On 9/20/21 10:17 AM, gregkh(a)linuxfoundation.org wrote:
>
> This is a note to let you know that I've just added the patch titled
>
> parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled
>
> to the 5.14-stable tree which can be found at:
> http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
>
> The filename of the patch is:
> parisc-declare-pci_iounmap-parisc-version-only-when-config_pci-enabled.patch
> and it can be found in the queue-5.14 subdirectory.
>
> If you, or anyone else, feels it should not be added to the stable tree,
> please let <stable(a)vger.kernel.org> know about it.
No, please don't add it to any stable tree yet.
This patch was applied by Linus in order to fix build errors on the alpha
architecture, but it triggers build errors on arm64 (and maybe other arches).
The whole issue is still being analyzed, as visible in e.g. this commit:
316e8d79a0959c302b0c462ab64b069599f10eef
Author: Linus Torvalds <torvalds(a)linux-foundation.org>
Date: Sun Sep 19 17:13:35 2021 -0700
pci_iounmap'2: Electric Boogaloo: try to make sense of it all
Helge
>
>
> From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001
> From: Helge Deller <deller(a)gmx.de>
> Date: Sun, 19 Sep 2021 10:36:09 -0700
> Subject: parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled
>
> From: Helge Deller <deller(a)gmx.de>
>
> commit 9caea0007601d3bc6debec04f8b4cd6f4c2394be upstream.
>
> Linus noticed odd declaration rules for pci_iounmap() in iomap.h and
> pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or
> GENERIC_IOMAP when CONFIG_PCI was disabled.
>
> Testing on parisc seems to indicate that we need pci_iounmap() only when
> CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved
> cleanly into pci_iomap.h in sync with the declarations of pci_iomap().
>
> Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=…
> Signed-off-by: Helge Deller <deller(a)gmx.de>
> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org>
> Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional")
> Cc: Arnd Bergmann <arnd(a)arndb.de>
> Cc: Guenter Roeck <linux(a)roeck-us.net>
> Cc: Ulrich Teichert <krypton(a)ulrich-teichert.org>
> Cc: James Bottomley <James.Bottomley(a)hansenpartnership.com>
> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
> ---
> arch/parisc/lib/iomap.c | 4 +++-
> include/asm-generic/iomap.h | 10 ----------
> include/asm-generic/pci_iomap.h | 3 +++
> 3 files changed, 6 insertions(+), 11 deletions(-)
>
> --- a/arch/parisc/lib/iomap.c
> +++ b/arch/parisc/lib/iomap.c
> @@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr)
> }
> }
>
> +#ifdef CONFIG_PCI
> void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
> {
> if (!INDIRECT_ADDR(addr)) {
> iounmap(addr);
> }
> }
> +EXPORT_SYMBOL(pci_iounmap);
> +#endif
>
> EXPORT_SYMBOL(ioread8);
> EXPORT_SYMBOL(ioread16);
> @@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep);
> EXPORT_SYMBOL(iowrite32_rep);
> EXPORT_SYMBOL(ioport_map);
> EXPORT_SYMBOL(ioport_unmap);
> -EXPORT_SYMBOL(pci_iounmap);
> --- a/include/asm-generic/iomap.h
> +++ b/include/asm-generic/iomap.h
> @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(p
> }
> #endif
>
> -#ifdef CONFIG_PCI
> -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
> -struct pci_dev;
> -extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
> -#elif defined(CONFIG_GENERIC_IOMAP)
> -struct pci_dev;
> -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
> -{ }
> -#endif
> -
> #include <asm-generic/pci_iomap.h>
>
> #endif
> --- a/include/asm-generic/pci_iomap.h
> +++ b/include/asm-generic/pci_iomap.h
> @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(str
> extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
> unsigned long offset,
> unsigned long maxlen);
> +extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
> /* Create a virtual mapping cookie for a port on a given PCI device.
