From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Yangyang Li <liyangyang20@huawei.com>,
Wenpeng Liang <liangwenpeng@huawei.com>,
Jason Gunthorpe <jgg@nvidia.com>, Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.15 017/128] RDMA/hns: Fix RNR retransmission issue for HIP08
Date: Mon, 27 Dec 2021 16:29:52 +0100 [thread overview]
Message-ID: <20211227151332.094820380@linuxfoundation.org> (raw)
In-Reply-To: <20211227151331.502501367@linuxfoundation.org>
From: Yangyang Li <liyangyang20@huawei.com>
[ Upstream commit 4ad8181426df92976feee5fbc55236293d069b37 ]
Due to the discrete nature of the HIP08 timer unit, a requester might
finish the timeout period sooner, in elapsed real time, than its responder
does, even when both sides share the identical RNR timeout length included
in the RNR Nak packet and the responder indeed starts the timing prior to
the requester. Furthermore, if a 'providential' resend packet arrived
before the responder's timeout period expired, the responder is certainly
entitled to drop the packet silently in the light of IB protocol.
To address this problem, our team made good use of certain hardware facts:
1) The timing resolution regards the transmission arrangements is 1
microsecond, e.g. if cq_period field is set to 3, it would be
interpreted as 3 microsecond by hardware
2) A QPC field shall inform the hardware how many timing unit (ticks)
constitutes a full microsecond, which, by default, is 1000
3) It takes 14ns for the processor to handle a packet in the buffer, so
the RNR timeout length of 10ns would ensure our processing mechanism is
disabled during the entire timeout period and the packet won't be
dropped silently
To achieve (3), we permanently set the QPC field mentioned in (2) to zero
which nominally indicates every time tick is equivalent to a microsecond
in wall-clock time; now, a RNR timeout period at face value of 10 would
only last 10 ticks, which is 10ns in wall-clock time.
It's worth noting that we adapt the driver by magnifying certain
configuration parameters(cq_period, eq_period and ack_timeout)by 1000
given the user assumes the configuring timing unit to be microseconds.
Also, this particular improvisation is only deployed on HIP08 since other
hardware has already solved this issue.
Fixes: cfc85f3e4b7f ("RDMA/hns: Add profile support for hip08 driver")
Link: https://lore.kernel.org/r/20211209140655.49493-1-liangwenpeng@huawei.com
Signed-off-by: Yangyang Li <liyangyang20@huawei.com>
Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 64 +++++++++++++++++++---
drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 8 +++
2 files changed, 65 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 51dd134952e77..96fe73ba689c1 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1604,11 +1604,17 @@ static int hns_roce_config_global_param(struct hns_roce_dev *hr_dev)
{
struct hns_roce_cmq_desc desc;
struct hns_roce_cmq_req *req = (struct hns_roce_cmq_req *)desc.data;
+ u32 clock_cycles_of_1us;
hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_GLOBAL_PARAM,
false);
- hr_reg_write(req, CFG_GLOBAL_PARAM_1US_CYCLES, 0x3e8);
+ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08)
+ clock_cycles_of_1us = HNS_ROCE_1NS_CFG;
+ else
+ clock_cycles_of_1us = HNS_ROCE_1US_CFG;
+
+ hr_reg_write(req, CFG_GLOBAL_PARAM_1US_CYCLES, clock_cycles_of_1us);
hr_reg_write(req, CFG_GLOBAL_PARAM_UDP_PORT, ROCE_V2_UDP_DPORT);
return hns_roce_cmq_send(hr_dev, &desc, 1);
@@ -4812,6 +4818,30 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp,
return ret;
}
+static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout)
+{
+#define QP_ACK_TIMEOUT_MAX_HIP08 20
+#define QP_ACK_TIMEOUT_OFFSET 10
+#define QP_ACK_TIMEOUT_MAX 31
+
+ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+ if (*timeout > QP_ACK_TIMEOUT_MAX_HIP08) {
+ ibdev_warn(&hr_dev->ib_dev,
+ "Local ACK timeout shall be 0 to 20.\n");
+ return false;
+ }
+ *timeout += QP_ACK_TIMEOUT_OFFSET;
+ } else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) {
+ if (*timeout > QP_ACK_TIMEOUT_MAX) {
+ ibdev_warn(&hr_dev->ib_dev,
+ "Local ACK timeout shall be 0 to 31.\n");
+ return false;
+ }
+ }
+
+ return true;
+}
+
static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
const struct ib_qp_attr *attr,
int attr_mask,
@@ -4821,6 +4851,7 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
int ret = 0;
+ u8 timeout;
if (attr_mask & IB_QP_AV) {
ret = hns_roce_v2_set_path(ibqp, attr, attr_mask, context,
@@ -4830,12 +4861,10 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
}
