It is possible that the usb power_supply is registered after the probe
of dwc3. In this case, trying to get the usb power_supply during the
probe will fail and there is no chance to try again. Also the usb
power_supply might be unregistered at anytime so that the handle of it
in dwc3 would become invalid. To fix this, get the handle right before
calling to power_supply functions and put it afterward.
Fixes: 6f0764b5adea ("usb: dwc3: add a power supply for current control")
Cc: stable(a)vger.kernel.org
Signed-off-by: Kyle Tso <kyletso(a)google.com>
---
drivers/usb/dwc3/core.c | 25 +++++--------------------
drivers/usb/dwc3/core.h | 4 ++--
drivers/usb/dwc3/gadget.c | 19 ++++++++++++++-----
3 files changed, 21 insertions(+), 27 deletions(-)
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 734de2a8bd21..ab563edd9b4c 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1631,8 +1631,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
u8 tx_thr_num_pkt_prd = 0;
u8 tx_max_burst_prd = 0;
u8 tx_fifo_resize_max_num;
- const char *usb_psy_name;
- int ret;
/* default to highest possible threshold */
lpm_nyet_threshold = 0xf;
@@ -1667,12 +1665,7 @@ static void dwc3_get_properties(struct dwc3 *dwc)
dwc->sys_wakeup = device_may_wakeup(dwc->sysdev);
- ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name);
- if (ret >= 0) {
- dwc->usb_psy = power_supply_get_by_name(usb_psy_name);
- if (!dwc->usb_psy)
- dev_err(dev, "couldn't get usb power supply\n");
- }
+ device_property_read_string(dev, "usb-psy-name", &dwc->usb_psy_name);
dwc->has_lpm_erratum = device_property_read_bool(dev,
"snps,has-lpm-erratum");
@@ -2133,18 +2126,16 @@ static int dwc3_probe(struct platform_device *pdev)
dwc3_get_software_properties(dwc);
dwc->reset = devm_reset_control_array_get_optional_shared(dev);
- if (IS_ERR(dwc->reset)) {
- ret = PTR_ERR(dwc->reset);
- goto err_put_psy;
- }
+ if (IS_ERR(dwc->reset))
+ return PTR_ERR(dwc->reset);
ret = dwc3_get_clocks(dwc);
if (ret)
- goto err_put_psy;
+ return ret;
ret = reset_control_deassert(dwc->reset);
if (ret)
- goto err_put_psy;
+ return ret;
ret = dwc3_clk_enable(dwc);
if (ret)
@@ -2245,9 +2236,6 @@ static int dwc3_probe(struct platform_device *pdev)
dwc3_clk_disable(dwc);
err_assert_reset:
reset_control_assert(dwc->reset);
-err_put_psy:
- if (dwc->usb_psy)
- power_supply_put(dwc->usb_psy);
return ret;
}
@@ -2276,9 +2264,6 @@ static void dwc3_remove(struct platform_device *pdev)
pm_runtime_set_suspended(&pdev->dev);
dwc3_free_event_buffers(dwc);
-
- if (dwc->usb_psy)
- power_supply_put(dwc->usb_psy);
}
#ifdef CONFIG_PM
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 1e561fd8b86e..ecfe2cc224f7 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1045,7 +1045,7 @@ struct dwc3_scratchpad_array {
* @role_sw: usb_role_switch handle
* @role_switch_default_mode: default operation mode of controller while
* usb role is USB_ROLE_NONE.
- * @usb_psy: pointer to power supply interface.
+ * @usb_psy_name: name of the usb power supply interface.
