Merge branch 'fortglx/3.8/time' of git://git.linaro.org/people/jstultz/linux into timers/core
Fix trivial conflicts in: kernel/time/tick-sched.c
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/kernel/Makefile b/kernel/Makefile
index 0dfeca4..86e3285 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -174,10 +174,8 @@
@echo "###"
@echo "### If this takes a long time, you might wish to run rngd in the"
@echo "### background to keep the supply of entropy topped up. It"
- @echo "### needs to be run as root, and should use a hardware random"
- @echo "### number generator if one is available, eg:"
- @echo "###"
- @echo "### rngd -r /dev/hwrandom"
+ @echo "### needs to be run as root, and uses a hardware random"
+ @echo "### number generator if one is available."
@echo "###"
openssl req -new -nodes -utf8 $(sign_key_with_hash) -days 36500 -batch \
-x509 -config x509.genkey \
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 13774b3..f24f724 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1962,9 +1962,8 @@
* trading it for newcg is protected by cgroup_mutex, we're safe to drop
* it here; it will be freed under RCU.
*/
- put_css_set(oldcg);
-
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+ put_css_set(oldcg);
}
/**
@@ -4815,31 +4814,20 @@
*
* A pointer to the shared css_set was automatically copied in
* fork.c by dup_task_struct(). However, we ignore that copy, since
- * it was not made under the protection of RCU, cgroup_mutex or
- * threadgroup_change_begin(), so it might no longer be a valid
- * cgroup pointer. cgroup_attach_task() might have already changed
- * current->cgroups, allowing the previously referenced cgroup
- * group to be removed and freed.
- *
- * Outside the pointer validity we also need to process the css_set
- * inheritance between threadgoup_change_begin() and
- * threadgoup_change_end(), this way there is no leak in any process
- * wide migration performed by cgroup_attach_proc() that could otherwise
- * miss a thread because it is too early or too late in the fork stage.
+ * it was not made under the protection of RCU or cgroup_mutex, so
+ * might no longer be a valid cgroup pointer. cgroup_attach_task() might
+ * have already changed current->cgroups, allowing the previously
+ * referenced cgroup group to be removed and freed.
*
* At the point that cgroup_fork() is called, 'current' is the parent
* task, and the passed argument 'child' points to the child task.
*/
void cgroup_fork(struct task_struct *child)
{
- /*
- * We don't need to task_lock() current because current->cgroups
- * can't be changed concurrently here. The parent obviously hasn't
- * exited and called cgroup_exit(), and we are synchronized against
- * cgroup migration through threadgroup_change_begin().
- */
+ task_lock(current);
child->cgroups = current->cgroups;
get_css_set(child->cgroups);
+ task_unlock(current);
INIT_LIST_HEAD(&child->cg_list);
}
@@ -4895,19 +4883,10 @@
*/
if (use_task_css_set_links) {
write_lock(&css_set_lock);
- if (list_empty(&child->cg_list)) {
- /*
- * It's safe to use child->cgroups without task_lock()
- * here because we are protected through
- * threadgroup_change_begin() against concurrent
- * css_set change in cgroup_task_migrate(). Also
- * the task can't exit at that point until
- * wake_up_new_task() is called, so we are protected
- * against cgroup_exit() setting child->cgroup to
- * init_css_set.