> * Do not call this directly, it exists to make it easier for architectures
> * to override */
> @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc
> {
> return NULL;
> }
> +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
> +{ }
> #endif
>
> #endif /* __ASM_GENERIC_IO_H */
>
>
> Patches currently in stable-queue which might be from deller(a)gmx.de are
>
> queue-5.14/parisc-declare-pci_iounmap-parisc-version-only-when-config_pci-enabled.patch
>
On 9/20/21 10:25 AM, gregkh(a)linuxfoundation.org wrote:
>
> This is a note to let you know that I've just added the patch titled
>
> parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled
>
> to the 4.9-stable tree which can be found at:
> http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
>
> The filename of the patch is:
> parisc-declare-pci_iounmap-parisc-version-only-when-config_pci-enabled.patch
> and it can be found in the queue-4.9 subdirectory.
>
> If you, or anyone else, feels it should not be added to the stable tree,
> please let <stable(a)vger.kernel.org> know about it.
No, please don't add it to any stable tree yet.
This patch was applied by Linus in order to fix build errors on the alpha
architecture, but it triggers build errors on arm64 (and maybe other arches).
The whole issue is still being analyzed, as visible in e.g. this commit:
316e8d79a0959c302b0c462ab64b069599f10eef
Author: Linus Torvalds <torvalds(a)linux-foundation.org>
Date: Sun Sep 19 17:13:35 2021 -0700
pci_iounmap'2: Electric Boogaloo: try to make sense of it all
Helge
>
>
> From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001
> From: Helge Deller <deller(a)gmx.de>
> Date: Sun, 19 Sep 2021 10:36:09 -0700
> Subject: parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled
>
> From: Helge Deller <deller(a)gmx.de>
>
> commit 9caea0007601d3bc6debec04f8b4cd6f4c2394be upstream.
>
> Linus noticed odd declaration rules for pci_iounmap() in iomap.h and
> pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or
> GENERIC_IOMAP when CONFIG_PCI was disabled.
>
> Testing on parisc seems to indicate that we need pci_iounmap() only when
> CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved
> cleanly into pci_iomap.h in sync with the declarations of pci_iomap().
>
> Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=…
> Signed-off-by: Helge Deller <deller(a)gmx.de>
> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org>
> Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional")
> Cc: Arnd Bergmann <arnd(a)arndb.de>
> Cc: Guenter Roeck <linux(a)roeck-us.net>
> Cc: Ulrich Teichert <krypton(a)ulrich-teichert.org>
> Cc: James Bottomley <James.Bottomley(a)hansenpartnership.com>
> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
> ---
> arch/parisc/lib/iomap.c | 4 +++-
> include/asm-generic/iomap.h | 10 ----------
> include/asm-generic/pci_iomap.h | 3 +++
> 3 files changed, 6 insertions(+), 11 deletions(-)
>
> --- a/arch/parisc/lib/iomap.c
> +++ b/arch/parisc/lib/iomap.c
> @@ -436,12 +436,15 @@ void ioport_unmap(void __iomem *addr)
> }
> }
>
> +#ifdef CONFIG_PCI
> void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
> {
> if (!INDIRECT_ADDR(addr)) {
> iounmap(addr);
> }
> }
> +EXPORT_SYMBOL(pci_iounmap);
> +#endif
>
> EXPORT_SYMBOL(ioread8);
> EXPORT_SYMBOL(ioread16);
> @@ -461,4 +464,3 @@ EXPORT_SYMBOL(iowrite16_rep);
> EXPORT_SYMBOL(iowrite32_rep);
> EXPORT_SYMBOL(ioport_map);
> EXPORT_SYMBOL(ioport_unmap);
> -EXPORT_SYMBOL(pci_iounmap);
> --- a/include/asm-generic/iomap.h
> +++ b/include/asm-generic/iomap.h
> @@ -78,16 +78,6 @@ extern void ioport_unmap(void __iomem *)
> #define ioremap_wt ioremap_nocache
> #endif
>
> -#ifdef CONFIG_PCI
> -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */
> -struct pci_dev;
> -extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
> -#elif defined(CONFIG_GENERIC_IOMAP)
> -struct pci_dev;
> -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
> -{ }
> -#endif
> -
> #include <asm-generic/pci_iomap.h>
>
> #endif
> --- a/include/asm-generic/pci_iomap.h
> +++ b/include/asm-generic/pci_iomap.h
> @@ -22,6 +22,7 @@ extern void __iomem *pci_iomap_range(str
> extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
> unsigned long offset,
> unsigned long maxlen);
> +extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
> /* Create a virtual mapping cookie for a port on a given PCI device.
