The patch below does not apply to the 6.3-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>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.3.y
git checkout FETCH_HEAD
git cherry-pick -x f1a0898b5d6a77d332d036da03bad6fa9770de5b
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023062625-squeamish-trident-4e6a@gregkh' --subject-prefix 'PATCH 6.3.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From f1a0898b5d6a77d332d036da03bad6fa9770de5b Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd(a)google.com>
Date: Fri, 9 Jun 2023 14:29:39 -0700
Subject: [PATCH] wifi: iwlwifi: mvm: spin_lock_bh() to fix lockdep regression
Lockdep on 6.4-rc on ThinkPad X1 Carbon 5th says
=====================================================
WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected
6.4.0-rc5 #1 Not tainted
-----------------------------------------------------
kworker/3:1/49 [HC0[0]:SC0[4]:HE1:SE0] is trying to acquire:
ffff8881066fa368 (&mvm_sta->deflink.lq_sta.rs_drv.pers.lock){+.+.}-{2:2}, at: rs_drv_get_rate+0x46/0xe7
and this task is already holding:
ffff8881066f80a8 (&sta->rate_ctrl_lock){+.-.}-{2:2}, at: rate_control_get_rate+0xbd/0x126
which would create a new lock dependency:
(&sta->rate_ctrl_lock){+.-.}-{2:2} -> (&mvm_sta->deflink.lq_sta.rs_drv.pers.lock){+.+.}-{2:2}
but this new dependency connects a SOFTIRQ-irq-safe lock:
(&sta->rate_ctrl_lock){+.-.}-{2:2}
etc. etc. etc.
Changing the spin_lock() in rs_drv_get_rate() to spin_lock_bh() was not
enough to pacify lockdep, but changing them all on pers.lock has worked.
Fixes: a8938bc881d2 ("wifi: iwlwifi: mvm: Add locking to the rate read flow")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Link: https://lore.kernel.org/r/79ffcc22-9775-cb6d-3ffd-1a517c40beef@google.com
Signed-off-by: Johannes Berg <johannes.berg(a)intel.com>
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 23266d0c9ce4..9a20468345e4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -2692,7 +2692,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
lq_sta = mvm_sta;
- spin_lock(&lq_sta->pers.lock);
+ spin_lock_bh(&lq_sta->pers.lock);
iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags,
info->band, &info->control.rates[0]);
info->control.rates[0].count = 1;
@@ -2707,7 +2707,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band,
&txrc->reported_rate);
}
- spin_unlock(&lq_sta->pers.lock);
+ spin_unlock_bh(&lq_sta->pers.lock);
}
static void *rs_drv_alloc_sta(void *mvm_rate, struct ieee80211_sta *sta,
@@ -3264,11 +3264,11 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
/* If it's locked we are in middle of init flow
* just wait for next tx status to update the lq_sta data
*/
- if (!spin_trylock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock))
+ if (!spin_trylock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock))
return;
__iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp);
- spin_unlock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
+ spin_unlock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
}
#ifdef CONFIG_MAC80211_DEBUGFS
@@ -4117,9 +4117,9 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm,
} else {
struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
- spin_lock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
+ spin_lock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
rs_drv_rate_init(mvm, sta, band);
- spin_unlock(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
+ spin_unlock_bh(&mvmsta->deflink.lq_sta.rs_drv.pers.lock);
}
}
When a grant entry is still in use by the remote domain, Linux must put
it on a deferred list. Normally, this list is very short, because
the PV network and block protocols expect the backend to unmap the grant
first. However, Qubes OS's GUI protocol is subject to the constraints
of the X Window System, and as such winds up with the frontend unmapping
the window first. As a result, the list can grow very large, resulting
in a massive memory leak and eventual VM freeze.
To partially solve this problem, make the number of entries that the VM
will attempt to free at each iteration tunable. The default is still
10, but it can be overridden at compile-time (via Kconfig), boot-time
(via a kernel command-line option), or runtime (via sysfs).
This is Cc: stable because (when combined with appropriate userspace
changes) it fixes a severe performance and stability problem for Qubes
OS users.
