This reverts commit 96e51ccf1af33e82f429a0d6baebba29c6448d0f.
Recently we started running the kernel with rstat infrastructure on
production traffic and begin to see negative memcg stats values.
Particularly the 'sock' stat is the one which we observed having
negative value.
$ grep "sock " /mnt/memory/job/memory.stat
sock 253952
total_sock 18446744073708724224
Re-run after couple of seconds
$ grep "sock " /mnt/memory/job/memory.stat
sock 253952
total_sock 53248
For now we are only seeing this issue on large machines (256 CPUs) and
only with 'sock' stat. I think the networking stack increase the stat on
one cpu and decrease it on another cpu much more often. So, this
negative sock is due to rstat flusher flushing the stats on the CPU that
has seen the decrement of sock but missed the CPU that has increments. A
typical race condition.
For easy stable backport, revert is the most simple solution. For long
term solution, I am thinking of two directions. First is just reduce the
race window by optimizing the rstat flusher. Second is if the reader
sees a negative stat value, force flush and restart the stat collection.
Basically retry but limited.
Signed-off-by: Shakeel Butt <shakeelb(a)google.com>
Cc: stable(a)vger.kernel.org # 5.15
---
include/linux/memcontrol.h | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 4d31ce55b1c0..6257867fbf95 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -987,19 +987,30 @@ static inline void mod_memcg_page_state(struct page *page,
static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
{
- return READ_ONCE(memcg->vmstats.state[idx]);
+ long x = READ_ONCE(memcg->vmstats.state[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
}
static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
enum node_stat_item idx)
{
struct mem_cgroup_per_node *pn;
+ long x;
if (mem_cgroup_disabled())
return node_page_state(lruvec_pgdat(lruvec), idx);
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- return READ_ONCE(pn->lruvec_stats.state[idx]);
+ x = READ_ONCE(pn->lruvec_stats.state[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
}
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
--
2.37.1.595.g718a3a8f04-goog
When the port does not support USB PD, prevent transition to PD
only states when power supply property is written. In this case,
TCPM transitions to SNK_NEGOTIATE_CAPABILITIES
which should not be the case given that the port is not pd_capable.
[ 84.308251] state change SNK_READY -> SNK_NEGOTIATE_CAPABILITIES [rev3 NONE_AMS]
[ 84.308335] Setting usb_comm capable false
[ 84.323367] set_auto_vbus_discharge_threshold mode:3 pps_active:n vbus:5000 ret:0
[ 84.323376] state change SNK_NEGOTIATE_CAPABILITIES -> SNK_WAIT_CAPABILITIES [rev3 NONE_AMS]
Fixes: e9e6e164ed8f6 ("usb: typec: tcpm: Support non-PD mode")
Cc: stable(a)vger.kernel.org
Signed-off-by: Badhri Jagan Sridharan <badhri(a)google.com>
---
Changes since v1:
- Add Fixes tag.
Changes since v2:
- CCed stable
---
drivers/usb/typec/tcpm/tcpm.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index ea5a917c51b1..904c7b4ce2f0 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -6320,6 +6320,13 @@ static int tcpm_psy_set_prop(struct power_supply *psy,
struct tcpm_port *port = power_supply_get_drvdata(psy);
int ret;
+ /*
+ * All the properties below are related to USB PD. The check needs to be
+ * property specific when a non-pd related property is added.
+ */
+ if (!port->pd_supported)
+ return -EOPNOTSUPP;
+
switch (psp) {
case POWER_SUPPLY_PROP_ONLINE:
ret = tcpm_psy_set_online(port, val);
--
2.37.1.595.g718a3a8f04-goog
The patch below was submitted to be applied to the 5.19-stable tree.
I fail to see how this patch meets the stable kernel rules as found at
Documentation/process/stable-kernel-rules.rst.
