From: Tianjia Zhang <tianjia.zhang@xxxxxxxxxxxxxxxxx>
In the init function, if the call to of_iomap() fails, the return
value is ENXIO instead of -ENXIO.
Change to the right negative errno.
Fixes: 691f8f878290f ("clocksource/drivers/h8300_timer8: Convert init function to return error")
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Signed-off-by: Tianjia Zhang <tianjia.zhang@xxxxxxxxxxxxxxxxx>
Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200802111541.5429-1-tianjia.zhang@xxxxxxxxxxxxxxxxx
---
drivers/clocksource/h8300_timer8.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
index 1d740a8c42ab..47114c2a7cb5 100644
--- a/drivers/clocksource/h8300_timer8.c
+++ b/drivers/clocksource/h8300_timer8.c
@@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node)
return PTR_ERR(clk);
}
- ret = ENXIO;
+ ret = -ENXIO;
base = of_iomap(node, 0);
if (!base) {
pr_err("failed to map registers for clockevent\n");
--
GitLab
>From 164805157f3c6834670afbaff563353c773131f1 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@xxxxxxxxxxx>
Date: Mon, 17 Aug 2020 12:24:28 +0300
Subject: [PATCH 002/126] clocksource/drivers/timer-ti-dm: Do reset before
enable
Commit 6cfcd5563b4f ("clocksource/drivers/timer-ti-dm: Fix suspend and
resume for am3 and am4") exposed a new issue for type2 dual mode timers
on at least omap5 where the clockevent will stop when the SoC starts
entering idle states during the boot.
Turns out we are wrongly first enabling the system timer and then
resetting it, while we must also re-enable it after reset. The current
sequence leaves the timer module in a partially initialized state. This
issue went unnoticed earlier with ti-sysc driver reconfiguring the timer
module until we fixed the issue of ti-sysc reconfiguring system timers.
Let's fix the issue by calling dmtimer_systimer_enable() from reset for
both type1 and type2 timers, and switch the order of reset and enable in
dmtimer_systimer_setup(). Let's also move dmtimer_systimer_enable() and
dmtimer_systimer_disable() to do this without adding forward declarations.
Fixes: 6cfcd5563b4f ("clocksource/drivers/timer-ti-dm: Fix suspend and resume for am3 and am4")
Reported-by: H. Nikolaus Schaller" <hns@xxxxxxxxxxxxx>
Signed-off-by: Tony Lindgren <tony@xxxxxxxxxxx>
Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200817092428.6176-1-tony@xxxxxxxxxxx
---
drivers/clocksource/timer-ti-dm-systimer.c | 44 +++++++++++-----------
1 file changed, 23 insertions(+), 21 deletions(-)
diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c
index f6fd1c1cc527..33b3e8aa2cc5 100644
--- a/drivers/clocksource/timer-ti-dm-systimer.c
+++ b/drivers/clocksource/timer-ti-dm-systimer.c
@@ -69,12 +69,33 @@ static bool dmtimer_systimer_revision1(struct dmtimer_systimer *t)
return !(tidr >> 16);
}
+static void dmtimer_systimer_enable(struct dmtimer_systimer *t)
+{
+ u32 val;
+
+ if (dmtimer_systimer_revision1(t))
+ val = DMTIMER_TYPE1_ENABLE;
+ else
+ val = DMTIMER_TYPE2_ENABLE;
+
+ writel_relaxed(val, t->base + t->sysc);
+}
+
+static void dmtimer_systimer_disable(struct dmtimer_systimer *t)
+{
+ if (!dmtimer_systimer_revision1(t))
+ return;
+
+ writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc);
+}
+
static int __init dmtimer_systimer_type1_reset(struct dmtimer_systimer *t)
{
void __iomem *syss = t->base + OMAP_TIMER_V1_SYS_STAT_OFFSET;
int ret;
u32 l;
+ dmtimer_systimer_enable(t);
writel_relaxed(BIT(1) | BIT(2), t->base + t->ifctrl);
ret = readl_poll_timeout_atomic(syss, l, l & BIT(0), 100,
DMTIMER_RESET_WAIT);
@@ -88,6 +109,7 @@ static int __init dmtimer_systimer_type2_reset(struct dmtimer_systimer *t)
void __iomem *sysc = t->base + t->sysc;
u32 l;
+ dmtimer_systimer_enable(t);
l = readl_relaxed(sysc);
l |= BIT(0);
writel_relaxed(l, sysc);
@@ -336,26 +358,6 @@ static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t,
return 0;
}
-static void dmtimer_systimer_enable(struct dmtimer_systimer *t)
-{
- u32 val;
-
- if (dmtimer_systimer_revision1(t))
- val = DMTIMER_TYPE1_ENABLE;
- else
- val = DMTIMER_TYPE2_ENABLE;
-
- writel_relaxed(val, t->base + t->sysc);
-}
-
-static void dmtimer_systimer_disable(struct dmtimer_systimer *t)
-{
- if (!dmtimer_systimer_revision1(t))
- return;
-
- writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc);
-}
-
static int __init dmtimer_systimer_setup(struct device_node *np,
struct dmtimer_systimer *t)
{
@@ -409,8 +411,8 @@ static int __init dmtimer_systimer_setup(struct device_node *np,
t->wakeup = regbase + _OMAP_TIMER_WAKEUP_EN_OFFSET;
t->ifctrl = regbase + _OMAP_TIMER_IF_CTRL_OFFSET;
- dmtimer_systimer_enable(t);
dmtimer_systimer_reset(t);
+ dmtimer_systimer_enable(t);
pr_debug("dmtimer rev %08x sysc %08x\n", readl_relaxed(t->base),
readl_relaxed(t->base + t->sysc));
--
GitLab
>From bc6717d55d07110d8f3c6d31ec2af50c11b07091 Mon Sep 17 00:00:00 2001
From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Date: Tue, 18 Aug 2020 07:31:17 +0000
Subject: [PATCH 003/126] clocksource/drivers/timer-gx6605s: Fixup counter
reload
When the timer counts to the upper limit, an overflow interrupt is
generated, and the count is reset with the value in the TIME_INI
register. But the software expects to start counting from 0 when
the count overflows, so it forces TIME_INI to 0 to solve the
potential interrupt storm problem.
Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
Tested-by: Xu Kai <xukai@xxxxxxxxxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Link: https://lore.kernel.org/r/1597735877-71115-1-git-send-email-guoren@xxxxxxxxxx
---
drivers/clocksource/timer-gx6605s.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/clocksource/timer-gx6605s.c b/drivers/clocksource/timer-gx6605s.c
index 80d0939d040b..8d386adbe800 100644
--- a/drivers/clocksource/timer-gx6605s.c
+++ b/drivers/clocksource/timer-gx6605s.c
@@ -28,6 +28,7 @@ static irqreturn_t gx6605s_timer_interrupt(int irq, void *dev)
void __iomem *base = timer_of_base(to_timer_of(ce));
writel_relaxed(GX6605S_STATUS_CLR, base + TIMER_STATUS);
+ writel_relaxed(0, base + TIMER_INI);
ce->event_handler(ce);
--
GitLab
>From d89a80ddbfd86d04d0901e576ca2016d324bcb85 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@xxxxxx>
Date: Tue, 25 Aug 2020 16:31:05 +0300
Subject: [PATCH 004/126] dt-bindings: crypto: sa2ul: fix a DT binding check
warning
DT binding check produces a warning about bad cell size:
Documentation/devicetree/bindings/crypto/ti,sa2ul.example.dt.yaml: example-0: crypto@4e00000:reg:0: [0, 81788928, 0, 4608] is too long
From schema: python3.6/site-packages/dtschema/schemas/reg.yaml
Fix this by reducing the address sizes for the example to 1 cell from
current 2.
