summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_fsnotify.c2
-rw-r--r--kernel/debug/debug_core.c11
-rw-r--r--kernel/dma/swiotlb.c310
-rw-r--r--kernel/events/core.c8
-rw-r--r--kernel/events/uprobes.c2
-rw-r--r--kernel/fork.c30
-rw-r--r--kernel/groups.c7
-rw-r--r--kernel/kexec_internal.h2
-rw-r--r--kernel/locking/rtmutex.c4
-rw-r--r--kernel/locking/rwsem.c2
-rw-r--r--kernel/locking/semaphore.c2
-rw-r--r--kernel/ptrace.c2
-rw-r--r--kernel/sched/fair.c2
-rw-r--r--kernel/sched/membarrier.c2
-rw-r--r--kernel/signal.c4
-rw-r--r--kernel/sysctl.c8
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/blktrace.c20
-rw-r--r--kernel/trace/error_report-traces.c11
-rw-r--r--kernel/trace/ring_buffer.c21
-rw-r--r--kernel/trace/trace.c6
-rw-r--r--kernel/trace/trace.h1
-rw-r--r--kernel/trace/trace_events_synth.c4
24 files changed, 308 insertions, 156 deletions
diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index 5b3f01da172b..60739d5e3373 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -84,7 +84,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
dentry = kern_path_locked(pathname, &path);
if (IS_ERR(dentry))
- return (void *)dentry; /* returning an error */
+ return ERR_CAST(dentry); /* returning an error */
inode = path.dentry->d_inode;
inode_unlock(inode);
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index b636d517c02c..4708aec492df 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -455,6 +455,17 @@ setundefined:
return 0;
}
+void kgdb_free_init_mem(void)
+{
+ int i;
+
+ /* Clear init memory breakpoints. */
+ for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
+ if (init_section_contains((void *)kgdb_break[i].bpt_addr, 0))
+ kgdb_break[i].state = BP_UNDEFINED;
+ }
+}
+
#ifdef CONFIG_KGDB_KDB
void kdb_dump_stack_on_cpu(int cpu)
{
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 7c42df6e6100..c10e855a03bc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -50,9 +50,6 @@
#define CREATE_TRACE_POINTS
#include <trace/events/swiotlb.h>
-#define OFFSET(val,align) ((unsigned long) \
- ( (val) & ( (align) - 1)))
-
#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
/*
@@ -103,6 +100,11 @@ static unsigned int max_segment;
static phys_addr_t *io_tlb_orig_addr;
/*
+ * The mapped buffer's size should be validated during a sync operation.
+ */
+static size_t *io_tlb_orig_size;
+
+/*
* Protect the above data structures in the map and unmap calls
*/
static DEFINE_SPINLOCK(io_tlb_lock);
@@ -171,7 +173,7 @@ void __init swiotlb_adjust_size(unsigned long new_size)
* adjust/expand SWIOTLB size for their use.
*/
if (!io_tlb_nslabs) {
- size = ALIGN(new_size, 1 << IO_TLB_SHIFT);
+ size = ALIGN(new_size, IO_TLB_SIZE);
io_tlb_nslabs = size >> IO_TLB_SHIFT;
io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
@@ -192,6 +194,16 @@ void swiotlb_print_info(void)
bytes >> 20);
}
+static inline unsigned long io_tlb_offset(unsigned long val)
+{
+ return val & (IO_TLB_SEGSIZE - 1);
+}
+
+static inline unsigned long nr_slots(u64 val)
+{
+ return DIV_ROUND_UP(val, IO_TLB_SIZE);
+}
+
/*
* Early SWIOTLB allocation may be too early to allow an architecture to
* perform the desired operations. This function allows the architecture to
@@ -240,9 +252,16 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
__func__, alloc_size, PAGE_SIZE);
+ alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t));
+ io_tlb_orig_size = memblock_alloc(alloc_size, PAGE_SIZE);
+ if (!io_tlb_orig_size)
+ panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__, alloc_size, PAGE_SIZE);
+
for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
io_tlb_index = 0;
no_iotlb_memory = false;
@@ -363,7 +382,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
* between io_tlb_start and io_tlb_end.
