From: Mario Limonciello <mario.limonciello(a)amd.com>
Donghun reports that a notebook that has an AMD Ryzen 5700U but supports
S3 has problems with USB after resuming from suspend. The issue was
bisected down to commit d1658268e439 ("usb: pci-quirks: disable D3cold on
xhci suspend for s2idle on AMD Renoir").
As this issue only happens on S3, narrow the broken D3cold quirk to only
run in s2idle.
Fixes: d1658268e439 ("usb: pci-quirks: disable D3cold on xhci suspend for s2idle on AMD Renoir")
Reported-and-tested-by: Donghun Yoon <donghun.yoon(a)lge.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello(a)amd.com>
Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com>
---
drivers/usb/host/xhci-pci.c | 12 ++++++++++--
drivers/usb/host/xhci.h | 2 +-
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index ddb79f23fb3b..79b3691f373f 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -13,6 +13,7 @@
#include <linux/module.h>
#include <linux/acpi.h>
#include <linux/reset.h>
+#include <linux/suspend.h>
#include "xhci.h"
#include "xhci-trace.h"
@@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
if (pdev->vendor == PCI_VENDOR_ID_AMD &&
pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI)
- xhci->quirks |= XHCI_BROKEN_D3COLD;
+ xhci->quirks |= XHCI_BROKEN_D3COLD_S2I;
if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
xhci->quirks |= XHCI_LPM_SUPPORT;
@@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
* Systems with the TI redriver that loses port status change events
* need to have the registers polled during D3, so avoid D3cold.
*/
- if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD))
+ if (xhci->quirks & XHCI_COMP_MODE_QUIRK)
pci_d3cold_disable(pdev);
+#ifdef CONFIG_SUSPEND
+ /* d3cold is broken, but only when s2idle is used */
+ if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE &&
+ xhci->quirks & (XHCI_BROKEN_D3COLD_S2I))
+ pci_d3cold_disable(pdev);
+#endif
+
if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
xhci_pme_quirk(hcd);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 08d721921b7b..6b690ec91ff3 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1901,7 +1901,7 @@ struct xhci_hcd {
#define XHCI_DISABLE_SPARSE BIT_ULL(38)
#define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39)
#define XHCI_NO_SOFT_RETRY BIT_ULL(40)
-#define XHCI_BROKEN_D3COLD BIT_ULL(41)
+#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41)
#define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42)
#define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43)
#define XHCI_RESET_TO_DEFAULT BIT_ULL(44)
--
2.25.1
This patch series backports a few VM preemption_status, steal_time and
PV TLB flushing fixes to 5.10 stable kernel.
Most of the changes backport cleanly except i had to work around a few
because of missing support/APIs in 5.10 kernel. I have captured those in
the changelog as well in the individual patches.
Earlier patch series that i'm resending for stable.
https://lore.kernel.org/all/20220909181351.23983-1-risbhat@amazon.com/
Changelog
- Use mark_page_dirty_in_slot api without kvm argument (KVM: x86: Fix
recording of guest steal time / preempted status)
- Avoid checking for xen_msr and SEV-ES conditions (KVM: x86:
do not set st->preempted when going back to user space)
- Use VCPU_STAT macro to expose preemption_reported and
preemption_other fields (KVM: x86: do not report a vCPU as preempted
outside instruction boundaries)
David Woodhouse (2):
KVM: x86: Fix recording of guest steal time / preempted status
KVM: Fix steal time asm constraints
Lai Jiangshan (1):
KVM: x86: Ensure PV TLB flush tracepoint reflects KVM behavior
Paolo Bonzini (5):
KVM: x86: do not set st->preempted when going back to user space
KVM: x86: do not report a vCPU as preempted outside instruction
boundaries
KVM: x86: revalidate steal time cache if MSR value changes
KVM: x86: do not report preemption if the steal time cache is stale
KVM: x86: move guest_pv_has out of user_access section
Sean Christopherson (1):
KVM: x86: Remove obsolete disabling of page faults in
kvm_arch_vcpu_put()
arch/x86/include/asm/kvm_host.h | 5 +-
arch/x86/kvm/svm/svm.c | 2 +
arch/x86/kvm/vmx/vmx.c | 1 +
arch/x86/kvm/x86.c | 164 ++++++++++++++++++++++----------
4 files changed, 122 insertions(+), 50 deletions(-)
--
2.39.2
As an alternative to backporting part of a large s390 patch series to the
6.3-stable tree as dependencies, here are just couple of rebased changes.
