From f948501b36c6b3d9352ce212a197098a7e958971 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 15 Jun 2012 14:51:39 +1000 Subject: Make hard_irq_disable() actually hard-disable interrupts At present, hard_irq_disable() does nothing on powerpc because of this code in include/linux/interrupt.h: #ifndef hard_irq_disable #define hard_irq_disable() do { } while(0) #endif So we need to make our hard_irq_disable be a macro. It was previously a macro until commit 7230c56441 ("powerpc: Rework lazy-interrupt handling") changed it to a static inline function. Cc: stable@vger.kernel.org Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras -- arch/powerpc/include/asm/hw_irq.h | 3 +++ 1 file changed, 3 insertions(+) --- arch/powerpc/include/asm/hw_irq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index c9aac24b02e2..32b394f3b854 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -100,6 +100,9 @@ static inline void hard_irq_disable(void) get_paca()->irq_happened |= PACA_IRQ_HARD_DIS; } +/* include/linux/interrupt.h needs hard_irq_disable to be a macro */ +#define hard_irq_disable hard_irq_disable + /* * This is called by asynchronous interrupts to conditionally * re-enable hard interrupts when soft-disabled after having -- cgit v1.2.3 From e2ae715d66bf4becfb85eb84b7150e23cf27df30 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Fri, 15 Jun 2012 14:07:51 +0200 Subject: kmsg - kmsg_dump() use iterator to receive log buffer content Provide an iterator to receive the log buffer content, and convert all kmsg_dump() users to it. The structured data in the kmsg buffer now contains binary data, which should no longer be copied verbatim to the kmsg_dump() users. The iterator should provide reliable access to the buffer data, and also supports proper log line-aware chunking of data while iterating. Signed-off-by: Kay Sievers Tested-by: Tony Luck Reported-by: Anton Vorontsov Tested-by: Anton Vorontsov Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/nvram.c | 61 +------- arch/x86/platform/mrst/early_printk_mrst.c | 13 +- drivers/mtd/mtdoops.c | 22 +-- fs/pstore/platform.c | 34 ++--- include/linux/kmsg_dump.h | 45 +++++- kernel/printk.c | 220 +++++++++++++++++++++++++---- 6 files changed, 258 insertions(+), 137 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 36f957f31842..8733a86ad52e 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -68,9 +68,7 @@ static const char *pseries_nvram_os_partitions[] = { }; static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len); + enum kmsg_dump_reason reason); static struct kmsg_dumper nvram_kmsg_dumper = { .dump = oops_to_nvram @@ -503,28 +501,6 @@ int __init pSeries_nvram_init(void) return 0; } -/* - * Try to capture the last capture_len bytes of the printk buffer. Return - * the amount actually captured. - */ -static size_t capture_last_msgs(const char *old_msgs, size_t old_len, - const char *new_msgs, size_t new_len, - char *captured, size_t capture_len) -{ - if (new_len >= capture_len) { - memcpy(captured, new_msgs + (new_len - capture_len), - capture_len); - return capture_len; - } else { - /* Grab the end of old_msgs. */ - size_t old_tail_len = min(old_len, capture_len - new_len); - memcpy(captured, old_msgs + (old_len - old_tail_len), - old_tail_len); - memcpy(captured + old_tail_len, new_msgs, new_len); - return old_tail_len + new_len; - } -} - /* * Are we using the ibm,rtas-log for oops/panic reports? And if so, * would logging this oops/panic overwrite an RTAS event that rtas_errd @@ -541,27 +517,6 @@ static int clobbering_unread_rtas_event(void) NVRAM_RTAS_READ_TIMEOUT); } -/* Squeeze out each line's severity prefix. */ -static size_t elide_severities(char *buf, size_t len) -{ - char *in, *out, *buf_end = buf + len; - /* Assume a at the very beginning marks the start of a line. */ - int newline = 1; - - in = out = buf; - while (in < buf_end) { - if (newline && in+3 <= buf_end && - *in == '<' && isdigit(in[1]) && in[2] == '>') { - in += 3; - newline = 0; - } else { - newline = (*in == '\n'); - *out++ = *in++; - } - } - return out - buf; -} - /* Derived from logfs_compress() */ static int nvram_compress(const void *in, void *out, size_t inlen, size_t outlen) @@ -619,9 +574,7 @@ static int zip_oops(size_t text_len) * partition. If that's too much, go back and capture uncompressed