if (attr_mask & IB_QP_TIMEOUT) {
- if (attr->timeout < 31) {
- hr_reg_write(context, QPC_AT, attr->timeout);
+ timeout = attr->timeout;
+ if (check_qp_timeout_cfg_range(hr_dev, &timeout)) {
+ hr_reg_write(context, QPC_AT, timeout);
hr_reg_clear(qpc_mask, QPC_AT);
- } else {
- ibdev_warn(&hr_dev->ib_dev,
- "Local ACK timeout shall be 0 to 30.\n");
}
}
@@ -4892,7 +4921,9 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
set_access_flags(hr_qp, context, qpc_mask, attr, attr_mask);
if (attr_mask & IB_QP_MIN_RNR_TIMER) {
- hr_reg_write(context, QPC_MIN_RNR_TIME, attr->min_rnr_timer);
+ hr_reg_write(context, QPC_MIN_RNR_TIME,
+ hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 ?
+ HNS_ROCE_RNR_TIMER_10NS : attr->min_rnr_timer);
hr_reg_clear(qpc_mask, QPC_MIN_RNR_TIME);
}
@@ -5509,6 +5540,16 @@ static int hns_roce_v2_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
hr_reg_write(cq_context, CQC_CQ_MAX_CNT, cq_count);
hr_reg_clear(cqc_mask, CQC_CQ_MAX_CNT);
+
+ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+ if (cq_period * HNS_ROCE_CLOCK_ADJUST > USHRT_MAX) {
+ dev_info(hr_dev->dev,
+ "cq_period(%u) reached the upper limit, adjusted to 65.\n",
+ cq_period);
+ cq_period = HNS_ROCE_MAX_CQ_PERIOD;
+ }
+ cq_period *= HNS_ROCE_CLOCK_ADJUST;
+ }
hr_reg_write(cq_context, CQC_CQ_PERIOD, cq_period);
hr_reg_clear(cqc_mask, CQC_CQ_PERIOD);
@@ -5904,6 +5945,15 @@ static int config_eqc(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq,
hr_reg_write(eqc, EQC_EQ_PROD_INDX, HNS_ROCE_EQ_INIT_PROD_IDX);
hr_reg_write(eqc, EQC_EQ_MAX_CNT, eq->eq_max_cnt);
+ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+ if (eq->eq_period * HNS_ROCE_CLOCK_ADJUST > USHRT_MAX) {
+ dev_info(hr_dev->dev, "eq_period(%u) reached the upper limit, adjusted to 65.\n",
+ eq->eq_period);
+ eq->eq_period = HNS_ROCE_MAX_EQ_PERIOD;
+ }
+ eq->eq_period *= HNS_ROCE_CLOCK_ADJUST;
+ }
+
hr_reg_write(eqc, EQC_EQ_PERIOD, eq->eq_period);
hr_reg_write(eqc, EQC_EQE_REPORT_TIMER, HNS_ROCE_EQ_INIT_REPORT_TIMER);
hr_reg_write(eqc, EQC_EQE_BA_L, bt_ba >> 3);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 4d904d5e82be4..35c61da7ba156 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -1444,6 +1444,14 @@ struct hns_roce_dip {
struct list_head node; /* all dips are on a list */
};
+/* only for RNR timeout issue of HIP08 */
+#define HNS_ROCE_CLOCK_ADJUST 1000
+#define HNS_ROCE_MAX_CQ_PERIOD 65
+#define HNS_ROCE_MAX_EQ_PERIOD 65
+#define HNS_ROCE_RNR_TIMER_10NS 1
+#define HNS_ROCE_1US_CFG 999
+#define HNS_ROCE_1NS_CFG 0
+
#define HNS_ROCE_AEQ_DEFAULT_BURST_NUM 0x0
#define HNS_ROCE_AEQ_DEFAULT_INTERVAL 0x0
#define HNS_ROCE_CEQ_DEFAULT_BURST_NUM 0x0
--
2.34.1
next prev parent reply other threads:[~2021-12-27 15:46 UTC|newest]
Thread overview: 138+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-12-27 15:29 [PATCH 5.15 000/128] 5.15.12-rc1 review Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 001/128] arm64: vdso32: require CROSS_COMPILE_COMPAT for gcc+bfd Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 002/128] net: usb: lan78xx: add Allied Telesis AT29M2-AF Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 003/128] ext4: prevent partial update of the extent blocks Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 004/128] ext4: check for out-of-order index extents in ext4_valid_extent_entries() Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 005/128] ext4: check for inconsistent extents between index and leaf block Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 006/128] selftests: KVM: Fix non-x86 compiling Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 007/128] HID: holtek: fix mouse probing Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 008/128] HID: potential dereference of null pointer Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 009/128] NFSD: Fix READDIR buffer overflow Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 010/128] PM: sleep: Fix error handling in dpm_prepare() Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 011/128] arm64: dts: allwinner: orangepi-zero-plus: fix PHY mode Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 012/128] bus: sunxi-rsb: Fix shutdown Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 013/128] spi: change clk_disable_unprepare to clk_unprepare Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 014/128] ucounts: Fix rlimit max values check Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 015/128] drm/mediatek: hdmi: Perform NULL pointer check for mtk_hdmi_conf Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 016/128] ASoC: meson: aiu: fifo: Add missing dma_coerce_mask_and_coherent() Greg Kroah-Hartman