> * Do not call this directly, it exists to make it easier for architectures
> * to override */
> @@ -54,6 +55,8 @@ static inline void __iomem *pci_iomap_wc
> {
> return NULL;
> }
> +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
> +{ }
> #endif
>
> #endif /* __ASM_GENERIC_IO_H */
>
>
> Patches currently in stable-queue which might be from deller(a)gmx.de are
>
> queue-4.9/parisc-declare-pci_iounmap-parisc-version-only-when-config_pci-enabled.patch
> queue-4.9/parisc-fix-crash-with-signals-and-alloca.patch
>
The patch below does not apply to the 5.10-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 b871895b148256f1721bc565d803860242755a0b Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin(a)gmail.com>
Date: Fri, 3 Sep 2021 22:57:06 +1000
Subject: [PATCH] powerpc/64s: system call scv tabort fix for corrupt irq
soft-mask state
If a system call is made with a transaction active, the kernel
immediately aborts it and returns. scv system calls disable irqs even
earlier in their interrupt handler, and tabort_syscall does not fix this
up.
This can result in irq soft-mask state being messed up on the next
kernel entry, and crashing at BUG_ON(arch_irq_disabled_regs(regs)) in
the kernel exit handlers, or possibly worse.
This can't easily be fixed in asm because at this point an async irq may
have hit, which is soft-masked and marked pending. The pending interrupt
has to be replayed before returning to userspace. The fix is to move the
tabort_syscall code to C in the main syscall handler, and just skip the
system call but otherwise return as usual, which will take care of the
pending irqs. This also does a bunch of other things including possible
signal delivery to the process, but the doomed transaction should still
be aborted when it is eventually returned to.
The sc system call path is changed to use the new C function as well to
reduce code and path differences. This slows down how quickly system
calls are aborted when called while a transaction is active, which could
potentially impact TM performance. But making any system call is already
bad for performance, and TM is on the way out, so go with simpler over
faster.
Fixes: 7fa95f9adaee7 ("powerpc/64s: system call support for scv/rfscv instructions")
Reported-by: Eirik Fuller <efuller(a)redhat.com>
Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com>
[mpe: Use #ifdef rather than IS_ENABLED() to fix build error on 32-bit]
Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au>
Link: https://lore.kernel.org/r/20210903125707.1601269-1-npiggin@gmail.com
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index a73f3f70a657..2ccc7ea5db00 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -18,6 +18,7 @@
#include <asm/switch_to.h>
#include <asm/syscall.h>
#include <asm/time.h>
+#include <asm/tm.h>
#include <asm/unistd.h>
#if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
@@ -136,6 +137,35 @@ notrace long system_call_exception(long r3, long r4, long r5,
*/
irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
+ /*
+ * If the system call was made with a transaction active, doom it and
+ * return without performing the system call. Unless it was an
+ * unsupported scv vector, in which case it's treated like an illegal
+ * instruction.
+ */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+ !trap_is_unsupported_scv(regs)) {
+ /* Enable TM in the kernel, and disable EE (for scv) */
+ hard_irq_disable();
+ mtmsr(mfmsr() | MSR_TM);
+
+ /* tabort, this dooms the transaction, nothing else */
+ asm volatile(".long 0x7c00071d | ((%0) << 16)"
+ :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
+
+ /*
+ * Userspace will never see the return value. Execution will
+ * resume after the tbegin. of the aborted transaction with the
+ * checkpointed register state. A context switch could occur
+ * or signal delivered to the process before resuming the
+ * doomed transaction context, but that should all be handled
+ * as expected.
+ */
+ return -ENOSYS;
+ }
+#endif // CONFIG_PPC_TRANSACTIONAL_MEM
+
local_irq_enable();
if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index d4212d2ff0b5..ec950b08a8dc 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -12,7 +12,6 @@
#include <asm/mmu.h>
#include <asm/ppc_asm.h>
#include <asm/ptrace.h>
-#include <asm/tm.h>
.section ".toc","aw"
SYS_CALL_TABLE:
@@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE:
.globl system_call_vectored_\name
system_call_vectored_\name:
_ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
- extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
- bne tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
SCV_INTERRUPT_TO_KERNEL
mr r10,r1
ld r1,PACAKSAVE(r13)
@@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real)
.globl system_call_common
system_call_common:
_ASM_NOKPROBE_SYMBOL(system_call_common)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
- extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
- bne tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
mr r10,r1
ld r1,PACAKSAVE(r13)
std r10,0(r1)
@@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b)
RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart)
#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-tabort_syscall:
-_ASM_NOKPROBE_SYMBOL(tabort_syscall)
- /* Firstly we need to enable TM in the kernel */
- mfmsr r10
- li r9, 1
- rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r10, 0
-
- /* tabort, this dooms the transaction, nothing else */
- li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
- TABORT(R9)
-
- /*
- * Return directly to userspace. We have corrupted user register state,
- * but userspace will never see that register state. Execution will
- * resume after the tbegin of the aborted transaction with the
- * checkpointed register state.