Fixes: 2ce9a7299bf6 ("dt-bindings: crypto: Add TI SA2UL crypto accelerator documentation")
Reported-by: Rob Herring <robh@xxxxxxxxxx>
Cc: Rob Herring <robh@xxxxxxxxxx>
Cc: devicetree@xxxxxxxxxxxxxxx
Signed-off-by: Tero Kristo <t-kristo@xxxxxx>
Link: https://lore.kernel.org/r/20200825133106.21542-2-t-kristo@xxxxxx
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
index 85ef69ffebed..1465c9ebaf93 100644
--- a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
+++ b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml
@@ -67,7 +67,7 @@ examples:
main_crypto: crypto@4e00000 {
compatible = "ti,j721-sa2ul";
- reg = <0x0 0x4e00000 0x0 0x1200>;
+ reg = <0x4e00000 0x1200>;
power-domains = <&k3_pds 264 TI_SCI_PD_EXCLUSIVE>;
dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>,
<&main_udmap 0x4001>;
--
GitLab
>From ec653df2a0cbc306a4bfcb0e3484d318fa779002 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@xxxxxxxxxxx>
Date: Wed, 1 Jul 2020 09:39:49 +0200
Subject: [PATCH 005/126] drm/vc4/vc4_hdmi: fill ASoC card owner
card->owner is a required property and since commit 81033c6b584b ("ALSA:
core: Warn on empty module") a warning is issued if it is empty. Fix lack
of it. This fixes following warning observed on RaspberryPi 3B board
with ARM 32bit kernel and multi_v7_defconfig:
------------[ cut here ]------------
WARNING: CPU: 1 PID: 210 at sound/core/init.c:207 snd_card_new+0x378/0x398 [snd]
Modules linked in: vc4(+) snd_soc_core ac97_bus snd_pcm_dmaengine bluetooth snd_pcm snd_timer crc32_arm_ce raspberrypi_hwmon snd soundcore ecdh_generic ecc bcm2835_thermal phy_generic
CPU: 1 PID: 210 Comm: systemd-udevd Not tainted 5.8.0-rc1-00027-g81033c6b584b #1087
Hardware name: BCM2835
[<c03113c0>] (unwind_backtrace) from [<c030bcb4>] (show_stack+0x10/0x14)
[<c030bcb4>] (show_stack) from [<c071cef8>] (dump_stack+0xd4/0xe8)
[<c071cef8>] (dump_stack) from [<c0345bfc>] (__warn+0xdc/0xf4)
[<c0345bfc>] (__warn) from [<c0345cc4>] (warn_slowpath_fmt+0xb0/0xb8)
[<c0345cc4>] (warn_slowpath_fmt) from [<bf02ff74>] (snd_card_new+0x378/0x398 [snd])
[<bf02ff74>] (snd_card_new [snd]) from [<bf11f0b4>] (snd_soc_bind_card+0x280/0x99c [snd_soc_core])
[<bf11f0b4>] (snd_soc_bind_card [snd_soc_core]) from [<bf12f000>] (devm_snd_soc_register_card+0x34/0x6c [snd_soc_core])
[<bf12f000>] (devm_snd_soc_register_card [snd_soc_core]) from [<bf165654>] (vc4_hdmi_bind+0x43c/0x5f4 [vc4])
[<bf165654>] (vc4_hdmi_bind [vc4]) from [<c09d660c>] (component_bind_all+0xec/0x24c)
[<c09d660c>] (component_bind_all) from [<bf15c44c>] (vc4_drm_bind+0xd4/0x174 [vc4])
[<bf15c44c>] (vc4_drm_bind [vc4]) from [<c09d6ac0>] (try_to_bring_up_master+0x160/0x1b0)
[<c09d6ac0>] (try_to_bring_up_master) from [<c09d6f38>] (component_master_add_with_match+0xd0/0x104)
[<c09d6f38>] (component_master_add_with_match) from [<bf15c588>] (vc4_platform_drm_probe+0x9c/0xbc [vc4])
[<bf15c588>] (vc4_platform_drm_probe [vc4]) from [<c09df740>] (platform_drv_probe+0x6c/0xa4)
[<c09df740>] (platform_drv_probe) from [<c09dd6f0>] (really_probe+0x210/0x350)
[<c09dd6f0>] (really_probe) from [<c09dd940>] (driver_probe_device+0x5c/0xb4)
[<c09dd940>] (driver_probe_device) from [<c09ddb38>] (device_driver_attach+0x58/0x60)
[<c09ddb38>] (device_driver_attach) from [<c09ddbc0>] (__driver_attach+0x80/0xbc)
[<c09ddbc0>] (__driver_attach) from [<c09db820>] (bus_for_each_dev+0x68/0xb4)
[<c09db820>] (bus_for_each_dev) from [<c09dc9f8>] (bus_add_driver+0x130/0x1e8)
[<c09dc9f8>] (bus_add_driver) from [<c09de648>] (driver_register+0x78/0x110)
[<c09de648>] (driver_register) from [<c0302038>] (do_one_initcall+0x50/0x220)
[<c0302038>] (do_one_initcall) from [<c03db544>] (do_init_module+0x60/0x210)
[<c03db544>] (do_init_module) from [<c03da4f8>] (load_module+0x1e34/0x2338)
[<c03da4f8>] (load_module) from [<c03dac00>] (sys_finit_module+0xac/0xbc)
[<c03dac00>] (sys_finit_module) from [<c03000c0>] (ret_fast_syscall+0x0/0x54)
Exception stack(0xeded9fa8 to 0xeded9ff0)
...
---[ end trace 6414689569c2bc08 ]---
Fixes: bb7d78568814 ("drm/vc4: Add HDMI audio support")
Suggested-by: Takashi Iwai <tiwai@xxxxxxx>
Signed-off-by: Marek Szyprowski <m.szyprowski@xxxxxxxxxxx>
Tested-by: Stefan Wahren <stefan.wahren@xxxxxxxx>
Signed-off-by: Maxime Ripard <maxime@xxxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20200701073949.28941-1-m.szyprowski@xxxxxxxxxxx
---
drivers/gpu/drm/vc4/vc4_hdmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 15a11cd4de25..6339c6f0f571 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1117,6 +1117,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi)
card->num_links = 1;
card->name = "vc4-hdmi";
card->dev = dev;
+ card->owner = THIS_MODULE;
/*
* Be careful, snd_soc_register_card() calls dev_set_drvdata() and
--
GitLab
>From cab4c03b4ba54c8d9378298cacb8bc0fd74ceece Mon Sep 17 00:00:00 2001
From: Martin Cerveny <m.cerveny@xxxxxxxxxxxx>
Date: Sun, 6 Sep 2020 18:21:39 +0200
Subject: [PATCH 006/126] drm/sun4i: sun8i-csc: Secondary CSC register
correction
"Allwinner V3s" has secondary video layer (VI).
Decoded video is displayed in wrong colors until
secondary CSC registers are programmed correctly.
Fixes: 883029390550 ("drm/sun4i: Add DE2 CSC library")
Signed-off-by: Martin Cerveny <m.cerveny@xxxxxxxxxxxx>
Reviewed-by: Jernej Skrabec <jernej.skrabec@xxxxxxxx>
Signed-off-by: Maxime Ripard <maxime@xxxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20200906162140.5584-2-m.cerveny@xxxxxxxxxxxx
---
drivers/gpu/drm/sun4i/sun8i_csc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h
index f42441b1b14d..a55a38ad849c 100644
--- a/drivers/gpu/drm/sun4i/sun8i_csc.h
+++ b/drivers/gpu/drm/sun4i/sun8i_csc.h
@@ -12,7 +12,7 @@ struct sun8i_mixer;
/* VI channel CSC units offsets */
#define CCSC00_OFFSET 0xAA050
-#define CCSC01_OFFSET 0xFA000
+#define CCSC01_OFFSET 0xFA050
#define CCSC10_OFFSET 0xA0000
#define CCSC11_OFFSET 0xF0000
--
GitLab
>From 74ea06164cda81dc80e97790164ca533fd7e3087 Mon Sep 17 00:00:00 2001
From: Martin Cerveny <m.cerveny@xxxxxxxxxxxx>
Date: Sun, 6 Sep 2020 18:21:40 +0200
Subject: [PATCH 007/126] drm/sun4i: mixer: Extend regmap max_register
Better guess. Secondary CSC registers are from 0xF0000.