Avoids the need for:
Patch "s390/boot: rework decompressor reserved tracking" has been added to the 6.3-stable tree
Patch "s390/boot: rename mem_detect to physmem_info" has been added to the 6.3-stable tree
Patch "s390/boot: remove non-functioning image bootable check" has been added to the 6.3-stable tree
Thank you
Heiko Carstens (2):
s390/mm: rename POPULATE_ONE2ONE to POPULATE_DIRECT
s390/mm: fix direct map accounting
arch/s390/boot/vmem.c | 27 ++++++++++++++++++++-------
arch/s390/include/asm/pgtable.h | 2 +-
arch/s390/mm/pageattr.c | 2 +-
3 files changed, 22 insertions(+), 9 deletions(-)
--
2.38.1
This triggers a -Wdeclaration-after-statement as the code has changed a
bit since upstream. It might be better to hoist the whole block up, but
this is a smaller change so I went with it.
arch/riscv/mm/init.c:755:16: warning: mixing declarations and code is a C99 extension [-Wdeclaration-after-statement]
unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT));
^
1 warning generated.
Fixes: bbf94b042155 ("riscv: Move early dtb mapping into the fixmap region")
Reported-by: kernel test robot <lkp(a)intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202304300429.SXZOA5up-lkp@intel.com/
Signed-off-by: Palmer Dabbelt <palmer(a)rivosinc.com>
Signed-off-by: Alexandre Ghiti <alexghiti(a)rivosinc.com>
---
v2:
- Fix rv64 warning introduced by the v1
- Add Fixes tag
arch/riscv/mm/init.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index e800d7981e99..a382623e91cf 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -716,6 +716,7 @@ static void __init setup_vm_final(void)
{
uintptr_t va, map_size;
phys_addr_t pa, start, end;
+ unsigned long idx __maybe_unused;
u64 i;
/**
@@ -735,7 +736,7 @@ static void __init setup_vm_final(void)
* directly in swapper_pg_dir in addition to the pgd entry that points
* to fixmap_pte.
*/
- unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT));
+ idx = pgd_index(__fix_to_virt(FIX_FDT));
set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]);
#endif
--
2.37.2
From: Hans de Goede <hdegoede(a)redhat.com>
commit 085a9f43433f30cbe8a1ade62d9d7827c3217f4d upstream.
Use down_read_nested() and down_write_nested() when taking the
ctrl->reset_lock rw-sem, passing the number of PCIe hotplug controllers in
the path to the PCI root bus as lock subclass parameter.
This fixes the following false-positive lockdep report when unplugging a
Lenovo X1C8 from a Lenovo 2nd gen TB3 dock:
pcieport 0000:06:01.0: pciehp: Slot(1): Link Down
pcieport 0000:06:01.0: pciehp: Slot(1): Card not present
============================================
WARNING: possible recursive locking detected
5.16.0-rc2+ #621 Not tainted
--------------------------------------------
irq/124-pciehp/86 is trying to acquire lock:
ffff8e5ac4299ef8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_check_presence+0x23/0x80
but task is already holding lock:
ffff8e5ac4298af8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_ist+0xf3/0x180
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&ctrl->reset_lock);
lock(&ctrl->reset_lock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by irq/124-pciehp/86:
#0: ffff8e5ac4298af8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_ist+0xf3/0x180
#1: ffffffffa3b024e8 (pci_rescan_remove_lock){+.+.}-{3:3}, at: pciehp_unconfigure_device+0x31/0x110
#2: ffff8e5ac1ee2248 (&dev->mutex){....}-{3:3}, at: device_release_driver+0x1c/0x40
stack backtrace:
CPU: 4 PID: 86 Comm: irq/124-pciehp Not tainted 5.16.0-rc2+ #621
Hardware name: LENOVO 20U90SIT19/20U90SIT19, BIOS N2WET30W (1.20 ) 08/26/2021
Call Trace:
<TASK>
dump_stack_lvl+0x59/0x73
__lock_acquire.cold+0xc5/0x2c6
lock_acquire+0xb5/0x2b0
down_read+0x3e/0x50
pciehp_check_presence+0x23/0x80
pciehp_runtime_resume+0x5c/0xa0
device_for_each_child+0x45/0x70
pcie_port_device_runtime_resume+0x20/0x30
pci_pm_runtime_resume+0xa7/0xc0
__rpm_callback+0x41/0x110
rpm_callback+0x59/0x70
rpm_resume+0x512/0x7b0
__pm_runtime_resume+0x4a/0x90
__device_release_driver+0x28/0x240
device_release_driver+0x26/0x40
pci_stop_bus_device+0x68/0x90
pci_stop_bus_device+0x2c/0x90
pci_stop_and_remove_bus_device+0xe/0x20
pciehp_unconfigure_device+0x6c/0x110
pciehp_disable_slot+0x5b/0xe0
pciehp_handle_presence_or_link_change+0xc3/0x2f0
pciehp_ist+0x179/0x180
This lockdep warning is triggered because with Thunderbolt, hotplug ports
are nested. When removing multiple devices in a daisy-chain, each hotplug
port's reset_lock may be acquired recursively. It's never the same lock, so
the lockdep splat is a false positive.
