From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org>
Masami Hiramatsu reported a memory leak in register_ftrace_direct() where
if the number of new entries are added is large enough to cause two
allocations in the loop:
for (i = 0; i < size; i++) {
hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
if (!new)
goto out_remove;
entry->direct = addr;
}
}
Where ftrace_add_rec_direct() has:
if (ftrace_hash_empty(direct_functions) ||
direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
struct ftrace_hash *new_hash;
int size = ftrace_hash_empty(direct_functions) ? 0 :
direct_functions->count + 1;
if (size < 32)
size = 32;
new_hash = dup_hash(direct_functions, size);
if (!new_hash)
return NULL;
*free_hash = direct_functions;
direct_functions = new_hash;
}
The "*free_hash = direct_functions;" can happen twice, losing the previous
allocation of direct_functions.
But this also exposed a more serious bug.
The modification of direct_functions above is not safe. As
direct_functions can be referenced at any time to find what direct caller
it should call, the time between:
new_hash = dup_hash(direct_functions, size);
and
direct_functions = new_hash;
can have a race with another CPU (or even this one if it gets interrupted),
and the entries being moved to the new hash are not referenced.
That's because the "dup_hash()" is really misnamed and is really a
"move_hash()". It moves the entries from the old hash to the new one.
Now even if that was changed, this code is not proper as direct_functions
should not be updated until the end. That is the best way to handle
function reference changes, and is the way other parts of ftrace handles
this.
The following is done:
1. Change add_hash_entry() to return the entry it created and inserted
into the hash, and not just return success or not.
2. Replace ftrace_add_rec_direct() with add_hash_entry(), and remove
the former.
3. Allocate a "new_hash" at the start that is made for holding both the
new hash entries as well as the existing entries in direct_functions.
4. Copy (not move) the direct_function entries over to the new_hash.
5. Copy the entries of the added hash to the new_hash.
6. If everything succeeds, then use rcu_pointer_assign() to update the
direct_functions with the new_hash.
This simplifies the code and fixes both the memory leak as well as the
race condition mentioned above.
Link: https://lore.kernel.org/all/170368070504.42064.8960569647118388081.stgit@de…
Link: https://lore.kernel.org/linux-trace-kernel/20231229115134.08dd5174@gandalf.…
Cc: stable(a)vger.kernel.org
Cc: Masami Hiramatsu <mhiramat(a)kernel.org>
Cc: Mark Rutland <mark.rutland(a)arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: Alexei Starovoitov <ast(a)kernel.org>
Cc: Daniel Borkmann <daniel(a)iogearbox.net>
Fixes: 763e34e74bb7d ("ftrace: Add register_ftrace_direct()")
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
---
kernel/trace/ftrace.c | 100 ++++++++++++++++++++----------------------
1 file changed, 47 insertions(+), 53 deletions(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8de8bec5f366..b01ae7d36021 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash,
hash->count++;
}
-static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
+static struct ftrace_func_entry *
+add_hash_entry(struct ftrace_hash *hash, unsigned long ip)
{
struct ftrace_func_entry *entry;
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
- return -ENOMEM;
+ return NULL;
entry->ip = ip;
__add_hash_entry(hash, entry);
- return 0;
+ return entry;
}
static void
@@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
struct ftrace_func_entry *entry;
struct ftrace_hash *new_hash;
int size;
- int ret;
int i;
new_hash = alloc_ftrace_hash(size_bits);
@@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
size = 1 << hash->size_bits;
for (i = 0; i < size; i++) {
hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
- ret = add_hash_entry(new_hash, entry->ip);
- if (ret < 0)
+ if (add_hash_entry(new_hash, entry->ip) == NULL)
goto free_hash;
}
}
@@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
/* Protected by rcu_tasks for reading, and direct_mutex for writing */
-static struct ftrace_hash *direct_functions = EMPTY_HASH;
+static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH;
static DEFINE_MUTEX(direct_mutex);
int ftrace_direct_func_count;
@@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
return entry->direct;
}
-static struct ftrace_func_entry*
-ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
- struct ftrace_hash **free_hash)