* @usb2_phy: pointer to USB2 PHY
* @usb3_phy: pointer to USB3 PHY
* @usb2_generic_phy: pointer to array of USB2 PHYs
@@ -1223,7 +1223,7 @@ struct dwc3 {
struct usb_role_switch *role_sw;
enum usb_dr_mode role_switch_default_mode;
- struct power_supply *usb_psy;
+ const char *usb_psy_name;
u32 fladj;
u32 ref_clk_per;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 89fc690fdf34..c89b5b5a64cf 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3049,20 +3049,29 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g,
static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA)
{
- struct dwc3 *dwc = gadget_to_dwc(g);
+ struct dwc3 *dwc = gadget_to_dwc(g);
+ struct power_supply *usb_psy;
union power_supply_propval val = {0};
int ret;
if (dwc->usb2_phy)
return usb_phy_set_power(dwc->usb2_phy, mA);
- if (!dwc->usb_psy)
+ if (!dwc->usb_psy_name)
return -EOPNOTSUPP;
- val.intval = 1000 * mA;
- ret = power_supply_set_property(dwc->usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val);
+ usb_psy = power_supply_get_by_name(dwc->usb_psy_name);
+ if (usb_psy) {
+ val.intval = 1000 * mA;
+ ret = power_supply_set_property(usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT,
+ &val);
+ power_supply_put(usb_psy);
+ return ret;
+ }
- return ret;
+ dev_err(dwc->dev, "couldn't get usb power supply\n");
+
+ return -EOPNOTSUPP;
}
/**
--
2.45.2.993.g49e7a77208-goog
This reverts commit 2e42b7f817acd6e8d78226445eb6fe44fe79c12a.
If the GC victim section has a pinned block when fallocate() trigger
FG_GC, the section is not able to be recycled. And this will return
-EAGAIN cause fallocate() failed, even though there are much spare space
as user see. As the GC policy prone to chose the same victim,
fallocate() may not successed at a long period.
This scenario has been found during Android OTA.
Link: https://lore.kernel.org/linux-f2fs-devel/20231030094024.263707-1-bo.wu@vivo…
CC: stable(a)vger.kernel.org
Signed-off-by: Wu Bo <bo.wu(a)vivo.com>
---
fs/f2fs/file.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b58ab1157b7e..19915faccee9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1725,7 +1725,7 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
f2fs_down_write(&sbi->gc_lock);
stat_inc_gc_call_count(sbi, FOREGROUND);
err = f2fs_gc(sbi, &gc_control);
- if (err && err != -ENODATA)
+ if (err && err != -ENODATA && err != -EAGAIN)
goto out_err;
}
--
2.25.1
From: Willem de Bruijn <willemb(a)google.com>
Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb
for GSO packets.
The function already checks that a checksum requested with
VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets
this might not hold for segs after segmentation.
Syzkaller demonstrated to reach this warning in skb_checksum_help
offset = skb_checksum_start_offset(skb);
ret = -EINVAL;
if (WARN_ON_ONCE(offset >= skb_headlen(skb)))
By injecting a TSO packet:
WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0
ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774
ip_finish_output_gso net/ipv4/ip_output.c:279 [inline]
__ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301
iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82
ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661
__netdev_start_xmit include/linux/netdevice.h:4850 [inline]
netdev_start_xmit include/linux/netdevice.h:4864 [inline]
xmit_one net/core/dev.c:3595 [inline]
dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611
__dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261
packet_snd net/packet/af_packet.c:3073 [inline]
The geometry of the bad input packet at tcp_gso_segment:
[ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0
[ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244
[ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0))
[ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536
ip_summed=3 complete_sw=0 valid=0 level=0)
Mitigate with stricter input validation.
csum_offset: for GSO packets, deduce the correct value from gso_type.
This is already done for USO. Extend it to TSO. Let UFO be:
udp[46]_ufo_fragment ignores these fields and always computes the
checksum in software.
csum_start: finding the real offset requires parsing to the transport
header. Do not add a parser, use existing segmentation parsing. Thanks
to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded.
Again test both TSO and USO. Do not test UFO for the above reason, and
do not test UDP tunnel offload.
GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be
CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit
from devices with no checksum offload"), but then still these fields
are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no
need to test for ip_summed == CHECKSUM_PARTIAL first.
This revises an existing fix mentioned in the Fixes tag, which broke
small packets with GSO offload, as detected by kselftests.
Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871
Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org
Fixes: e269d79c7d35 ("net: missing check virtio")
Cc: stable(a)vger.kernel.org
Signed-off-by: Willem de Bruijn <willemb(a)google.com>
---
v1->v2
- skb_transport_header instead of skb->transport_header (edumazet@)
- typo: migitate -> mitigate
---
include/linux/virtio_net.h | 16 +++++-----------
net/ipv4/tcp_offload.c | 3 +++
net/ipv4/udp_offload.c | 4 ++++
3 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index d1d7825318c32..6c395a2600e8d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
unsigned int thlen = 0;
unsigned int p_off = 0;
unsigned int ip_proto;
- u64 ret, remainder, gso_size;
if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
- if (hdr->gso_size) {
- gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
- ret = div64_u64_rem(skb->len, gso_size, &remainder);
- if (!(ret && (hdr->gso_size > needed) &&
- ((remainder > needed) || (remainder == 0)))) {
- return -EINVAL;
- }
- skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
- }
-
if (!pskb_may_pull(skb, needed))
return -EINVAL;
@@ -182,6 +171,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
if (gso_type != SKB_GSO_UDP_L4)
return -EINVAL;
break;
+ case SKB_GSO_TCPV4:
+ case SKB_GSO_TCPV6:
+ if (skb->csum_offset != offsetof(struct tcphdr, check))
+ return -EINVAL;
+ break;
}
/* Kernel has a special handling for GSO_BY_FRAGS. */
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 4b791e74529e1..e4ad3311e1489 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
if (thlen < sizeof(*th))
goto out;
+ if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
+ goto out;
+
if (!pskb_may_pull(skb, thlen))
goto out;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index aa2e0a28ca613..bc8a9da750fed 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
if (gso_skb->len <= sizeof(*uh) + mss)
return ERR_PTR(-EINVAL);
+ if (unlikely(skb_checksum_start(gso_skb) !=
+ skb_transport_header(gso_skb)))
+ return ERR_PTR(-EINVAL);
+
if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
/* Packet is from an untrusted source, reset gso_segs. */
skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
--
2.46.0.rc1.232.g9752f9e123-goog
Two bitmasks in 'struct sdw_slave_prop' - 'source_ports' and
'sink_ports' - define which ports to program in
sdw_program_slave_port_params(). The masks are used to get the
appropriate data port properties ('struct sdw_get_slave_dpn_prop') from
an array.
Bitmasks can be non-continuous or can start from index different than 0,
thus when looking for matching port property for given port, we must
iterate over mask bits, not from 0 up to number of ports.
This fixes allocation and programming slave ports, when a source or sink
masks start from further index.
Fixes: f8101c74aa54 ("soundwire: Add Master and Slave port programming")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org>
---
drivers/soundwire/stream.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 7aa4900dcf31..f275143d7b18 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -1291,18 +1291,18 @@ struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
unsigned int port_num)
{
struct sdw_dpn_prop *dpn_prop;
- u8 num_ports;
+ unsigned long mask;
int i;
if (direction == SDW_DATA_DIR_TX) {
- num_ports = hweight32(slave->prop.source_ports);
+ mask = slave->prop.source_ports;
dpn_prop = slave->prop.src_dpn_prop;
} else {
- num_ports = hweight32(slave->prop.sink_ports);
+ mask = slave->prop.sink_ports;
dpn_prop = slave->prop.sink_dpn_prop;
}
- for (i = 0; i < num_ports; i++) {
+ for_each_set_bit(i, &mask, 32) {
if (dpn_prop[i].num == port_num)
return &dpn_prop[i];
}
--
2.43.0
It may be possible for the sum of the values derived from
i915_ggtt_offset() and __get_parent_scratch_offset()/
i915_ggtt_offset() to go over the u32 limit before being assigned
to wq offsets of u64 type.
Mitigate these issues by expanding one of the right operands
to u64 to avoid any overflow issues just in case.
Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.