Because locks at the same hierarchy level are never acquired recursively, a
per-level lockdep class is sufficient to fix the lockdep warning.
The choice to use one lockdep subclass per pcie-hotplug controller in the
path to the root-bus was made to conserve class keys because their number
is limited and the complexity grows quadratically with number of keys
according to Documentation/locking/lockdep-design.rst.
Link: https://lore.kernel.org/linux-pci/20190402021933.GA2966@mit.edu/
Link: https://lore.kernel.org/linux-pci/de684a28-9038-8fc6-27ca-3f6f2f6400d7@redh…
Link: https://lore.kernel.org/r/20211217141709.379663-1-hdegoede@redhat.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=208855
Reported-by: "Theodore Ts'o" <tytso(a)mit.edu>
Signed-off-by: Hans de Goede <hdegoede(a)redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Reviewed-by: Lukas Wunner <lukas(a)wunner.de>
Cc: stable(a)vger.kernel.org
[lukas: backport to v5.4-stable]
Signed-off-by: Lukas Wunner <lukas(a)wunner.de>
---
drivers/pci/hotplug/pciehp.h | 3 +++
drivers/pci/hotplug/pciehp_core.c | 2 +-
drivers/pci/hotplug/pciehp_hpc.c | 19 +++++++++++++++++--
3 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index aa61d4c219d7..79a713f5dbf4 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -72,6 +72,8 @@ extern int pciehp_poll_time;
* @reset_lock: prevents access to the Data Link Layer Link Active bit in the
* Link Status register and to the Presence Detect State bit in the Slot
* Status register during a slot reset which may cause them to flap
+ * @depth: Number of additional hotplug ports in the path to the root bus,
+ * used as lock subclass for @reset_lock
* @ist_running: flag to keep user request waiting while IRQ thread is running
* @request_result: result of last user request submitted to the IRQ thread
* @requester: wait queue to wake up on completion of user request,
@@ -102,6 +104,7 @@ struct controller {
struct hotplug_slot hotplug_slot; /* hotplug core interface */
struct rw_semaphore reset_lock;
+ unsigned int depth;
unsigned int ist_running;
int request_result;
wait_queue_head_t requester;
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 312cc45c44c7..f5255045b149 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -165,7 +165,7 @@ static void pciehp_check_presence(struct controller *ctrl)
{
int occupied;
- down_read(&ctrl->reset_lock);
+ down_read_nested(&ctrl->reset_lock, ctrl->depth);
mutex_lock(&ctrl->state_lock);
occupied = pciehp_card_present_or_link_active(ctrl);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 13f3bc239c66..651664fe4058 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -674,7 +674,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
* Disable requests have higher priority than Presence Detect Changed
* or Data Link Layer State Changed events.
