The padding field in the structure was previously reserved to
maintain a stable interface for potential new fields, ensuring
compatibility with user-space shared data structures.
However,it was accidentally removed by tiantao in a prior commit,
which may lead to incompatibility between user space and the kernel.
This patch reinstates the padding to restore the original structure
layout and preserve compatibility.
Fixes: 8ddde07a3d28 ("dma-mapping: benchmark: extract a common header file for map_benchmark definition")
Cc: stable(a)vger.kernel.org
Acked-by: Barry Song <baohua(a)kernel.org>
Signed-off-by: Qinxin Xia <xiaqinxin(a)huawei.com>
---
include/linux/map_benchmark.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h
index 62674c83bde4..48e2ff95332f 100644
--- a/include/linux/map_benchmark.h
+++ b/include/linux/map_benchmark.h
@@ -27,5 +27,6 @@ struct map_benchmark {
__u32 dma_dir; /* DMA data direction */
__u32 dma_trans_ns; /* time for DMA transmission in ns */
__u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */
+ __u8 expansion[76]; /* For future use */
};
#endif /* _KERNEL_DMA_BENCHMARK_H */
--
2.33.0
On s390 systems, which use a machine level hypervisor, PCI devices are
always accessed through a form of PCI pass-through which fundamentally
operates on a per PCI function granularity. This is also reflected in the
s390 PCI hotplug driver which creates hotplug slots for individual PCI
functions. Its reset_slot() function, which is a wrapper for
zpci_hot_reset_device(), thus also resets individual functions.
Currently, the kernel's PCI_SLOT() macro assigns the same pci_slot object
to multifunction devices. This approach worked fine on s390 systems that
only exposed virtual functions as individual PCI domains to the operating
system. Since commit 44510d6fa0c0 ("s390/pci: Handling multifunctions")
s390 supports exposing the topology of multifunction PCI devices by
grouping them in a shared PCI domain. When attempting to reset a function
through the hotplug driver, the shared slot assignment causes the wrong
function to be reset instead of the intended one. It also leaks memory as
we do create a pci_slot object for the function, but don't correctly free
it in pci_slot_release().
Add a flag for struct pci_slot to allow per function PCI slots for
functions managed through a hypervisor, which exposes individual PCI
functions while retaining the topology.
Fixes: 44510d6fa0c0 ("s390/pci: Handling multifunctions")
Cc: stable(a)vger.kernel.org
Suggested-by: Niklas Schnelle <schnelle(a)linux.ibm.com>
Signed-off-by: Farhan Ali <alifm(a)linux.ibm.com>
---
drivers/pci/pci.c | 5 +++--
drivers/pci/slot.c | 25 ++++++++++++++++++++++---
include/linux/pci.h | 1 +
3 files changed, 26 insertions(+), 5 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b14dd064006c..36ee38e0d817 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4980,8 +4980,9 @@ static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, bool probe)
static int pci_dev_reset_slot_function(struct pci_dev *dev, bool probe)
{
- if (dev->multifunction || dev->subordinate || !dev->slot ||
- dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
+ if (dev->subordinate || !dev->slot ||
+ dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+ (dev->multifunction && !dev->slot->per_func_slot))
return -ENOTTY;
return pci_reset_hotplug_slot(dev->slot->hotplug, probe);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 50fb3eb595fe..ed10fa3ae727 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -63,6 +63,22 @@ static ssize_t cur_speed_read_file(struct pci_slot *slot, char *buf)
return bus_speed_read(slot->bus->cur_bus_speed, buf);
}
+static bool pci_dev_matches_slot(struct pci_dev *dev, struct pci_slot *slot)
+{
+ if (slot->per_func_slot)
+ return dev->devfn == slot->number;
+
+ return PCI_SLOT(dev->devfn) == slot->number;
+}
+
+static bool pci_slot_enabled_per_func(void)
+{
+ if (IS_ENABLED(CONFIG_S390))
+ return true;
+
+ return false;
+}
+
static void pci_slot_release(struct kobject *kobj)
{
struct pci_dev *dev;
@@ -73,7 +89,7 @@ static void pci_slot_release(struct kobject *kobj)
down_read(&pci_bus_sem);
list_for_each_entry(dev, &slot->bus->devices, bus_list)
- if (PCI_SLOT(dev->devfn) == slot->number)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = NULL;
up_read(&pci_bus_sem);
@@ -166,7 +182,7 @@ void pci_dev_assign_slot(struct pci_dev *dev)
mutex_lock(&pci_slot_mutex);
list_for_each_entry(slot, &dev->bus->slots, list)
- if (PCI_SLOT(dev->devfn) == slot->number)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = slot;
mutex_unlock(&pci_slot_mutex);
}
@@ -265,6 +281,9 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
slot->bus = pci_bus_get(parent);
slot->number = slot_nr;
+ if (pci_slot_enabled_per_func())
+ slot->per_func_slot = 1;
+
slot->kobj.kset = pci_slots_kset;
slot_name = make_slot_name(name);
@@ -285,7 +304,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
down_read(&pci_bus_sem);
list_for_each_entry(dev, &parent->devices, bus_list)
- if (PCI_SLOT(dev->devfn) == slot_nr)
+ if (pci_dev_matches_slot(dev, slot))
dev->slot = slot;
up_read(&pci_bus_sem);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index d1fdf81fbe1e..6ad194597ab5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -78,6 +78,7 @@ struct pci_slot {
struct list_head list; /* Node in list of slots */
struct hotplug_slot *hotplug; /* Hotplug info (move here) */
unsigned char number; /* PCI_SLOT(pci_dev->devfn) */
+ unsigned int per_func_slot:1; /* Allow per function slot */
struct kobject kobj;
};
--
2.43.0
Commit 56a06bd40fab ("virtio_net: enable gso over UDP tunnel support.")
