec->ip); } - if (probe_kernel_write(to, from, size)) + /* Verify that the to be replaced code matches what we expect. */ + if (memcmp(&orig, &old, sizeof(old))) + return -EINVAL; + if (probe_kernel_write((void *) rec->ip, &new, sizeof(new))) return -EPERM; return 0; } -- cgit v1.2.3 From eba8452525e3fd0b982f78365dea8bd2ce11a20a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 12 Dec 2014 12:46:35 +0100 Subject: s390/pci: add missing address space annotation Signed-off-by: Heiko Carstens --- arch/s390/pci/pci_mmio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 62c5ea6d8682..8aa271b3d1ad 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -55,7 +55,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, ret = get_pfn(mmio_addr, VM_WRITE, &pfn); if (ret) goto out; - io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); ret = -EFAULT; if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) @@ -96,7 +96,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, ret = get_pfn(mmio_addr, VM_READ, &pfn); if (ret) goto out; - io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); ret = -EFAULT; if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) -- cgit v1.2.3 From 8d1f211ebbdfd57843a52fa7efe34251530beec1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 12 Dec 2014 12:52:00 +0100 Subject: s390/disassembler: remove indentical initializer Remove one of the two identical initializer entries. Signed-off-by: Heiko Carstens --- arch/s390/kernel/dis.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index f3762937dd82..d46d0b0b2cda 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -226,7 +226,6 @@ static const struct s390_operand operands[] = [U16_32] = { 16, 32, 0 }, [J16_16] = { 16, 16, OPERAND_PCREL }, [J16_32] = { 16, 32, OPERAND_PCREL }, - [I16_32] = { 16, 32, OPERAND_SIGNED }, [I24_24] = { 24, 24, OPERAND_SIGNED }, [J32_16] = { 32, 16, OPERAND_PCREL }, [I32_16] = { 32, 16, OPERAND_SIGNED }, -- cgit v1.2.3 From 925dfc020a41ce484172a43b603437e58aecd1c1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 12 Dec 2014 13:04:21 +0100 Subject: s390/pgtable: add unsigned long casts Get rid of warnings like this one: warning: constant 0xffe0000000000000 is so big it is unsigned long Signed-off-by: Heiko Carstens --- arch/s390/mm/pgtable.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 601deb85d2a0..47cbca079740 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -527,7 +527,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 53) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY, - gaddr & 0xffe0000000000000)) + gaddr & 0xffe0000000000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } @@ -535,7 +535,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 42) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY, - gaddr & 0xfffffc0000000000)) + gaddr & 0xfffffc0000000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } @@ -543,7 +543,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) table += (gaddr >> 31) & 0x7ff; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY, - gaddr & 0xffffffff80000000)) + gaddr & 0xffffffff80000000UL)) return -ENOMEM; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); } -- cgit v1.2.3 From e0a50545480de0936ab867168d9bd086e56f465c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 12 Dec 2014 13:11:08 +0100 Subject: s390/signal: add sys_sigreturn and sys_rt_sigreturn declarations Get rid of sparse warnings like this one: arch/s390/kernel/signal.c:244:1: warning: symbol 'sys_sigreturn' was not declared. Should it be static? Signed-off-by: Heiko Carstens --- arch/s390/kernel/entry.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 8e61393c8275..834df047d35f 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -71,9 +71,11 @@ struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; +long sys_rt_sigreturn(void); +long sys_sigreturn(void); + long sys_s390_personality(unsigned int personality); long sys_s390_runtime_instr(int command, int signum); - long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t); long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t); #endif /* _ENTRY_H */ -- cgit v1.2.3 From 8ebd51a705c56520481f2b813790dc5afdb0a751 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Sat, 20 Dec 2014 13:27:49 +0100 Subject: s390/cio: idset.c: remove some unused functions Removes some functions that are not used anywhere: idset_clear() idset_sch_get_first() This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- drivers/s390/cio/idset.c | 20 -------------------- drivers/s390/cio/idset.h | 2 -- 2 files changed, 22 deletions(-) diff --git a/drivers/s390/cio/idset.c b/drivers/s390/cio/idset.c index 5a999084a229..b3e06a7b9480 100644 --- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -38,11 +38,6 @@ void idset_free(struct idset *set) vfree(set); } -void idset_clear(struct idset *set) -{ - memset(set->bitmap, 0, bitmap_size(set->num_ssid, set->num_id)); -} - void idset_fill(struct idset *set) { memset(set->bitmap, 0xff, bitmap_size(set->num_ssid, set->num_id)); @@ -103,21 +98,6 @@ int idset_sch_contains(struct idset *set, struct subchannel_id schid) return idset_contains(set, schid.ssid, schid.sch_no); } -int idset_sch_get_first(struct idset *set, struct subchannel_id *schid) -{ - int ssid = 0; - int id = 0; - int rc; - - rc = idset_get_first(set, &ssid, &id); - if (rc) { - init_subchannel_id(schid); - schid->ssid = ssid; - schid->sch_no = id; - } - return rc; -} - int idset_is_empty(struct idset *set) { return bitmap_empty(set->bitmap, set->num_ssid * set->num_id); diff --git a/drivers/s390/cio/idset.h b/drivers/s390/cio/idset.h index 06d3bc01bb09..22b58104683b 100644 --- a/drivers/s390/cio/idset.h +++ b/drivers/s390/cio/idset.h @@ -11,7 +11,6 @@ struct idset; void idset_free(struct idset *set); -void idset_clear(struct idset *set); void idset_fill(struct idset *set); struct idset *idset_sch_new(void); @@ -19,7 +18,6 @@ void idset_sch_add(struct idset *set, struct subchannel_id id); void idset_sch_del(struct idset *set, struct subchannel_id id); void idset_sch_del_subseq(struct idset *set, struct subchannel_id schid); int idset_sch_contains(struct idset *set, struct subchannel_id id); -int idset_sch_get_first(struct idset *set, struct subchannel_id *id); int idset_is_empty(struct idset *set); void idset_add_set(struct idset *to, struct idset *from); -- cgit v1.2.3 From 47523c983f55448c3a09cc3f1a885bf81cd422e3 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 22 Dec 2014 10:07:04 +0100 Subject: s390: keep Kconfig sorted Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 68b68d755fdf..e79c3eab40b9 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -66,6 +66,7 @@ config S390 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_SG_CHAIN select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH @@ -151,7 +152,6 @@ config S390 select TTY select VIRT_CPU_ACCOUNTING select VIRT_TO_BUS - select ARCH_HAS_SG_CHAIN config SCHED_OMIT_FRAME_POINTER def_bool y -- cgit v1.2.3 From fbf87dff6706d412fe69b8158f7ae415e5e7380b Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sat, 3 Jan 2015 17:29:07 +0800 Subject: s390/sclp: fix declaration of _sclp_print_early() _sclp_print_early() has return value: at present, return 0 for OK, 1 for failure. It returns '%r2', so use 'long' as return value (upper caller can check '%r2' directly). The related warning: CC arch/s390/boot/compressed/misc.o arch/s390/boot/compressed/misc.c:66:8: warning: type defaults to 'int' in declaration of '_sclp_print_early' [-Wimplicit-int] extern _sclp_print_early(const char *); ^ At present, _sclp_print_early() is only used by puts(), so can still remain its declaration in 'misc.c' file. [heiko.carstens@de.ibm.com]: move declaration to sclp.h header file Signed-off-by: Chen Gang Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/boot/compressed/misc.c | 3 +-- arch/s390/include/asm/sclp.h | 2 ++ 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 57cbaff1f397..42506b371b74 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -8,6 +8,7 @@ #include #include +#include #include #include "sizes.h" @@ -63,8 +64,6 @@ static unsigned long free_mem_end_ptr; #include "../../../../lib/decompress_unxz.c" #endif -extern _sclp_print_early(const char *); - static int puts(const char *s) { _sclp_print_early(s); diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 1aba89b53cb9..b6f8066789c1 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -68,4 +68,6 @@ void sclp_early_detect(void); int sclp_has_siif(void); unsigned int sclp_get_ibc(void); +long _sclp_print_early(const char *); + #endif /* _ASM_S390_SCLP_H */ -- cgit v1.2.3 From a7e75d434b53b45ae60779903904d4fbdbd145a5 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 5 Jan 2015 10:10:14 +0100 Subject: s390/sclp: sign extend return value of _sclp_print_early() _sclp_print_early() has a return value, but misses to sign extend it if called from 64 bit code. This is not really a bug, since currently no caller cares what the return value is. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/sclp.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index a41f2c99dcc8..7e77e03378f3 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -294,7 +294,8 @@ ENTRY(_sclp_print_early) #ifdef CONFIG_64BIT tm LC_AR_MODE_ID,1 jno .Lesa3 - lmh %r6,%r15,96(%r15) # store upper register halves + lgfr %r2,%r2 # sign extend return value + lmh %r6,%r15,96(%r15) # restore upper register halves ahi %r15,80 .Lesa3: #endif -- cgit v1.2.3 From 91c0837e6dee8c694c8849c70e1f0f770d92d072 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 5 Jan 2015 04:29:18 -0800 Subject: s390: remove unnecessary KERN_CONT This has no effect as KERN_CONT is an empty string, It's probably just a missing conversion artifact as the other pr_cont uses in the same file don't have this prefix. Signed-off-by: Joe Perches Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 811937bb90be..232c14ea4269 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -171,7 +171,7 @@ static void dump_pagetable(unsigned long asce, unsigned long address) table = table + ((address >> 20) & 0x7ff); if (bad_address(table)) goto bad; - pr_cont(KERN_CONT "S:%016lx ", *table); + pr_cont("S:%016lx ", *table); if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE)) goto out; table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); -- cgit v1.2.3 From e6a67ad0e29087201536792f7d5cecec4ff6fc64 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 1 Jan 2015 22:56:02 +0800 Subject: s390/crypto: remove 'const' to avoid compiler warnings In aes_encrypt() and aes_decrypt(), need let 'sctx->key' be modified, so remove 'const' for it. The related warnings: CC [M] arch/s390/crypto/aes_s390.o arch/s390/crypto/aes_s390.c: In function 'aes_encrypt': arch/s390/crypto/aes_s390.c:146:37: warning: passing argument 2 of 'crypt_s390_km' discards 'const' qualifier from pointer target type [-Wdiscarded-array-qualifiers] crypt_s390_km(KM_AES_128_ENCRYPT, &sctx->key, out, in, ^ ... In file included from arch/s390/crypto/aes_s390.c:29:0: arch/s390/crypto/crypt_s390.h:154:19: note: expected 'void *' but argument is of type 'const u8 (*)[32] {aka const unsigned char (*)[32]}' static inline int crypt_s390_km(long func, void *param, ^ Signed-off-by: Chen Gang Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/crypto/aes_s390.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 1f272b24fc0b..5566ce80abdb 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -134,7 +134,7 @@ static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - const struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); if (unlikely(need_fallback(sctx->key_len))) { crypto_cipher_encrypt_one(sctx->fallback.cip, out, in); @@ -159,7 +159,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in) { - const struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); + struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm); if (unlikely(need_fallback(sctx->key_len))) { crypto_cipher_decrypt_one(sctx->fallback.cip, out, in); -- cgit v1.2.3 From d97d929f06d0e072cd36fba6bd9d25b29bae34fd Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 8 Jan 2015 07:41:52 +0000 Subject: s390: move cacheinfo sysfs to generic cacheinfo infrastructure This patch removes the redundant sysfs cacheinfo code by reusing the newly introduced generic cacheinfo infrastructure through the commit 246246cbde5e ("drivers: base: support cpu cache information interface to userspace via sysfs") Signed-off-by: Sudeep Holla Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/cache.c | 388 +++++++++++------------------------------------ 1 file changed, 92 insertions(+), 296 deletions(-) diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index c0b03c28d157..fe21f074cf9f 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -5,37 +5,11 @@ * Author(s): Heiko Carstens */ -#include #include -#include -#include -#include #include +#include #include -struct cache { - unsigned long size; - unsigned int line_size; - unsigned int associativity; - unsigned int nr_sets; - unsigned int level : 3; - unsigned int type : 2; - unsigned int private : 1; - struct list_head list; -}; - -struct cache_dir { - struct kobject *kobj; - struct cache_index_dir *index; -}; - -struct cache_index_dir { - struct kobject kobj; - int cpu; - struct cache *cache; - struct cache_index_dir *next; -}; - enum { CACHE_SCOPE_NOTEXISTS, CACHE_SCOPE_PRIVATE, @@ -44,10 +18,10 @@ enum { }; enum { - CACHE_TYPE_SEPARATE, - CACHE_TYPE_DATA, - CACHE_TYPE_INSTRUCTION, - CACHE_TYPE_UNIFIED, + CTYPE_SEPARATE, + CTYPE_DATA, + CTYPE_INSTRUCTION, + CTYPE_UNIFIED, }; enum { @@ -70,39 +44,59 @@ struct