Signed-off-by: Martin Cerveny <m.cerveny@xxxxxxxxxxxx>
Reviewed-by: Jernej Skrabec <jernej.skrabec@xxxxxxxx>
Signed-off-by: Maxime Ripard <maxime@xxxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20200906162140.5584-3-m.cerveny@xxxxxxxxxxxx
---
drivers/gpu/drm/sun4i/sun8i_mixer.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index cc4fb916318f..c3304028e3dc 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -307,7 +307,7 @@ static struct regmap_config sun8i_mixer_regmap_config = {
.reg_bits = 32,
.val_bits = 32,
.reg_stride = 4,
- .max_register = 0xbfffc, /* guessed */
+ .max_register = 0xffffc, /* guessed */
};
static int sun8i_mixer_of_get_id(struct device_node *node)
--
GitLab
>From 288eceb0858323d66bff03cf386630a797b248ad Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xxxxxxxxx>
Date: Tue, 8 Sep 2020 12:02:53 +0200
Subject: [PATCH 008/126] media: cec-adap.c: don't use flush_scheduled_work()
For some inexplicable reason I decided to call flush_scheduled_work()
instead of cancel_delayed_work_sync(). The problem with that is that
flush_scheduled_work() waits for *all* queued scheduled work to be
completed instead of just the work itself.
This can cause a deadlock if a CEC driver also schedules work that
takes the same lock. See the comments for flush_scheduled_work() in
linux/workqueue.h.
This is exactly what has been observed a few times.
This patch simply replaces flush_scheduled_work() by
cancel_delayed_work_sync().
Signed-off-by: Hans Verkuil <hverkuil-cisco@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # for v5.8 and up
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@xxxxxxxxxx>
---
drivers/media/cec/core/cec-adap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c
index 4efe8014445e..926d65db6d3e 100644
--- a/drivers/media/cec/core/cec-adap.c
+++ b/drivers/media/cec/core/cec-adap.c
@@ -1199,7 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap,
/* Cancel the pending timeout work */
if (!cancel_delayed_work(&data->work)) {
mutex_unlock(&adap->lock);
- flush_scheduled_work();
+ cancel_delayed_work_sync(&data->work);
mutex_lock(&adap->lock);
}
/*
--
GitLab
>From 505623a2be48b36de533951ced130876a76a2d55 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@xxxxxxx>
Date: Thu, 10 Sep 2020 15:15:32 +0300
Subject: [PATCH 009/126] spi: spi-fsl-dspi: use XSPI mode instead of DMA for
DPAA2 SoCs
The arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi device tree lacks DMA
channels for DSPI, so naturally, the driver fails to probe:
[ 2.945302] fsl-dspi 2100000.spi: rx dma channel not available
[ 2.951134] fsl-dspi 2100000.spi: can't get dma channels
In retrospect, this should have been obvious, because LS2080A, LS2085A
LS2088A and LX2160A don't appear to have an eDMA module at all. Looking
again at their datasheets, the CTARE register (which is specific to XSPI
functionality) seems to be documented, so switch them to XSPI mode
instead.
Fixes: 0feaf8f5afe0 ("spi: spi-fsl-dspi: Convert the instantiations that support it to DMA")
Reported-by: Qiang Zhao <qiang.zhao@xxxxxxx>
Tested-by: Qiang Zhao <qiang.zhao@xxxxxxx>
Signed-off-by: Vladimir Oltean <vladimir.oltean@xxxxxxx>
Link: https://lore.kernel.org/r/20200910121532.1138596-1-olteanv@xxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/spi/spi-fsl-dspi.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 91c6affe139c..283f2468a2f4 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -174,17 +174,17 @@ static const struct fsl_dspi_devtype_data devtype_data[] = {
.fifo_size = 16,
},
[LS2080A] = {
- .trans_mode = DSPI_DMA_MODE,
+ .trans_mode = DSPI_XSPI_MODE,
.max_clock_factor = 8,
.fifo_size = 4,
},
[LS2085A] = {
- .trans_mode = DSPI_DMA_MODE,
+ .trans_mode = DSPI_XSPI_MODE,
.max_clock_factor = 8,
.fifo_size = 4,
},
[LX2160A] = {
- .trans_mode = DSPI_DMA_MODE,
+ .trans_mode = DSPI_XSPI_MODE,
.max_clock_factor = 8,
.fifo_size = 4,
},
--
GitLab
>From 28284943ac94014767ecc2f7b3c5747c4a5617a0 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@xxxxxxxxxxxxxxx>
Date: Mon, 14 Sep 2020 11:03:02 +0800
Subject: [PATCH 010/126] drm/i915/gvt: Fix port number for BDW on EDID region
setup
Current BDW virtual display port is initialized as PORT_B, so need
to use same port for VFIO EDID region, otherwise invalid EDID blob
pointer is assigned which caused kernel null pointer reference. We
might evaluate actual display hotplug for BDW to make this function
work as expected, anyway this is always required to be fixed first.
Reported-by: Alejandro Sior <aho@xxxxxxx>
Cc: Alejandro Sior <aho@xxxxxxx>
Fixes: 0178f4ce3c3b ("drm/i915/gvt: Enable vfio edid for all GVT supported platform")
Reviewed-by: Hang Yuan <hang.yuan@xxxxxxxxx>
Signed-off-by: Zhenyu Wang <zhenyuw@xxxxxxxxxxxxxxx>
Link: http://patchwork.freedesktop.org/patch/msgid/20200914030302.2775505-1-zhenyuw@xxxxxxxxxxxxxxx
---
drivers/gpu/drm/i915/gvt/vgpu.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 7d361623ff67..041f601b07d0 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -367,6 +367,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu)
static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
struct intel_vgpu_creation_params *param)
{
+ struct drm_i915_private *dev_priv = gvt->gt->i915;
struct intel_vgpu *vgpu;
int ret;
@@ -434,7 +435,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
if (ret)
goto out_clean_sched_policy;
- ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
+ if (IS_BROADWELL(dev_priv))
+ ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
+ else
+ ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
if (ret)
goto out_clean_sched_policy;
--
GitLab
>From 14801c624066a55139c2c57963eb1b859d0a316a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
Date: Mon, 14 Sep 2020 11:42:43 +0200
Subject: [PATCH 011/126] mmc: mmc_spi: Fix mmc_spi_dma_alloc() return type for
!HAS_DMA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If CONFIG_NO_DMA=y (e.g. Sun-3 allmodconfig):
drivers/mmc/host/mmc_spi.c:1323:15: warning: return type defaults to ‘int’ [-Wreturn-type]
static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
^~~~~~~~~~~~~~~~~
Fix this by adding the missing return type.
Fixes: a395acf0f6dc6409 ("mmc: mmc_spi: Allow the driver to be built when CONFIG_HAS_DMA is unset")
Signed-off-by: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200914094243.3912-1-geert@xxxxxxxxxxxxxx
Signed-off-by: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
---
drivers/mmc/host/mmc_spi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 5055a7eb134a..18a850f37ddc 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1320,7 +1320,7 @@ static void mmc_spi_dma_free(struct mmc_spi_host *host)
DMA_BIDIRECTIONAL);
}
#else
-static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
+static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; }
static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {}
#endif
--
GitLab
>From 129134e5415d46f38b9978b3809af94ed649b57d Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Date: Fri, 11 Sep 2020 05:07:58 +0200
Subject: [PATCH 012/126] media: media/v4l2: remove
V4L2_FLAG_MEMORY_NON_CONSISTENT flag
The patch partially reverts some of the UAPI bits of the buffer
cache management hints. Namely, the queue consistency (memory
coherency) user-space hint because, as it turned out, the kernel
implementation of this feature was misusing DMA_ATTR_NON_CONSISTENT.
The patch reverts both kernel and user space parts: removes the
DMA consistency attr functions, rolls back changes to v4l2_requestbuffers,
v4l2_create_buffers structures and corresponding UAPI functions
(plus compat32 layer) and cleans up the documentation.