*/
io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
- get_order(io_tlb_nslabs * sizeof(int)));
+ get_order(io_tlb_nslabs * sizeof(int)));
if (!io_tlb_list)
goto cleanup3;
@@ -374,9 +393,18 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
if (!io_tlb_orig_addr)
goto cleanup4;
+ io_tlb_orig_size = (size_t *)
+ __get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs *
+ sizeof(size_t)));
+ if (!io_tlb_orig_size)
+ goto cleanup5;
+
+
for (i = 0; i < io_tlb_nslabs; i++) {
- io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i);
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
io_tlb_index = 0;
no_iotlb_memory = false;
@@ -389,6 +417,10 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
return 0;
+cleanup5:
+ free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
+ sizeof(phys_addr_t)));
+
cleanup4:
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
sizeof(int)));
@@ -404,6 +436,8 @@ void __init swiotlb_exit(void)
return;
if (late_alloc) {
+ free_pages((unsigned long)io_tlb_orig_size,
+ get_order(io_tlb_nslabs * sizeof(size_t)));
free_pages((unsigned long)io_tlb_orig_addr,
get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -413,6 +447,8 @@ void __init swiotlb_exit(void)
} else {
memblock_free_late(__pa(io_tlb_orig_addr),
PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
+ memblock_free_late(__pa(io_tlb_orig_size),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t)));
memblock_free_late(__pa(io_tlb_list),
PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
memblock_free_late(io_tlb_start,
@@ -461,79 +497,71 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
}
}
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
- size_t mapping_size, size_t alloc_size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
- unsigned long flags;
- phys_addr_t tlb_addr;
- unsigned int nslots, stride, index, wrap;
- int i;
- unsigned long mask;
- unsigned long offset_slots;
- unsigned long max_slots;
- unsigned long tmp_io_tlb_used;
-
- if (no_iotlb_memory)
- panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
-
- if (mem_encrypt_active())
- pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
+#define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT))
- if (mapping_size > alloc_size) {
- dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
- mapping_size, alloc_size);
- return (phys_addr_t)DMA_MAPPING_ERROR;
- }
+/*
+ * Return the offset into a iotlb slot required to keep the device happy.
+ */
+static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+{
+ return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+}
- mask = dma_get_seg_boundary(hwdev);
+/*
+ * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
+ */
+static inline unsigned long get_max_slots(unsigned long boundary_mask)
+{
+ if (boundary_mask == ~0UL)
+ return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+ return nr_slots(boundary_mask + 1);
+}
- tbl_dma_addr &= mask;
+static unsigned int wrap_index(unsigned int index)
+{
+ if (index >= io_tlb_nslabs)
+ return 0;
+ return index;
+}
- offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+/*
+ * Find a suitable number of IO TLB entries size that will fit this request and
+ * allocate a buffer from that IO TLB pool.
+ */
+static int find_slots(struct device *dev, phys_addr_t orig_addr,
+ size_t alloc_size)
+{
+ unsigned long boundary_mask = dma_get_seg_boundary(dev);
+ dma_addr_t tbl_dma_addr =
+ phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask;
+ unsigned long max_slots = get_max_slots(boundary_mask);
+ unsigned int iotlb_align_mask =
+ dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+ unsigned int nslots = nr_slots(alloc_size), stride;
+ unsigned int index, wrap, count = 0, i;
+ unsigned long flags;
- /*
- * Carefully handle integer overflow which can occur when mask == ~0UL.
- */
- max_slots = mask + 1
- ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
- : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+ BUG_ON(!nslots);
/*
- * For mappings greater than or equal to a page, we limit the stride
- * (and hence alignment) to a page size.