- */
- li r9, MSR_RI
- andc r10, r10, r9
- mtmsrd r10, 1
- mtspr SPRN_SRR0, r11
- mtspr SPRN_SRR1, r12
- RFI_TO_USER
- b . /* prevent speculative execution */
-#endif
-
/*
* If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
* touched, no exit work created, then this can be used.
The patch below does not apply to the 5.14-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 44df58d441a94de40d52fca67dc60790daee4266 Mon Sep 17 00:00:00 2001
From: Xiaoguang Wang <xiaoguang.wang(a)linux.alibaba.com>
Date: Tue, 14 Sep 2021 22:38:52 +0800
Subject: [PATCH] io_uring: fix missing sigmask restore in io_cqring_wait()
Move get_timespec() section in io_cqring_wait() before the sigmask
saving, otherwise we'll fail to restore sigmask once get_timespec()
returns error.
Fixes: c73ebb685fb6 ("io_uring: add timeout support for io_uring_enter()")
Signed-off-by: Xiaoguang Wang <xiaoguang.wang(a)linux.alibaba.com>
Link: https://lore.kernel.org/r/20210914143852.9663-1-xiaoguang.wang@linux.alibab…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a864a94364c6..94afd087e97b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -7518,6 +7518,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
break;
} while (1);
+ if (uts) {
+ struct timespec64 ts;
+
+ if (get_timespec64(&ts, uts))
+ return -EFAULT;
+ timeout = timespec64_to_jiffies(&ts);
+ }
+
if (sig) {
#ifdef CONFIG_COMPAT
if (in_compat_syscall())
@@ -7531,14 +7539,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
return ret;
}
- if (uts) {
- struct timespec64 ts;
-
- if (get_timespec64(&ts, uts))
- return -EFAULT;
- timeout = timespec64_to_jiffies(&ts);
- }
-
init_waitqueue_func_entry(&iowq.wq, io_wake_function);
iowq.wq.private = current;
INIT_LIST_HEAD(&iowq.wq.entry);
The patch below does not apply to the 5.10-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 40ee363c844fcb6ae0f1f5cfea68aed7e268c2f4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni(a)redhat.com>
Date: Wed, 15 Sep 2021 10:19:07 -0700
Subject: [PATCH] igc: fix tunnel offloading
Checking tunnel offloading, it turns out that offloading doesn't work
as expected. The following script allows to reproduce the issue.
Call it as `testscript DEVICE LOCALIP REMOTEIP NETMASK'
=== SNIP ===
if [ $# -ne 4 ]
then
echo "Usage $0 DEVICE LOCALIP REMOTEIP NETMASK"
exit 1
fi
DEVICE="$1"
LOCAL_ADDRESS="$2"
REMOTE_ADDRESS="$3"
NWMASK="$4"
echo "Driver: $(ethtool -i ${DEVICE} | awk '/^driver:/{print $2}') "
ethtool -k "${DEVICE}" | grep tx-udp
echo
echo "Set up NIC and tunnel..."
ip addr add "${LOCAL_ADDRESS}/${NWMASK}" dev "${DEVICE}"
ip link set "${DEVICE}" up
sleep 2
ip link add vxlan1 type vxlan id 42 \
remote "${REMOTE_ADDRESS}" \
local "${LOCAL_ADDRESS}" \
dstport 0 \
dev "${DEVICE}"
ip addr add fc00::1/64 dev vxlan1
ip link set vxlan1 up
sleep 2
rm -f vxlan.pcap
echo "Running tcpdump and iperf3..."