-{
- struct ftrace_func_entry *entry;
-
- if (ftrace_hash_empty(direct_functions) ||
- direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
- struct ftrace_hash *new_hash;
- int size = ftrace_hash_empty(direct_functions) ? 0 :
- direct_functions->count + 1;
-
- if (size < 32)
- size = 32;
-
- new_hash = dup_hash(direct_functions, size);
- if (!new_hash)
- return NULL;
-
- *free_hash = direct_functions;
- direct_functions = new_hash;
- }
-
- entry = kmalloc(sizeof(*entry), GFP_KERNEL);
- if (!entry)
- return NULL;
-
- entry->ip = ip;
- entry->direct = addr;
- __add_hash_entry(direct_functions, entry);
- return entry;
-}
-
static void call_direct_funcs(unsigned long ip, unsigned long pip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
@@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter)
/* Do nothing if it exists */
if (entry)
return 0;
-
- ret = add_hash_entry(hash, rec->ip);
+ if (add_hash_entry(hash, rec->ip) == NULL)
+ ret = -ENOMEM;
}
return ret;
}
@@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
return 0;
}
- return add_hash_entry(hash, ip);
+ entry = add_hash_entry(hash, ip);
+ return entry ? 0 : -ENOMEM;
}
static int
@@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
*/
int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
{
- struct ftrace_hash *hash, *free_hash = NULL;
+ struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL;
struct ftrace_func_entry *entry, *new;
int err = -EBUSY, size, i;
@@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
}
}
- /* ... and insert them to direct_functions hash. */
err = -ENOMEM;
+
+ /* Make a copy hash to place the new and the old entries in */
+ size = hash->count + direct_functions->count;
+ if (size > 32)
+ size = 32;
+ new_hash = alloc_ftrace_hash(fls(size));
+ if (!new_hash)
+ goto out_unlock;
+
+ /* Now copy over the existing direct entries */
+ size = 1 << direct_functions->size_bits;
+ for (i = 0; i < size; i++) {
+ hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) {
+ new = add_hash_entry(new_hash, entry->ip);
+ if (!new)
+ goto out_unlock;
+ new->direct = entry->direct;
+ }
+ }
+
+ /* ... and add the new entries */
+ size = 1 << hash->size_bits;
for (i = 0; i < size; i++) {
hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
- new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+ new = add_hash_entry(new_hash, entry->ip);
if (!new)
- goto out_remove;
+ goto out_unlock;
+ /* Update both the copy and the hash entry */
+ new->direct = addr;
entry->direct = addr;
}
}
+ free_hash = direct_functions;
+ rcu_assign_pointer(direct_functions, new_hash);
+ new_hash = NULL;
+
ops->func = call_direct_funcs;
ops->flags = MULTI_FLAGS;
ops->trampoline = FTRACE_REGS_ADDR;
@@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
err = register_ftrace_function_nolock(ops);
- out_remove:
- if (err)
- remove_direct_functions_hash(hash, addr);
-
out_unlock:
mutex_unlock(&direct_mutex);
- if (free_hash) {
+ if (free_hash && free_hash != EMPTY_HASH) {
synchronize_rcu_tasks();
free_ftrace_hash(free_hash);
}
+
+ if (new_hash)
+ free_ftrace_hash(new_hash);
+
return err;
}
EXPORT_SYMBOL_GPL(register_ftrace_direct);
@@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
if (entry)
continue;
- if (add_hash_entry(hash, rec->ip) < 0)
+ if (add_hash_entry(hash, rec->ip) == NULL)
goto out;
} else {
if (entry) {
--
2.42.0
From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org>
If an application blocks on the snapshot or snapshot_raw files, expecting
to be woken up when a snapshot occurs, it will not happen. Or it may
happen with an unexpected result.
That result is that the application will be reading the main buffer
instead of the snapshot buffer. That is because when the snapshot occurs,
the main and snapshot buffers are swapped. But the reader has a descriptor
still pointing to the buffer that it originally connected to.
This is fine for the main buffer readers, as they may be blocked waiting
for a watermark to be hit, and when a snapshot occurs, the data that the
main readers want is now on the snapshot buffer.
But for waiters of the snapshot buffer, they are waiting for an event to
occur that will trigger the snapshot and they can then consume it quickly
to save the snapshot before the next snapshot occurs. But to do this, they
need to read the new snapshot buffer, not the old one that is now
receiving new data.
Also, it does not make sense to have a watermark "buffer_percent" on the
snapshot buffer, as the snapshot buffer is static and does not receive new
data except all at once.