[hverkuil: fixed a few typos in the commit log]
[hverkuil: fixed vb2_core_reqbufs call in drivers/media/dvb-core/dvb_vb2.c]
[mchehab: fixed a typo in the commit log: revers->reverts]
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xxxxxxxxx>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@xxxxxxxxxx>
---
.../userspace-api/media/v4l/buffer.rst | 17 -------
.../media/v4l/vidioc-create-bufs.rst | 6 +--
.../media/v4l/vidioc-reqbufs.rst | 12 +----
.../media/common/videobuf2/videobuf2-core.c | 46 +++----------------
.../common/videobuf2/videobuf2-dma-contig.c | 19 --------
.../media/common/videobuf2/videobuf2-dma-sg.c | 3 +-
.../media/common/videobuf2/videobuf2-v4l2.c | 18 +-------
drivers/media/dvb-core/dvb_vb2.c | 2 +-
drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 10 +---
drivers/media/v4l2-core/v4l2-ioctl.c | 5 +-
include/media/videobuf2-core.h | 7 +--
include/uapi/linux/videodev2.h | 13 +-----
12 files changed, 23 insertions(+), 135 deletions(-)
diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst
index 57e752aaf414..2044ed13cd9d 100644
--- a/Documentation/userspace-api/media/v4l/buffer.rst
+++ b/Documentation/userspace-api/media/v4l/buffer.rst
@@ -701,23 +701,6 @@ Memory Consistency Flags
:stub-columns: 0
:widths: 3 1 4
- * .. _`V4L2-FLAG-MEMORY-NON-CONSISTENT`:
-
- - ``V4L2_FLAG_MEMORY_NON_CONSISTENT``
- - 0x00000001
- - A buffer is allocated either in consistent (it will be automatically
- coherent between the CPU and the bus) or non-consistent memory. The
- latter can provide performance gains, for instance the CPU cache
- sync/flush operations can be avoided if the buffer is accessed by the
- corresponding device only and the CPU does not read/write to/from that
- buffer. However, this requires extra care from the driver -- it must
- guarantee memory consistency by issuing a cache flush/sync when
- consistency is needed. If this flag is set V4L2 will attempt to
- allocate the buffer in non-consistent memory. The flag takes effect
- only if the buffer is used for :ref:`memory mapping <mmap>` I/O and the
- queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS
- <V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS>` capability.
-
.. c:type:: v4l2_memory
enum v4l2_memory
diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
index f2a702870fad..12cf6b44f414 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
@@ -120,13 +120,9 @@ than the number requested.
If you want to just query the capabilities without making any
other changes, then set ``count`` to 0, ``memory`` to
``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type.
- * - __u32
- - ``flags``
- - Specifies additional buffer management attributes.
- See :ref:`memory-flags`.
* - __u32
- - ``reserved``\ [6]
+ - ``reserved``\ [7]
- A place holder for future extensions. Drivers and applications
must set the array to zero.
diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
index 75d894d9c36c..0e3e2fde65e8 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
@@ -112,17 +112,10 @@ aborting or finishing any DMA in progress, an implicit
``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will
free any previously allocated buffers, so this is typically something
that will be done at the start of the application.
- * - union {
- - (anonymous)
- * - __u32
- - ``flags``
- - Specifies additional buffer management attributes.
- See :ref:`memory-flags`.
* - __u32
- ``reserved``\ [1]
- - Kept for backwards compatibility. Use ``flags`` instead.
- * - }
- -
+ - A place holder for future extensions. Drivers and applications
+ must set the array to zero.
.. tabularcolumns:: |p{6.1cm}|p{2.2cm}|p{8.7cm}|
@@ -169,7 +162,6 @@ aborting or finishing any DMA in progress, an implicit
- This capability is set by the driver to indicate that the queue supports
cache and memory management hints. However, it's only valid when the
queue is used for :ref:`memory mapping <mmap>` streaming I/O. See
- :ref:`V4L2_FLAG_MEMORY_NON_CONSISTENT <V4L2-FLAG-MEMORY-NON-CONSISTENT>`,
:ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE <V4L2-BUF-FLAG-NO-CACHE-INVALIDATE>` and
:ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN <V4L2-BUF-FLAG-NO-CACHE-CLEAN>`.
diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index f544d3393e9d..4eab6d81cce1 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -721,39 +721,14 @@ int vb2_verify_memory_type(struct vb2_queue *q,
}
EXPORT_SYMBOL(vb2_verify_memory_type);
-static void set_queue_consistency(struct vb2_queue *q, bool consistent_mem)
-{
- q->dma_attrs &= ~DMA_ATTR_NON_CONSISTENT;
-
- if (!vb2_queue_allows_cache_hints(q))
- return;
- if (!consistent_mem)
- q->dma_attrs |= DMA_ATTR_NON_CONSISTENT;
-}
-
-static bool verify_consistency_attr(struct vb2_queue *q, bool consistent_mem)
-{
- bool queue_is_consistent = !(q->dma_attrs & DMA_ATTR_NON_CONSISTENT);
-
- if (consistent_mem != queue_is_consistent) {
- dprintk(q, 1, "memory consistency model mismatch\n");
- return false;
- }
- return true;
-}
-
int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
- unsigned int flags, unsigned int *count)
+ unsigned int *count)
{
unsigned int num_buffers, allocated_buffers, num_planes = 0;
unsigned plane_sizes[VB2_MAX_PLANES] = { };
- bool consistent_mem = true;
unsigned int i;
int ret;
- if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT)
- consistent_mem = false;
-
if (q->streaming) {
dprintk(q, 1, "streaming active\n");
return -EBUSY;
@@ -765,8 +740,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
}
if (*count == 0 || q->num_buffers != 0 ||
- (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory) ||
- !verify_consistency_attr(q, consistent_mem)) {
+ (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory)) {
/*
* We already have buffers allocated, so first check if they
* are not in use and can be freed.
@@ -803,7 +777,6 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME);
memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
q->memory = memory;
- set_queue_consistency(q, consistent_mem);
/*
* Ask the driver how many buffers and planes per buffer it requires.
@@ -888,18 +861,14 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
EXPORT_SYMBOL_GPL(vb2_core_reqbufs);
int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
- unsigned int flags, unsigned int *count,
+ unsigned int *count,
unsigned int requested_planes,
const unsigned int requested_sizes[])
{
unsigned int num_planes = 0, num_buffers, allocated_buffers;
unsigned plane_sizes[VB2_MAX_PLANES] = { };
- bool consistent_mem = true;
int ret;
- if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT)
- consistent_mem = false;
-
if (q->num_buffers == VB2_MAX_FRAME) {
dprintk(q, 1, "maximum number of buffers already allocated\n");
return -ENOBUFS;
@@ -912,15 +881,12 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
}
memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
q->memory = memory;
- set_queue_consistency(q, consistent_mem);
q->waiting_for_buffers = !q->is_output;
} else {
if (q->memory != memory) {
dprintk(q, 1, "memory model mismatch\n");
return -EINVAL;
}
- if (!verify_consistency_attr(q, consistent_mem))
- return -EINVAL;
}
num_buffers = min(*count, VB2_MAX_FRAME - q->num_buffers);
@@ -2581,7 +2547,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read)
fileio->memory = VB2_MEMORY_MMAP;
fileio->type = q->type;
q->fileio = fileio;
- ret = vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count);
+ ret = vb2_core_reqbufs(q, fileio->memory, &fileio->count);
if (ret)
goto err_kfree;
@@ -2638,7 +2604,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read)
err_reqbufs:
fileio->count = 0;
- vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count);
+ vb2_core_reqbufs(q, fileio->memory, &fileio->count);
err_kfree:
q->fileio = NULL;
@@ -2658,7 +2624,7 @@ static int __vb2_cleanup_fileio(struct vb2_queue *q)
vb2_core_streamoff(q, q->type);
q->fileio = NULL;
fileio->count = 0;
- vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count);
+ vb2_core_reqbufs(q, fileio->memory, &fileio->count);
kfree(fileio);
dprintk(q, 3, "file io emulator closed\n");
}
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index ec3446cc45b8..7b1b86ec942d 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -42,11 +42,6 @@ struct vb2_dc_buf {
struct dma_buf_attachment *db_attach;
};
-static inline bool vb2_dc_buffer_consistent(unsigned long attr)
-{
- return !(attr & DMA_ATTR_NON_CONSISTENT);
-}
-
/*********************************************/
/* scatterlist table functions */
/*********************************************/
@@ -341,13 +336,6 @@ static int
vb2_dc_dmabuf_ops_begin_cpu_access(struct dma_buf *dbuf,
enum dma_data_direction direction)
{
- struct vb2_dc_buf *buf = dbuf->priv;
- struct sg_table *sgt = buf->dma_sgt;
-
- if (vb2_dc_buffer_consistent(buf->attrs))
- return 0;
-
- dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir);
return 0;
}
@@ -355,13 +343,6 @@ static int
vb2_dc_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf,
enum dma_data_direction direction)
{
- struct vb2_dc_buf *buf = dbuf->priv;
- struct sg_table *sgt = buf->dma_sgt;
-
- if (vb2_dc_buffer_consistent(buf->attrs))
- return 0;
-
- dma_sync_sg_for_device(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir);
return 0;
}
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 0a40e00f0d7e..a86fce5d8ea8 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -123,8 +123,7 @@ static void *vb2_dma_sg_alloc(struct device *dev, unsigned long dma_attrs,
/*
* NOTE: dma-sg allocates memory using the page allocator directly, so
* there is no memory consistency guarantee, hence dma-sg ignores DMA
- * attributes passed from the upper layer. That means that
- * V4L2_FLAG_MEMORY_NON_CONSISTENT has no effect on dma-sg buffers.