+ * For mappings with an alignment requirement don't bother looping to
+ * unaligned slots once we found an aligned one. For allocations of
+ * PAGE_SIZE or larger only look for page aligned allocations.
*/
- nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
if (alloc_size >= PAGE_SIZE)
- stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
- else
- stride = 1;
-
- BUG_ON(!nslots);
+ stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT));
- /*
- * Find suitable number of IO TLB entries size that will fit this
- * request and allocate a buffer from that IO TLB pool.
- */
spin_lock_irqsave(&io_tlb_lock, flags);
-
if (unlikely(nslots > io_tlb_nslabs - io_tlb_used))
goto not_found;
- index = ALIGN(io_tlb_index, stride);
- if (index >= io_tlb_nslabs)
- index = 0;
- wrap = index;
-
+ index = wrap = wrap_index(ALIGN(io_tlb_index, stride));
do {
- while (iommu_is_span_boundary(index, nslots, offset_slots,
- max_slots)) {
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- if (index == wrap)
- goto not_found;
+ if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) !=
+ (orig_addr & iotlb_align_mask)) {
+ index = wrap_index(index + 1);
+ continue;
}
/*
@@ -541,55 +569,96 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
* contiguous buffers, we allocate the buffers from that slot
* and mark the entries as '0' indicating unavailable.
*/
- if (io_tlb_list[index] >= nslots) {
- int count = 0;
-
- for (i = index; i < (int) (index + nslots); i++)
- io_tlb_list[i] = 0;
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
- /*
- * Update the indices to avoid searching in the next
- * round.
- */
- io_tlb_index = ((index + nslots) < io_tlb_nslabs
- ? (index + nslots) : 0);
-
- goto found;
+ if (!iommu_is_span_boundary(index, nslots,
+ nr_slots(tbl_dma_addr),
+ max_slots)) {
+ if (io_tlb_list[index] >= nslots)
+ goto found;
}
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
+ index = wrap_index(index + stride);
} while (index != wrap);
not_found:
- tmp_io_tlb_used = io_tlb_used;
-
spin_unlock_irqrestore(&io_tlb_lock, flags);
- if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
- dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
- alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
- return (phys_addr_t)DMA_MAPPING_ERROR;
+ return -1;
+
found:
+ for (i = index; i < index + nslots; i++)
+ io_tlb_list[i] = 0;
+ for (i = index - 1;
+ io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
+ io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+
+ /*
+ * Update the indices to avoid searching in the next round.
+ */
+ if (index + nslots < io_tlb_nslabs)
+ io_tlb_index = index + nslots;
+ else
+ io_tlb_index = 0;
io_tlb_used += nslots;
+
spin_unlock_irqrestore(&io_tlb_lock, flags);
+ return index;
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+ unsigned int index, i;
+ phys_addr_t tlb_addr;
+
+ if (no_iotlb_memory)
+ panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
+ if (mem_encrypt_active())
+ pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
+
+ if (mapping_size > alloc_size) {
+ dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+ mapping_size, alloc_size);
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
+
+ index = find_slots(dev, orig_addr, alloc_size + offset);
+ if (index == -1) {
+ if (!(attrs & DMA_ATTR_NO_WARN))
+ dev_warn_ratelimited(dev,
+ "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
+ alloc_size, io_tlb_nslabs, io_tlb_used);
+ return (phys_addr_t)DMA_MAPPING_ERROR;
+ }
/*
* Save away the mapping from the original address to the DMA address.
* This is needed when we sync the memory. Then we sync the buffer if
* needed.