Fixes: 2584b3549f4c ("drm/i915/guc: Update to GuC version 70.1.1")
Cc: stable(a)vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich(a)fintech.ru>
---
drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 9400d0eb682b..908ebfa22933 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2842,9 +2842,9 @@ static void prepare_context_registration_info_v70(struct intel_context *ce,
ce->parallel.guc.wqi_tail = 0;
ce->parallel.guc.wqi_head = 0;
- wq_desc_offset = i915_ggtt_offset(ce->state) +
+ wq_desc_offset = (u64)i915_ggtt_offset(ce->state) +
__get_parent_scratch_offset(ce);
- wq_base_offset = i915_ggtt_offset(ce->state) +
+ wq_base_offset = (u64)i915_ggtt_offset(ce->state) +
__get_wq_offset(ce);
info->wq_desc_lo = lower_32_bits(wq_desc_offset);
info->wq_desc_hi = upper_32_bits(wq_desc_offset);
v3:
- Amends the commit log for patch #1 per Johan's suggestion.
- Link to v2: https://lore.kernel.org/r/20240716-linux-next-24-07-13-camss-fixes-v2-0-e60…
v2:
- Updates commits with Johan's Review/Reported tags
- Adds Closes: https://lore.kernel.org/lkml/ZoVNHOTI0PKMNt4_@hovoldconsulting.com
- Cc's stable
- Adds in suggested kernel log to allow others to more easily match kernel
log to fixes
- Link to v1: https://lore.kernel.org/r/20240714-linux-next-24-07-13-camss-fixes-v1-0-8f8…
V1:
Dogfooding with SoftISP has uncovered two bugs in this series which I'm
posting fixes for.
- The first error:
A simple race condition which to be honest I'm surprised I haven't found
earlier nor has anybody else. Simply stated the order we typically
end up loading CAMSS on boot has masked out the pm_runtime_enable() race
condition that has been present in CAMSS for a long time.
If you blacklist qcom-camss in modules.d and then modprobe after boot,
the race condition shows up easily.
Moving the pm_runtime_enable prior to subdevice registration fixes the
problem.
The second error:
Nomenclature:
- CSIPHY: CSI Physical layer analogue to digital domain serialiser
- CSID: CSI Decoder
- VFE: Video Front End
- RDI: Raw Data Interface
- VC: Virtual Channel
In order to support streaming multiple virtual-channels on the same RDI a
V4L2 provided use_count variable is used to decide whether or not to actually
terminate streaming and release buffers for 'msm_vfe_rdiX'.
Unfortunately use_count indicates the number of times msm_vfe_rdiX has
been opened by user-space not the number of concurrent streams on
msm_vfe_rdiX.
Simply stated use_count and stream_count are two different things.
The silicon enabling code to select between VCs is valid but, a different
solution needs to be found to support _concurrent_ VC streams.
Right now the upstream use_count as-is is breaking the non concurrent VC
case and I don't believe there are upstream users of concurrent VCs on
CAMSS.
This series implements a revert for the invalid use_count check,
retaining the ability to select which VC is active on the RDI.
Dogfooding with libcamera's SoftISP in Hangouts, Zoom and multiple runs
of libcamera's "qcam" application is a very different test-case to the
simple capture of frames we previously did when validating the
'use_count' change.
A partial revert in expectation of a renewed push to fixup that
concurrent VC issue is included.
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>
---
Bryan O'Donoghue (2):
media: qcom: camss: Remove use_count guard in stop_streaming
media: qcom: camss: Fix ordering of pm_runtime_enable
drivers/media/platform/qcom/camss/camss-video.c | 6 ------
drivers/media/platform/qcom/camss/camss.c | 5 +++--
2 files changed, 3 insertions(+), 8 deletions(-)
---
base-commit: c6ce8f9ab92edc9726996a0130bfc1c408132d47
change-id: 20240713-linux-next-24-07-13-camss-fixes-fa98c0965a5d
Best regards,
--
Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>
From: yangge <yangge1116(a)126.com>
If a large number of CMA memory are configured in system (for example, the
CMA memory accounts for 50% of the system memory), starting a virtual
virtual machine, it will call pin_user_pages_remote(..., FOLL_LONGTERM,
...) to pin memory. Normally if a page is present and in CMA area,
pin_user_pages_remote() will migrate the page from CMA area to non-CMA
area because of FOLL_LONGTERM flag. But the current code will cause the
migration failure due to unexpected page refcounts, and eventually cause
the virtual machine fail to start.