cache_info { }; #define CACHE_MAX_LEVEL 8 - union cache_topology { struct cache_info ci[CACHE_MAX_LEVEL]; unsigned long long raw; }; static const char * const cache_type_string[] = { - "Data", + "", "Instruction", + "Data", + "", "Unified", }; -static struct cache_dir *cache_dir_cpu[NR_CPUS]; -static LIST_HEAD(cache_list); +static const enum cache_type cache_type_map[] = { + [CTYPE_SEPARATE] = CACHE_TYPE_SEPARATE, + [CTYPE_DATA] = CACHE_TYPE_DATA, + [CTYPE_INSTRUCTION] = CACHE_TYPE_INST, + [CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED, +}; void show_cacheinfo(struct seq_file *m) { - struct cache *cache; - int index = 0; + int cpu = smp_processor_id(), idx; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *cache; - list_for_each_entry(cache, &cache_list, list) { - seq_printf(m, "cache%-11d: ", index); + for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) { + cache = this_cpu_ci->info_list + idx; + seq_printf(m, "cache%-11d: ", idx); seq_printf(m, "level=%d ", cache->level); seq_printf(m, "type=%s ", cache_type_string[cache->type]); - seq_printf(m, "scope=%s ", cache->private ? "Private" : "Shared"); - seq_printf(m, "size=%luK ", cache->size >> 10); - seq_printf(m, "line_size=%u ", cache->line_size); - seq_printf(m, "associativity=%d", cache->associativity); + seq_printf(m, "scope=%s ", + cache->disable_sysfs ? "Shared" : "Private"); + seq_printf(m, "size=%dK ", cache->size >> 10); + seq_printf(m, "line_size=%u ", cache->coherency_line_size); + seq_printf(m, "associativity=%d", cache->ways_of_associativity); seq_puts(m, "\n"); - index++; } } +static inline enum cache_type get_cache_type(struct cache_info *ci, int level) +{ + if (level >= CACHE_MAX_LEVEL) + return CACHE_TYPE_NOCACHE; + + ci += level; + + if (ci->scope != CACHE_SCOPE_SHARED && ci->scope != CACHE_SCOPE_PRIVATE) + return CACHE_TYPE_NOCACHE; + + return cache_type_map[ci->type]; +} + static inline unsigned long ecag(int ai, int li, int ti) { unsigned long cmd, val; @@ -113,277 +107,79 @@ static inline unsigned long ecag(int ai, int li, int ti) return val; } -static int __init cache_add(int level, int private, int type) +static void ci_leaf_init(struct cacheinfo *this_leaf, int private, + enum cache_type type, unsigned int level) { - struct cache *cache; - int ti; + int ti, num_sets; + int cpu = smp_processor_id(); - cache = kzalloc(sizeof(*cache), GFP_KERNEL); - if (!cache) - return -ENOMEM; - if (type == CACHE_TYPE_INSTRUCTION) + if (type == CACHE_TYPE_INST) ti = CACHE_TI_INSTRUCTION; else ti = CACHE_TI_UNIFIED; - cache->size = ecag(EXTRACT_SIZE, level, ti); - cache->line_size = ecag(EXTRACT_LINE_SIZE, level, ti); - cache->associativity = ecag(EXTRACT_ASSOCIATIVITY, level, ti); - cache->nr_sets = cache->size / cache->associativity; - cache->nr_sets /= cache->line_size; - cache->private = private; - cache->level = level + 1; - cache->type = type - 1; - list_add_tail(&cache->list, &cache_list); - return 0; -} - -static void __init cache_build_info(void) -{ - struct cache *cache, *next; - union cache_topology ct; - int level, private, rc; - - ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); - for (level = 0; level < CACHE_MAX_LEVEL; level++) { - switch (ct.ci[level].scope) { - case CACHE_SCOPE_SHARED: - private = 0; - break; - case CACHE_SCOPE_PRIVATE: - private = 1; - break; - default: - return; - } - if (ct.ci[level].type == CACHE_TYPE_SEPARATE) { - rc = cache_add(level, private, CACHE_TYPE_DATA); - rc |= cache_add(level, private, CACHE_TYPE_INSTRUCTION); - } else { - rc = cache_add(level, private, ct.ci[level].type); - } - if (rc) - goto error; - } - return; -error: - list_for_each_entry_safe(cache, next, &cache_list, list) { - list_del(&cache->list); - kfree(cache); - } -} - -static struct cache_dir *cache_create_cache_dir(int cpu) -{ - struct cache_dir *cache_dir; - struct kobject *kobj = NULL; - struct device *dev; - - dev = get_cpu_device(cpu); - if (!dev) - goto out; - kobj = kobject_create_and_add("cache", &dev->kobj); - if (!kobj) - goto out; - cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL); - if (!cache_dir) - goto out; - cache_dir->kobj = kobj; - cache_dir_cpu[cpu] = cache_dir; - return cache_dir; -out: - kobject_put(kobj); - return NULL; -} - -static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *kobj) -{ - return container_of(kobj, struct cache_index_dir, kobj); -} - -static void cache_index_release(struct kobject *kobj) -{ - struct cache_index_dir *index; - - index = kobj_to_cache_index_dir(kobj); - kfree(index); -} - -static ssize_t cache_index_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct kobj_attribute *kobj_attr; - - kobj_attr = container_of(attr, struct kobj_attribute, attr); - return kobj_attr->show(kobj, kobj_attr, buf); -} - -#define DEFINE_CACHE_ATTR(_name, _format, _value) \ -static ssize_t cache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, \ - char *buf) \ -{ \ - struct cache_index_dir *index; \ - \ - index = kobj_to_cache_index_dir(kobj); \ - return sprintf(buf, _format, _value); \ -} \ -static struct kobj_attribute cache_##_name##_attr = \ - __ATTR(_name, 0444, cache_##_name##_show, NULL); -DEFINE_CACHE_ATTR(size, "%luK\n", index->cache->size >> 10); -DEFINE_CACHE_ATTR(coherency_line_size, "%u\n", index->cache->line_size); -DEFINE_CACHE_ATTR(number_of_sets, "%u\n", index->cache->nr_sets); -DEFINE_CACHE_ATTR(ways_of_associativity, "%u\n", index->cache->associativity); -DEFINE_CACHE_ATTR(type, "%s\n", cache_type_string[index->cache->type]); -DEFINE_CACHE_ATTR(level, "%d\n", index->cache->level); + this_leaf->level = level + 1; + this_leaf->type = type; + this_leaf->coherency_line_size = ecag(EXTRACT_LINE_SIZE, level, ti); + this_leaf->ways_of_associativity = ecag(EXTRACT_ASSOCIATIVITY, + level, ti); + this_leaf->size = ecag(EXTRACT_SIZE, level, ti); -static ssize_t shared_cpu_map_func(struct kobject *kobj, int type, char *buf) -{ - struct cache_index_dir *index; - int len; - - index = kobj_to_cache_index_dir(kobj); - len = type ? - cpulist_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)) : - cpumask_scnprintf(buf, PAGE_SIZE - 2, cpumask_of(index->cpu)); - len += sprintf(&buf[len], "\n"); - return len; -} - -static ssize_t shared_cpu_map_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return shared_cpu_map_func(kobj, 0, buf); + num_sets = this_leaf->size / this_leaf->coherency_line_size; + num_sets /= this_leaf->ways_of_associativity; + this_leaf->number_of_sets = num_sets; + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); + if (!private) + this_leaf->disable_sysfs = true; } -static struct kobj_attribute cache_shared_cpu_map_attr = - __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL); -static ssize_t shared_cpu_list_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +int init_cache_level(unsigned int cpu) { - return shared_cpu_map_func(kobj, 