Cc: stable(a)vger.kernel.org
Signed-off-by: Demi Marie Obenour <demi(a)invisiblethingslab.com>
---
drivers/xen/grant-table.c | 40 ++++++++++++++++++++++++++++-----------
2 files changed, 41 insertions(+), 11 deletions(-)
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index e1ec725c2819d4d5dede063eb00d86a6d52944c0..fa666aa6abc3e786dddc94f895641505ec0b23d8 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -498,14 +498,20 @@ static LIST_HEAD(deferred_list);
static void gnttab_handle_deferred(struct timer_list *);
static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred);
+static atomic64_t deferred_count;
+static atomic64_t leaked_count;
+static unsigned int free_per_iteration = 10;
+
static void gnttab_handle_deferred(struct timer_list *unused)
{
- unsigned int nr = 10;
+ unsigned int nr = READ_ONCE(free_per_iteration);
+ const bool ignore_limit = nr == 0;
struct deferred_entry *first = NULL;
unsigned long flags;
+ size_t freed = 0;
spin_lock_irqsave(&gnttab_list_lock, flags);
- while (nr--) {
+ while ((ignore_limit || nr--) && !list_empty(&deferred_list)) {
struct deferred_entry *entry
= list_first_entry(&deferred_list,
struct deferred_entry, list);
@@ -515,10 +521,13 @@ static void gnttab_handle_deferred(struct timer_list *unused)
list_del(&entry->list);
spin_unlock_irqrestore(&gnttab_list_lock, flags);
if (_gnttab_end_foreign_access_ref(entry->ref)) {
+ uint64_t ret = atomic64_sub_return(1, &deferred_count);
put_free_entry(entry->ref);
- pr_debug("freeing g.e. %#x (pfn %#lx)\n",
- entry->ref, page_to_pfn(entry->page));
+ pr_debug("freeing g.e. %#x (pfn %#lx), %llu remaining\n",
+ entry->ref, page_to_pfn(entry->page),
+ (unsigned long long)ret);
put_page(entry->page);
+ freed++;
kfree(entry);
entry = NULL;
} else {
@@ -530,21 +539,22 @@ static void gnttab_handle_deferred(struct timer_list *unused)
spin_lock_irqsave(&gnttab_list_lock, flags);
if (entry)
list_add_tail(&entry->list, &deferred_list);
- else if (list_empty(&deferred_list))
- break;
}
- if (!list_empty(&deferred_list) && !timer_pending(&deferred_timer)) {
+ if (list_empty(&deferred_list))
+ WARN_ON(atomic64_read(&deferred_count));
+ else if (!timer_pending(&deferred_timer)) {
deferred_timer.expires = jiffies + HZ;
add_timer(&deferred_timer);
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
+ pr_debug("Freed %zu references", freed);
}
static void gnttab_add_deferred(grant_ref_t ref, struct page *page)
{
struct deferred_entry *entry;
gfp_t gfp = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
- const char *what = KERN_WARNING "leaking";
+ uint64_t leaked, deferred;
entry = kmalloc(sizeof(*entry), gfp);
if (!page) {
@@ -567,12 +577,20 @@ static void gnttab_add_deferred(grant_ref_t ref, struct page *page)
add_timer(&deferred_timer);
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
- what = KERN_DEBUG "deferring";
+ deferred = atomic64_add_return(1, &deferred_count);
+ leaked = atomic64_read(&leaked_count);
+ pr_debug("deferring g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
+ ref, page ? page_to_pfn(page) : -1, deferred, leaked);
+ } else {
+ deferred = atomic64_read(&deferred_count);
+ leaked = atomic64_add_return(1, &leaked_count);
+ pr_warn("leaking g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
+ ref, page ? page_to_pfn(page) : -1, deferred, leaked);
}
- printk("%s g.e. %#x (pfn %#lx)\n",
- what, ref, page ? page_to_pfn(page) : -1);
}
+module_param(free_per_iteration, uint, 0600);
+
int gnttab_try_end_foreign_access(grant_ref_t ref)
{
int ret = _gnttab_end_foreign_access_ref(ref);
--
Sincerely,
Demi Marie Obenour (she/her/hers)
Invisible Things Lab