2021-12-27 15:29 ` Greg Kroah-Hartman [this message]
2021-12-27 15:29 ` [PATCH 5.15 018/128] IB/qib: Fix memory leak in qib_user_sdma_queue_pkts() Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 019/128] RDMA/hns: Replace kfree() with kvfree() Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 020/128] netfilter: nf_tables: fix use-after-free in nft_set_catchall_destroy() Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 021/128] netfilter: fix regression in looped (broad|multi)casts MAC handling Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 022/128] ARM: dts: imx6qdl-wandboard: Fix Ethernet support Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 023/128] ice: Use xdp_buf instead of rx_buf for xsk zero-copy Greg Kroah-Hartman
2021-12-27 15:29 ` [PATCH 5.15 024/128] ice: xsk: return xsk buffers back to pool when cleaning the ring Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 025/128] net: marvell: prestera: fix incorrect return of port_find Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 026/128] net: marvell: prestera: fix incorrect structure access Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 027/128] qlcnic: potential dereference null pointer of rx_queue->page_ring Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 028/128] tcp: move inet->rx_dst_ifindex to sk->sk_rx_dst_ifindex Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 029/128] ipv6: move inet6_sk(sk)->rx_dst_cookie to sk->sk_rx_dst_cookie Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 030/128] inet: fully convert sk->sk_rx_dst to RCU rules Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 031/128] net: accept UFOv6 packages in virtio_net_hdr_to_skb Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 032/128] net: skip virtio_net_hdr_set_proto if protocol already set Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 033/128] igb: fix deadlock caused by taking RTNL in RPM resume path Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 034/128] ipmi: Fix UAF when uninstall ipmi_si and ipmi_msghandler module Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 035/128] gpio: virtio: remove timeout Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 036/128] bonding: fix ad_actor_system option setting to default Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 037/128] fjes: Check for error irq Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 038/128] drivers: net: smc911x: " Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 039/128] net: ks8851: " Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 040/128] sfc: Check null pointer of rx_queue->page_ring Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 041/128] sfc: falcon: " Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 042/128] asix: fix uninit-value in asix_mdio_read() Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 043/128] asix: fix wrong return value in asix_check_host_enable() Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 044/128] io_uring: zero iocb->ki_pos for stream file types Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 045/128] veth: ensure skb entering GRO are not cloned Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 046/128] net: stmmac: ptp: fix potentially overflowing expression Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 047/128] net: bridge: Use array_size() helper in copy_to_user() Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 048/128] net: bridge: fix ioctl old_deviceless bridge argument Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 049/128] r8152: fix the force speed doesnt work for RTL8156 Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 050/128] net: stmmac: dwmac-visconti: Fix value of ETHER_CLK_SEL_FREQ_SEL_2P5M Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 051/128] Input: elantech - fix stack out of bound access in elantech_change_report_id() Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 052/128] pinctrl: bcm2835: Change init order for gpio hogs Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 053/128] hwmon: (lm90) Fix usage of CONFIG2 register in detect function Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 054/128] hwmon: (lm90) Prevent integer overflow/underflow in hysteresis calculations Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 055/128] hwmon: (lm90) Introduce flag indicating extended temperature support Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 