1, buf); -} -static struct kobj_attribute cache_shared_cpu_list_attr = - __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL); - -static struct attribute *cache_index_default_attrs[] = { - &cache_type_attr.attr, - &cache_size_attr.attr, - &cache_number_of_sets_attr.attr, - &cache_ways_of_associativity_attr.attr, - &cache_level_attr.attr, - &cache_coherency_line_size_attr.attr, - &cache_shared_cpu_map_attr.attr, - &cache_shared_cpu_list_attr.attr, - NULL, -}; - -static const struct sysfs_ops cache_index_ops = { - .show = cache_index_show, -}; - -static struct kobj_type cache_index_type = { - .sysfs_ops = &cache_index_ops, - .release = cache_index_release, - .default_attrs = cache_index_default_attrs, -}; - -static int cache_create_index_dir(struct cache_dir *cache_dir, - struct cache *cache, int index, int cpu) -{ - struct cache_index_dir *index_dir; - int rc; - - index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL); - if (!index_dir) - return -ENOMEM; - index_dir->cache = cache; - index_dir->cpu = cpu; - rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type, - cache_dir->kobj, "index%d", index); - if (rc) - goto out; - index_dir->next = cache_dir->index; - cache_dir->index = index_dir; - return 0; -out: - kfree(index_dir); - return rc; -} + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + unsigned int level = 0, leaves = 0; + union cache_topology ct; + enum cache_type ctype; -static int cache_add_cpu(int cpu) -{ - struct cache_dir *cache_dir; - struct cache *cache; - int rc, index = 0; + if (!this_cpu_ci) + return -EINVAL; - if (list_empty(&cache_list)) - return 0; - cache_dir = cache_create_cache_dir(cpu); - if (!cache_dir) - return -ENOMEM; - list_for_each_entry(cache, &cache_list, list) { - if (!cache->private) + ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); + do { + ctype = get_cache_type(&ct.ci[0], level); + if (ctype == CACHE_TYPE_NOCACHE) break; - rc = cache_create_index_dir(cache_dir, cache, index, cpu); - if (rc) - return rc; - index++; - } - return 0; -} + /* Separate instruction and data caches */ + leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; + } while (++level < CACHE_MAX_LEVEL); -static void cache_remove_cpu(int cpu) -{ - struct cache_index_dir *index, *next; - struct cache_dir *cache_dir; + this_cpu_ci->num_levels = level; + this_cpu_ci->num_leaves = leaves; - cache_dir = cache_dir_cpu[cpu]; - if (!cache_dir) - return; - index = cache_dir->index; - while (index) { - next = index->next; - kobject_put(&index->kobj); - index = next; - } - kobject_put(cache_dir->kobj); - kfree(cache_dir); - cache_dir_cpu[cpu] = NULL; + return 0; } -static int cache_hotplug(struct notifier_block *nfb, unsigned long action, - void *hcpu) +int populate_cache_leaves(unsigned int cpu) { - int cpu = (long)hcpu; - int rc = 0; + unsigned int level, idx, pvt; + union cache_topology ct; + enum cache_type ctype; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - rc = cache_add_cpu(cpu); - if (rc) - cache_remove_cpu(cpu); - break; - case CPU_DEAD: - cache_remove_cpu(cpu); - break; + ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0); + for (idx = 0, level = 0; level < this_cpu_ci->num_levels && + idx < this_cpu_ci->num_leaves; idx++, level++) { + if (!this_leaf) + return -EINVAL; + + pvt = (ct.ci[level].scope == CACHE_SCOPE_PRIVATE) ? 1 : 0; + ctype = get_cache_type(&ct.ci[0], level); + if (ctype == CACHE_TYPE_SEPARATE) { + ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_DATA, level); + ci_leaf_init(this_leaf++, pvt, CACHE_TYPE_INST, level); + } else { + ci_leaf_init(this_leaf++, pvt, ctype, level); + } } - return rc ? NOTIFY_BAD : NOTIFY_OK; -} - -static int __init cache_init(void) -{ - int cpu; - - if (!test_facility(34)) - return 0; - cache_build_info(); - - cpu_notifier_register_begin(); - for_each_online_cpu(cpu) - cache_add_cpu(cpu); - __hotcpu_notifier(cache_hotplug, 0); - cpu_notifier_register_done(); return 0; } -device_initcall(cache_init); -- cgit v1.2.3 From bae2a3cc4f5e2cd5b1902a040e6d3ff1f21f488a Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 9 Jan 2015 09:49:20 +0100 Subject: s390/docs: Break long lines in Debugging390.txt There are a lot of lines that are longer than 80 columns in this file, rendering it hard to read in a terminal window. This patch fixes most of these long lines, and while we're at it, also makes some sentences more readable, e.g. by replacing "&" with "and", adding proper punctuation, removing superfluous clauses, etc. Signed-off-by: Thomas Huth Signed-off-by: Martin Schwidefsky --- Documentation/s390/Debugging390.txt | 464 ++++++++++++++++++------------------ 1 file changed, 237 insertions(+), 227 deletions(-) diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt index 08911b5c6b0e..ae75366cc3d0 100644 --- a/Documentation/s390/Debugging390.txt +++ b/Documentation/s390/Debugging390.txt @@ -1,14 +1,14 @@ - - Debugging on Linux for s/390 & z/Architecture - by - Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) - Copyright (C) 2000-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation - Best viewed with fixed width fonts + + Debugging on Linux for s/390 & z/Architecture + by + Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) + Copyright (C) 2000-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation + Best viewed with fixed width fonts Overview of Document: ===================== -This document is intended to give a good overview of how to debug -Linux for s/390 & z/Architecture. It isn't intended as a complete reference & not a +This document is intended to give a good overview of how to debug Linux for +s/390 and z/Architecture. It is not intended as a complete reference and not a tutorial on the fundamentals of C & assembly. It doesn't go into 390 IO in any detail. It is intended to complement the documents in the reference section below & any other worthwhile references you get. @@ -44,18 +44,20 @@ Register Set ============ The current architectures have the following registers. -16 General propose registers, 32 bit on s/390 64 bit on z/Architecture, r0-r15 or gpr0-gpr15 used for arithmetic & addressing. - -16 Control registers, 32 bit on s/390 64 bit on z/Architecture, ( cr0-cr15 kernel usage only ) used for memory management, -interrupt control,debugging control etc. - -16 Access registers ( ar0-ar15 ) 32 bit on s/390 & z/Architecture -not used by normal programs but potentially could -be used as temporary storage. Their main purpose is their 1 to 1 -association with general purpose registers and are used in -the kernel for copying data between kernel & user address spaces. -Access register 0 ( & access register 1 on z/Architecture ( needs 64 bit -pointer ) ) is currently used by the pthread library as a pointer to +16 General propose registers, 32 bit on s/390 and 64 bit on