*/
- for (i = 0; i < nslots; i++)
- io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+ for (i = 0; i < nr_slots(alloc_size + offset); i++) {
+ io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i);
+ io_tlb_orig_size[index+i] = alloc_size - (i << IO_TLB_SHIFT);
+ }
+ tlb_addr = slot_addr(io_tlb_start, index) + offset;
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
-
return tlb_addr;
}
+static void validate_sync_size_and_truncate(struct device *hwdev, size_t orig_size, size_t *size)
+{
+ if (*size > orig_size) {
+ /* Warn and truncate mapping_size */
+ dev_WARN_ONCE(hwdev, 1,
+ "Attempt for buffer overflow. Original size: %zu. Mapping size: %zu.\n",
+ orig_size, *size);
+ *size = orig_size;
+ }
+}
+
/*
* tlb_addr is the physical address of the bounce buffer to unmap.
*/
@@ -598,10 +667,13 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
enum dma_data_direction dir, unsigned long attrs)
{
unsigned long flags;
- int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
- int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr);
+ int i, count, nslots = nr_slots(alloc_size + offset);
+ int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = io_tlb_orig_addr[index];
+ validate_sync_size_and_truncate(hwdev, io_tlb_orig_size[index], &mapping_size);
+
/*
* First, sync the memory before unmapping the entry
*/
@@ -617,26 +689,30 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
* with slots below and above the pool being returned.
*/
spin_lock_irqsave(&io_tlb_lock, flags);
- {
- count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
- io_tlb_list[index + nslots] : 0);
- /*
- * Step 1: return the slots to the free list, merging the
- * slots with superceeding slots
- */
- for (i = index + nslots - 1; i >= index; i--) {
- io_tlb_list[i] = ++count;
- io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
- }
- /*
- * Step 2: merge the returned slots with the preceding slots,
- * if available (non zero)
- */
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
+ if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
+ count = io_tlb_list[index + nslots];
+ else
+ count = 0;
- io_tlb_used -= nslots;
+ /*
+ * Step 1: return the slots to the free list, merging the slots with
+ * superceeding slots
+ */
+ for (i = index + nslots - 1; i >= index; i--) {
+ io_tlb_list[i] = ++count;
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ io_tlb_orig_size[i] = 0;
}
+
+ /*
+ * Step 2: merge the returned slots with the preceding slots, if
+ * available (non zero)
+ */
+ for (i = index - 1;
+ io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i];
+ i--)
+ io_tlb_list[i] = ++count;
+ io_tlb_used -= nslots;
spin_unlock_irqrestore(&io_tlb_lock, flags);
}
@@ -645,11 +721,13 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
enum dma_sync_target target)
{
int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ size_t orig_size = io_tlb_orig_size[index];
phys_addr_t orig_addr = io_tlb_orig_addr[index];
if (orig_addr == INVALID_PHYS_ADDR)
return;
- orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
+
+ validate_sync_size_and_truncate(hwdev, orig_size, &size);
switch (target) {
case SYNC_FOR_CPU:
@@ -707,7 +785,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
size_t swiotlb_max_mapping_size(struct device *dev)
{
- return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+ return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE;
}
bool is_swiotlb_active(void)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 129dee540a8b..0aeca5f3c0ac 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -269,7 +269,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da
if (!event->parent) {
/*
* If this is a !child event, we must hold ctx::mutex to
- * stabilize the the event->ctx relation. See
+ * stabilize the event->ctx relation. See
* perf_event_ctx_lock().
*/
lockdep_assert_held(&ctx->mutex);
@@ -1303,7 +1303,7 @@ static void put_ctx(struct perf_event_context *ctx)
* life-time rules separate them. That is an exiting task cannot fork, and a
* spawning task cannot (yet) exit.
*
- * But remember that that these are parent<->child context relations, and
+ * But remember that these are parent<->child context relations, and
* migration does not affect children, therefore these two orderings should not
* interact.
*
@@ -1442,7 +1442,7 @@ static u64 primary_event_id(struct perf_event *event)
/*
* Get the perf_event_context for a task and lock it.
*
- * This has to cope with with the fact that until it is locked,
+ * This has to cope with the fact that until it is locked,
* the context could get moved to another task.