text. */ static void oops_to_nvram(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *old_msgs, unsigned long old_len, - const char *new_msgs, unsigned long new_len) + enum kmsg_dump_reason reason) { static unsigned int oops_count = 0; static bool panicking = false; @@ -660,14 +613,14 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, return; if (big_oops_buf) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, big_oops_buf, big_oops_buf_sz); - text_len = elide_severities(big_oops_buf, text_len); + kmsg_dump_get_buffer(dumper, false, + big_oops_buf, big_oops_buf_sz, &text_len); rc = zip_oops(text_len); } if (rc != 0) { - text_len = capture_last_msgs(old_msgs, old_len, - new_msgs, new_len, oops_data, oops_data_sz); + kmsg_dump_rewind(dumper); + kmsg_dump_get_buffer(dumper, true, + oops_data, oops_data_sz, &text_len); err_type = ERR_TYPE_KERNEL_PANIC; *oops_len = (u16) text_len; } diff --git a/arch/x86/platform/mrst/early_printk_mrst.c b/arch/x86/platform/mrst/early_printk_mrst.c index 3c6e328483c7..028454f0c3a5 100644 --- a/arch/x86/platform/mrst/early_printk_mrst.c +++ b/arch/x86/platform/mrst/early_printk_mrst.c @@ -110,19 +110,16 @@ static struct kmsg_dumper dw_dumper; static int dumper_registered; static void dw_kmsg_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - int i; + static char line[1024]; + size_t len; /* When run to this, we'd better re-init the HW */ mrst_early_console_init(); - for (i = 0; i < l1; i++) - early_mrst_console.write(&early_mrst_console, s1 + i, 1); - for (i = 0; i < l2; i++) - early_mrst_console.write(&early_mrst_console, s2 + i, 1); + while (kmsg_dump_get_line(dumper, true, line, sizeof(line), &len)) + early_mrst_console.write(&early_mrst_console, line, len); } /* Set the ratio rate to 115200, 8n1, IRQ disabled */ diff --git a/drivers/mtd/mtdoops.c b/drivers/mtd/mtdoops.c index ae36d7e1e913..551e316e4454 100644 --- a/drivers/mtd/mtdoops.c +++ b/drivers/mtd/mtdoops.c @@ -304,32 +304,17 @@ static void find_next_position(struct mtdoops_context *cxt) } static void mtdoops_do_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { struct mtdoops_context *cxt = container_of(dumper, struct mtdoops_context, dump); - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - char *dst; - - if (reason != KMSG_DUMP_OOPS && - reason != KMSG_DUMP_PANIC) - return; /* Only dump oopses if dump_oops is set */ if (reason == KMSG_DUMP_OOPS && !dump_oops) return; - dst = cxt->oops_buf + MTDOOPS_HEADER_SIZE; /* Skip the header */ - l2_cpy = min(l2, record_size - MTDOOPS_HEADER_SIZE); - l1_cpy = min(l1, record_size - MTDOOPS_HEADER_SIZE - l2_cpy); - - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); + kmsg_dump_get_buffer(dumper, true, cxt->oops_buf + MTDOOPS_HEADER_SIZE, + record_size - MTDOOPS_HEADER_SIZE, NULL); /* Panics must be written immediately */ if (reason != KMSG_DUMP_OOPS) @@ -375,6 +360,7 @@ static void mtdoops_notify_add(struct mtd_info *mtd) return; } + cxt->dump.max_reason = KMSG_DUMP_OOPS; cxt->dump.dump = mtdoops_do_dump; err = kmsg_dump_register(&cxt->dump); if (err) { diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 82c585f715e3..03ce7a9b81cc 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,20 +94,15 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) * as we can from the end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - unsigned long size, total = 0; - char *dst; + unsigned long total = 0; const char *why; u64 id; - int hsize, ret; unsigned int part = 1; unsigned long flags = 0; int is_locked = 0; + int ret; why = get_reason_str(reason); @@ -119,30 +114,25 @@ static void pstore_dump(struct kmsg_dumper *dumper, spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { + char *dst; + unsigned long size; + int hsize; + size_t len; + dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; - l2_cpy = min(l2, size); - l1_cpy = min(l1, size - l2_cpy); - - if (l1_cpy + l2_cpy == 0) + if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) break; - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - hsize + l1_cpy + l2_cpy, psinfo); + hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - l1 -= l1_cpy; - l2 -= l2_cpy; - total += l1_cpy + l2_cpy; + + total += hsize + len; part++; } if (in_nmi()) { diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 35f7237ec972..af4eb5a39d9a 