z/Architecture, +r0-r15 (or gpr0-gpr15), used for arithmetic and addressing. + +16 Control registers, 32 bit on s/390 and 64 bit on z/Architecture, cr0-cr15, +kernel usage only, used for memory management, interrupt control, debugging +control etc. + +16 Access registers (ar0-ar15), 32 bit on both s/390 and z/Architecture, +normally not used by normal programs but potentially could be used as +temporary storage. These registers have a 1:1 association with general +purpose registers and are designed to be used in the so-called access +register mode to select different address spaces. +Access register 0 (and access register 1 on z/Architecture, which needs a +64 bit pointer) is currently used by the pthread library as a pointer to the current running threads private area. 16 64 bit floating point registers (fp0-fp15 ) IEEE & HFP floating @@ -90,18 +92,19 @@ s/390 z/Architecture 6 6 Input/Output interrupt Mask -7 7 External interrupt Mask used primarily for interprocessor signalling & - clock interrupts. +7 7 External interrupt Mask used primarily for interprocessor + signalling and clock interrupts. -8-11 8-11 PSW Key used for complex memory protection mechanism not used under linux +8-11 8-11 PSW Key used for complex memory protection mechanism + (not used under linux) 12 12 1 on s/390 0 on z/Architecture 13 13 Machine Check Mask 1=enable machine check interrupts -14 14 Wait State set this to 1 to stop the processor except for interrupts & give - time to other LPARS used in CPU idle in the kernel to increase overall - usage of processor resources. +14 14 Wait State. Set this to 1 to stop the processor except for + interrupts and give time to other LPARS. Used in CPU idle in + the kernel to increase overall usage of processor resources. 15 15 Problem state ( if set to 1 certain instructions are disabled ) all linux user programs run with this bit 1 @@ -165,21 +168,23 @@ s/390 z/Architecture when loading the address with LPSWE otherwise a specification exception occurs, LPSW is fully backward compatible. - - + + Prefix Page(s) --------------- +-------------- This per cpu memory area is too intimately tied to the processor not to mention. -It exists between the real addresses 0-4096 on s/390 & 0-8192 z/Architecture & is exchanged -with a 1 page on s/390 or 2 pages on z/Architecture in absolute storage by the set -prefix instruction in linux'es startup. -This page is mapped to a different prefix for each processor in an SMP configuration -( assuming the os designer is sane of course :-) ). -Bytes 0-512 ( 200 hex ) on s/390 & 0-512,4096-4544,4604-5119 currently on z/Architecture -are used by the processor itself for holding such information as exception indications & -entry points for exceptions. -Bytes after 0xc00 hex are used by linux for per processor globals on s/390 & z/Architecture -( there is a gap on z/Architecture too currently between 0xc00 & 1000 which linux uses ). +It exists between the real addresses 0-4096 on s/390 and between 0-8192 on +z/Architecture and is exchanged with one page on s/390 or two pages on +z/Architecture in absolute storage by the set prefix instruction during Linux +startup. +This page is mapped to a different prefix for each processor in an SMP +configuration (assuming the OS designer is sane of course). +Bytes 0-512 (200 hex) on s/390 and 0-512, 4096-4544, 4604-5119 currently on +z/Architecture are used by the processor itself for holding such information +as exception indications and entry points for exceptions. +Bytes after 0xc00 hex are used by linux for per processor globals on s/390 and +z/Architecture (there is a gap on z/Architecture currently between 0xc00 and +0x1000, too, which is used by Linux). The closest thing to this on traditional architectures is the interrupt vector table. This is a good thing & does simplify some of the kernel coding however it means that we now cannot catch stray NULL pointers in the @@ -192,26 +197,26 @@ Address Spaces on Intel Linux The traditional Intel Linux is approximately mapped as follows forgive the ascii art. -0xFFFFFFFF 4GB Himem ***************** - * * - * Kernel Space * - * * - ***************** **************** -User Space Himem (typically 0xC0000000 3GB )* User Stack * * * - ***************** * * - * Shared Libs * * Next Process * - ***************** * to * - * * <== * Run * <== - * User Program * * * - * Data BSS * * * - * Text * * * - * Sections * * * -0x00000000 ***************** **************** - -Now it is easy to see that on Intel it is quite easy to recognise a kernel address -as being one greater than user space himem ( in this case 0xC0000000). -& addresses of less than this are the ones in the current running program on this -processor ( if an smp box ). +0xFFFFFFFF 4GB Himem ***************** + * * + * Kernel Space * + * * + ***************** **************** +User Space Himem * User Stack * * * +(typically 0xC0000000 3GB ) ***************** * * + * Shared Libs * * Next Process * + ***************** * to * + * * <== * Run * <== + * User Program * * * + * Data BSS * * * + * Text * * * + * Sections * * * +0x00000000 ***************** **************** + +Now it is easy to see that on Intel it is quite easy to recognise a kernel +address as being one greater than user space himem (in this case 0xC0000000), +and addresses of less than this are the ones in the current running program on +this processor (if an smp box). If using the virtual machine ( VM ) as a debugger it is quite difficult to know which user process is running as the address space you are looking at could be from any process in the run queue. @@ -247,8 +252,8 @@ Our addressing scheme is basically as follows: Himem 0x7fffffff 2GB on s/390 ***************** **************** currently 0x3ffffffffff (2^42)-1 * User Stack * * * on z/Architecture. ***************** * * - * Shared Libs * * * - ***************** * * + * Shared Libs * * * + ***************** * * * * * Kernel * * User Program * * * * Data BSS * * * @@ -301,10 +306,10 @@ Virtual Addresses on s/390 & z/Architecture =========================================== A virtual address on s/390 is made up of 3 parts -The SX ( segment index, roughly corresponding to the PGD & PMD in linux terminology ) -being bits 1-11. -The PX ( page index, corresponding to the page table entry (pte) in linux terminology ) -being bits 12-19. +The SX (segment index, roughly corresponding to the PGD & PMD in Linux +terminology) being bits 1-11. +The PX (page index, corresponding to the page table entry (pte) in Linux +terminology) being bits 12-19. The remaining bits BX (the byte index are the offset in the page ) i.e. bits 20 to 31. @@ -368,9 +373,9 @@ each processor as follows. * ( 8K ) * 16K aligned ************************ -What this means is that we don't need to dedicate any register or global variable -to point to