If a page is added in LRU batch, its refcount increases one, remove the
page from LRU batch decreases one. Page migration requires the page is not
referenced by others except page mapping. Before migrating a page, we
should try to drain the page from LRU batch in case the page is in it,
however, folio_test_lru() is not sufficient to tell whether the page is
in LRU batch or not, if the page is in LRU batch, the migration will fail.
To solve the problem above, we modify the logic of adding to LRU batch.
Before adding a page to LRU batch, we clear the LRU flag of the page so
that we can check whether the page is in LRU batch by folio_test_lru(page).
Seems making the LRU flag of the page invisible a long time is no problem,
because a new page is allocated from buddy and added to the lru batch,
its LRU flag is also not visible for a long time.
Cc: <stable(a)vger.kernel.org>
Signed-off-by: yangge <yangge1116(a)126.com>
---
mm/swap.c | 43 +++++++++++++++++++++++++++++++------------
1 file changed, 31 insertions(+), 12 deletions(-)
diff --git a/mm/swap.c b/mm/swap.c
index dc205bd..9caf6b0 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -211,10 +211,6 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
for (i = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
- /* block memcg migration while the folio moves between lru */
- if (move_fn != lru_add_fn && !folio_test_clear_lru(folio))
- continue;
-
folio_lruvec_relock_irqsave(folio, &lruvec, &flags);
move_fn(lruvec, folio);
@@ -255,11 +251,16 @@ static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio)
void folio_rotate_reclaimable(struct folio *folio)
{
if (!folio_test_locked(folio) && !folio_test_dirty(folio) &&
- !folio_test_unevictable(folio) && folio_test_lru(folio)) {
+ !folio_test_unevictable(folio)) {
struct folio_batch *fbatch;
unsigned long flags;
folio_get(folio);
+ if (!folio_test_clear_lru(folio)) {
+ folio_put(folio);
+ return;
+ }
+
local_lock_irqsave(&lru_rotate.lock, flags);
fbatch = this_cpu_ptr(&lru_rotate.fbatch);
folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn);
@@ -352,11 +353,15 @@ static void folio_activate_drain(int cpu)
void folio_activate(struct folio *folio)
{
- if (folio_test_lru(folio) && !folio_test_active(folio) &&
- !folio_test_unevictable(folio)) {
+ if (!folio_test_active(folio) && !folio_test_unevictable(folio)) {
struct folio_batch *fbatch;
folio_get(folio);
+ if (!folio_test_clear_lru(folio)) {
+ folio_put(folio);
+ return;
+ }
+
local_lock(&cpu_fbatches.lock);
fbatch = this_cpu_ptr(&cpu_fbatches.activate);
folio_batch_add_and_move(fbatch, folio, folio_activate_fn);
@@ -700,6 +705,11 @@ void deactivate_file_folio(struct folio *folio)
return;
folio_get(folio);
+ if (!folio_test_clear_lru(folio)) {
+ folio_put(folio);
+ return;
+ }
+
local_lock(&cpu_fbatches.lock);
fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file);
folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn);
@@ -716,11 +726,16 @@ void deactivate_file_folio(struct folio *folio)
*/
void folio_deactivate(struct folio *folio)
{
- if (folio_test_lru(folio) && !folio_test_unevictable(folio) &&
- (folio_test_active(folio) || lru_gen_enabled())) {
+ if (!folio_test_unevictable(folio) && (folio_test_active(folio) ||
+ lru_gen_enabled())) {
struct folio_batch *fbatch;
folio_get(folio);
+ if (!folio_test_clear_lru(folio)) {
+ folio_put(folio);
+ return;
+ }
+
local_lock(&cpu_fbatches.lock);
fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate);
folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn);
@@ -737,12 +752,16 @@ void folio_deactivate(struct folio *folio)
*/
void folio_mark_lazyfree(struct folio *folio)
{
- if (folio_test_lru(folio) && folio_test_anon(folio) &&
- folio_test_swapbacked(folio) && !folio_test_swapcache(folio) &&
- !folio_test_unevictable(folio)) {
+ if (folio_test_anon(folio) && folio_test_swapbacked(folio) &&
+ !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) {
struct folio_batch *fbatch;
folio_get(folio);
+ if (!folio_test_clear_lru(folio)) {
+ folio_put(folio);
+ return;
+ }
+
local_lock(&cpu_fbatches.lock);
fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree);
folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn);
--
2.7.4
From: Andrey Konovalov <andreyknvl(a)gmail.com>
Commit a7f3813e589f ("usb: gadget: dummy_hcd: Switch to hrtimer transfer
scheduler") switched dummy_hcd to use hrtimer and made the timer's
callback be executed in the hardirq context.