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -21,6 +21,7 @@ * is passed to the kernel. */ enum kmsg_dump_reason { + KMSG_DUMP_UNDEF, KMSG_DUMP_PANIC, KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, @@ -31,23 +32,37 @@ enum kmsg_dump_reason { /** * struct kmsg_dumper - kernel crash message dumper structure - * @dump: The callback which gets called on crashes. The buffer is passed - * as two sections, where s1 (length l1) contains the older - * messages and s2 (length l2) contains the newer. * @list: Entry in the dumper list (private) + * @dump: Call into dumping code which will retrieve the data with + * through the record iterator + * @max_reason: filter for highest reason number that should be dumped * @registered: Flag that specifies if this is already registered */ struct kmsg_dumper { - void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2); struct list_head list; - int registered; + void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason); + enum kmsg_dump_reason max_reason; + bool active; + bool registered; + + /* private state of the kmsg iterator */ + u32 cur_idx; + u32 next_idx; + u64 cur_seq; + u64 next_seq; }; #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len); + +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len); + +void kmsg_dump_rewind(struct kmsg_dumper *dumper); + int kmsg_dump_register(struct kmsg_dumper *dumper); int kmsg_dump_unregister(struct kmsg_dumper *dumper); @@ -56,6 +71,22 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + const char *line, size_t size, size_t *len) +{ + return false; +} + +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + return false; +} + +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ +} + static inline int kmsg_dump_register(struct kmsg_dumper *dumper) { return -EINVAL; diff --git a/kernel/printk.c b/kernel/printk.c index f205c25c37e2..ceb4a2f775a1 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -909,7 +909,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. - */ + */ seq = clear_seq; idx = clear_idx; while (seq < log_next_seq) { @@ -919,6 +919,8 @@ static int syslog_print_all(char __user *buf, int size, bool clear) idx = log_next(idx); seq++; } + + /* move first record forward until length fits into the buffer */ seq = clear_seq; idx = clear_idx; while (len > size && seq < log_next_seq) { @@ -929,7 +931,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) seq++; } - /* last message in this dump */ + /* last message fitting into this dump */ next_seq = log_next_seq; len = 0; @@ -2300,48 +2302,210 @@ module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * - * Iterate through each of the dump devices and call the oops/panic - * callbacks with the log buffer. + * Call each of the registered dumper's dump() callback, which can + * retrieve the kmsg records with kmsg_dump_get_line() or + * kmsg_dump_get_buffer(). */ void kmsg_dump(enum kmsg_dump_reason reason) { - u64 idx; struct kmsg_dumper *dumper; - const char *s1, *s2; - unsigned long l1, l2; unsigned long flags; if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) return; - /* Theoretically, the log could move on after we do this, but - there's not a lot we can do about that. The new messages - will overwrite the start of what we dump. */ + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) { + if (dumper->max_reason && reason > dumper->max_reason) + continue; + + /* initialize iterator with data about the stored records */ + dumper->active = true; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + /* invoke dumper which will iterate over records */ + dumper->dump(dumper, reason); + + /* reset iterator */ + dumper->active = false; + } + rcu_read_unlock(); +} + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + struct log *msg; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; raw_spin_lock_irqsave(&logbuf_lock, flags); - if (syslog_seq < log_first_seq) - idx = syslog_idx; - else - idx = log_first_idx; + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } - if (idx > log_next_idx) { - s1 = log_buf; - l1 = log_next_idx; + /* last entry */ + if (dumper->cur_seq >= log_next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } - s2 = log_buf + idx; - l2 = log_buf_len - idx; - } else { - s1 = ""; - l1 = 0; + msg = log_from_idx(dumper->cur_idx); + l = msg_print_text(msg, syslog, + line, size); + + dumper->cur_idx = log_next(dumper->cur_idx); + dumper->cur_seq++; + ret = true; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_line); + +/** + * kmsg_dump_get_buffer - copy kmsg log lines + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the end of the kmsg buffer and fill the provided buffer + * with as many of the the *youngest* kmsg records that fit into it. + * If the buffer is large enough, all available kmsg records will be + * copied with a single call. + * + * Consecutive calls will fill the buffer with the next block of + * available older records, not including the earlier retrieved ones. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + unsigned long flags; + u64 seq; + u32 idx; + u64 next_seq; + u32 next_idx; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= dumper->next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } + + /* calculate length of entire buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; + } + + /* move first record forward until length fits into the buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + while (l > size && seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); - s2 = log_buf + idx; - l2 = log_next_idx - idx; + l -= msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; } + + /* last message in next interation */ + next_seq = seq; + next_idx = idx; + + l = 0; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, syslog, + buf + l, size - l); + + idx = log_next(idx); + seq++; + } + + dumper->next_seq = next_seq; + dumper->next_idx = next_idx; + ret = true; raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); - rcu_read_lock(); - list_for_each_entry_rcu(dumper, &dump_list, list) - dumper->dump(dumper, reason, s1, l1, s2, l2); - rcu_read_unlock(); +/** + * kmsg_dump_rewind - reset the interator + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + */ +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); } +EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif -- cgit v1.2.3 From 081f323bd3cc3a4d5ee6276e53cc52eddfc20a63 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 1 Jun 2012 20:20:24 +1000 Subject: KVM: PPC: Book3S HV: Drop locks around call to kvmppc_pin_guest_page At the moment we call kvmppc_pin_guest_page() in kvmppc_update_vpa() with two spinlocks held: the vcore lock and the vcpu->vpa_update_lock. This is not good, since kvmppc_pin_guest_page() calls down_read() and get_user_pages_fast(), both of which can sleep. This bug was introduced in 2e25aa5f ("KVM: PPC: Book3S HV: Make virtual processor area registration more robust"). This arranges to drop those spinlocks before calling kvmppc_pin_guest_page() and re-take them afterwards. Dropping the vcore lock in kvmppc_run_core() means we have to set the vcore_state field to VCORE_RUNNING before we drop the lock, so that other vcpus won't try to run this vcore. Signed-off-by: Paul Mackerras Acked-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/powerpc/kvm/book3s_hv.c | 96 ++++++++++++++++++++++++++++++-------------- 1 file changed, 66 insertions(+), 30 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c6af1d623839..3abe1b86e583 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -268,24 +268,45 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, return err; } -static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap) +static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) { + struct kvm *kvm = vcpu->kvm; void *va; unsigned long nb; + unsigned long gpa; - vpap->update_pending = 0; - va = NULL; - if (vpap->next_gpa) { - va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb); - if (nb < vpap->len) { - /* - * If it's now too short, it must be that userspace - * has changed the mappings underlying guest memory, - * so unregister the region. - */ + /* + * We need to pin the page pointed to by vpap->next_gpa, + * but we can't call kvmppc_pin_guest_page under the lock + * as it does get_user_pages() and down_read(). So we + * have to drop the lock, pin the page, then get the lock + * again and check that a new area didn't get registered + * in the meantime. + */ + for (;;) { + gpa = vpap->next_gpa; + spin_unlock(&vcpu->arch.vpa_update_lock); + va = NULL; + nb = 0; + if (gpa) + va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb); + spin_lock(&vcpu->arch.vpa_update_lock); + if (gpa == vpap->next_gpa) + break; + /* sigh... unpin that one and try again */ + if (va) kvmppc_unpin_guest_page(kvm, va); - va = NULL; - } + } + + vpap->update_pending = 0; + if (va && nb < vpap->len) { + /* + * If it's now too short, it must be that userspace + * has changed the mappings underlying guest memory, + * so unregister the region. + */ + kvmppc_unpin_guest_page(kvm, va); + va = NULL; } if (vpap->pinned_addr) kvmppc_unpin_guest_page(kvm, vpap->pinned_addr); @@ -296,20 +317,18 @@ static void kvmppc_update_vpa(struct kvm *kvm, struct kvmppc_vpa *vpap) static void kvmppc_update_vpas(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; - spin_lock(&vcpu->arch.vpa_update_lock); if (vcpu->arch.vpa.update_pending) { - kvmppc_update_vpa(kvm, &vcpu->arch.vpa); + kvmppc_update_vpa(vcpu, &vcpu->arch.vpa); init_vpa(vcpu, vcpu->arch.vpa.pinned_addr); } if (vcpu->arch.dtl.update_pending) { - kvmppc_update_vpa(kvm, &vcpu->arch.dtl); + kvmppc_update_vpa(vcpu, &vcpu->arch.dtl); vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr; vcpu->arch.dtl_index = 0; } if (vcpu->arch.slb_shadow.update_pending) - kvmppc_update_vpa(kvm, &vcpu->arch.slb_shadow); + kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow); spin_unlock(&vcpu->arch.vpa_update_lock); } @@ -800,12 +819,39 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) struct kvm_vcpu *vcpu, *vcpu0, *vnext; long ret; u64 now; - int ptid, i; + int ptid, i, need_vpa_update; /* don't start if any threads have a signal pending */ - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + need_vpa_update = 0; + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { if (signal_pending(vcpu->arch.run_task)) return 0; + need_vpa_update |= vcpu->arch.vpa.update_pending | + vcpu->arch.slb_shadow.update_pending | + vcpu->arch.dtl.update_pending; + } + + /* + * Initialize *vc, in particular vc->vcore_state, so we can + * drop the vcore lock if necessary. + */ + vc->n_woken = 0; + vc->nap_count = 0; + vc->entry_exit_count = 0; + vc->vcore_state = VCORE_RUNNING; + vc->in_guest = 0; + vc->napping_threads = 0; + + /* + * Updating any of the vpas requires calling kvmppc_pin_guest_page, + * which can't be called with any spinlocks held. + */ + if (need_vpa_update) { + spin_unlock(&vc->lock); + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + kvmppc_update_vpas(vcpu); + spin_lock(&vc->lock); + } /* * Make sure we are running on thread 0, and that @@ -838,20 +884,10 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) if (vcpu->arch.ceded) vcpu->arch.ptid = ptid++; - vc->n_woken = 0; - vc->nap_count = 0; - vc->entry_exit_count = 0; - vc->vcore_state = VCORE_RUNNING; vc->stolen_tb += mftb() - vc->preempt_tb; - vc->in_guest = 0; vc->pcpu = smp_processor_id(); - vc->napping_threads = 0; list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { kvmppc_start_thread(vcpu); - if (vcpu->arch.vpa.update_pending || - vcpu->arch.slb_shadow.update_pending || - vcpu->arch.dtl.update_pending) - kvmppc_update_vpas(vcpu); kvmppc_create_dtl_entry(vcpu, vc); } /* Grab any remaining hw threads so they can't go into the kernel */ -- cgit v1.2.3 From 7784655acc5a946aac49af423cc1099c5d593d73 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 21 Jun 2012 17:50:27 +0000 Subject: powerpc: Fix BPF_JIT code to link with multiple TOCs If the kernel is big enough (eg. allyesconfig), the linker may need to switch TOCs when calling from the BPF JIT code out to the external helpers (skb_copy_bits() & bpf_internal_load_pointer_neg_helper()). In order to do that we need to leave space after the bl for the linker to insert a reload of our TOC pointer. Signed-off-by: Michael Ellerman Acked-by: Matt Evans Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/net/bpf_jit_64.S | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S index 55ba3855a97f..7d3a3b5619a2 100644 --- a/arch/powerpc/net/bpf_jit_64.S +++ b/arch/powerpc/net/bpf_jit_64.S @@ -105,6 +105,7 @@ sk_load_byte_msh_positive_offset: mr r4, r_addr; \ li r6, SIZE; \ bl skb_copy_bits; \ + nop; \ /* R3 = 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ @@ -156,6 +157,7 @@ bpf_slow_path_byte_msh: mr r4, r_addr; \ li r5, SIZE; \ bl bpf_internal_load_pointer_neg_helper; \ + nop; \ /* R3 != 0 on success */ \ addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ ld r0, 16(r1); \ -- cgit v1.2.3 From 82b2521d257b5c0efd51821cf5fa306e53bbb6ba Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 19 Jun 2012 20:01:45 +0000 Subject: powerpc: Fix uninitialised error in numa.c chroma_defconfig currently gives me this with gcc 4.6: arch/powerpc/mm/numa.c:638:13: error: 'dm' may be used uninitialized in this function [-Werror=uninitialized] It's a bogus warning/error since of_get_drconf_memory() only writes it anyway. Signed-off-by: Michael Neuling cc: [v3.3+] Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/mm/numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b6edbb3b4a54..6e8f677f5646 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -635,7 +635,7 @@ static inline int __init read_usm_ranges(const u32 **usm) */ static void __init parse_drconf_memory(struct device_node *memory) { - const u32 *dm, *usm; + const u32 *uninitialized_var(dm), *usm; unsigned int n, rc, ranges, is_kexec_kdump = 0; unsigned long lmb_size, base, size, sz; int nid; -- cgit v1.2.3 From c58ce2b1e3c75c55e7ebf751afce9f5a30f60b42 Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Wed, 6 Jun 2012 20:56:43 +0000 Subject: ppc64: fix missing to check all bits of _TIF_USER_WORK_MASK in preempt In entry_64.S version of ret_from_except_lite, you'll notice that in the !preempt case, after we've checked MSR_PR we test for any TIF flag in _TIF_USER_WORK_MASK to decide whether to go to do_work or not. However, in the preempt case, we do a convoluted trick to test SIGPENDING only if PR was set and always test NEED_RESCHED ... but we forget to test any other bit of _TIF_USER_WORK_MASK !!! So that means that with preempt, we completely fail to test for things like single step, syscall tracing, etc... This should be fixed as the following path: - Test PR. If not set, go to resume_kernel, else continue. - If go resume_kernel, to do that original do_work. - If else, then always test for _TIF_USER_WORK_MASK to decide to do that original user_work, else restore directly. Signed-off-by: Tiejun Chen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/entry_64.S | 97 +++++++++++++++++------------------------- 1 file changed, 40 insertions(+), 57 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index ed1718feb9d9..5971c85df136 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -558,27 +558,54 @@ _GLOBAL(ret_from_except_lite) mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ -#ifdef CONFIG_PREEMPT clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ - li r0,_TIF_NEED_RESCHED /* bits to check */ ld r3,_MSR(r1) ld r4,TI_FLAGS(r9) - /* Move MSR_PR bit in r3 to _TIF_SIGPENDING position in r0 */ - rlwimi r0,r3,32+TIF_SIGPENDING-MSR_PR_LG,_TIF_SIGPENDING - and. r0,r4,r0 /* check NEED_RESCHED and maybe SIGPENDING */ - bne do_work - -#else /* !CONFIG_PREEMPT */ - ld r3,_MSR(r1) /* Returning to user mode? */ andi. r3,r3,MSR_PR - beq restore /* if not, just restore regs and return */ + beq resume_kernel /* Check current_thread_info()->flags */ + andi. r0,r4,_TIF_USER_WORK_MASK + beq restore + + andi. r0,r4,_TIF_NEED_RESCHED + beq 1f + bl .restore_interrupts + bl .schedule + b .ret_from_except_lite + +1: bl .save_nvgprs + bl .restore_interrupts + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_notify_resume + b .ret_from_except + +resume_kernel: +#ifdef CONFIG_PREEMPT + /* Check if we need to preempt */ + andi. r0,r4,_TIF_NEED_RESCHED + beq+ restore + /* Check that preempt_count() == 0 and interrupts are enabled */ + lwz r8,TI_PREEMPT(r9) + cmpwi cr1,r8,0 + ld r0,SOFTE(r1) + cmpdi r0,0 + crandc eq,cr1*4+eq,eq + bne restore + + /* + * Here we are preempting the current task. We want to make + * sure we are soft-disabled first + */ + SOFT_DISABLE_INTS(r3,r4) +1: bl .preempt_schedule_irq + + /* Re-test flags and eventually loop */ clrrdi r9,r1,THREAD_SHIFT ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_USER_WORK_MASK - bne do_work -#endif /* !CONFIG_PREEMPT */ + andi. r0,r4,_TIF_NEED_RESCHED + bne 1b +#endif /* CONFIG_PREEMPT */ .globl fast_exc_return_irq fast_exc_return_irq: @@ -759,50 +786,6 @@ restore_check_irq_replay: #endif /* CONFIG_PPC_BOOK3E */ 1: b .ret_from_except /* What else to do here ? */ - - -3: -do_work: -#ifdef CONFIG_PREEMPT - andi. r0,r3,MSR_PR /* Returning to user mode? */ - bne user_work - /* Check that preempt_count() == 0 and interrupts are enabled */ - lwz r8,TI_PREEMPT(r9) - cmpwi cr1,r8,0 - ld r0,SOFTE(r1) - cmpdi r0,0 - crandc eq,cr1*4+eq,eq - bne restore - - /* - * Here we are preempting the current task. We want to make - * sure we are soft-disabled first - */ - SOFT_DISABLE_INTS(r3,r4) -1: bl .preempt_schedule_irq - - /* Re-test flags and eventually loop */ - clrrdi r9,r1,THREAD_SHIFT - ld r4,TI_FLAGS(r9) - andi. r0,r4,_TIF_NEED_RESCHED - bne 1b - b restore - -user_work: -#endif /* CONFIG_PREEMPT */ - - andi. r0,r4,_TIF_NEED_RESCHED - beq 1f - bl .restore_interrupts - bl .schedule - b .ret_from_except_lite - -1: bl .save_nvgprs - bl .restore_interrupts - addi r3,r1,STACK_FRAME_OVERHEAD - bl .do_notify_resume - b .ret_from_except - unrecov_restore: addi r3,r1,STACK_FRAME_OVERHEAD bl .unrecoverable_exception -- cgit v1.2.3 From 2cb387ae758d97ee7396a82528c824b8dc510b8a Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Thu, 7 Jun 2012 17:44:23 +0000 Subject: powerpc: Fix Section mismatch warnings in prom_init.c This patches tries to fix a couple of Section mismatch warnings like following one: WARNING: arch/powerpc/kernel/built-in.o(.text+0x2923c): Section mismatch in reference from the function .prom_query_opal() to the function .init.text:.call_prom() The function .prom_query_opal() references the function __init .call_prom(). This is often because .prom_query_opal lacks a __init annotation or the annotation of .call_prom is wrong. Signed-off-by: Li Zhong Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/prom_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 1b488e5305c5..0794a3017b1b 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1312,7 +1312,7 @@ static struct opal_secondary_data { extern char opal_secondary_entry; -static void prom_query_opal(void) +static void __init prom_query_opal(void) { long rc; @@ -1436,7 +1436,7 @@ static void __init prom_opal_hold_cpus(void) prom_debug("prom_opal_hold_cpus: end...\n"); } -static void prom_opal_takeover(void) +static void __init prom_opal_takeover(void) { struct opal_secondary_data *data = &RELOC(opal_secondary_data); struct opal_takeover_args *args = &data->args; -- cgit v1.2.3 From 2d773aa4810d4a612d1c879faacc38594cc3f841 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 4 Jun 2012 16:27:54 +0000 Subject: powerpc/ftrace: Do not trace restore_interrupts() As I was adding code that affects all archs, I started testing function tracer against PPC64 and found that it currently locks up with 3.4 kernel. I figured it was due to tracing a function that shouldn't be, so I went through the following process to bisect to find the culprit: cat /debug/tracing/available_filter_functions > t num=`wc -l t` sed -ne "1,${num}p" t > t1 let num=num+1 sed -ne "${num},$p" t > t2 cat t1 > /debug/tracing/set_ftrace_filter echo function /debug/tracing/current_tracer It finally came down to this function: restore_interrupts() I'm not sure why this locks up the system. It just seems to prevent scheduling from occurring. Interrupts seem to still work, as I can ping the box. But all user processes freeze. When restore_interrupts() is not traced, function tracing works fine. Cc: stable@kernel.org Signed-off-by: Steven Rostedt Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 7835a5e1ea5f..1b415027ec0e 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -277,7 +277,7 @@ EXPORT_SYMBOL(arch_local_irq_restore); * NOTE: This is called with interrupts hard disabled but not marked * as such in paca->irq_happened, so we need to resync this. */ -void restore_interrupts(void) +void notrace restore_interrupts(void) { if (irqs_disabled()) { local_paca->irq_happened |= PACA_IRQ_HARD_DIS; -- cgit v1.2.3 From 0b17ba7258db83cd02da560884e053b85de371f2 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 27 Jun 2012 13:13:52 +0000 Subject: powerpc: check_and_cede_processor() never cedes Commit f948501b36c6 ("Make hard_irq_disable() actually hard-disable interrupts") caused check_and_cede_processor to stop working. ->irq_happened will never be zero right after a hard_irq_disable so the compiler removes the call to cede_processor completely. The bug was introduced back in the lazy interrupt handling rework of 3.4 but was hidden until recently because hard_irq_disable did nothing. This issue will eventually appear in 3.4 stable since the hard_irq_disable fix is marked stable, so mark this one for stable too. Signed-off-by: Anton Blanchard Cc: stable@vger.kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hw_irq.h | 5 +++++ arch/powerpc/platforms/pseries/processor_idle.