Link: https://lore.kernel.org/linux-trace-kernel/20231228095149.77f5b45d@gandalf.…
Cc: stable(a)vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com>
Cc: Mark Rutland <mark.rutland(a)arm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org>
Fixes: debdd57f5145f ("tracing: Make a snapshot feature available from userspace")
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
---
kernel/trace/ring_buffer.c | 3 ++-
kernel/trace/trace.c | 20 +++++++++++++++++---
2 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 32c0dd2fd1c3..9286f88fcd32 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -949,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
/* make sure the waiters see the new index */
smp_wmb();
- rb_wake_up_waiters(&rbwork->work);
+ /* This can be called in any context */
+ irq_work_queue(&rbwork->work);
}
/**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 199df497db07..a0defe156b57 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1894,6 +1894,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
+
+ /* Any waiters on the old snapshot buffer need to wake up */
+ ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS);
}
/**
@@ -1945,12 +1948,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
static int wait_on_pipe(struct trace_iterator *iter, int full)
{
+ int ret;
+
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
return 0;
- return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file,
- full);
+ ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ /*
+ * Make sure this is still the snapshot buffer, as if a snapshot were
+ * to happen, this would now be the main buffer.
+ */
+ if (iter->snapshot)
+ iter->array_buffer = &iter->tr->max_buffer;
+#endif
+ return ret;
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -8517,7 +8531,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
wait_index = READ_ONCE(iter->wait_index);
- ret = wait_on_pipe(iter, iter->tr->buffer_percent);
+ ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent);
if (ret)
goto out;
--
2.42.0
From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org>
The tracefs file "buffer_percent" is to allow user space to set a
water-mark on how much of the tracing ring buffer needs to be filled in
order to wake up a blocked reader.
0 - is to wait until any data is in the buffer
1 - is to wait for 1% of the sub buffers to be filled
50 - would be half of the sub buffers are filled with data
100 - is not to wake the waiter until the ring buffer is completely full
Unfortunately the test for being full was:
dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
return (dirty * 100) > (full * nr_pages);
Where "full" is the value for "buffer_percent".
There is two issues with the above when full == 100.
1. dirty * 100 > 100 * nr_pages will never be true
That is, the above is basically saying that if the user sets
buffer_percent to 100, more pages need to be dirty than exist in the
ring buffer!
2. The page that the writer is on is never considered dirty, as dirty
pages are only those that are full. When the writer goes to a new
sub-buffer, it clears the contents of that sub-buffer.
That is, even if the check was ">=" it would still not be equal as the
most pages that can be considered "dirty" is nr_pages - 1.
To fix this, add one to dirty and use ">=" in the compare.
Link: https://lore.kernel.org/linux-trace-kernel/20231226125902.4a057f1d@gandalf.…
Cc: stable(a)vger.kernel.org
Cc: Mark Rutland <mark.rutland(a)arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org>
Fixes: 03329f9939781 ("tracing: Add tracefs file buffer_percentage")
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
---
kernel/trace/ring_buffer.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 83eab547f1d1..32c0dd2fd1c3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -881,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f
if (!nr_pages || !full)
return true;
- dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+ /*
+ * Add one as dirty will never equal nr_pages, as the sub-buffer
+ * that the writer is on is not counted as dirty.
+ * This is needed if "buffer_percent" is set to 100.
+ */
+ dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1;
- return (dirty * 100) > (full * nr_pages);
+ return (dirty * 100) >= (full * nr_pages);
}
/*
--
2.42.0
The quilt patch titled
Subject: mm/sparsemem: fix race in accessing memory_section->usage
has been removed from the -mm tree. Its filename was
mm-sparsemem-fix-race-in-accessing-memory_section-usage.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Charan Teja Kalla <quic_charante(a)quicinc.com>
Subject: mm/sparsemem: fix race in accessing memory_section->usage
Date: Fri, 13 Oct 2023 18:34:27 +0530
The below race is observed on a PFN which falls into the device memory
region with the system memory configuration where PFN's are such that
[ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL]. Since normal zone start and end
pfn contains the device memory PFN's as well, the compaction triggered
will try on the device memory PFN's too though they end up in NOP(because
pfn_to_online_page() returns NULL for ZONE_DEVICE memory sections). When
from other core, the section mappings are being removed for the
ZONE_DEVICE region, that the PFN in question belongs to, on which
compaction is currently being operated is resulting into the kernel crash
with CONFIG_SPASEMEM_VMEMAP enabled. The crash logs can be seen at [1].
compact_zone() memunmap_pages
------------- ---------------
__pageblock_pfn_to_page
......