- */
+ task_lock(child);
+ if (list_empty(&child->cg_list))
list_add(&child->cg_list, &child->cgroups->tasks);
- }
+ task_unlock(child);
write_unlock(&css_set_lock);
}
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 98256bc..5cc4e7e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -78,15 +78,23 @@
*/
static atomic_t uprobe_events = ATOMIC_INIT(0);
+/* Have a copy of original instruction */
+#define UPROBE_COPY_INSN 0
+/* Dont run handlers when first register/ last unregister in progress*/
+#define UPROBE_RUN_HANDLER 1
+/* Can skip singlestep */
+#define UPROBE_SKIP_SSTEP 2
+
struct uprobe {
struct rb_node rb_node; /* node in the rb tree */
atomic_t ref;
struct rw_semaphore consumer_rwsem;
+ struct mutex copy_mutex; /* TODO: kill me and UPROBE_COPY_INSN */
struct list_head pending_list;
struct uprobe_consumer *consumers;
struct inode *inode; /* Also hold a ref to inode */
loff_t offset;
- int flags;
+ unsigned long flags;
struct arch_uprobe arch;
};
@@ -100,17 +108,12 @@
*/
static bool valid_vma(struct vm_area_struct *vma, bool is_register)
{
- if (!vma->vm_file)
- return false;
+ vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
- if (!is_register)
- return true;
+ if (is_register)
+ flags |= VM_WRITE;
- if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED))
- == (VM_READ|VM_EXEC))
- return true;
-
- return false;
+ return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC;
}
static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
@@ -193,19 +196,44 @@
return *insn == UPROBE_SWBP_INSN;
}
+static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode)
+{
+ void *kaddr = kmap_atomic(page);
+ memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE);
+ kunmap_atomic(kaddr);
+}
+
+static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
+{
+ uprobe_opcode_t old_opcode;
+ bool is_swbp;
+
+ copy_opcode(page, vaddr, &old_opcode);
+ is_swbp = is_swbp_insn(&old_opcode);
+
+ if (is_swbp_insn(new_opcode)) {
+ if (is_swbp) /* register: already installed? */
+ return 0;
+ } else {
+ if (!is_swbp) /* unregister: was it changed by us? */
+ return 0;
+ }
+
+ return 1;
+}
+
/*
* NOTE:
* Expect the breakpoint instruction to be the smallest size instruction for
* the architecture. If an arch has variable length instruction and the
* breakpoint instruction is not of the smallest length instruction
- * supported by that architecture then we need to modify read_opcode /
+ * supported by that architecture then we need to modify is_swbp_at_addr and
* write_opcode accordingly. This would never be a problem for archs that
* have fixed length instructions.
*/
/*
* write_opcode - write the opcode at a given virtual address.
- * @auprobe: arch breakpointing information.
* @mm: the probed process address space.
* @vaddr: the virtual address to store the opcode.
* @opcode: opcode to be written at @vaddr.
@@ -216,8 +244,8 @@
* For mm @mm, write the opcode at @vaddr.
* Return 0 (success) or a negative errno.
*/
-static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
- unsigned long vaddr, uprobe_opcode_t opcode)
+static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
+ uprobe_opcode_t opcode)
{
struct page *old_page, *new_page;
void *vaddr_old, *vaddr_new;
@@ -226,10 +254,14 @@
retry:
/* Read the page with vaddr into memory */
- ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
+ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
if (ret <= 0)
return ret;
+ ret = verify_opcode(old_page, vaddr, &opcode);
+ if (ret <= 0)
+ goto put_old;
+
ret = -ENOMEM;
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
if (!new_page)
@@ -264,63 +296,6 @@
}
/**
- * read_opcode - read the opcode at a given virtual address.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to read the opcode.
- * @opcode: location to store the read opcode.
- *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm.
- *
- * For mm @mm, read the opcode at @vaddr and store it in @opcode.
- * Return 0 (success) or a negative errno.
- */
-static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode)
-{
- struct page *page;
- void *vaddr_new;
- int ret;
-
- ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
- if (ret <= 0)
- return ret;
-
- vaddr_new = kmap_atomic(page);
- vaddr &= ~PAGE_MASK;
- memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
- kunmap_atomic(vaddr_new);
-
- put_page(page);
-
- return 0;
-}
-
-static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
-{
- uprobe_opcode_t opcode;
- int result;
-
- if (current->mm == mm) {
- pagefault_disable();
- result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
- sizeof(opcode));
- pagefault_enable();
-
- if (likely(result == 0))
- goto out;
- }
-
- result = read_opcode(mm, vaddr, &opcode);
- if (result)
- return result;
-out:
- if (is_swbp_insn(&opcode))
- return 1;
-
- return 0;
-}
-
-/**
* set_swbp - store breakpoint at a given address.
* @auprobe: arch specific probepoint information.
* @mm: the probed process address space.
@@ -331,18 +306,7 @@
*/
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- int result;
- /*
- * See the comment near uprobes_hash().