switches to check the alignment of the virtio_net_hdr_v1_hash_tunnel
even when doing the transmission even if the feature is not
negotiated. This will cause a series performance degradation of pktgen
as the skb->data can't satisfy the alignment requirement due to the
increase of the header size then virtio-net must prepare at least 2
sgs with indirect descriptors which will introduce overheads in the
device.
Fixing this by calculate the header alignment during probe so when
tunnel gso is not negotiated, we can less strict.
Pktgen in guest + XDP_DROP on TAP + vhost_net shows the TX PPS is
recovered from 2.4Mpps to 4.45Mpps.
Note that we still need a way to recover the performance when tunnel
gso is enabled, probably a new vnet header format.
Fixes: 56a06bd40fab ("virtio_net: enable gso over UDP tunnel support.")
Cc: stable(a)vger.kernel.org
Signed-off-by: Jason Wang <jasowang(a)redhat.com>
---
drivers/net/virtio_net.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 31bd32bdecaf..5b851df749c0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -441,6 +441,9 @@ struct virtnet_info {
/* Packet virtio header size */
u8 hdr_len;
+ /* header alignment */
+ size_t hdr_align;
+
/* Work struct for delayed refilling if we run low on memory. */
struct delayed_work refill;
@@ -3308,8 +3311,9 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
can_push = vi->any_header_sg &&
- !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) &&
+ !((unsigned long)skb->data & (vi->hdr_align - 1)) &&
!skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len;
+
/* Even if we can, don't push here yet as this would skew
* csum_start offset below. */
if (can_push)
@@ -6926,15 +6930,20 @@ static int virtnet_probe(struct virtio_device *vdev)
}
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO) ||
- virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO))
+ virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO)) {
vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash_tunnel);
- else if (vi->has_rss_hash_report)
+ vi->hdr_align = __alignof__(struct virtio_net_hdr_v1_hash_tunnel);
+ } else if (vi->has_rss_hash_report) {
vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash);
- else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
- virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
+ vi->hdr_align = __alignof__(struct virtio_net_hdr_v1_hash);
+ } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) ||
+ virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
- else
+ vi->hdr_align = __alignof__(struct virtio_net_hdr_mrg_rxbuf);
+ } else {
vi->hdr_len = sizeof(struct virtio_net_hdr);
+ vi->hdr_align = __alignof__(struct virtio_net_hdr);
+ }
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM))
vi->rx_tnl_csum = true;
--
2.31.1
The function mtk_dp_dt_parse() calls of_graph_get_endpoint_by_regs()
to get the endpoint device node, but fails to call of_node_put() to release
the reference when the function returns. This results in a device node
reference leak.
Fix this by adding the missing of_node_put() call before returning from
the function.
Found via static analysis and code review.
Fixes: f70ac097a2cf ("drm/mediatek: Add MT8195 Embedded DisplayPort driver")
Cc: stable(a)vger.kernel.org
Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com>
---
drivers/gpu/drm/mediatek/mtk_dp.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c
index bef6eeb30d3e..b0b1e158600f 100644
--- a/drivers/gpu/drm/mediatek/mtk_dp.c
+++ b/drivers/gpu/drm/mediatek/mtk_dp.c
@@ -2087,6 +2087,7 @@ static int mtk_dp_dt_parse(struct mtk_dp *mtk_dp,
endpoint = of_graph_get_endpoint_by_regs(pdev->dev.of_node, 1, -1);
len = of_property_count_elems_of_size(endpoint,
"data-lanes", sizeof(u32));
+ of_node_put(endpoint);
if (len < 0 || len > 4 || len == 3) {
dev_err(dev, "invalid data lane size: %d\n", len);
return -EINVAL;
--
2.39.5 (Apple Git-154)
of_graph_get_endpoint_by_regs() gets a reference to the endpoint node
to read the "bus-width" property but fails to call of_node_put()
to release the reference, causing a reference count leak.