With that change, __usb_hcd_giveback_urb now gets executed in the hardirq
context, which causes problems for KCOV and KMSAN.
One problem is that KCOV now is unable to collect coverage from
the USB code that gets executed from the dummy_hcd's timer callback,
as KCOV cannot collect coverage in the hardirq context.
Another problem is that the dummy_hcd hrtimer might get triggered in the
middle of a softirq with KCOV remote coverage collection enabled, and that
causes a WARNING in KCOV, as reported by syzbot. (I sent a separate patch
to shut down this WARNING, but that doesn't fix the other two issues.)
Finally, KMSAN appears to ignore tracking memory copying operations
that happen in the hardirq context, which causes false positive
kernel-infoleaks, as reported by syzbot.
Change the hrtimer in dummy_hcd to execute the callback in the softirq
context.
Reported-by: syzbot+2388cdaeb6b10f0c13ac(a)syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2388cdaeb6b10f0c13ac
Reported-by: syzbot+17ca2339e34a1d863aad(a)syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=17ca2339e34a1d863aad
Fixes: a7f3813e589f ("usb: gadget: dummy_hcd: Switch to hrtimer transfer scheduler")
Cc: stable(a)vger.kernel.org
Signed-off-by: Andrey Konovalov <andreyknvl(a)gmail.com>
---
Marcello, would this change be acceptable for your use case?
If we wanted to keep the hardirq hrtimer, we would need teach KCOV to
collect coverage in the hardirq context (or disable it, which would be
unfortunate) and also fix whatever is wrong with KMSAN, but all that
requires some work.
---
drivers/usb/gadget/udc/dummy_hcd.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index f37b0d8386c1a..ff7bee78bcc49 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1304,7 +1304,8 @@ static int dummy_urb_enqueue(
/* kick the scheduler, it'll do the rest */
if (!hrtimer_active(&dum_hcd->timer))
- hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS), HRTIMER_MODE_REL);
+ hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS),
+ HRTIMER_MODE_REL_SOFT);
done:
spin_unlock_irqrestore(&dum_hcd->dum->lock, flags);
@@ -1325,7 +1326,7 @@ static int dummy_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
rc = usb_hcd_check_unlink_urb(hcd, urb, status);
if (!rc && dum_hcd->rh_state != DUMMY_RH_RUNNING &&
!list_empty(&dum_hcd->urbp_list))
- hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL);
+ hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL_SOFT);
spin_unlock_irqrestore(&dum_hcd->dum->lock, flags);
return rc;
@@ -1995,7 +1996,8 @@ static enum hrtimer_restart dummy_timer(struct hrtimer *t)
dum_hcd->udev = NULL;
} else if (dum_hcd->rh_state == DUMMY_RH_RUNNING) {
/* want a 1 msec delay here */
- hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS), HRTIMER_MODE_REL);
+ hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS),
+ HRTIMER_MODE_REL_SOFT);
}
spin_unlock_irqrestore(&dum->lock, flags);
@@ -2389,7 +2391,7 @@ static int dummy_bus_resume(struct usb_hcd *hcd)
dum_hcd->rh_state = DUMMY_RH_RUNNING;
set_link_state(dum_hcd);
if (!list_empty(&dum_hcd->urbp_list))
- hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL);
+ hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL_SOFT);
hcd->state = HC_STATE_RUNNING;
}
spin_unlock_irq(&dum_hcd->dum->lock);
@@ -2467,7 +2469,7 @@ static DEVICE_ATTR_RO(urbs);
static int dummy_start_ss(struct dummy_hcd *dum_hcd)
{
- hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
dum_hcd->timer.function = dummy_timer;
dum_hcd->rh_state = DUMMY_RH_RUNNING;
dum_hcd->stream_en_ep = 0;
@@ -2497,7 +2499,7 @@ static int dummy_start(struct usb_hcd *hcd)
return dummy_start_ss(dum_hcd);
spin_lock_init(&dum_hcd->dum->lock);
- hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
dum_hcd->timer.function = dummy_timer;
dum_hcd->rh_state = DUMMY_RH_RUNNING;
--
2.25.1
The patch below does not apply to the 6.1-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-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x 8e7860543a94784d744c7ce34b78a2e11beefa5c
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024072924-overact-drainable-8abb@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..