*/
static struct perf_event_context *
@@ -2486,7 +2486,7 @@ static void perf_set_shadow_time(struct perf_event *event,
* But this is a bit hairy.
*
* So instead, we have an explicit cgroup call to remain
- * within the time time source all along. We believe it
+ * within the time source all along. We believe it
* is cleaner and simpler to understand.
*/
if (is_cgroup_event(event))
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 3ea7f8f92f1d..6addc9780319 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1733,7 +1733,7 @@ void uprobe_free_utask(struct task_struct *t)
}
/*
- * Allocate a uprobe_task object for the task if if necessary.
+ * Allocate a uprobe_task object for the task if necessary.
* Called when the thread hits a breakpoint.
*
* Returns:
diff --git a/kernel/fork.c b/kernel/fork.c
index d66cd1014211..d3171e8e88e5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1940,6 +1940,8 @@ static __latent_entropy struct task_struct *copy_process(
p = dup_task_struct(current, node);
if (!p)
goto fork_out;
+ if (args->io_thread)
+ p->flags |= PF_IO_WORKER;
/*
* This _must_ happen before we call free_task(), i.e. before we jump
@@ -2411,6 +2413,34 @@ struct mm_struct *copy_init_mm(void)
}
/*
+ * This is like kernel_clone(), but shaved down and tailored to just
+ * creating io_uring workers. It returns a created task, or an error pointer.
+ * The returned task is inactive, and the caller must fire it up through
+ * wake_up_new_task(p). All signals are blocked in the created task.
+ */
+struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node)
+{
+ unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|
+ CLONE_IO;
+ struct kernel_clone_args args = {
+ .flags = ((lower_32_bits(flags) | CLONE_VM |
+ CLONE_UNTRACED) & ~CSIGNAL),
+ .exit_signal = (lower_32_bits(flags) & CSIGNAL),
+ .stack = (unsigned long)fn,
+ .stack_size = (unsigned long)arg,
+ .io_thread = 1,
+ };
+ struct task_struct *tsk;
+
+ tsk = copy_process(NULL, 0, node, &args);
+ if (!IS_ERR(tsk)) {
+ sigfillset(&tsk->blocked);
+ sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
+ }
+ return tsk;
+}
+
+/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
diff --git a/kernel/groups.c b/kernel/groups.c
index fe7e6385530e..787b381c7c00 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -15,12 +15,7 @@
struct group_info *groups_alloc(int gidsetsize)
{
struct group_info *gi;
- unsigned int len;
-
- len = sizeof(struct group_info) + sizeof(kgid_t) * gidsetsize;
- gi = kmalloc(len, GFP_KERNEL_ACCOUNT|__GFP_NOWARN|__GFP_NORETRY);
- if (!gi)
- gi = __vmalloc(len, GFP_KERNEL_ACCOUNT);
+ gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT);
if (!gi)
return NULL;
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 39d30ccf8d87..48aaf2ac0d0d 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -13,8 +13,6 @@ void kimage_terminate(struct kimage *image);
int kimage_is_destination_range(struct kimage *image,
unsigned long start, unsigned long end);
-int machine_kexec_post_load(struct kimage *image);
-
extern struct mutex kexec_mutex;
#ifdef CONFIG_KEXEC_FILE
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 03b21135313c..48fff6437901 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1420,7 +1420,7 @@ rt_mutex_fasttrylock(struct rt_mutex *lock,
}
/*
- * Performs the wakeup of the the top-waiter and re-enables preemption.
+ * Performs the wakeup of the top-waiter and re-enables preemption.
*/
void rt_mutex_postunlock(struct wake_q_head *wake_q)
{
@@ -1819,7 +1819,7 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
* been started.
* @waiter: the pre-initialized rt_mutex_waiter
*
- * Wait for the the lock acquisition started on our behalf by
+ * Wait for the lock acquisition started on our behalf by
* rt_mutex_start_proxy_lock(). Upon failure, the caller must call
* rt_mutex_cleanup_proxy_lock().