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 32b394f3b854..6eb75b80488c 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -103,6 +103,11 @@ static inline void hard_irq_disable(void) /* include/linux/interrupt.h needs hard_irq_disable to be a macro */ #define hard_irq_disable hard_irq_disable +static inline bool lazy_irq_pending(void) +{ + return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS); +} + /* * This is called by asynchronous interrupts to conditionally * re-enable hard interrupts when soft-disabled after having diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index 41a34bc4a9a2..e61483e8e960 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -106,7 +106,7 @@ static void check_and_cede_processor(void) * we first hard disable then check. */ hard_irq_disable(); - if (get_paca()->irq_happened == 0) + if (!lazy_irq_pending()) cede_processor(); } -- cgit v1.2.3 From bc6dc752f35488160ffac07ae91bed1bddaea32a Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 26 Jun 2012 21:26:37 +0000 Subject: powerpc/pseries: Fix software invalidate TCE The following added support for powernv but broke pseries/BML: 1f1616e powerpc/powernv: Add TCE SW invalidation support TCE_PCI_SW_INVAL was split into FREE and CREATE flags but the tests in the pseries code were not updated to reflect this. Signed-off-by: Michael Neuling cc: stable@kernel.org [v3.3+] Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 0915b1ad66ce..2d311c0caf8e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -106,7 +106,7 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, tcep++; } - if (tbl->it_type == TCE_PCI_SWINV_CREATE) + if (tbl->it_type & TCE_PCI_SWINV_CREATE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); return 0; } @@ -121,7 +121,7 @@ static void tce_free_pSeries(struct iommu_table *tbl, long index, long npages) while (npages--) *(tcep++) = 0; - if (tbl->it_type == TCE_PCI_SWINV_FREE) + if (tbl->it_type & TCE_PCI_SWINV_FREE) tce_invalidate_pSeries_sw(tbl, tces, tcep - 1); } -- cgit v1.2.3 From bc1d7702910c7c7e88eb60b58429dbfe293683ce Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 28 Jun 2012 19:28:57 +0000 Subject: powerpc/xmon: Use cpumask iterator to avoid warning We have a bug report where the kernel hits a warning in the cpumask code: WARNING: at include/linux/cpumask.h:107 Which is: WARN_ON_ONCE(cpu >= nr_cpumask_bits); The backtrace is: cpu_cmd cmds xmon_core xmon die xmon is iterating through 0 to NR_CPUS. I'm not sure why we are still open coding this but iterating above nr_cpu_ids is definitely a bug. This patch iterates through all possible cpus, in case we issue a system reset and CPUs in an offline state call in. Perhaps the old code was trying to handle CPUs that were in the partition but were never started (eg kexec into a kernel with an nr_cpus= boot option). They are going to die way before we get into xmon since we haven't set any kernel state up for them. Signed-off-by: Anton Blanchard CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0f3ab06d2222..eab3492a45c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -971,7 +971,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); -- cgit v1.2.3 From 2f584a146a2965b82fce89b8d2f95dc5cfe468d0 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Mon, 25 Jun 2012 13:33:11 +0000 Subject: powerpc/kvm: sldi should be sld Since we are taking a registers, this should never have been an sldi. Talking to paulus offline, this is the correct fix. Was introduced by: commit 19ccb76a1938ab364a412253daec64613acbf3df Author: Paul Mackerras Date: Sat Jul 23 17:42:46 2011 +1000 Talking to paulus, this shouldn't be a literal. Signed-off-by: Michael Neuling CC: [v3.2+] Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a84aafce2a12..a1044f43becd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) lwz r3,VCORE_NAPPING_THREADS(r5) lwz r4,VCPU_PTID(r9) li r0,1 - sldi r0,r0,r4 + sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ -- cgit v1.2.3