I could be totally wrong, and if so, please respond to
<stable(a)vger.kernel.org> and let me know why this patch should be
applied. Otherwise, it is now dropped from my patch queues, never to be
seen again.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From b1f707146923335849fb70237eec27d4d1ae7d62 Mon Sep 17 00:00:00 2001
From: Arun Easi <aeasi(a)marvell.com>
Date: Tue, 12 Jul 2022 22:20:39 -0700
Subject: [PATCH] scsi: qla2xxx: Fix response queue handler reading stale
packets
On some platforms, the current logic of relying on finding new packet
solely based on signature pattern can lead to driver reading stale
packets. Though this is a bug in those platforms, reduce such exposures by
limiting reading packets until the IN pointer.
Two module parameters are introduced:
ql2xrspq_follow_inptr:
When set, on newer adapters that has queue pointer shadowing, look for
response packets only until response queue in pointer.
When reset, response packets are read based on a signature pattern
logic (old way).
ql2xrspq_follow_inptr_legacy:
Like ql2xrspq_follow_inptr, but for those adapters where there is no
queue pointer shadowing.
Link: https://lore.kernel.org/r/20220713052045.10683-5-njavali@marvell.com
Cc: stable(a)vger.kernel.org
Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com>
Signed-off-by: Arun Easi <aeasi(a)marvell.com>
Signed-off-by: Nilesh Javali <njavali(a)marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 3674b35196b0..96147ca40126 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -193,6 +193,8 @@ extern int ql2xsecenable;
extern int ql2xenforce_iocb_limit;
extern int ql2xabts_wait_nvme;
extern u32 ql2xnvme_queues;
+extern int ql2xrspq_follow_inptr;
+extern int ql2xrspq_follow_inptr_legacy;
extern int qla2x00_loop_reset(scsi_qla_host_t *);
extern void qla2x00_abort_all_cmds(scsi_qla_host_t *, int);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 4fa24d318f14..35b425c446b9 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3780,6 +3780,8 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
struct qla_hw_data *ha = vha->hw;
struct purex_entry_24xx *purex_entry;
struct purex_item *pure_item;
+ u16 rsp_in = 0;
+ int follow_inptr, is_shadow_hba;
if (!ha->flags.fw_started)
return;
@@ -3789,7 +3791,25 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
qla_cpu_update(rsp->qpair, smp_processor_id());
}
- while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
+#define __update_rsp_in(_update, _is_shadow_hba, _rsp, _rsp_in) \
+ do { \
+ if (_update) { \
+ _rsp_in = _is_shadow_hba ? *(_rsp)->in_ptr : \
+ rd_reg_dword_relaxed((_rsp)->rsp_q_in); \
+ } \
+ } while (0)
+
+ is_shadow_hba = IS_SHADOW_REG_CAPABLE(ha);
+ follow_inptr = is_shadow_hba ? ql2xrspq_follow_inptr :
+ ql2xrspq_follow_inptr_legacy;
+
+ __update_rsp_in(follow_inptr, is_shadow_hba, rsp, rsp_in);
+
+ while ((likely(follow_inptr &&
+ rsp->ring_index != rsp_in &&
+ rsp->ring_ptr->signature != RESPONSE_PROCESSED)) ||
+ (!follow_inptr &&
+ rsp->ring_ptr->signature != RESPONSE_PROCESSED)) {
pkt = (struct sts_entry_24xx *)rsp->ring_ptr;
rsp->ring_index++;
@@ -3902,6 +3922,8 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
}
pure_item = qla27xx_copy_fpin_pkt(vha,
(void **)&pkt, &rsp);
+ __update_rsp_in(follow_inptr, is_shadow_hba,
+ rsp, rsp_in);
if (!pure_item)
break;
qla24xx_queue_purex_item(vha, pure_item,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1c7fb6484db2..0bd0fd1042df 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -338,6 +338,16 @@ module_param(ql2xdelay_before_pci_error_handling, uint, 0644);
MODULE_PARM_DESC(ql2xdelay_before_pci_error_handling,
"Number of seconds delayed before qla begin PCI error self-handling (default: 5).\n");