+ * attributes passed from the upper layer.
*/
buf->pages = kvmalloc_array(buf->num_pages, sizeof(struct page *),
GFP_KERNEL | __GFP_ZERO);
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 30caad27281e..cfe197df970d 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -722,22 +722,12 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps)
#endif
}
-static void clear_consistency_attr(struct vb2_queue *q,
- int memory,
- unsigned int *flags)
-{
- if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP)
- *flags &= ~V4L2_FLAG_MEMORY_NON_CONSISTENT;
-}
-
int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
{
int ret = vb2_verify_memory_type(q, req->memory, req->type);
fill_buf_caps(q, &req->capabilities);
- clear_consistency_attr(q, req->memory, &req->flags);
- return ret ? ret : vb2_core_reqbufs(q, req->memory,
- req->flags, &req->count);
+ return ret ? ret : vb2_core_reqbufs(q, req->memory, &req->count);
}
EXPORT_SYMBOL_GPL(vb2_reqbufs);
@@ -769,7 +759,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
unsigned i;
fill_buf_caps(q, &create->capabilities);
- clear_consistency_attr(q, create->memory, &create->flags);
create->index = q->num_buffers;
if (create->count == 0)
return ret != -EBUSY ? ret : 0;
@@ -813,7 +802,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
if (requested_sizes[i] == 0)
return -EINVAL;
return ret ? ret : vb2_core_create_bufs(q, create->memory,
- create->flags,
&create->count,
requested_planes,
requested_sizes);
@@ -998,12 +986,11 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv,
int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type);
fill_buf_caps(vdev->queue, &p->capabilities);
- clear_consistency_attr(vdev->queue, p->memory, &p->flags);
if (res)
return res;
if (vb2_queue_is_busy(vdev, file))
return -EBUSY;
- res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count);
+ res = vb2_core_reqbufs(vdev->queue, p->memory, &p->count);
/* If count == 0, then the owner has released all buffers and he
is no longer owner of the queue. Otherwise we have a new owner. */
if (res == 0)
@@ -1021,7 +1008,6 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv,
p->index = vdev->queue->num_buffers;
fill_buf_caps(vdev->queue, &p->capabilities);
- clear_consistency_attr(vdev->queue, p->memory, &p->flags);
/*
* If count == 0, then just check if memory and type are valid.
* Any -EBUSY result from vb2_verify_memory_type can be mapped to 0.
diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c
index 959d110407a4..6974f1731529 100644
--- a/drivers/media/dvb-core/dvb_vb2.c
+++ b/drivers/media/dvb-core/dvb_vb2.c
@@ -342,7 +342,7 @@ int dvb_vb2_reqbufs(struct dvb_vb2_ctx *ctx, struct dmx_requestbuffers *req)
ctx->buf_siz = req->size;
ctx->buf_cnt = req->count;
- ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, 0, &req->count);
+ ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, &req->count);
if (ret) {
ctx->state = DVB_VB2_STATE_NONE;
dprintk(1, "[%s] count=%d size=%d errno=%d\n", ctx->name,
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 593bcf6c3735..a99e82ec9ab6 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -246,9 +246,6 @@ struct v4l2_format32 {
* @memory: buffer memory type
* @format: frame format, for which buffers are requested
* @capabilities: capabilities of this buffer type.
- * @flags: additional buffer management attributes (ignored unless the
- * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and
- * configured for MMAP streaming I/O).
* @reserved: future extensions
*/
struct v4l2_create_buffers32 {
@@ -257,8 +254,7 @@ struct v4l2_create_buffers32 {
__u32 memory; /* enum v4l2_memory */
struct v4l2_format32 format;
__u32 capabilities;
- __u32 flags;
- __u32 reserved[6];
+ __u32 reserved[7];
};
static int __bufsize_v4l2_format(struct v4l2_format32 __user *p32, u32 *size)
@@ -359,8 +355,7 @@ static int get_v4l2_create32(struct v4l2_create_buffers __user *p64,
{
if (!access_ok(p32, sizeof(*p32)) ||
copy_in_user(p64, p32,
- offsetof(struct v4l2_create_buffers32, format)) ||
- assign_in_user(&p64->flags, &p32->flags))
+ offsetof(struct v4l2_create_buffers32, format)))
return -EFAULT;
return __get_v4l2_format32(&p64->format, &p32->format,
aux_buf, aux_space);
@@ -422,7 +417,6 @@ static int put_v4l2_create32(struct v4l2_create_buffers __user *p64,
copy_in_user(p32, p64,
offsetof(struct v4l2_create_buffers32, format)) ||
assign_in_user(&p32->capabilities, &p64->capabilities) ||
- assign_in_user(&p32->flags, &p64->flags) ||
copy_in_user(p32->reserved, p64->reserved, sizeof(p64->reserved)))
return -EFAULT;
return __put_v4l2_format32(&p64->format, &p32->format);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index e3a25ea913ac..ccf947632a3b 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2044,6 +2044,9 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops,
if (ret)
return ret;
+
+ CLEAR_AFTER_FIELD(p, capabilities);
+
return ops->vidioc_reqbufs(file, fh, p);
}
@@ -2083,7 +2086,7 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops,
if (ret)
return ret;
- CLEAR_AFTER_FIELD(create, flags);
+ CLEAR_AFTER_FIELD(create, capabilities);
v4l_sanitize_format(&create->format);
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 52ef92049073..bbb3f26fbde9 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -744,8 +744,6 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb);
* vb2_core_reqbufs() - Initiate streaming.
* @q: pointer to &struct vb2_queue with videobuf2 queue.
* @memory: memory type, as defined by &enum vb2_memory.
- * @flags: auxiliary queue/buffer management flags. Currently, the only
- * used flag is %V4L2_FLAG_MEMORY_NON_CONSISTENT.
* @count: requested buffer count.
*
* Videobuf2 core helper to implement VIDIOC_REQBUF() operation. It is called
@@ -770,13 +768,12 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb);
* Return: returns zero on success; an error code otherwise.
*/
int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
- unsigned int flags, unsigned int *count);
+ unsigned int *count);
/**
* vb2_core_create_bufs() - Allocate buffers and any required auxiliary structs
* @q: pointer to &struct vb2_queue with videobuf2 queue.
* @memory: memory type, as defined by &enum vb2_memory.
- * @flags: auxiliary queue/buffer management flags.
* @count: requested buffer count.
* @requested_planes: number of planes requested.
* @requested_sizes: array with the size of the planes.
@@ -794,7 +791,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
* Return: returns zero on success; an error code otherwise.
*/
int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
- unsigned int flags, unsigned int *count,
+ unsigned int *count,
unsigned int requested_planes,
const unsigned int requested_sizes[]);
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index c7b70ff53bc1..235db7754606 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -191,8 +191,6 @@ enum v4l2_memory {
V4L2_MEMORY_DMABUF = 4,
};
-#define V4L2_FLAG_MEMORY_NON_CONSISTENT (1 << 0)
-
/* see also http://vektor.theorem.ca/graphics/ycbcr/ */
enum v4l2_colorspace {
/*
@@ -949,10 +947,7 @@ struct v4l2_requestbuffers {
__u32 type; /* enum v4l2_buf_type */
__u32 memory; /* enum v4l2_memory */
__u32 capabilities;
- union {
- __u32 flags;
- __u32 reserved[1];
- };
+ __u32 reserved[1];
};
/* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */
@@ -2456,9 +2451,6 @@ struct v4l2_dbg_chip_info {
* @memory: enum v4l2_memory; buffer memory type
* @format: frame format, for which buffers are requested
* @capabilities: capabilities of this buffer type.