- */
- result = is_swbp_at_addr(mm, vaddr);
- if (result == 1)
- return 0;
-
- if (result)
- return result;
-
- return write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+ return write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
}
/**
@@ -357,16 +321,7 @@
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- int result;
-
- result = is_swbp_at_addr(mm, vaddr);
- if (!result)
- return -EINVAL;
-
- if (result != 1)
- return result;
-
- return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+ return write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
}
static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -473,7 +428,7 @@
spin_unlock(&uprobes_treelock);
/* For now assume that the instruction need not be single-stepped */
- uprobe->flags |= UPROBE_SKIP_SSTEP;
+ __set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
return u;
}
@@ -495,6 +450,7 @@
uprobe->inode = igrab(inode);
uprobe->offset = offset;
init_rwsem(&uprobe->consumer_rwsem);
+ mutex_init(&uprobe->copy_mutex);
/* add to uprobes_tree, sorted on inode:offset */
cur_uprobe = insert_uprobe(uprobe);
@@ -515,7 +471,7 @@
{
struct uprobe_consumer *uc;
- if (!(uprobe->flags & UPROBE_RUN_HANDLER))
+ if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags))
return;
down_read(&uprobe->consumer_rwsem);
@@ -621,29 +577,43 @@
return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset);
}
-/*
- * How mm->uprobes_state.count gets updated
- * uprobe_mmap() increments the count if
- * - it successfully adds a breakpoint.
- * - it cannot add a breakpoint, but sees that there is a underlying
- * breakpoint (via a is_swbp_at_addr()).
- *
- * uprobe_munmap() decrements the count if
- * - it sees a underlying breakpoint, (via is_swbp_at_addr)
- * (Subsequent uprobe_unregister wouldnt find the breakpoint
- * unless a uprobe_mmap kicks in, since the old vma would be
- * dropped just after uprobe_munmap.)
- *
- * uprobe_register increments the count if:
- * - it successfully adds a breakpoint.
- *
- * uprobe_unregister decrements the count if:
- * - it sees a underlying breakpoint and removes successfully.
- * (via is_swbp_at_addr)
- * (Subsequent uprobe_munmap wouldnt find the breakpoint
- * since there is no underlying breakpoint after the
- * breakpoint removal.)
- */
+static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
+ struct mm_struct *mm, unsigned long vaddr)
+{
+ int ret = 0;
+
+ if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
+ return ret;
+
+ mutex_lock(&uprobe->copy_mutex);
+ if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
+ goto out;
+
+ ret = copy_insn(uprobe, file);
+ if (ret)
+ goto out;
+
+ ret = -ENOTSUPP;
+ if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
+ goto out;
+
+ ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
+ if (ret)
+ goto out;
+
+ /* write_opcode() assumes we don't cross page boundary */
+ BUG_ON((uprobe->offset & ~PAGE_MASK) +
+ UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
+
+ smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+ set_bit(UPROBE_COPY_INSN, &uprobe->flags);
+
+ out:
+ mutex_unlock(&uprobe->copy_mutex);
+
+ return ret;
+}
+
static int
install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long vaddr)
@@ -661,24 +631,9 @@
if (!uprobe->consumers)
return 0;
- if (!(uprobe->flags & UPROBE_COPY_INSN)) {
- ret = copy_insn(uprobe, vma->vm_file);
- if (ret)
- return ret;
-
- if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
- return -ENOTSUPP;
-
- ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
- if (ret)
- return ret;
-
- /* write_opcode() assumes we don't cross page boundary */
- BUG_ON((uprobe->offset & ~PAGE_MASK) +
- UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
-
- uprobe->flags |= UPROBE_COPY_INSN;
- }
+ ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
+ if (ret)
+ return ret;
/*
* set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
@@ -697,15 +652,15 @@
return ret;
}
-static void
+static int
remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
{
/* can happen if uprobe_register() fails */
if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
- return;
+ return 0;