056/128] hwmon: (lm90) Add basic support for TI TMP461 Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 057/128] hwmon: (lm90) Drop critical attribute support for MAX6654 Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 058/128] ARM: 9160/1: NOMMU: Reload __secondary_data after PROCINFO_INITFUNC Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 059/128] uapi: Fix undefined __always_inline on non-glibc systems Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 060/128] compiler.h: Fix annotation macro misplacement with Clang Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 061/128] platform/x86/intel: Remove X86_PLATFORM_DRIVERS_INTEL Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 062/128] kernel/crash_core: suppress unknown crashkernel parameter warning Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 063/128] Revert "x86/boot: Pull up cmdline preparation and early param parsing" Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 064/128] x86/boot: Move EFI range reservation after cmdline parsing Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 065/128] ALSA: jack: Check the return value of kstrdup() Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 066/128] ALSA: drivers: opl3: Fix incorrect use of vp->state Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 067/128] ALSA: rawmidi - fix the uninitalized user_pversion Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 068/128] ALSA: hda/hdmi: Disable silent stream on GLK Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 069/128] ALSA: hda/realtek: Amp init fixup for HP ZBook 15 G6 Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 070/128] ALSA: hda/realtek: Add new alc285-hp-amp-init model Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 071/128] ALSA: hda/realtek: fix mute/micmute LEDs for a HP ProBook Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 072/128] ALSA: hda/realtek: Fix quirk for Clevo NJ51CU Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 073/128] ASoC: meson: aiu: Move AIU_I2S_MISC hold setting to aiu-fifo-i2s Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 074/128] ASoC: tegra: Add DAPM switches for headphones and mic jack Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 075/128] ASoC: tegra: Restore headphones jack name on Nyan Big Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 076/128] Input: atmel_mxt_ts - fix double free in mxt_read_info_block Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 077/128] ipmi: bail out if init_srcu_struct fails Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 078/128] ipmi: ssif: initialize ssif_info->client early Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 079/128] ipmi: fix initialization when workqueue allocation fails Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 080/128] parisc: Correct completer in lws start Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 081/128] parisc: Fix mask used to select futex spinlock Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 082/128] tee: handle lookup of shm with reference count 0 Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 083/128] x86/pkey: Fix undefined behaviour with PKRU_WD_BIT Greg Kroah-Hartman
2021-12-27 15:30 ` [PATCH 5.15 084/128] platform/x86: amd-pmc: only use callbacks for suspend Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 085/128] platform/x86: intel_pmc_core: fix memleak on registration failure Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 086/128] KVM: x86: Always set kvm_run->if_flag Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 087/128] KVM: x86/mmu: Dont advance iterator after restart due to yielding Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 088/128] KVM: nVMX: Synthesize TRIPLE_FAULT for L2 if emulation is required Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 089/128] KVM: VMX: Always clear vmx->fail on emulation_required Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 090/128] KVM: VMX: Wake vCPU when delivering posted IRQ even if vCPU == this vCPU Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 091/128] pinctrl: stm32: consider the GPIO offset to expose all the GPIO lines Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 092/128] gpio: dln2: Fix interrupts when replugging the device Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 093/128] mmc: sdhci-tegra: Fix switch to HS400ES mode Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 094/128] mmc: meson-mx-sdhc: Set MANUAL_STOP for multi-block SDIO