the current running process & can retrieve it with the following -very simple construct for s/390 & one very similar for z/Architecture. +What this means is that we don't need to dedicate any register or global +variable to point to the current running process & can retrieve it with the +following very simple construct for s/390 & one very similar for z/Architecture. static inline struct task_struct * get_current(void) { @@ -403,8 +408,8 @@ Note: To follow stackframes requires a knowledge of C or Pascal & limited knowledge of one assembly language. It should be noted that there are some differences between the -s/390 & z/Architecture stack layouts as the z/Architecture stack layout didn't have -to maintain compatibility with older linkage formats. +s/390 and z/Architecture stack layouts as the z/Architecture stack layout +didn't have to maintain compatibility with older linkage formats. Glossary: --------- @@ -440,7 +445,7 @@ The code generated by the compiler to return to the caller. frameless-function A frameless function in Linux for s390 & z/Architecture is one which doesn't -need more than the register save area ( 96 bytes on s/390, 160 on z/Architecture ) +need more than the register save area (96 bytes on s/390, 160 on z/Architecture) given to it by the caller. A frameless function never: 1) Sets up a back chain. @@ -588,8 +593,8 @@ A sample program with comments. Comments on the function test ----------------------------- -1) It didn't need to set up a pointer to the constant pool gpr13 as it isn't used -( :-( ). +1) It didn't need to set up a pointer to the constant pool gpr13 as it is not +used ( :-( ). 2) This is a frameless function & no stack is bought. 3) The compiler was clever enough to recognise that it could return the value in r2 as well as use it for the passed in parameter ( :-) ). @@ -743,35 +748,34 @@ Debugging under VM Notes ----- Addresses & values in the VM debugger are always hex never decimal -Address ranges are of the format - or . -e.g. The address range 0x2000 to 0x3000 can be described as 2000-3000 or 2000.1000 +Address ranges are of the format - or +. +For example, the address range 0x2000 to 0x3000 can be described as 2000-3000 +or 2000.1000 The VM Debugger is case insensitive. -VM's strengths are usually other debuggers weaknesses you can get at any resource -no matter how sensitive e.g. memory management resources,change address translation -in the PSW. For kernel hacking you will reap dividends if you get good at it. - -The VM Debugger displays operators but not operands, probably because some -of it was written when memory was expensive & the programmer was probably proud that -it fitted into 2k of memory & the programmers & didn't want to shock hardcore VM'ers by -changing the interface :-), also the debugger displays useful information on the same line & -the author of the code probably felt that it was a good idea not to go over -the 80 columns on the screen. - -As some of you are probably in a panic now this isn't as unintuitive as it may seem -as the 390 instructions are easy to decode mentally & you can make a good guess at a lot -of them as all the operands are nibble ( half byte aligned ) & if you have an objdump listing -also it is quite easy to follow, if you don't have an objdump listing keep a copy of -the s/390 Reference Summary & look at between pages 2 & 7 or alternatively the -s/390 principles of operation. +VM's strengths are usually other debuggers weaknesses you can get at any +resource no matter how sensitive e.g. memory management resources, change +address translation in the PSW. For kernel hacking you will reap dividends if +you get good at it. + +The VM Debugger displays operators but not operands, and also the debugger +displays useful information on the same line as the author of the code probably +felt that it was a good idea not to go over the 80 columns on the screen. +This isn't as unintuitive as it may seem as the s/390 instructions are easy to +decode mentally and you can make a good guess at a lot of them as all the +operands are nibble (half byte aligned). +So if you have an objdump listing by hand, it is quite easy to follow, and if +you don't have an objdump listing keep a copy of the s/390 Reference Summary +or alternatively the s/390 principles of operation next to you. e.g. even I can guess that 0001AFF8' LR 180F CC 0 is a ( load register ) lr r0,r15 -Also it is very easy to tell the length of a 390 instruction from the 2 most significant -bits in the instruction ( not that this info is really useful except if you are trying to -make sense of a hexdump of code ). +Also it is very easy to tell the length of a 390 instruction from the 2 most +significant bits in the instruction (not that this info is really useful except +if you are trying to make sense of a hexdump of code). Here is a table Bits Instruction Length ------------------------------------------ @@ -780,9 +784,6 @@ Bits Instruction Length 10 4 Bytes 11 6 Bytes - - - The debugger also displays other useful info on the same line such as the addresses being operated on destination addresses of branches & condition codes. e.g. @@ -853,8 +854,8 @@ Displaying & modifying Registers -------------------------------- D G will display all the gprs Adding a extra G to all the commands is necessary to access the full 64 bit -content in VM on z/Architecture obviously this isn't required for access registers -as these are still 32 bit. +content in VM on z/Architecture. Obviously this isn't required for access +registers as these are still 32 bit. e.g. DGG instead of DG D X will display all the control registers D AR will display all the access registers @@ -870,10 +871,11 @@ Displaying Memory ----------------- To display memory mapped using the current PSW's mapping try D -To make VM display a message each time it hits a particular address & continue try +To make VM display a message each time it hits a particular address and +continue try D I will disassemble/display a range of instructions. ST addr 32 bit word will store a 32 bit aligned address -D T will display the EBCDIC in an address ( if you are that way inclined ) +D T will display the EBCDIC in an address (if you are that way inclined) D R will display real addresses ( without DAT ) but with prefixing. There are other complex options to display if you need to get at say home space but are in primary space the easiest thing to do is to temporarily @@ -884,8 +886,8 @@ restore it. Hints ----- -If you want to issue a debugger command without halting your virtual machine with the -PA1 key try prefixing the command with #CP e.g. +If you want to issue a debugger command without halting your virtual machine +with the PA1 key try prefixing the command with #CP e.g. #cp tr i pswa 2000 also suffixing most debugger commands with