set_bit(MMF_RECALC_UPROBES, &mm->flags);
- set_orig_insn(&uprobe->arch, mm, vaddr);
+ return set_orig_insn(&uprobe->arch, mm, vaddr);
}
/*
@@ -820,7 +775,7 @@
struct mm_struct *mm = info->mm;
struct vm_area_struct *vma;
- if (err)
+ if (err && is_register)
goto free;
down_write(&mm->mmap_sem);
@@ -836,7 +791,7 @@
if (is_register)
err = install_breakpoint(uprobe, mm, vma, info->vaddr);
else
- remove_breakpoint(uprobe, mm, info->vaddr);
+ err |= remove_breakpoint(uprobe, mm, info->vaddr);
unlock:
up_write(&mm->mmap_sem);
@@ -893,13 +848,15 @@
mutex_lock(uprobes_hash(inode));
uprobe = alloc_uprobe(inode, offset);
- if (uprobe && !consumer_add(uprobe, uc)) {
+ if (!uprobe) {
+ ret = -ENOMEM;
+ } else if (!consumer_add(uprobe, uc)) {
ret = __uprobe_register(uprobe);
if (ret) {
uprobe->consumers = NULL;
__uprobe_unregister(uprobe);
} else {
- uprobe->flags |= UPROBE_RUN_HANDLER;
+ set_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
}
}
@@ -932,7 +889,7 @@
if (consumer_del(uprobe, uc)) {
if (!uprobe->consumers) {
__uprobe_unregister(uprobe);
- uprobe->flags &= ~UPROBE_RUN_HANDLER;
+ clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
}
}
@@ -1393,10 +1350,11 @@
*/
static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
{
- if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
- return true;
-
- uprobe->flags &= ~UPROBE_SKIP_SSTEP;
+ if (test_bit(UPROBE_SKIP_SSTEP, &uprobe->flags)) {
+ if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
+ return true;
+ clear_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
+ }
return false;
}
@@ -1419,6 +1377,30 @@
clear_bit(MMF_HAS_UPROBES, &mm->flags);
}
+static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
+{
+ struct page *page;
+ uprobe_opcode_t opcode;
+ int result;
+
+ pagefault_disable();
+ result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
+ sizeof(opcode));
+ pagefault_enable();
+
+ if (likely(result == 0))
+ goto out;
+
+ result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+ if (result < 0)
+ return result;
+
+ copy_opcode(page, vaddr, &opcode);
+ put_page(page);
+ out:
+ return is_swbp_insn(&opcode);
+}
+
static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
{
struct mm_struct *mm = current->mm;
@@ -1489,38 +1471,41 @@
}
return;
}
+ /*
+ * TODO: move copy_insn/etc into _register and remove this hack.
+ * After we hit the bp, _unregister + _register can install the
+ * new and not-yet-analyzed uprobe at the same address, restart.
+ */
+ smp_rmb(); /* pairs with wmb() in install_breakpoint() */
+ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
+ goto restart;
utask = current->utask;
if (!utask) {
utask = add_utask();
/* Cannot allocate; re-execute the instruction. */
if (!utask)
- goto cleanup_ret;
+ goto restart;
}
- utask->active_uprobe = uprobe;
- handler_chain(uprobe, regs);
- if (uprobe->flags & UPROBE_SKIP_SSTEP && can_skip_sstep(uprobe, regs))
- goto cleanup_ret;
- utask->state = UTASK_SSTEP;
+ handler_chain(uprobe, regs);
+ if (can_skip_sstep(uprobe, regs))
+ goto out;
+
if (!pre_ssout(uprobe, regs, bp_vaddr)) {
arch_uprobe_enable_step(&uprobe->arch);
+ utask->active_uprobe = uprobe;
+ utask->state = UTASK_SSTEP;
return;
}
-cleanup_ret:
- if (utask) {
- utask->active_uprobe = NULL;
- utask->state = UTASK_RUNNING;
- }
- if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
-
- /*
- * cannot singlestep; cannot skip instruction;
- * re-execute the instruction.
- */
- instruction_pointer_set(regs, bp_vaddr);
-
+restart:
+ /*
+ * cannot singlestep; cannot skip instruction;
+ * re-execute the instruction.
+ */
+ instruction_pointer_set(regs, bp_vaddr);
+out:
put_uprobe(uprobe);
}
@@ -1552,13 +1537,12 @@
}
/*
- * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag. (and on
- * subsequent probe hits on the thread sets the state to UTASK_BP_HIT) and
- * allows the thread to return from interrupt.
+ * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and
+ * allows the thread to return from interrupt. After that handle_swbp()
+ * sets utask->active_uprobe.
*
- * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag and
- * also sets the state to UTASK_SSTEP_ACK and allows the thread to return from
- * interrupt.
+ * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag
+ * and allows the thread to return from interrupt.
*
* While returning to userspace, thread notices the TIF_UPROBE flag and calls
* uprobe_notify_resume().
@@ -1567,11 +1551,13 @@
{
struct uprobe_task *utask;
+ clear_thread_flag(TIF_UPROBE);
+
utask = current->utask;
- if (!utask || utask->state == UTASK_BP_HIT)
- handle_swbp(regs);
- else
+ if (utask && utask->active_uprobe)
handle_singlestep(utask, regs);
+ else
+ handle_swbp(regs);
}
/*
@@ -1580,17 +1566,10 @@
*/
int uprobe_pre_sstep_notifier(struct pt_regs *regs)
{
- struct uprobe_task *utask;
-
if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags))
return 0;
- utask = current->utask;
- if (utask)
- utask->state = UTASK_BP_HIT;
-
set_thread_flag(TIF_UPROBE);
-
return 1;
}
diff --git a/kernel/module.c b/kernel/module.c
index 6085f5e..6e48c3a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2293,12 +2293,17 @@
src = (void *)info->hdr + symsect->sh_offset;
nsrc = symsect->sh_size / sizeof(*src);
+ /* strtab always starts with a nul, so offset 0 is the empty string. */
+ strtab_size = 1;
+
/* Compute total space required for the core symbols' strtab. */
- for (ndst = i = strtab_size = 1; i < nsrc; ++i, ++src)
- if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) {
- strtab_size += strlen(&info->strtab[src->st_name]) + 1;
+ for (ndst = i = 0; i < nsrc; i++) {
+ if (i == 0 ||
+ is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+ strtab_size += strlen(&info->strtab[src[i].st_name])+1;
ndst++;
}
+ }
/* Append room for core symbols at end of core part. */
info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);
@@ -2332,15 +2337,15 @@
mod->core_symtab = dst = mod->module_core + info->symoffs;
mod->core_strtab = s = mod->module_core + info->stroffs;
src = mod->symtab;
- *dst = *src;
*s++ = 0;
- for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) {
- if (!is_core_symbol(src, info->sechdrs, info->hdr->e_shnum))
- continue;
-
- dst[ndst] = *src;
- dst[ndst++].st_name = s - mod->core_strtab;
- s += strlcpy(s, &mod->strtab[src->st_name], KSYM_NAME_LEN) + 1;
+ for (ndst = i = 0; i < mod->num_symtab; i++) {
+ if (i == 0 ||
+ is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+ dst[ndst] = src[i];
+ dst[ndst++].st_name = s - mod->core_strtab;
+ s += strlcpy(s, &mod->strtab[src[i].st_name],
+ KSYM_NAME_LEN) + 1;
+ }
}
mod->core_num_syms = ndst;
}
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index d492a23..ea1b1df 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -192,7 +192,7 @@
size_t modlen = *_modlen, sig_len;
int ret;
- pr_devel("==>%s(,%lu)\n", __func__, modlen);
+ pr_devel("==>%s(,%zu)\n", __func__, modlen);
if (modlen <= sizeof(ms))
return -EBADMSG;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index eb00be2..7b07cc0 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -71,12 +71,22 @@
return NULL;
}
+/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
+#define MAX_PID_NS_LEVEL 32
+
static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns)
{
struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1;
- int i, err = -ENOMEM;
+ int i;
+ int err;
+ if (level > MAX_PID_NS_LEVEL) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = -ENOMEM;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
if (ns == NULL)
goto out;
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 6629bf7..7a925ba 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -58,7 +58,7 @@
return (cycle_t) jiffies;
}
-struct clocksource clocksource_jiffies = {
+static struct clocksource clocksource_jiffies = {
.name = "jiffies",
.rating = 1, /* lowest valid rating*/
.read = jiffies_read,
@@ -67,6 +67,8 @@
.shift = JIFFIES_SHIFT,
};
+__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
+
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
{
@@ -74,9 +76,9 @@
u64 ret;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqbegin(&jiffies_lock);
ret = jiffies_64;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqretry(&jiffies_lock, seq));
return ret;
}
EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index da6c9ec..b1600a6 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -63,13 +63,13 @@
static void tick_periodic(int cpu)
{
if (tick_do_timer_cpu == cpu) {
- write_seqlock(&xtime_lock);
+ write_seqlock(&jiffies_lock);
/* Keep track of the next tick event */
tick_next_period = ktime_add(tick_next_period, tick_period);
do_timer(1);
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
}
update_process_times(user_mode(get_irq_regs()));
@@ -130,9 +130,9 @@
ktime_t next;
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqbegin(&jiffies_lock);
next = tick_next_period;
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqretry(&jiffies_lock, seq));
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 4e265b9..cf3e59e 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,4 +141,3 @@
#endif
extern void do_timer(unsigned long ticks);
-extern seqlock_t xtime_lock;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 77729cc..c96fd6a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -31,7 +31,7 @@
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
/*
- * The time, when the last jiffy update happened. Protected by xtime_lock.