- * @flags: additional buffer management attributes (ignored unless the
- * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability
- * and configured for MMAP streaming I/O).
* @reserved: future extensions
*/
struct v4l2_create_buffers {
@@ -2467,8 +2459,7 @@ struct v4l2_create_buffers {
__u32 memory;
struct v4l2_format format;
__u32 capabilities;
- __u32 flags;
- __u32 reserved[6];
+ __u32 reserved[7];
};
/*
--
GitLab
>From 4aa1615268a8ac2b20096211d3f9ac53874067d7 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@xxxxxxxxxx>
Date: Mon, 14 Sep 2020 15:20:18 -0300
Subject: [PATCH 013/126] RDMA/core: Fix ordering of CQ pool destruction
rxe will hold a refcount on the IB device as long as CQ objects exist,
this causes destruction of a rxe device to hang if the CQ pool has any
cached CQs since they are being destroyed after the refcount must go to
zero.
Treat the CQ pool like a client and create/destroy it before/after all
other clients. No users of CQ pool can exist past a client remove call.
Link: https://lore.kernel.org/r/e8a240aa-9e9b-3dca-062f-9130b787f29b@xxxxxxx
Fixes: c7ff819aefea ("RDMA/core: Introduce shared CQ pool API")
Tested-by: Bart Van Assche <bvanassche@xxxxxxx>
Tested-by: Yi Zhang <yi.zhang@xxxxxxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
---
drivers/infiniband/core/device.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index c36b4d2b61e0..23ee65a9185f 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1285,6 +1285,8 @@ static void disable_device(struct ib_device *device)
remove_client_context(device, cid);
}
+ ib_cq_pool_destroy(device);
+
/* Pairs with refcount_set in enable_device */
ib_device_put(device);
wait_for_completion(&device->unreg_completion);
@@ -1328,6 +1330,8 @@ static int enable_device_and_get(struct ib_device *device)
goto out;
}
+ ib_cq_pool_init(device);
+
down_read(&clients_rwsem);
xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) {
ret = add_client_context(device, client);
@@ -1400,7 +1404,6 @@ int ib_register_device(struct ib_device *device, const char *name)
goto dev_cleanup;
}
- ib_cq_pool_init(device);
ret = enable_device_and_get(device);
dev_set_uevent_suppress(&device->dev, false);
/* Mark for userspace that device is ready */
@@ -1455,7 +1458,6 @@ static void __ib_unregister_device(struct ib_device *ib_dev)
goto out;
disable_device(ib_dev);
- ib_cq_pool_destroy(ib_dev);
/* Expedite removing unregistered pointers from the hash table */
free_netdevs(ib_dev);
--
GitLab
>From 50851f5033a34fb9f2ecefa57fc9efd862634416 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@xxxxxxxxxx>
Date: Sat, 12 Sep 2020 15:22:11 +0800
Subject: [PATCH 014/126] spi: bcm2835: Make polling_limit_us static
This eliminates the following sparse warning:
drivers/spi/spi-bcm2835.c:78:14: warning: symbol 'polling_limit_us' was
not declared. Should it be static?
Reported-by: Hulk Robot <hulkci@xxxxxxxxxx>
Signed-off-by: Jason Yan <yanaijie@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200912072211.602735-1-yanaijie@xxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/spi/spi-bcm2835.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index c45d76c848c8..41986ac0fbfb 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -75,7 +75,7 @@
#define DRV_NAME "spi-bcm2835"
/* define polling limits */
-unsigned int polling_limit_us = 30;
+static unsigned int polling_limit_us = 30;
module_param(polling_limit_us, uint, 0664);
MODULE_PARM_DESC(polling_limit_us,
"time in us to run a transfer in polling mode\n");
--
GitLab
>From 7f04839ec4483563f38062b4dd90253e45447198 Mon Sep 17 00:00:00 2001
From: James Smart <james.smart@xxxxxxxxxxxx>
Date: Fri, 11 Sep 2020 13:01:47 -0700
Subject: [PATCH 015/126] scsi: lpfc: Fix initial FLOGI failure due to BBSCN
not supported
Initial FLOGIs are failing with the following message:
lpfc 0000:13:00.1: 1:(0):0820 FLOGI Failed (x300). BBCredit Not Supported
In a prior patch, the READ_SPARAM command was re-ordered to post after
CONFIG_LINK as the driver is expected to update the driver's copy of the
service parameters for the FLOGI payload. If the bb-credit recovery feature
is enabled, this is fine. But on adapters were bb-credit recovery isn't
enabled, it would cause the FLOGI to fail.
Fix by restoring the original command order (READ_SPARAM before
CONFIG_LINK), and after issuing CONFIG_LINK, detect bb-credit recovery
support and reissuing READ_SPARAM to obtain the updated service parameters
(effectively adding in the fix command order).
[mkp: corrected SHA]
Link: https://lore.kernel.org/r/20200911200147.110826-1-james.smart@xxxxxxxxxxxx
Fixes: 835214f5d5f5 ("scsi: lpfc: Fix broken Credit Recovery after driver load")
CC: <stable@xxxxxxxxxxxxxxx> # v5.7+
Co-developed-by: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>
Signed-off-by: Dick Kennedy <dick.kennedy@xxxxxxxxxxxx>
Signed-off-by: James Smart <james.smart@xxxxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
---
drivers/scsi/lpfc/lpfc_hbadisc.c | 76 ++++++++++++++++++++++----------
1 file changed, 52 insertions(+), 24 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 142a02114479..bf06d8549bd3 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -71,6 +71,7 @@ static void lpfc_disc_timeout_handler(struct lpfc_vport *);
static void lpfc_disc_flush_list(struct lpfc_vport *vport);
static void lpfc_unregister_fcfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
static int lpfc_fcf_inuse(struct lpfc_hba *);
+static void lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *, LPFC_MBOXQ_t *);
void
lpfc_terminate_rport_io(struct fc_rport *rport)
@@ -1138,11 +1139,13 @@ lpfc_mbx_cmpl_clear_la(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
return;
}
-
void
lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
{
struct lpfc_vport *vport = pmb->vport;
+ LPFC_MBOXQ_t *sparam_mb;
+ struct lpfc_dmabuf *sparam_mp;
+ int rc;
if (pmb->u.mb.mbxStatus)
goto out;
@@ -1167,12 +1170,42 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
}
/* Start discovery by sending a FLOGI. port_state is identically
- * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending
- * the FLOGI is being deferred till after MBX_READ_SPARAM completes.
+ * LPFC_FLOGI while waiting for FLOGI cmpl.
*/
if (vport->port_state != LPFC_FLOGI) {
- if (!(phba->hba_flag & HBA_DEFER_FLOGI))
+ /* Issue MBX_READ_SPARAM to update CSPs before FLOGI if
+ * bb-credit recovery is in place.