RUN will cause them not to stop just display the mnemonic at the current instruction on the console. @@ -903,9 +905,10 @@ This sends a message to your own console each time do_signal is entered. script with breakpoints on every kernel procedure, this isn't a good idea because there are thousands of these routines & VM can only set 255 breakpoints at a time so you nearly had to spend as long pruning the file down as you would -entering the msg's by hand ),however, the trick might be useful for a single object file. -On linux'es 3270 emulator x3270 there is a very useful option under the file ment -Save Screens In File this is very good of keeping a copy of traces. +entering the msgs by hand), however, the trick might be useful for a single +object file. In the 3270 terminal emulator x3270 there is a very useful option +in the file menu called "Save Screen In File" - this is very good for keeping a +copy of traces. From CMS help will give you online help on a particular command. e.g. @@ -920,7 +923,8 @@ SET PF9 IMM B This does a single step in VM on pressing F8. SET PF10 ^ This sets up the ^ key. -which can be used for ^c (ctrl-c),^z (ctrl-z) which can't be typed directly into some 3270 consoles. +which can be used for ^c (ctrl-c),^z (ctrl-z) which can't be typed directly +into some 3270 consoles. SET PF11 ^- This types the starting keystrokes for a sysrq see SysRq below. SET PF12 RETRIEVE @@ -1014,8 +1018,8 @@ Tracing Program Exceptions -------------------------- If you get a crash which says something like illegal operation or specification exception followed by a register dump -You can restart linux & trace these using the tr prog trace option. - +You can restart linux & trace these using the tr prog trace +option. The most common ones you will normally be tracing for is @@ -1057,9 +1061,10 @@ TR GOTO INITIAL Tracing linux syscalls under VM ------------------------------- -Syscalls are implemented on Linux for S390 by the Supervisor call instruction (SVC) there 256 -possibilities of these as the instruction is made up of a 0xA opcode & the second byte being -the syscall number. They are traced using the simple command. +Syscalls are implemented on Linux for S390 by the Supervisor call instruction +(SVC). There 256 possibilities of these as the instruction is made up of a 0xA +opcode and the second byte being the syscall number. They are traced using the +simple command: TR SVC the syscalls are defined in linux/arch/s390/include/asm/unistd.h e.g. to trace all file opens just do @@ -1070,12 +1075,12 @@ SMP Specific commands --------------------- To find out how many cpus you have Q CPUS displays all the CPU's available to your virtual machine -To find the cpu that the current cpu VM debugger commands are being directed at do -Q CPU to change the current cpu VM debugger commands are being directed at do +To find the cpu that the current cpu VM debugger commands are being directed at +do Q CPU to change the current cpu VM debugger commands are being directed at do CPU -On a SMP guest issue a command to all CPUs try prefixing the command with cpu all. -To issue a command to a particular cpu try cpu e.g. +On a SMP guest issue a command to all CPUs try prefixing the command with cpu +all. To issue a command to a particular cpu try cpu e.g. CPU 01 TR I R 2000.3000 If you are running on a guest with several cpus & you have a IO related problem & cannot follow the flow of code but you know it isn't smp related. @@ -1101,10 +1106,10 @@ D TX0.100 Alternatively ============= -Under older VM debuggers ( I love EBDIC too ) you can use this little program I wrote which -will convert a command line of hex digits to ascii text which can be compiled under linux & -you can copy the hex digits from your x3270 terminal to your xterm if you are debugging -from a linuxbox. +Under older VM debuggers (I love EBDIC too) you can use following little +program which converts a command line of hex digits to ascii text. It can be +compiled under linux and you can copy the hex digits from your x3270 terminal +to your xterm if you are debugging from a linuxbox. This is quite useful when looking at a parameter passed in as a text string under VM ( unless you are good at decoding ASCII in your head ). @@ -1114,14 +1119,14 @@ TR SVC 5 We have stopped at a breakpoint 000151B0' SVC 0A05 -> 0001909A' CC 0 -D 20.8 to check the SVC old psw in the prefix area & see was it from userspace -( for the layout of the prefix area consult P18 of the s/390 390 Reference Summary -if you have it available ). +D 20.8 to check the SVC old psw in the prefix area and see was it from userspace +(for the layout of the prefix area consult the "Fixed Storage Locations" +chapter of the s/390 Reference Summary if you have it available). V00000020 070C2000 800151B2 The problem state bit wasn't set & it's also too early in the boot sequence for it to be a userspace SVC if it was we would have to temporarily switch the -psw to user space addressing so we could get at the first parameter of the open in -gpr2. +psw to user space addressing so we could get at the first parameter of the open +in gpr2. Next do a D G2 GPR 2 = 00014CB4 @@ -1208,9 +1213,9 @@ Here are the tricks I use 9 out of 10 times it works pretty well, When your backchain reaches a dead end -------------------------------------- -This can happen when an exception happens in the kernel & the kernel is entered twice -if you reach the NULL pointer at the end of the back chain you should be -able to sniff further back if you follow the following tricks. +This can happen when an exception happens in the kernel and the kernel is +entered twice. If you reach the NULL pointer at the end of the back chain you +should be able to sniff further back if you follow the following tricks. 1) A kernel address should be easy to recognise since it is in primary space & the problem state bit isn't set & also The Hi bit of the address is set. @@ -1260,8 +1265,8 @@ V000FFFD0 00010400 80010802 8001085A 000FFFA0 our 3rd return address is 8001085A -as the 04B52002 looks suspiciously like rubbish it is fair to assume that the kernel entry routines -for the sake of optimisation don't set up a backchain. +as the 04B52002 looks suspiciously like rubbish it is fair to assume that the +kernel entry routines for the sake of optimisation don't set up a backchain. now look at System.map to see if the addresses make any sense. @@ -1289,67 +1294,75 @@ Congrats you've done your first backchain. s/390 & z/Architecture IO Overview ================================== -I am not going to give a course in 390 IO architecture as this would take me quite a -while & I'm no expert. Instead I'll give a 390 IO architecture summary for Dummies if you have -the s/390 principles of operation available read this instead. If nothing else you may find a