+ * The time, when the last jiffy update happened. Protected by jiffies_lock.
*/
static ktime_t last_jiffies_update;
@@ -49,14 +49,14 @@
ktime_t delta;
/*
- * Do a quick check without holding xtime_lock:
+ * Do a quick check without holding jiffies_lock:
*/
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 < tick_period.tv64)
return;
- /* Reevalute with xtime_lock held */
- write_seqlock(&xtime_lock);
+ /* Reevalute with jiffies_lock held */
+ write_seqlock(&jiffies_lock);
delta = ktime_sub(now, last_jiffies_update);
if (delta.tv64 >= tick_period.tv64) {
@@ -79,7 +79,7 @@
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
}
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
}
/*
@@ -89,12 +89,12 @@
{
ktime_t period;
- write_seqlock(&xtime_lock);
+ write_seqlock(&jiffies_lock);
/* Did we start the jiffies update yet ? */
if (last_jiffies_update.tv64 == 0)
last_jiffies_update = tick_next_period;
period = last_jiffies_update;
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
return period;
}
@@ -109,7 +109,7 @@
* concurrency: This happens only when the cpu in charge went
* into a long sleep. If two cpus happen to assign themself to
* this duty, then the jiffies update is still serialized by
- * xtime_lock.
+ * jiffies_lock.
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
tick_do_timer_cpu = cpu;
@@ -325,11 +325,11 @@
/* Read jiffies and the time when jiffies were updated last */
do {
- seq = read_seqbegin(&xtime_lock);
+ seq = read_seqbegin(&jiffies_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
time_delta = timekeeping_max_deferment();
- } while (read_seqretry(&xtime_lock, seq));
+ } while (read_seqretry(&jiffies_lock, seq));
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
@@ -859,7 +859,7 @@
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
- /* Offset the tick to avert xtime_lock contention. */
+ /* Offset the tick to avert jiffies_lock contention. */
if (sched_skew_tick) {
u64 offset = ktime_to_ns(tick_period) >> 1;
do_div(offset, num_possible_cpus());
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e424970..4c7de02 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -25,12 +25,6 @@
static struct timekeeper timekeeper;
-/*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime.
- */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
-
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
@@ -1299,9 +1293,7 @@
}
/*
- * The 64-bit jiffies value is not atomic - you MUST NOT read it
- * without sampling the sequence number in xtime_lock.
- * jiffies is defined in the linker script...
+ * Must hold jiffies_lock
*/
void do_timer(unsigned long ticks)
{
@@ -1389,7 +1381,7 @@
*/
void xtime_update(unsigned long ticks)
{
- write_seqlock(&xtime_lock);
+ write_seqlock(&jiffies_lock);
do_timer(ticks);
- write_sequnlock(&xtime_lock);
+ write_sequnlock(&jiffies_lock);
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b32ed0e..b979426 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1567,6 +1567,10 @@
put_online_cpus();
} else {
+ /* Make sure this CPU has been intitialized */
+ if (!cpumask_test_cpu(cpu_id, buffer->cpumask))
+ goto out;
+
cpu_buffer = buffer->buffers[cpu_id];
if (nr_pages == cpu_buffer->nr_pages)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d951daa..042d221 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2982,7 +2982,7 @@
set_work_cpu_and_clear_pending(&dwork->work, work_cpu(&dwork->work));
local_irq_restore(flags);
- return true;
+ return ret;
}
EXPORT_SYMBOL(cancel_delayed_work);