(a)pfn_valid():
valid_section()//return true
(b)__remove_pages()->
sparse_remove_section()->
section_deactivate():
[Free the array ms->usage and set
ms->usage = NULL]
pfn_section_valid()
[Access ms->usage which
is NULL]
NOTE: From the above it can be said that the race is reduced to between
the pfn_valid()/pfn_section_valid() and the section deactivate with
SPASEMEM_VMEMAP enabled.
The commit b943f045a9af("mm/sparse: fix kernel crash with
pfn_section_valid check") tried to address the same problem by clearing
the SECTION_HAS_MEM_MAP with the expectation of valid_section() returns
false thus ms->usage is not accessed.
Fix this issue by the below steps:
a) Clear SECTION_HAS_MEM_MAP before freeing the ->usage.
b) RCU protected read side critical section will either return NULL
when SECTION_HAS_MEM_MAP is cleared or can successfully access ->usage.
c) Free the ->usage with kfree_rcu() and set ms->usage = NULL. No
attempt will be made to access ->usage after this as the
SECTION_HAS_MEM_MAP is cleared thus valid_section() return false.
Thanks to David/Pavan for their inputs on this patch.
[1] https://lore.kernel.org/linux-mm/994410bb-89aa-d987-1f50-f514903c55aa@quici…
On Snapdragon SoC, with the mentioned memory configuration of PFN's as
[ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL], we are able to see bunch of
issues daily while testing on a device farm.
For this particular issue below is the log. Though the below log is
not directly pointing to the pfn_section_valid(){ ms->usage;}, when we
loaded this dump on T32 lauterbach tool, it is pointing.
[ 540.578056] Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000000
[ 540.578068] Mem abort info:
[ 540.578070] ESR = 0x0000000096000005
[ 540.578073] EC = 0x25: DABT (current EL), IL = 32 bits
[ 540.578077] SET = 0, FnV = 0
[ 540.578080] EA = 0, S1PTW = 0
[ 540.578082] FSC = 0x05: level 1 translation fault
[ 540.578085] Data abort info:
[ 540.578086] ISV = 0, ISS = 0x00000005
[ 540.578088] CM = 0, WnR = 0
[ 540.579431] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBSBTYPE=--)
[ 540.579436] pc : __pageblock_pfn_to_page+0x6c/0x14c
[ 540.579454] lr : compact_zone+0x994/0x1058
[ 540.579460] sp : ffffffc03579b510
[ 540.579463] x29: ffffffc03579b510 x28: 0000000000235800 x27:000000000000000c
[ 540.579470] x26: 0000000000235c00 x25: 0000000000000068 x24:ffffffc03579b640
[ 540.579477] x23: 0000000000000001 x22: ffffffc03579b660 x21:0000000000000000
[ 540.579483] x20: 0000000000235bff x19: ffffffdebf7e3940 x18:ffffffdebf66d140
[ 540.579489] x17: 00000000739ba063 x16: 00000000739ba063 x15:00000000009f4bff
[ 540.579495] x14: 0000008000000000 x13: 0000000000000000 x12:0000000000000001
[ 540.579501] x11: 0000000000000000 x10: 0000000000000000 x9 :ffffff897d2cd440
[ 540.579507] x8 : 0000000000000000 x7 : 0000000000000000 x6 :ffffffc03579b5b4
[ 540.579512] x5 : 0000000000027f25 x4 : ffffffc03579b5b8 x3 :0000000000000001
[ 540.579518] x2 : ffffffdebf7e3940 x1 : 0000000000235c00 x0 :0000000000235800
[ 540.579524] Call trace:
[ 540.579527] __pageblock_pfn_to_page+0x6c/0x14c
[ 540.579533] compact_zone+0x994/0x1058
[ 540.579536] try_to_compact_pages+0x128/0x378
[ 540.579540] __alloc_pages_direct_compact+0x80/0x2b0
[ 540.579544] __alloc_pages_slowpath+0x5c0/0xe10
[ 540.579547] __alloc_pages+0x250/0x2d0
[ 540.579550] __iommu_dma_alloc_noncontiguous+0x13c/0x3fc
[ 540.579561] iommu_dma_alloc+0xa0/0x320
[ 540.579565] dma_alloc_attrs+0xd4/0x108
[quic_charante(a)quicinc.com: use kfree_rcu() in place of synchronize_rcu(), per David]
Link: https://lkml.kernel.org/r/1698403778-20938-1-git-send-email-quic_charante@q…
Link: https://lkml.kernel.org/r/1697202267-23600-1-git-send-email-quic_charante@q…