( nohup tcpdump -i any -w vxlan.pcap >/dev/null 2>&1 ) &
sleep 2
iperf3 -c fc00::2 >/dev/null
pkill tcpdump
echo
echo -n "Max. Paket Size: "
tcpdump -r vxlan.pcap -nnle 2>/dev/null \
| grep "${LOCAL_ADDRESS}.*> ${REMOTE_ADDRESS}.*OTV" \
| awk '{print $8}' | awk -F ':' '{print $1}' \
| sort -n | tail -1
echo
ip link del vxlan1
ip addr del ${LOCAL_ADDRESS}/${NWMASK} dev "${DEVICE}"
=== SNAP ===
The expected outcome is
Max. Paket Size: 64904
This is what you see on igb, the code igc has been taken from.
However, on igc the output is
Max. Paket Size: 1516
so the GSO aggregate packets are segmented by the kernel before calling
igc_xmit_frame. Inside the subsequent call to igc_tso, the check for
skb_is_gso(skb) fails and the function returns prematurely.
It turns out that this occurs because the feature flags aren't set
entirely correctly in igc_probe. In contrast to the original code
from igb_probe, igc_probe neglects to set the flags required to allow
tunnel offloading.
Setting the same flags as igb fixes the issue on igc.
Fixes: 34428dff3679 ("igc: Add GSO partial support")
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
Tested-by: Corinna Vinschen <vinschen(a)redhat.com>
Acked-by: Sasha Neftin <sasha.neftin(a)intel.com>
Tested-by: Nechama Kraus <nechamax.kraus(a)linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index b877efae61df..0e19b4d02e62 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6350,7 +6350,9 @@ static int igc_probe(struct pci_dev *pdev,
if (pci_using_dac)
netdev->features |= NETIF_F_HIGHDMA;
- netdev->vlan_features |= netdev->features;
+ netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
+ netdev->mpls_features |= NETIF_F_HW_CSUM;
+ netdev->hw_enc_features |= netdev->vlan_features;
/* MTU range: 68 - 9216 */
netdev->min_mtu = ETH_MIN_MTU;
The patch below does not apply to the 4.9-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 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Date: Wed, 8 Sep 2021 15:43:35 +0800
Subject: [PATCH] net: stmmac: fix system hang caused by eee_ctrl_timer during
suspend/resume
commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after
napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer,
unfortunately, it only can resolve it for system reboot stress test. System
hang also can be reproduced easily during system suspend/resume stess test
when mount NFS on i.MX8MP EVK board.
In stmmac driver, eee feature is combined to phylink framework. When do
system suspend, phylink_stop() would queue delayed work, it invokes
stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly.
In above commit, try to fix issue by deactivating eee_ctrl_timer obviously,
but it is not enough. Looking into eee_ctrl_timer expire callback
stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is
unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always
asserted. This interrupt has chance to be issued when LPI state entry/exit
from the MAC, and at that time, clock could have been already disabled.
The result is that system hang when driver try to touch register from
interrupt handler.
The reason why above commit can fix system hang issue in stmmac_release()
is that, deactivate eee_ctrl_timer not just after napi disabled, further
after irq freed.
In conclusion, hardware would generate LPI interrupt when clock has been
disabled during suspend or resume, since hardware is in eee mode and LPI
interrupt enabled.
Interrupts from MAC, MTL and DMA level are enabled and never been disabled
when system suspend, so postpone clocks management from suspend stage to
noirq suspend stage should be more safe.
Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled")
Signed-off-by: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ece02b35a6ce..246f84fedbc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
u32 chan;
- int ret;
if (!ndev || !netif_running(ndev))
return 0;
@@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev)
} else {
stmmac_mac_set(priv, priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
- /* Disable clock in case of PWM is off */
- clk_disable_unprepare(priv->plat->clk_ptp_ref);
- ret = pm_runtime_force_suspend(dev);
- if (ret) {
- mutex_unlock(&priv->lock);
- return ret;
- }
}
mutex_unlock(&priv->lock);
@@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev)
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
- /* enable the clk previously disabled */
- ret = pm_runtime_force_resume(dev);
- if (ret)
- return ret;
- if (priv->plat->clk_ptp_ref)
- clk_prepare_enable(priv->plat->clk_ptp_ref);
/* reset the phy so that it's ready */
if (priv->mii)
stmmac_mdio_reset(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5ca710844cc1..4885f9ad1b1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -9,6 +9,7 @@
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
@@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
return stmmac_bus_clks_config(priv, true);
}
+static int stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* Disable clock in case of PWM is off */
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+ ret = pm_runtime_force_suspend(dev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int stmmac_pltfr_noirq_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* enable the clk previously disabled */
+ ret = pm_runtime_force_resume(dev);
+ if (ret)
+ return ret;
+
+ clk_prepare_enable(priv->plat->clk_ptp_ref);
+ }
+
+ return 0;
+}
+
const struct dev_pm_ops stmmac_pltfr_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
};
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
The patch below does not apply to the 4.4-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 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Date: Wed, 8 Sep 2021 15:43:35 +0800
Subject: [PATCH] net: stmmac: fix system hang caused by eee_ctrl_timer during
suspend/resume
commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after
napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer,
unfortunately, it only can resolve it for system reboot stress test. System
hang also can be reproduced easily during system suspend/resume stess test
when mount NFS on i.MX8MP EVK board.
In stmmac driver, eee feature is combined to phylink framework. When do
system suspend, phylink_stop() would queue delayed work, it invokes
stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly.
In above commit, try to fix issue by deactivating eee_ctrl_timer obviously,
but it is not enough. Looking into eee_ctrl_timer expire callback
stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is
unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always
asserted. This interrupt has chance to be issued when LPI state entry/exit
from the MAC, and at that time, clock could have been already disabled.
The result is that system hang when driver try to touch register from
interrupt handler.
The reason why above commit can fix system hang issue in stmmac_release()
is that, deactivate eee_ctrl_timer not just after napi disabled, further
after irq freed.
In conclusion, hardware would generate LPI interrupt when clock has been
disabled during suspend or resume, since hardware is in eee mode and LPI
interrupt enabled.
Interrupts from MAC, MTL and DMA level are enabled and never been disabled
when system suspend, so postpone clocks management from suspend stage to
noirq suspend stage should be more safe.
Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled")
Signed-off-by: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ece02b35a6ce..246f84fedbc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
u32 chan;
- int ret;
if (!ndev || !netif_running(ndev))
return 0;
@@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev)
} else {
stmmac_mac_set(priv, priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
- /* Disable clock in case of PWM is off */
- clk_disable_unprepare(priv->plat->clk_ptp_ref);
- ret = pm_runtime_force_suspend(dev);
- if (ret) {
- mutex_unlock(&priv->lock);
- return ret;
- }
}
mutex_unlock(&priv->lock);
@@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev)
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
- /* enable the clk previously disabled */
- ret = pm_runtime_force_resume(dev);
- if (ret)
- return ret;
- if (priv->plat->clk_ptp_ref)
- clk_prepare_enable(priv->plat->clk_ptp_ref);
/* reset the phy so that it's ready */
if (priv->mii)
stmmac_mdio_reset(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5ca710844cc1..4885f9ad1b1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -9,6 +9,7 @@
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
@@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
return stmmac_bus_clks_config(priv, true);
}
+static int stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* Disable clock in case of PWM is off */
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+ ret = pm_runtime_force_suspend(dev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int stmmac_pltfr_noirq_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* enable the clk previously disabled */
+ ret = pm_runtime_force_resume(dev);
+ if (ret)
+ return ret;
+
+ clk_prepare_enable(priv->plat->clk_ptp_ref);
+ }
+
+ return 0;
+}
+
const struct dev_pm_ops stmmac_pltfr_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
};
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
The patch below does not apply to the 4.14-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 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Date: Wed, 8 Sep 2021 15:43:35 +0800
Subject: [PATCH] net: stmmac: fix system hang caused by eee_ctrl_timer during
suspend/resume
commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after
napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer,
unfortunately, it only can resolve it for system reboot stress test. System
hang also can be reproduced easily during system suspend/resume stess test
when mount NFS on i.MX8MP EVK board.
In stmmac driver, eee feature is combined to phylink framework. When do
system suspend, phylink_stop() would queue delayed work, it invokes
stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly.
In above commit, try to fix issue by deactivating eee_ctrl_timer obviously,
but it is not enough. Looking into eee_ctrl_timer expire callback
stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is
unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always
asserted. This interrupt has chance to be issued when LPI state entry/exit
from the MAC, and at that time, clock could have been already disabled.