few -useful keywords in here & be able to use them on a web search engine like altavista to find -more useful information. +I am not going to give a course in 390 IO architecture as this would take me +quite a while and I'm no expert. Instead I'll give a 390 IO architecture +summary for Dummies. If you have the s/390 principles of operation available +read this instead. If nothing else you may find a few useful keywords in here +and be able to use them on a web search engine to find more useful information. Unlike other bus architectures modern 390 systems do their IO using mostly -fibre optics & devices such as tapes & disks can be shared between several mainframes, -also S390 can support up to 65536 devices while a high end PC based system might be choking -with around 64. Here is some of the common IO terminology +fibre optics and devices such as tapes and disks can be shared between several +mainframes. Also S390 can support up to 65536 devices while a high end PC based +system might be choking with around 64. -Subchannel: -This is the logical number most IO commands use to talk to an IO device there can be up to -0x10000 (65536) of these in a configuration typically there is a few hundred. Under VM -for simplicity they are allocated contiguously, however on the native hardware they are not -they typically stay consistent between boots provided no new hardware is inserted or removed. -Under Linux for 390 we use these as IRQ's & also when issuing an IO command (CLEAR SUBCHANNEL, -HALT SUBCHANNEL,MODIFY SUBCHANNEL,RESUME SUBCHANNEL,START SUBCHANNEL,STORE SUBCHANNEL & -TEST SUBCHANNEL ) we use this as the ID of the device we wish to talk to, the most -important of these instructions are START SUBCHANNEL ( to start IO ), TEST SUBCHANNEL ( to check -whether the IO completed successfully ), & HALT SUBCHANNEL ( to kill IO ), a subchannel -can have up to 8 channel paths to a device this offers redundancy if one is not available. +Here is some of the common IO terminology: +Subchannel: +This is the logical number most IO commands use to talk to an IO device. There +can be up to 0x10000 (65536) of these in a configuration, typically there are a +few hundred. Under VM for simplicity they are allocated contiguously, however +on the native hardware they are not. They typically stay consistent between +boots provided no new hardware is inserted or removed. +Under Linux for s390 we use these as IRQ's and also when issuing an IO command +(CLEAR SUBCHANNEL, HALT SUBCHANNEL, MODIFY SUBCHANNEL, RESUME SUBCHANNEL, +START SUBCHANNEL, STORE SUBCHANNEL and TEST SUBCHANNEL). We use this as the ID +of the device we wish to talk to. The most important of these instructions are +START SUBCHANNEL (to start IO), TEST SUBCHANNEL (to check whether the IO +completed successfully) and HALT SUBCHANNEL (to kill IO). A subchannel can have +up to 8 channel paths to a device, this offers redundancy if one is not +available. Device Number: -This number remains static & Is closely tied to the hardware, there are 65536 of these -also they are made up of a CHPID ( Channel Path ID, the most significant 8 bits ) -& another lsb 8 bits. These remain static even if more devices are inserted or removed -from the hardware, there is a 1 to 1 mapping between Subchannels & Device Numbers provided -devices aren't inserted or removed. +This number remains static and is closely tied to the hardware. There are 65536 +of these, made up of a CHPID (Channel Path ID, the most significant 8 bits) and +another lsb 8 bits. These remain static even if more devices are inserted or +removed from the hardware. There is a 1 to 1 mapping between subchannels and +device numbers, provided devices aren't inserted or removed. Channel Control Words: -CCWS are linked lists of instructions initially pointed to by an operation request block (ORB), -which is initially given to Start Subchannel (SSCH) command along with the subchannel number -for the IO subsystem to process while the CPU continues executing normal code. -These come in two flavours, Format 0 ( 24 bit for backward ) -compatibility & Format 1 ( 31 bit ). These are typically used to issue read & write -( & many other instructions ) they consist of a length field & an absolute address field. -For each IO typically get 1 or 2 interrupts one for channel end ( primary status ) when the -channel is idle & the second for device end ( secondary status ) sometimes you get both -concurrently, you check how the IO went on by issuing a TEST SUBCHANNEL at each interrupt, -from which you receive an Interruption response block (IRB). If you get channel & device end -status in the IRB without channel checks etc. your IO probably went okay. If you didn't you -probably need a doctor to examine the IRB & extended status word etc. +CCWs are linked lists of instructions initially pointed to by an operation +request block (ORB), which is initially given to Start Subchannel (SSCH) +command along with the subchannel number for the IO subsystem to process +while the CPU continues executing normal code. +CCWs come in two flavours, Format 0 (24 bit for backward compatibility) and +Format 1 (31 bit). These are typically used to issue read and write (and many +other) instructions. They consist of a length field and an absolute address +field. +Each IO typically gets 1 or 2 interrupts, one for channel end (primary status) +when the channel is idle, and the second for device end (secondary status). +Sometimes you get both concurrently. You check how the IO went on by issuing a +TEST SUBCHANNEL at each interrupt, from which you receive an Interruption +response block (IRB). If you get channel and device end status in the IRB +without channel checks etc. your IO probably went okay. If you didn't you +probably need to examine the IRB, extended status word etc. If an error occurs, more sophisticated control units have a facility known as -concurrent sense this means that if an error occurs Extended sense information will -be presented in the Extended status word in the IRB if not you have to issue a -subsequent SENSE CCW command after the test subchannel. +concurrent sense. This means that if an error occurs Extended sense information +will be presented in the Extended status word in the IRB. If not you have to +issue a subsequent SENSE CCW command after the test subchannel. -TPI( Test pending interrupt) can also be used for polled IO but in multitasking multiprocessor -systems it isn't recommended except for checking special cases ( i.e. non looping checks for -pending IO etc. ). +TPI (Test pending interrupt) can also be used for polled IO, but in +multitasking multiprocessor systems it isn't recommended except for +checking special cases (i.e. non looping checks for pending IO etc.). -Store Subchannel & Modify Subchannel can be used to exa