Fixes: f46edbd1b151 ("mm/sparsemem: add helpers track active portions of a section at boot")
Signed-off-by: Charan Teja Kalla <quic_charante(a)quicinc.com>
Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com>
Cc: Dan Williams <dan.j.williams(a)intel.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Mel Gorman <mgorman(a)techsingularity.net>
Cc: Oscar Salvador <osalvador(a)suse.de>
Cc: Vlastimil Babka <vbabka(a)suse.cz>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/mmzone.h | 14 +++++++++++---
mm/sparse.c | 17 +++++++++--------
2 files changed, 20 insertions(+), 11 deletions(-)
--- a/include/linux/mmzone.h~mm-sparsemem-fix-race-in-accessing-memory_section-usage
+++ a/include/linux/mmzone.h
@@ -1799,6 +1799,7 @@ static inline unsigned long section_nr_t
#define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
struct mem_section_usage {
+ struct rcu_head rcu;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
#endif
@@ -1992,7 +1993,7 @@ static inline int pfn_section_valid(stru
{
int idx = subsection_map_index(pfn);
- return test_bit(idx, ms->usage->subsection_map);
+ return test_bit(idx, READ_ONCE(ms->usage)->subsection_map);
}
#else
static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
@@ -2016,6 +2017,7 @@ static inline int pfn_section_valid(stru
static inline int pfn_valid(unsigned long pfn)
{
struct mem_section *ms;
+ int ret;
/*
* Ensure the upper PAGE_SHIFT bits are clear in the
@@ -2029,13 +2031,19 @@ static inline int pfn_valid(unsigned lon
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
ms = __pfn_to_section(pfn);
- if (!valid_section(ms))
+ rcu_read_lock();
+ if (!valid_section(ms)) {
+ rcu_read_unlock();
return 0;
+ }
/*
* Traditionally early sections always returned pfn_valid() for
* the entire section-sized span.
*/
- return early_section(ms) || pfn_section_valid(ms, pfn);
+ ret = early_section(ms) || pfn_section_valid(ms, pfn);
+ rcu_read_unlock();
+
+ return ret;
}
#endif
--- a/mm/sparse.c~mm-sparsemem-fix-race-in-accessing-memory_section-usage
+++ a/mm/sparse.c
@@ -792,6 +792,13 @@ static void section_deactivate(unsigned
unsigned long section_nr = pfn_to_section_nr(pfn);
/*
+ * Mark the section invalid so that valid_section()
+ * return false. This prevents code from dereferencing
+ * ms->usage array.
+ */
+ ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+
+ /*
* When removing an early section, the usage map is kept (as the
* usage maps of other sections fall into the same page). It
* will be re-used when re-adding the section - which is then no
@@ -799,16 +806,10 @@ static void section_deactivate(unsigned
* was allocated during boot.
*/
if (!PageReserved(virt_to_page(ms->usage))) {
- kfree(ms->usage);
- ms->usage = NULL;
+ kfree_rcu(ms->usage, rcu);
+ WRITE_ONCE(ms->usage, NULL);
}
memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
- /*
- * Mark the section invalid so that valid_section()
- * return false. This prevents code from dereferencing
- * ms->usage array.
- */
- ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
}
/*
_
Patches currently in -mm which might be from quic_charante(a)quicinc.com are
The quilt patch titled
Subject: mm: migrate: fix getting incorrect page mapping during page migration
has been removed from the -mm tree. Its filename was
mm-migrate-fix-getting-incorrect-page-mapping-during-page-migration.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Subject: mm: migrate: fix getting incorrect page mapping during page migration
Date: Fri, 15 Dec 2023 20:07:52 +0800
When running stress-ng testing, we found below kernel crash after a few hours:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
pc : dentry_name+0xd8/0x224
lr : pointer+0x22c/0x370
sp : ffff800025f134c0
......