*
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index ba67600c7b2c..abba5df50006 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1048,7 +1048,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
/*
* If there were already threads queued before us and:
- * 1) there are no no active locks, wake the front
+ * 1) there are no active locks, wake the front
* queued process(es) as the handoff bit might be set.
* 2) there are no active writers and some readers, the lock
* must be read owned; so we try to wake any read lock
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index d9dd94defc0a..9aa855a96c4a 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -119,7 +119,7 @@ EXPORT_SYMBOL(down_killable);
* @sem: the semaphore to be acquired
*
* Try to acquire the semaphore atomically. Returns 0 if the semaphore has
- * been acquired successfully or 1 if it it cannot be acquired.
+ * been acquired successfully or 1 if it cannot be acquired.
*
* NOTE: This return value is inverted from both spin_trylock and
* mutex_trylock! Be careful about this when converting code.
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 61db50f7ca86..821cf1723814 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request,
audit_ptrace(task);
retval = -EPERM;
- if (unlikely(task->flags & PF_KTHREAD))
+ if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
goto out;
if (same_thread_group(task, current))
goto out;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8a8bd7b13634..794c2cb945f8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5126,7 +5126,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
/*
* When a group wakes up we want to make sure that its quota is not already
* expired/exceeded, otherwise it may be allowed to steal additional ticks of
- * runtime as update_curr() throttling can not not trigger until it's on-rq.
+ * runtime as update_curr() throttling can not trigger until it's on-rq.
*/
static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
{
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 08ae45ad9261..acdae625c636 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -454,7 +454,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm)
/*
* For each cpu runqueue, if the task's mm match @mm, ensure that all
- * @mm's membarrier state set bits are also set in in the runqueue's
+ * @mm's membarrier state set bits are also set in the runqueue's
* membarrier state. This ensures that a runqueue scheduling
* between threads which are users of @mm has its membarrier state
* updated.
diff --git a/kernel/signal.c b/kernel/signal.c
index 5ad8566534e7..ba4d1ef39a9e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force)
return true;
/* Only allow kernel generated signals to this kthread */
- if (unlikely((t->flags & PF_KTHREAD) &&
+ if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
(handler == SIG_KTHREAD_KERNEL) && !force))
return true;
@@ -1096,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
/*
* Skip useless siginfo allocation for SIGKILL and kernel threads.
*/
- if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
+ if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
goto out_set;
/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c9fbdd848138..62fbd09b5dc1 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2962,7 +2962,7 @@ static struct ctl_table vm_table[] = {
.data = &block_dump,
.maxlen = sizeof(block_dump),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
{
@@ -2970,7 +2970,7 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_vfs_cache_pressure,
.maxlen = sizeof(sysctl_vfs_cache_pressure),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \
@@ -2980,7 +2980,7 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_legacy_va_layout,
.maxlen = sizeof(sysctl_legacy_va_layout),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
#endif
@@ -2990,7 +2990,7 @@ static struct ctl_table vm_table[] = {
.data = &node_reclaim_mode,
.maxlen = sizeof(node_reclaim_mode),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
},
{
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9c266b93cbc0..7fa82778c3e6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -694,7 +694,7 @@ config TRACEPOINT_BENCHMARK
help
This option creates the tracepoint "benchmark:benchmark_event".