+ */
+ if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
+ !(phba->link_flag & LS_LOOPBACK_MODE)) {
+ sparam_mb = mempool_alloc(phba->mbox_mem_pool,
+ GFP_KERNEL);
+ if (!sparam_mb)
+ goto sparam_out;
+
+ rc = lpfc_read_sparam(phba, sparam_mb, 0);
+ if (rc) {
+ mempool_free(sparam_mb, phba->mbox_mem_pool);
+ goto sparam_out;
+ }
+ sparam_mb->vport = vport;
+ sparam_mb->mbox_cmpl = lpfc_mbx_cmpl_read_sparam;
+ rc = lpfc_sli_issue_mbox(phba, sparam_mb, MBX_NOWAIT);
+ if (rc == MBX_NOT_FINISHED) {
+ sparam_mp = (struct lpfc_dmabuf *)
+ sparam_mb->ctx_buf;
+ lpfc_mbuf_free(phba, sparam_mp->virt,
+ sparam_mp->phys);
+ kfree(sparam_mp);
+ sparam_mb->ctx_buf = NULL;
+ mempool_free(sparam_mb, phba->mbox_mem_pool);
+ goto sparam_out;
+ }
+
+ phba->hba_flag |= HBA_DEFER_FLOGI;
+ } else {
lpfc_initial_flogi(vport);
+ }
} else {
if (vport->fc_flag & FC_PT2PT)
lpfc_disc_start(vport);
@@ -1184,6 +1217,7 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
"0306 CONFIG_LINK mbxStatus error x%x "
"HBA state x%x\n",
pmb->u.mb.mbxStatus, vport->port_state);
+sparam_out:
mempool_free(pmb, phba->mbox_mem_pool);
lpfc_linkdown(phba);
@@ -3239,21 +3273,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
lpfc_linkup(phba);
sparam_mbox = NULL;
- if (!(phba->hba_flag & HBA_FCOE_MODE)) {
- cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
- if (!cfglink_mbox)
- goto out;
- vport->port_state = LPFC_LOCAL_CFG_LINK;
- lpfc_config_link(phba, cfglink_mbox);
- cfglink_mbox->vport = vport;
- cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
- rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
- if (rc == MBX_NOT_FINISHED) {
- mempool_free(cfglink_mbox, phba->mbox_mem_pool);
- goto out;
- }
- }
-
sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
if (!sparam_mbox)
goto out;
@@ -3274,7 +3293,20 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
goto out;
}
- if (phba->hba_flag & HBA_FCOE_MODE) {
+ if (!(phba->hba_flag & HBA_FCOE_MODE)) {
+ cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+ if (!cfglink_mbox)
+ goto out;
+ vport->port_state = LPFC_LOCAL_CFG_LINK;
+ lpfc_config_link(phba, cfglink_mbox);
+ cfglink_mbox->vport = vport;
+ cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+ rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
+ if (rc == MBX_NOT_FINISHED) {
+ mempool_free(cfglink_mbox, phba->mbox_mem_pool);
+ goto out;
+ }
+ } else {
vport->port_state = LPFC_VPORT_UNKNOWN;
/*
* Add the driver's default FCF record at FCF index 0 now. This
@@ -3331,10 +3363,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
}
/* Reset FCF roundrobin bmask for new discovery */
lpfc_sli4_clear_fcf_rr_bmask(phba);
- } else {
- if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
- !(phba->link_flag & LS_LOOPBACK_MODE))
- phba->hba_flag |= HBA_DEFER_FLOGI;
}
/* Prepare for LINK up registrations */
--
GitLab
>From 27ba3e8ff3ab86449e63d38a8d623053591e65fa Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@xxxxxxx>
Date: Tue, 15 Sep 2020 16:33:46 +0900
Subject: [PATCH 016/126] scsi: sd: sd_zbc: Fix handling of host-aware ZBC
disks
When CONFIG_BLK_DEV_ZONED is disabled, allow using host-aware ZBC disks as
regular disks. In this case, ensure that command completion is correctly
executed by changing sd_zbc_complete() to return good_bytes instead of 0
and causing a hang during device probe (endless retries).
When CONFIG_BLK_DEV_ZONED is enabled and a host-aware disk is detected to
have partitions, it will be used as a regular disk. In this case, make sure
to not do anything in sd_zbc_revalidate_zones() as that triggers warnings.
Since all these different cases result in subtle settings of the disk queue
zoned model, introduce the block layer helper function
blk_queue_set_zoned() to generically implement setting up the effective
zoned model according to the disk type, the presence of partitions on the
disk and CONFIG_BLK_DEV_ZONED configuration.
Link: https://lore.kernel.org/r/20200915073347.832424-2-damien.lemoal@xxxxxxx
Fixes: b72053072c0b ("block: allow partitions on host aware zone devices")
Cc: <stable@xxxxxxxxxxxxxxx>
Reported-by: Borislav Petkov <bp@xxxxxxxxx>
Suggested-by: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
---
block/blk-settings.c | 46 ++++++++++++++++++++++++++++++++++++++++++
drivers/scsi/sd.c | 30 ++++++++++++++++-----------
drivers/scsi/sd.h | 2 +-
drivers/scsi/sd_zbc.c | 6 +++++-
include/linux/blkdev.h | 2 ++
5 files changed, 72 insertions(+), 14 deletions(-)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 76a7e03bcd6c..34b721a2743a 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
+/**
+ * blk_queue_set_zoned - configure a disk queue zoned model.
+ * @disk: the gendisk of the queue to configure
+ * @model: the zoned model to set
+ *
+ * Set the zoned model of the request queue of @disk according to @model.
+ * When @model is BLK_ZONED_HM (host managed), this should be called only
+ * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
+ * If @model specifies BLK_ZONED_HA (host aware), the effective model used
+ * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
+ * on the disk.
+ */
+void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+{
+ switch (model) {
+ case BLK_ZONED_HM:
+ /*
+ * Host managed devices are supported only if
+ * CONFIG_BLK_DEV_ZONED is enabled.
+ */
+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
+ break;
+ case BLK_ZONED_HA:
+ /*
+ * Host aware devices can be treated either as regular block
+ * devices (similar to drive managed devices) or as zoned block
+ * devices to take advantage of the zone command set, similarly
+ * to host managed devices. We try the latter if there are no
+ * partitions and zoned block device support is enabled, else
+ * we do nothing special as far as the block layer is concerned.
+ */
+ if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
+ disk_has_partitions(disk))
+ model = BLK_ZONED_NONE;
+ break;
+ case BLK_ZONED_NONE:
+ default:
+ if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
+ model = BLK_ZONED_NONE;
+ break;
+ }
+
+ disk->queue->limits.zoned = model;
+}
+EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
+
static int __init blk_settings_init(void)
{
blk_max_low_pfn = max_low_pfn - 1;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 95018e650f2d..06286b6aeaec 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2964,26 +2964,32 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
if (sdkp->device->type == TYPE_ZBC) {
/* Host-managed */
- q->limits.zoned = BLK_ZONED_HM;
+ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM);
} else {
sdkp->zoned = (buffer[8] >> 4) & 3;
- if (sdkp->zoned == 1 && !disk_has_partitions(sdkp->disk)) {
+ if (sdkp->zoned == 1) {
/* Host-aware */
- q->limits.zoned = BLK_ZONED_HA;
+ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA);
} else {
- /*
- * Treat drive-managed devices and host-aware devices
- * with partitions as regular block devices.
- */
- q->limits.zoned = BLK_ZONED_NONE;
- if (sdkp->zoned == 2 && sdkp->first_scan)
- sd_printk(KERN_NOTICE, sdkp,
- "Drive-managed SMR disk\n");
+ /* Regular disk or drive managed disk */
+ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE);
}
}
- if (blk_queue_is_zoned(q) && sdkp->first_scan)
+
+ if (!sdkp->first_scan)
+ goto out;
+
+ if (blk_queue_is_zoned(q)) {
sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
+ } else {
+ if (sdkp->zoned == 1)
+ sd_printk(KERN_NOTICE, sdkp,
+ "Host-aware SMR disk used as regular disk\n");
+ else if (sdkp->zoned == 2)
+ sd_printk(KERN_NOTICE, sdkp,
+ "Drive-managed SMR disk\n");
+ }
out:
kfree(buffer);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4933e7daf17d..7251434100e6 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -259,7 +259,7 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
unsigned int good_bytes, struct scsi_sense_hdr *sshdr)
{
- return 0;
+ return good_bytes;
}
static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd,
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 0e94ff056bff..a739456dea02 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -667,7 +667,11 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
u32 max_append;
int ret = 0;
- if (!sd_is_zoned(sdkp))
+ /*
+ * There is nothing to do for regular disks, including host-aware disks
+ * that have partitions.