Call trace:
dentry_name+0xd8/0x224
pointer+0x22c/0x370
vsnprintf+0x1ec/0x730
vscnprintf+0x2c/0x60
vprintk_store+0x70/0x234
vprintk_emit+0xe0/0x24c
vprintk_default+0x3c/0x44
vprintk_func+0x84/0x2d0
printk+0x64/0x88
__dump_page+0x52c/0x530
dump_page+0x14/0x20
set_migratetype_isolate+0x110/0x224
start_isolate_page_range+0xc4/0x20c
offline_pages+0x124/0x474
memory_block_offline+0x44/0xf4
memory_subsys_offline+0x3c/0x70
device_offline+0xf0/0x120
......
After analyzing the vmcore, I found this issue is caused by page migration.
The scenario is that, one thread is doing page migration, and we will use the
target page's ->mapping field to save 'anon_vma' pointer between page unmap and
page move, and now the target page is locked and refcount is 1.
Currently, there is another stress-ng thread performing memory hotplug,
attempting to offline the target page that is being migrated. It discovers that
the refcount of this target page is 1, preventing the offline operation, thus
proceeding to dump the page. However, page_mapping() of the target page may
return an incorrect file mapping to crash the system in dump_mapping(), since
the target page->mapping only saves 'anon_vma' pointer without setting
PAGE_MAPPING_ANON flag.
There are seveval ways to fix this issue:
(1) Setting the PAGE_MAPPING_ANON flag for target page's ->mapping when saving
'anon_vma', but this can confuse PageAnon() for PFN walkers, since the target
page has not built mappings yet.
(2) Getting the page lock to call page_mapping() in __dump_page() to avoid crashing
the system, however, there are still some PFN walkers that call page_mapping()
without holding the page lock, such as compaction.
(3) Using target page->private field to save the 'anon_vma' pointer and 2 bits
page state, just as page->mapping records an anonymous page, which can remove
the page_mapping() impact for PFN walkers and also seems a simple way.
So I choose option 3 to fix this issue, and this can also fix other potential
issues for PFN walkers, such as compaction.
Link: https://lkml.kernel.org/r/e60b17a88afc38cb32f84c3e30837ec70b343d2b.17026417…
Fixes: 64c8902ed441 ("migrate_pages: split unmap_and_move() to _unmap() and _move()")
Signed-off-by: Baolin Wang <baolin.wang(a)linux.alibaba.com>
Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: Xu Yu <xuyu(a)linux.alibaba.com>
Cc: Zi Yan <ziy(a)nvidia.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/migrate.c | 27 ++++++++++-----------------
1 file changed, 10 insertions(+), 17 deletions(-)
--- a/mm/migrate.c~mm-migrate-fix-getting-incorrect-page-mapping-during-page-migration
+++ a/mm/migrate.c
@@ -1025,38 +1025,31 @@ out:
}
/*
- * To record some information during migration, we use some unused
- * fields (mapping and private) of struct folio of the newly allocated
- * destination folio. This is safe because nobody is using them
- * except us.
+ * To record some information during migration, we use unused private
+ * field of struct folio of the newly allocated destination folio.
+ * This is safe because nobody is using it except us.