+int ql2xrspq_follow_inptr = 1;
+module_param(ql2xrspq_follow_inptr, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr,
+ "Follow RSP IN pointer for RSP updates for HBAs 27xx and newer (default: 1).");
+
+int ql2xrspq_follow_inptr_legacy = 1;
+module_param(ql2xrspq_follow_inptr_legacy, int, 0644);
+MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy,
+ "Follow RSP IN pointer for RSP updates for HBAs older than 27XX. (default: 1).");
+
static void qla2x00_clear_drv_active(struct qla_hw_data *);
static void qla2x00_free_device(scsi_qla_host_t *);
static int qla2xxx_map_queues(struct Scsi_Host *shost);
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 689a71493bd2f31c024f8c0395f85a1fd4b2138e Mon Sep 17 00:00:00 2001
From: Coiby Xu <coxu(a)redhat.com>
Date: Thu, 14 Jul 2022 21:40:24 +0800
Subject: [PATCH] kexec: clean up arch_kexec_kernel_verify_sig
Before commit 105e10e2cf1c ("kexec_file: drop weak attribute from
functions"), there was already no arch-specific implementation
of arch_kexec_kernel_verify_sig. With weak attribute dropped by that
commit, arch_kexec_kernel_verify_sig is completely useless. So clean it
up.
Note later patches are dependent on this patch so it should be backported
to the stable tree as well.
Cc: stable(a)vger.kernel.org
Suggested-by: Eric W. Biederman <ebiederm(a)xmission.com>
Reviewed-by: Michal Suchanek <msuchanek(a)suse.de>
Acked-by: Baoquan He <bhe(a)redhat.com>
Signed-off-by: Coiby Xu <coxu(a)redhat.com>
[zohar(a)linux.ibm.com: reworded patch description "Note"]
Link: https://lore.kernel.org/linux-integrity/20220714134027.394370-1-coxu@redhat…
Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com>
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 8107606ad1e8..7f710fb3712b 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -212,11 +212,6 @@ static inline void *arch_kexec_kernel_image_load(struct kimage *image)
}
#endif
-#ifdef CONFIG_KEXEC_SIG
-int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf,
- unsigned long buf_len);
-#endif
-
extern int kexec_add_buffer(struct kexec_buf *kbuf);
int kexec_locate_mem_hole(struct kexec_buf *kbuf);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 0c27c81351ee..6dc1294c90fc 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -81,24 +81,6 @@ int kexec_image_post_load_cleanup_default(struct kimage *image)
return image->fops->cleanup(image->image_loader_data);
}
-#ifdef CONFIG_KEXEC_SIG
-static int kexec_image_verify_sig_default(struct kimage *image, void *buf,
- unsigned long buf_len)
-{
- if (!image->fops || !image->fops->verify_sig) {
- pr_debug("kernel loader does not support signature verification.\n");
- return -EKEYREJECTED;
- }
-
- return image->fops->verify_sig(buf, buf_len);
-}
-
-int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, unsigned long buf_len)
-{
- return kexec_image_verify_sig_default(image, buf, buf_len);
-}
-#endif
-
/*
* Free up memory used by kernel, initrd, and command line. This is temporary
* memory allocation which is not needed any more after these buffers have
@@ -141,13 +123,24 @@ void kimage_file_post_load_cleanup(struct kimage *image)
}
#ifdef CONFIG_KEXEC_SIG
+static int kexec_image_verify_sig(struct kimage *image, void *buf,
+ unsigned long buf_len)
+{
+ if (!image->fops || !image->fops->verify_sig) {
+ pr_debug("kernel loader does not support signature verification.\n");
+ return -EKEYREJECTED;
+ }
+
+ return image->fops->verify_sig(buf, buf_len);
+}
+
static int
kimage_validate_signature(struct kimage *image)
{
int ret;
- ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
- image->kernel_buf_len);
+ ret = kexec_image_verify_sig(image, image->kernel_buf,
+ image->kernel_buf_len);
if (ret) {
if (sig_enforce) {