*/
- down_read(&ctrl->reset_lock);
+ down_read_nested(&ctrl->reset_lock, ctrl->depth);
if (events & DISABLE_SLOT)
pciehp_handle_disable_request(ctrl);
else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC))
@@ -808,7 +808,7 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, int probe)
if (probe)
return 0;
- down_write(&ctrl->reset_lock);
+ down_write_nested(&ctrl->reset_lock, ctrl->depth);
if (!ATTN_BUTTN(ctrl)) {
ctrl_mask |= PCI_EXP_SLTCTL_PDCE;
@@ -864,6 +864,20 @@ static inline void dbg_ctrl(struct controller *ctrl)
#define FLAG(x, y) (((x) & (y)) ? '+' : '-')
+static inline int pcie_hotplug_depth(struct pci_dev *dev)
+{
+ struct pci_bus *bus = dev->bus;
+ int depth = 0;
+
+ while (bus->parent) {
+ bus = bus->parent;
+ if (bus->self && bus->self->is_hotplug_bridge)
+ depth++;
+ }
+
+ return depth;
+}
+
struct controller *pcie_init(struct pcie_device *dev)
{
struct controller *ctrl;
@@ -877,6 +891,7 @@ struct controller *pcie_init(struct pcie_device *dev)
return NULL;
ctrl->pcie = dev;
+ ctrl->depth = pcie_hotplug_depth(dev->port);
pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, &slot_cap);
if (pdev->hotplug_user_indicators)
--
2.39.2
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>.
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-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 3899d94e3831ee07ea6821c032dc297aec80586a
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023050708-absently-subsidy-099a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
3899d94e3831 ("drbd: correctly submit flush bio on barrier")
07888c665b40 ("block: pass a block_device and opf to bio_alloc")
b77c88c2100c ("block: pass a block_device and opf to bio_alloc_kiocb")
609be1066731 ("block: pass a block_device and opf to bio_alloc_bioset")
0a3140ea0fae ("block: pass a block_device and opf to blk_next_bio")
3b005bf6acf0 ("block: move blk_next_bio to bio.c")
7d8d0c658d48 ("xen-blkback: bio_alloc can't fail if it is allow to sleep")
d7b78de2b155 ("rnbd-srv: remove struct rnbd_dev_blk_io")
1fe0640ff94f ("rnbd-srv: simplify bio mapping in process_rdma")
4b1dc86d1857 ("drbd: bio_alloc can't fail if it is allow to sleep")
3f868c09ea8f ("dm-crypt: remove clone_init")
53db984e004c ("dm: bio_alloc can't fail if it is allowed to sleep")
39146b6f66ba ("ntfs3: remove ntfs_alloc_bio")
5d2ca2132f88 ("nfs/blocklayout: remove bl_alloc_init_bio")
f0d911927b3c ("nilfs2: remove nilfs_alloc_seg_bio")
d5f68a42da7a ("fs: remove mpage_alloc")
ae4c81644e91 ("RDMA/rtrs-srv: Rename rtrs_srv_sess to rtrs_srv_path")
d9372794717f ("RDMA/rtrs: Rename rtrs_sess to rtrs_path")
512b7931ad05 ("Merge branch 'akpm' (patches from Andrew)")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 3899d94e3831ee07ea6821c032dc297aec80586a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?=
<christoph.boehmwalder(a)linbit.com>
Date: Wed, 3 May 2023 14:19:37 +0200
Subject: [PATCH] drbd: correctly submit flush bio on barrier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When we receive a flush command (or "barrier" in DRBD), we currently use
a REQ_OP_FLUSH with the REQ_PREFLUSH flag set.
The correct way to submit a flush bio is by using a REQ_OP_WRITE without
any data, and set the REQ_PREFLUSH flag.
Since commit b4a6bb3a67aa ("block: add a sanity check for non-write
flush/fua bios"), this triggers a warning in the block layer, but this
has been broken for quite some time before that.
So use the correct set of flags to actually make the flush happen.
Cc: Christoph Hellwig <hch(a)infradead.org>
Cc: stable(a)vger.kernel.org
Fixes: f9ff0da56437 ("drbd: allow parallel flushes for multi-volume resources")
Reported-by: Thomas Voegtle <tv(a)lio96.de>
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder(a)linbit.com>
Reviewed-by: Christoph Hellwig <hch(a)lst.de>
Link: https://lore.kernel.org/r/20230503121937.17232-1-christoph.boehmwalder@linb…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index e54404c632e7..34b112752ab1 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1283,7 +1283,7 @@ static void one_flush_endio(struct bio *bio)
static void submit_one_flush(struct drbd_device *device, struct issue_flush_context *ctx)
{
struct bio *bio = bio_alloc(device->ldev->backing_bdev, 0,
- REQ_OP_FLUSH | REQ_PREFLUSH, GFP_NOIO);
+ REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO);
struct one_flush_context *octx = kmalloc(sizeof(*octx), GFP_NOIO);
if (!octx) {