Add the missing of_node_put() call to fix this.
Found via static analysis and code review.
Fixes: d284ccd8588c ("drm/bridge: sii902x: Set input bus format based on bus-width")
Cc: stable(a)vger.kernel.org
Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com>
---
drivers/gpu/drm/bridge/sii902x.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index d537b1d036fb..3a247ac3c7dd 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -1189,8 +1189,10 @@ static int sii902x_probe(struct i2c_client *client)
sii902x->bus_width = 24;
endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, -1);
- if (endpoint)
+ if (endpoint) {
of_property_read_u32(endpoint, "bus-width", &sii902x->bus_width);
+ of_node_put(endpoint);
+ }
endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 1, -1);
if (endpoint) {
--
2.39.5 (Apple Git-154)
If SMT is disabled or a partial SMT state is enabled, when a new kernel
image is loaded for kexec, on reboot the following warning is observed:
kexec: Waking offline cpu 228.
WARNING: CPU: 0 PID: 9062 at arch/powerpc/kexec/core_64.c:223 kexec_prepare_cpus+0x1b0/0x1bc
[snip]
NIP kexec_prepare_cpus+0x1b0/0x1bc
LR kexec_prepare_cpus+0x1a0/0x1bc
Call Trace:
kexec_prepare_cpus+0x1a0/0x1bc (unreliable)
default_machine_kexec+0x160/0x19c
machine_kexec+0x80/0x88
kernel_kexec+0xd0/0x118
__do_sys_reboot+0x210/0x2c4
system_call_exception+0x124/0x320
system_call_vectored_common+0x15c/0x2ec
This occurs as add_cpu() fails due to cpu_bootable() returning false for
CPUs that fail the cpu_smt_thread_allowed() check or non primary
threads if SMT is disabled.
Fix the issue by enabling SMT and resetting the number of SMT threads to
the number of threads per core, before attempting to wake up all present
CPUs.
Fixes: 38253464bc82 ("cpu/SMT: Create topology_smt_thread_allowed()")
Reported-by: Sachin P Bappalige <sachinpb(a)linux.ibm.com>
Cc: stable(a)vger.kernel.org # v6.6+
Signed-off-by: Nysal Jan K.A. <nysal(a)linux.ibm.com>
---
arch/powerpc/kexec/core_64.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 222aa326dace..ff6df43720c4 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -216,6 +216,11 @@ static void wake_offline_cpus(void)
{
int cpu = 0;
+ lock_device_hotplug();
+ cpu_smt_num_threads = threads_per_core;
+ cpu_smt_control = CPU_SMT_ENABLED;
+ unlock_device_hotplug();
+
for_each_present_cpu(cpu) {
if (!cpu_online(cpu)) {
printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
--
2.51.0
From: Hao Ge <gehao(a)kylinos.cn>
When alloc_slab_obj_exts() fails and then later succeeds in allocating
a slab extension vector, it calls handle_failed_objexts_alloc() to
mark all objects in the vector as empty. As a result all objects in
this slab (slabA) will have their extensions set to CODETAG_EMPTY.
Later on if this slabA is used to allocate a slabobj_ext vector for
another slab (slabB), we end up with the slabB->obj_exts pointing to a
slabobj_ext vector that itself has a non-NULL slabobj_ext equal to
CODETAG_EMPTY. When slabB gets freed, free_slab_obj_exts() is called
to free slabB->obj_exts vector. free_slab_obj_exts() calls
mark_objexts_empty(slabB->obj_exts) which will generate a warning
because it expects slabobj_ext vectors to have a NULL obj_ext, not
CODETAG_EMPTY.
Modify mark_objexts_empty() to skip the warning and setting the
obj_ext value if it's already set to CODETAG_EMPTY.
Fixes: 09c46563ff6d ("codetag: debug: introduce OBJEXTS_ALLOC_FAIL to mark failed slab_ext allocations")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Hao Ge <gehao(a)kylinos.cn>
---
v2: Update the commit message and code comments for greater accuracy,
incorporating Suren's suggestions.
Thanks for Suren's help.
---
mm/slub.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/mm/slub.c b/mm/slub.c
index d4367f25b20d..589c596163c4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2046,7 +2046,11 @@ static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
if (slab_exts) {
unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
obj_exts_slab, obj_exts);
- /* codetag should be NULL */
+
+ if (unlikely(is_codetag_empty(&slab_exts[offs].ref)))
+ return;
+
+ /* codetag should be NULL here */
WARN_ON(slab_exts[offs].ref.ct);
set_codetag_empty(&slab_exts[offs].ref);
}
--
2.25.1