The result is that system hang when driver try to touch register from
interrupt handler.
The reason why above commit can fix system hang issue in stmmac_release()
is that, deactivate eee_ctrl_timer not just after napi disabled, further
after irq freed.
In conclusion, hardware would generate LPI interrupt when clock has been
disabled during suspend or resume, since hardware is in eee mode and LPI
interrupt enabled.
Interrupts from MAC, MTL and DMA level are enabled and never been disabled
when system suspend, so postpone clocks management from suspend stage to
noirq suspend stage should be more safe.
Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled")
Signed-off-by: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ece02b35a6ce..246f84fedbc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
u32 chan;
- int ret;
if (!ndev || !netif_running(ndev))
return 0;
@@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev)
} else {
stmmac_mac_set(priv, priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
- /* Disable clock in case of PWM is off */
- clk_disable_unprepare(priv->plat->clk_ptp_ref);
- ret = pm_runtime_force_suspend(dev);
- if (ret) {
- mutex_unlock(&priv->lock);
- return ret;
- }
}
mutex_unlock(&priv->lock);
@@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev)
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
- /* enable the clk previously disabled */
- ret = pm_runtime_force_resume(dev);
- if (ret)
- return ret;
- if (priv->plat->clk_ptp_ref)
- clk_prepare_enable(priv->plat->clk_ptp_ref);
/* reset the phy so that it's ready */
if (priv->mii)
stmmac_mdio_reset(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5ca710844cc1..4885f9ad1b1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -9,6 +9,7 @@
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
@@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
return stmmac_bus_clks_config(priv, true);
}
+static int stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* Disable clock in case of PWM is off */
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+ ret = pm_runtime_force_suspend(dev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int stmmac_pltfr_noirq_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* enable the clk previously disabled */
+ ret = pm_runtime_force_resume(dev);
+ if (ret)
+ return ret;
+
+ clk_prepare_enable(priv->plat->clk_ptp_ref);
+ }
+
+ return 0;
+}
+
const struct dev_pm_ops stmmac_pltfr_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
};
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
The patch below does not apply to the 4.19-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 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Date: Wed, 8 Sep 2021 15:43:35 +0800
Subject: [PATCH] net: stmmac: fix system hang caused by eee_ctrl_timer during
suspend/resume
commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after
napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer,
unfortunately, it only can resolve it for system reboot stress test. System
hang also can be reproduced easily during system suspend/resume stess test
when mount NFS on i.MX8MP EVK board.
In stmmac driver, eee feature is combined to phylink framework. When do
system suspend, phylink_stop() would queue delayed work, it invokes
stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly.
In above commit, try to fix issue by deactivating eee_ctrl_timer obviously,
but it is not enough. Looking into eee_ctrl_timer expire callback
stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is
unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always
asserted. This interrupt has chance to be issued when LPI state entry/exit
from the MAC, and at that time, clock could have been already disabled.
The result is that system hang when driver try to touch register from
interrupt handler.
The reason why above commit can fix system hang issue in stmmac_release()
is that, deactivate eee_ctrl_timer not just after napi disabled, further
after irq freed.
In conclusion, hardware would generate LPI interrupt when clock has been
disabled during suspend or resume, since hardware is in eee mode and LPI
interrupt enabled.
Interrupts from MAC, MTL and DMA level are enabled and never been disabled
when system suspend, so postpone clocks management from suspend stage to
noirq suspend stage should be more safe.
Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled")
Signed-off-by: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ece02b35a6ce..246f84fedbc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
u32 chan;
- int ret;
if (!ndev || !netif_running(ndev))
return 0;
@@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev)
} else {
stmmac_mac_set(priv, priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
- /* Disable clock in case of PWM is off */
- clk_disable_unprepare(priv->plat->clk_ptp_ref);
- ret = pm_runtime_force_suspend(dev);
- if (ret) {
- mutex_unlock(&priv->lock);
- return ret;
- }
}
mutex_unlock(&priv->lock);
@@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev)
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
- /* enable the clk previously disabled */
- ret = pm_runtime_force_resume(dev);
- if (ret)
- return ret;
- if (priv->plat->clk_ptp_ref)
- clk_prepare_enable(priv->plat->clk_ptp_ref);
/* reset the phy so that it's ready */
if (priv->mii)
stmmac_mdio_reset(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5ca710844cc1..4885f9ad1b1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -9,6 +9,7 @@
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
@@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
return stmmac_bus_clks_config(priv, true);
}
+static int stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* Disable clock in case of PWM is off */
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+ ret = pm_runtime_force_suspend(dev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int stmmac_pltfr_noirq_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* enable the clk previously disabled */
+ ret = pm_runtime_force_resume(dev);
+ if (ret)
+ return ret;
+
+ clk_prepare_enable(priv->plat->clk_ptp_ref);
+ }
+
+ return 0;
+}
+
const struct dev_pm_ops stmmac_pltfr_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
};
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
The patch below does not apply to the 5.4-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 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001
From: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Date: Wed, 8 Sep 2021 15:43:35 +0800
Subject: [PATCH] net: stmmac: fix system hang caused by eee_ctrl_timer during
suspend/resume
commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after
napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer,
unfortunately, it only can resolve it for system reboot stress test. System
hang also can be reproduced easily during system suspend/resume stess test
when mount NFS on i.MX8MP EVK board.
In stmmac driver, eee feature is combined to phylink framework. When do
system suspend, phylink_stop() would queue delayed work, it invokes
stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly.
In above commit, try to fix issue by deactivating eee_ctrl_timer obviously,
but it is not enough. Looking into eee_ctrl_timer expire callback
stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is
unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always
asserted. This interrupt has chance to be issued when LPI state entry/exit
from the MAC, and at that time, clock could have been already disabled.
The result is that system hang when driver try to touch register from
interrupt handler.
The reason why above commit can fix system hang issue in stmmac_release()
is that, deactivate eee_ctrl_timer not just after napi disabled, further
after irq freed.
In conclusion, hardware would generate LPI interrupt when clock has been
disabled during suspend or resume, since hardware is in eee mode and LPI
interrupt enabled.
Interrupts from MAC, MTL and DMA level are enabled and never been disabled
when system suspend, so postpone clocks management from suspend stage to
noirq suspend stage should be more safe.
Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled")
Signed-off-by: Joakim Zhang <qiangqing.zhang(a)nxp.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ece02b35a6ce..246f84fedbc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
u32 chan;
- int ret;
if (!ndev || !netif_running(ndev))
return 0;
@@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev)
} else {
stmmac_mac_set(priv, priv->ioaddr, false);
pinctrl_pm_select_sleep_state(priv->device);
- /* Disable clock in case of PWM is off */
- clk_disable_unprepare(priv->plat->clk_ptp_ref);
- ret = pm_runtime_force_suspend(dev);
- if (ret) {
- mutex_unlock(&priv->lock);
- return ret;
- }
}
mutex_unlock(&priv->lock);
@@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev)
priv->irq_wake = 0;
} else {
pinctrl_pm_select_default_state(priv->device);
- /* enable the clk previously disabled */
- ret = pm_runtime_force_resume(dev);
- if (ret)
- return ret;
- if (priv->plat->clk_ptp_ref)
- clk_prepare_enable(priv->plat->clk_ptp_ref);
/* reset the phy so that it's ready */
if (priv->mii)
stmmac_mdio_reset(priv->mii);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 5ca710844cc1..4885f9ad1b1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -9,6 +9,7 @@
*******************************************************************************/
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/of.h>
@@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev)
return stmmac_bus_clks_config(priv, true);
}
+static int stmmac_pltfr_noirq_suspend(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* Disable clock in case of PWM is off */
+ clk_disable_unprepare(priv->plat->clk_ptp_ref);
+
+ ret = pm_runtime_force_suspend(dev);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int stmmac_pltfr_noirq_resume(struct device *dev)
+{
+ struct net_device *ndev = dev_get_drvdata(dev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ int ret;
+
+ if (!netif_running(ndev))
+ return 0;
+
+ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
+ /* enable the clk previously disabled */
+ ret = pm_runtime_force_resume(dev);
+ if (ret)
+ return ret;
+
+ clk_prepare_enable(priv->plat->clk_ptp_ref);
+ }
+
+ return 0;
+}
+
const struct dev_pm_ops stmmac_pltfr_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume)
SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume)
};
EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);