When the tracepoint is enabled, it kicks off a kernel thread that
- goes into an infinite loop (calling cond_sched() to let other tasks
+ goes into an infinite loop (calling cond_resched() to let other tasks
run), and calls the tracepoint. Each iteration will record the time
it took to write to the tracepoint and the next iteration that
data will be passed to the tracepoint itself. That is, the tracepoint
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 7e44cea89fdc..b28d3e5013cd 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
+obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM),y)
obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c286c13bd31a..c221e4c3f625 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -312,8 +312,6 @@ record_it:
static void blk_trace_free(struct blk_trace *bt)
{
- debugfs_remove(bt->msg_file);
- debugfs_remove(bt->dropped_file);
relay_close(bt->rchan);
debugfs_remove(bt->dir);
free_percpu(bt->sequence);
@@ -545,10 +543,8 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
INIT_LIST_HEAD(&bt->running_list);
ret = -EIO;
- bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt,
- &blk_dropped_fops);
-
- bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
+ debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops);
+ debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
bt->rchan = relay_open("trace", dir, buts->buf_size,
buts->buf_nr, &blk_relay_callbacks, bt);
@@ -1868,7 +1864,17 @@ void blk_trace_remove_sysfs(struct device *dev)
#ifdef CONFIG_EVENT_TRACING
-void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes)
+/**
+ * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string.
+ * @rwbs: buffer to be filled
+ * @op: REQ_OP_XXX for the tracepoint
+ *
+ * Description:
+ * Maps the REQ_OP_XXX to character and fills the buffer provided by the
+ * caller with resulting string.
+ *
+ **/
+void blk_fill_rwbs(char *rwbs, unsigned int op)
{
int i = 0;
diff --git a/kernel/trace/error_report-traces.c b/kernel/trace/error_report-traces.c
new file mode 100644
index 000000000000..f89792c25b11
--- /dev/null
+++ b/kernel/trace/error_report-traces.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Error reporting trace points.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/error_report.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(error_report_end);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b9dad3500041..68744c51517e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2815,6 +2815,17 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
return 0;
/*
+ * It's possible that the event time delta is zero
+ * (has the same time stamp as the previous event)
+ * in which case write_stamp and before_stamp could
+ * be the same. In such a case, force before_stamp
+ * to be different than write_stamp. It doesn't
+ * matter what it is, as long as its different.
+ */
+ if (!delta)
+ rb_time_set(&cpu_buffer->before_stamp, 0);
+
+ /*
* If an event were to come in now, it would see that the
* write_stamp and the before_stamp are different, and assume
* that this event just added itself before updating
@@ -3307,9 +3318,13 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer,
goto out;
}
atomic_inc(&cpu_buffer->record_disabled);
- pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld after:%lld\n",
- cpu_buffer->cpu,
- ts + info->delta, info->ts, info->delta, info->after);
+ /* There's some cases in boot up that this can happen */
+ WARN_ON_ONCE(system_state != SYSTEM_BOOTING);
+ pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld before:%lld after:%lld%s\n",
+ cpu_buffer->cpu,
+ ts + info->delta, info->ts, info->delta,
+ info->before, info->after,
+ full ? " (full)" : "");
dump_buffer_page(bpage, info, tail);
atomic_dec(&ts_dump);
/* Do not re-enable checking */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e295c413580e..eccb4e1187cc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1929,6 +1929,12 @@ static int run_tracer_selftest(struct tracer *type)
if (!selftests_can_run)
return save_selftest(type);
+ if (!tracing_is_on()) {
+ pr_warn("Selftest for tracer %s skipped due to tracing disabled\n",
+ type->name);
+ return 0;
+ }
+
/*
* Run a selftest on this tracer.
* Here we reset the trace buffer, and set the current
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index dec13ff66077..a6446c03cfbc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -605,7 +605,6 @@ void trace_graph_function(struct trace_array *tr,
void trace_latency_header(struct seq_file *m);
void trace_default_header(struct seq_file *m);
void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
-int trace_empty(struct trace_iterator *iter);
void trace_graph_return(struct ftrace_graph_ret *trace);
int trace_graph_entry(struct ftrace_graph_ent *trace);
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 2979a96595b4..8d71e6c83f10 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1225,8 +1225,10 @@ static int __create_synth_event(const char *name, const char *raw_fields)
goto err;
}
- if (!argc)
+ if (!argc) {
+ argv_free(argv);
continue;
+ }
n_fields_this_loop = 0;
consumed = 0;
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-16 07:30:44 +0000