Possible dependencies:
8e7860543a94 ("btrfs: fix extent map use-after-free when adding pages to compressed bio")
b7d463a1d125 ("btrfs: store a pointer to the original btrfs_bio in struct compressed_bio")
690834e47cf7 ("btrfs: pass a btrfs_bio to btrfs_submit_compressed_read")
7edb9a3e7200 ("btrfs: move zero filling of compressed read bios into common code")
32586c5bca72 ("btrfs: factor out a btrfs_free_compressed_pages helper")
10e924bc320a ("btrfs: factor out a btrfs_add_compressed_bio_pages helper")
d7294e4deeb9 ("btrfs: use the bbio file offset in add_ra_bio_pages")
e7aff33e3161 ("btrfs: use the bbio file offset in btrfs_submit_compressed_read")
798c9fc74d03 ("btrfs: remove redundant free_extent_map in btrfs_submit_compressed_read")
544fe4a903ce ("btrfs: embed a btrfs_bio into struct compressed_bio")
d5e4377d5051 ("btrfs: split zone append bios in btrfs_submit_bio")
35a8d7da3ca8 ("btrfs: remove now spurious bio submission helpers")
285599b6fe15 ("btrfs: remove the fs_info argument to btrfs_submit_bio")
48253076c3a9 ("btrfs: open code submit_encoded_read_bio")
30493ff49f81 ("btrfs: remove stripe boundary calculation for compressed I/O")
2380220e1e13 ("btrfs: remove stripe boundary calculation for buffered I/O")
67d669825090 ("btrfs: pass the iomap bio to btrfs_submit_bio")
852eee62d31a ("btrfs: allow btrfs_submit_bio to split bios")
69ccf3f4244a ("btrfs: handle recording of zoned writes in the storage layer")
f8a53bb58ec7 ("btrfs: handle checksum generation in the storage layer")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 8e7860543a94784d744c7ce34b78a2e11beefa5c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana(a)suse.com>
Date: Thu, 4 Jul 2024 16:11:20 +0100
Subject: [PATCH] btrfs: fix extent map use-after-free when adding pages to
compressed bio
At add_ra_bio_pages() we are accessing the extent map to calculate
'add_size' after we dropped our reference on the extent map, resulting
in a use-after-free. Fix this by computing 'add_size' before dropping our
extent map reference.
Reported-by: syzbot+853d80cba98ce1157ae6(a)syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/000000000000038144061c6d18f2@google.com/
Fixes: 6a4049102055 ("btrfs: subpage: make add_ra_bio_pages() compatible")
CC: stable(a)vger.kernel.org # 6.1+
Signed-off-by: Filipe Manana <fdmanana(a)suse.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index a149f3659b15..a8e2c461aff7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -515,6 +515,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
put_page(page);
break;
}
+ add_size = min(em->start + em->len, page_end + 1) - cur;
free_extent_map(em);
if (page->index == end_index) {
@@ -527,7 +528,6 @@ static noinline int add_ra_bio_pages(struct inode *inode,
}
}
- add_size = min(em->start + em->len, page_end + 1) - cur;
ret = bio_add_page(orig_bio, page, add_size, offset_in_page(cur));
if (ret != add_size) {
unlock_extent(tree, cur, page_end, NULL);