commands Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 095/128] mmc: core: Disable card detect during shutdown Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 096/128] mmc: mmci: stm32: clear DLYB_CR after sending tuning command Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 097/128] ARM: 9169/1: entry: fix Thumb2 bug in iWMMXt exception handling Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 098/128] ksmbd: fix error code in ndr_read_int32() Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 099/128] ksmbd: fix uninitialized symbol pntsd_size Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 100/128] ksmbd: disable SMB2_GLOBAL_CAP_ENCRYPTION for SMB 3.1.1 Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 101/128] mac80211: fix locking in ieee80211_start_ap error path Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 102/128] mm: mempolicy: fix THP allocations escaping mempolicy restrictions Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 103/128] mm, hwpoison: fix condition in free hugetlb page path Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 104/128] mm/hwpoison: clear MF_COUNT_INCREASED before retrying get_any_page() Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 105/128] mm/damon/dbgfs: protect targets destructions with kdamond_lock Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 106/128] tee: optee: Fix incorrect page free bug Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 107/128] f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr() Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 108/128] netfs: fix parameter of cleanup() Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 109/128] KVM: VMX: Fix stale docs for kvm-intel.emulate_invalid_guest_state Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 110/128] arm64: dts: lx2160a: fix scl-gpios property name Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 111/128] kfence: fix memory leak when cat kfence objects Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 112/128] Input: iqs626a - prohibit inlining of channel parsing functions Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 113/128] Input: elants_i2c - do not check Remark ID on eKTH3900/eKTH5312 Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 114/128] Input: i8042 - enable deferred probe quirk for ASUS UM325UA Greg Kroah-Hartman
2021-12-27 15:53 ` Samuel Čavoj
2021-12-27 16:00 ` Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 115/128] Input: goodix - add id->model mapping for the "9111" model Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 116/128] ASoC: tas2770: Fix setting of high sample rates Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 117/128] ASoC: SOF: Intel: pci-tgl: add new ADL-P variant Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 118/128] ASoC: SOF: Intel: pci-tgl: add ADL-N support Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 119/128] ASoC: rt5682: fix the wrong jack type detected Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 120/128] pinctrl: mediatek: fix global-out-of-bounds issue Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 121/128] hwmom: (lm90) Fix citical alarm status for MAX6680/MAX6681 Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 122/128] hwmon: (lm90) Do not report busy status bit as alarm Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 123/128] r8152: sync ocp base Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 124/128] ax25: NPD bug when detaching AX25 device Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 125/128] hamradio: defer ax25 kfree after unregister_netdev Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 126/128] hamradio: improve the incomplete fix to avoid NPD Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 127/128] tun: avoid double free in tun_free_netdev Greg Kroah-Hartman
2021-12-27 15:31 ` [PATCH 5.15 128/128] phonet/pep: refuse to enable an unbound pipe Greg Kroah-Hartman
2021-12-27 18:32 ` [PATCH 5.15 000/128] 5.15.12-rc1 review Florian Fainelli
2021-12-28 8:01 ` Naresh Kamboju
2021-12-28 11:12 ` Rudi Heitbaum
2021-12-28 13:25 ` Sudip Mukherjee
2021-12-28 13:27 ` Jeffrin Jose T
2021-12-28 17:07 ` Guenter Roeck
2021-12-28 21:26 ` Shuah Khan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211227151332.094820380@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=jgg@nvidia.com \
--cc=liangwenpeng@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=liyangyang20@huawei.com \
--cc=sashal@kernel.org \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.