*/
-union migration_ptr {
- struct anon_vma *anon_vma;
- struct address_space *mapping;
-};
-
enum {
PAGE_WAS_MAPPED = BIT(0),
PAGE_WAS_MLOCKED = BIT(1),
+ PAGE_OLD_STATES = PAGE_WAS_MAPPED | PAGE_WAS_MLOCKED,
};
static void __migrate_folio_record(struct folio *dst,
- unsigned long old_page_state,
+ int old_page_state,
struct anon_vma *anon_vma)
{
- union migration_ptr ptr = { .anon_vma = anon_vma };
- dst->mapping = ptr.mapping;
- dst->private = (void *)old_page_state;
+ dst->private = (void *)anon_vma + old_page_state;
}
static void __migrate_folio_extract(struct folio *dst,
int *old_page_state,
struct anon_vma **anon_vmap)
{
- union migration_ptr ptr = { .mapping = dst->mapping };
- *anon_vmap = ptr.anon_vma;
- *old_page_state = (unsigned long)dst->private;
- dst->mapping = NULL;
+ unsigned long private = (unsigned long)dst->private;
+
+ *anon_vmap = (struct anon_vma *)(private & ~PAGE_OLD_STATES);
+ *old_page_state = private & PAGE_OLD_STATES;
dst->private = NULL;
}
_
Patches currently in -mm which might be from baolin.wang(a)linux.alibaba.com are
The quilt patch titled
Subject: mm: fix unmap_mapping_range high bits shift bug
has been removed from the -mm tree. Its filename was
mm-fix-unmap_mapping_range-high-bits-shift-bug.patch
This patch was dropped because it was merged into the mm-hotfixes-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Jiajun Xie <jiajun.xie.sh(a)gmail.com>
Subject: mm: fix unmap_mapping_range high bits shift bug
Date: Wed, 20 Dec 2023 13:28:39 +0800
The bug happens when highest bit of holebegin is 1, suppose holebegin is
0x8000000111111000, after shift, hba would be 0xfff8000000111111, then
vma_interval_tree_foreach would look it up fail or leads to the wrong
result.
error call seq e.g.:
- mmap(..., offset=0x8000000111111000)
|- syscall(mmap, ... unsigned long, off):
|- ksys_mmap_pgoff( ... , off >> PAGE_SHIFT);
here pgoff is correctly shifted to 0x8000000111111,
but pass 0x8000000111111000 as holebegin to unmap
would then cause terrible result, as shown below:
- unmap_mapping_range(..., loff_t const holebegin)
|- pgoff_t hba = holebegin >> PAGE_SHIFT;
/* hba = 0xfff8000000111111 unexpectedly */
The issue happens in Heterogeneous computing, where the device(e.g.
gpu) and host share the same virtual address space.
A simple workflow pattern which hit the issue is:
/* host */
1. userspace first mmap a file backed VA range with specified offset.
e.g. (offset=0x800..., mmap return: va_a)
2. write some data to the corresponding sys page
e.g. (va_a = 0xAABB)
/* device */
3. gpu workload touches VA, triggers gpu fault and notify the host.
/* host */
4. reviced gpu fault notification, then it will:
4.1 unmap host pages and also takes care of cpu tlb
(use unmap_mapping_range with offset=0x800...)
4.2 migrate sys page to device
4.3 setup device page table and resolve device fault.
/* device */
5. gpu workload continued, it accessed va_a and got 0xAABB.
6. gpu workload continued, it wrote 0xBBCC to va_a.
/* host */
7. userspace access va_a, as expected, it will:
7.1 trigger cpu vm fault.
7.2 driver handling fault to migrate gpu local page to host.
8. userspace then could correctly get 0xBBCC from va_a
9. done
But in step 4.1, if we hit the bug this patch mentioned, then userspace
would never trigger cpu fault, and still get the old value: 0xAABB.
Making holebegin unsigned first fixes the bug.
Link: https://lkml.kernel.org/r/20231220052839.26970-1-jiajun.xie.sh@gmail.com
Signed-off-by: Jiajun Xie <jiajun.xie.sh(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/memory.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/mm/memory.c~mm-fix-unmap_mapping_range-high-bits-shift-bug
+++ a/mm/memory.c
@@ -3624,8 +3624,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages);
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
- pgoff_t hba = holebegin >> PAGE_SHIFT;
- pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT;
+ pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
_
Patches currently in -mm which might be from jiajun.xie.sh(a)gmail.com are
The TongFang GMxXGxx, which needs IRQ overriding for the keyboard to work,
is also sold as the Eluktronics RP-15 which does not use the standard
TongFang GMxXGxx DMI board_name.
Add an entry for this laptop to the irq1_edge_low_force_override[] DMI
table to make the internal keyboard functional.
Reported-by: Luis Acuna <ldacuna(a)gmail.com>
Cc: Werner Sembach <wse(a)tuxedocomputers.com>
Cc: All applicable <stable(a)vger.kernel.org>
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
---
Note reportedy by private email so not Closes tag
---
drivers/acpi/resource.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 9bd9f79cd409..c3536c236be9 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -510,6 +510,13 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"),
},
},
+ {
+ /* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+ DMI_MATCH(DMI_BOARD_NAME, "RP-15"),
+ },
+ },
{
/* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */
.matches = {
--
2.41.0