+ */
+ if (!blk_queue_is_zoned(q))
return 0;
/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb5636cc17b9..868e11face00 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -352,6 +352,8 @@ struct queue_limits {
typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
void *data);
+void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+
#ifdef CONFIG_BLK_DEV_ZONED
#define BLK_ALL_ZONES ((unsigned int)-1)
--
GitLab
>From 6c5dee18756b4721ac8518c69b22ee8ac0c9c442 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@xxxxxxx>
Date: Tue, 15 Sep 2020 16:33:47 +0900
Subject: [PATCH 017/126] scsi: sd: sd_zbc: Fix ZBC disk initialization
Make sure to call sd_zbc_init_disk() when the sdkp->zoned field is known,
that is, once sd_read_block_characteristics() is executed in
sd_revalidate_disk(), so that host-aware disks also get initialized. To do
so, move sd_zbc_init_disk() call in sd_zbc_revalidate_zones() and make sure
to execute it for all zoned disks, including for host-aware disks used as
regular disks as these disk zoned model may be changed back to BLK_ZONED_HA
when partitions are deleted.
Link: https://lore.kernel.org/r/20200915073347.832424-3-damien.lemoal@xxxxxxx
Fixes: 5795eb443060 ("scsi: sd_zbc: emulate ZONE_APPEND commands")
Cc: <stable@xxxxxxxxxxxxxxx> # v5.8+
Reported-by: Borislav Petkov <bp@xxxxxxxxx>
Tested-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Damien Le Moal <damien.lemoal@xxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
---
drivers/scsi/sd.c | 4 ---
drivers/scsi/sd.h | 6 -----
drivers/scsi/sd_zbc.c | 60 +++++++++++++++++++++++++------------------
3 files changed, 35 insertions(+), 35 deletions(-)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 06286b6aeaec..16503e22691e 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3410,10 +3410,6 @@ static int sd_probe(struct device *dev)
sdkp->first_scan = 1;
sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
- error = sd_zbc_init_disk(sdkp);
- if (error)
- goto out_free_index;
-
sd_revalidate_disk(gd);
gd->flags = GENHD_FL_EXT_DEVT;
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 7251434100e6..a3aad608bc38 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -215,7 +215,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
#ifdef CONFIG_BLK_DEV_ZONED
-int sd_zbc_init_disk(struct scsi_disk *sdkp);
void sd_zbc_release_disk(struct scsi_disk *sdkp);
int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
int sd_zbc_revalidate_zones(struct scsi_disk *sdkp);
@@ -231,11 +230,6 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
#else /* CONFIG_BLK_DEV_ZONED */
-static inline int sd_zbc_init_disk(struct scsi_disk *sdkp)
-{
- return 0;
-}
-
static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {}
static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a739456dea02..cf07b7f93579 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -651,6 +651,28 @@ static void sd_zbc_print_zones(struct scsi_disk *sdkp)
sdkp->zone_blocks);
}
+static int sd_zbc_init_disk(struct scsi_disk *sdkp)
+{
+ sdkp->zones_wp_offset = NULL;
+ spin_lock_init(&sdkp->zones_wp_offset_lock);
+ sdkp->rev_wp_offset = NULL;
+ mutex_init(&sdkp->rev_mutex);
+ INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
+ sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
+ if (!sdkp->zone_wp_update_buf)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void sd_zbc_release_disk(struct scsi_disk *sdkp)
+{
+ kvfree(sdkp->zones_wp_offset);
+ sdkp->zones_wp_offset = NULL;
+ kfree(sdkp->zone_wp_update_buf);
+ sdkp->zone_wp_update_buf = NULL;
+}
+
static void sd_zbc_revalidate_zones_cb(struct gendisk *disk)
{
struct scsi_disk *sdkp = scsi_disk(disk);
@@ -667,6 +689,19 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
u32 max_append;
int ret = 0;
+ /*
+ * For all zoned disks, initialize zone append emulation data if not
+ * already done. This is necessary also for host-aware disks used as
+ * regular disks due to the presence of partitions as these partitions
+ * may be deleted and the disk zoned model changed back from
+ * BLK_ZONED_NONE to BLK_ZONED_HA.
+ */
+ if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) {
+ ret = sd_zbc_init_disk(sdkp);
+ if (ret)
+ return ret;
+ }
+
/*
* There is nothing to do for regular disks, including host-aware disks
* that have partitions.
@@ -768,28 +803,3 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
return ret;
}
-
-int sd_zbc_init_disk(struct scsi_disk *sdkp)
-{
- if (!sd_is_zoned(sdkp))
- return 0;
-
- sdkp->zones_wp_offset = NULL;
- spin_lock_init(&sdkp->zones_wp_offset_lock);
- sdkp->rev_wp_offset = NULL;
- mutex_init(&sdkp->rev_mutex);
- INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
- sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
- if (!sdkp->zone_wp_update_buf)
- return -ENOMEM;
-
- return 0;
-}
-
-void sd_zbc_release_disk(struct scsi_disk *sdkp)
-{
- kvfree(sdkp->zones_wp_offset);
- sdkp->zones_wp_offset = NULL;
- kfree(sdkp->zone_wp_update_buf);
- sdkp->zone_wp_update_buf = NULL;
-}
--
GitLab
>From e5467b672bd99f0c1904900013e778e3a5ce30b7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <marek.behun@xxxxxx>
Date: Tue, 15 Sep 2020 02:54:26 +0200
Subject: [PATCH 018/126] dt-bindings: leds: cznic,turris-omnia-leds: fix error
in binding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
There is a bug in the device tree binding for cznic,turris-omnia-leds
which causes make dt_binding_check to complain.
The reason is that the multi-led property binding's regular expression
does not contain the `@` character, while the example nodes do.
Fix this, and also adjust the maximum address to 'b' as there are 12
LEDs.
Cc: Rob Herring <robh+dt@xxxxxxxxxx>
Cc: devicetree@xxxxxxxxxxxxxxx
Cc: Pavel Machek <pavel@xxxxxx>
Signed-off-by: Marek Behún <marek.behun@xxxxxx>
Link: https://lore.kernel.org/r/20200915005426.15957-1-marek.behun@xxxxxx
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
.../devicetree/bindings/leds/cznic,turris-omnia-leds.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
index 24ad1446445e..fe7fa25877fd 100644
--- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
+++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
@@ -30,7 +30,7 @@ properties:
const: 0
patternProperties:
- "^multi-led[0-9a-f]$":
+ "^multi-led@[0-9a-b]$":
type: object
allOf:
- $ref: leds-class-multicolor.yaml#
--
GitLab
>From d33030e2ee3508d65db5644551435310df86010e Mon Sep 17 00:00:00 2001
From: Jeffrey Mitchell <jeffrey.mitchell@xxxxxxxxxx>
Date: Tue, 15 Sep 2020 16:42:52 -0500
Subject: [PATCH 019/126] nfs: Fix security label length not being reset
nfs_readdir_page_filler() iterates over entries in a directory, reusing
the same security label buffer, but does not reset the buffer's length.
This causes decode_attr_security_label() to return -ERANGE if an entry's
security label is longer than the previous one's. This error, in
nfs4_decode_dirent(), only gets passed up as -EAGAIN, which causes another
failed attempt to copy into the buffer. The second error is ignored and
the remaining entries do not show up in ls, specifically the getdents64()
syscall.
Reproduce by creating multiple files in NFS and giving one of the later
files a longer security label. ls will not see that file nor any that are
added afterwards, though they will exist on the backend.
In nfs_readdir_page_filler(), reset security label buffer length before
every reuse
Signed-off-by: Jeffrey Mitchell <jeffrey.mitchell@xxxxxxxxxx>
Fixes: b4487b935452 ("nfs: Fix getxattr kernel panic and memory overflow")
Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
---
fs/nfs/dir.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e732580fe47b..cb52db9a0cfb 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -579,6 +579,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
do {
+ if (entry->label)
+ entry->label->len = NFS4_MAXLABELLEN;
+
status = xdr_decode(desc, entry, &stream);
if (status != 0) {
if (status == -EAGAIN)
--
GitLab
>From 16abd2a0c124a6c3543c88ca4c53c997c9fb4114 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@xxxxxxxxxx>
Date: Wed, 16 Sep 2020 09:07:54 -0400
Subject: [PATCH 020/126] NFSv4.2: fix client's attribute cache management for
copy_file_range
After client is done with the COPY operation, it needs to invalidate
its pagecache (as it did no reading or writing of the data locally)
and it needs to invalidate it's attributes just like it would have
for a read on the source file and write on the destination file.
Once the linux server started giving out read delegations to
read+write opens, the destination file of the copy_file range
started having delegations and not doing syncup on close of the
file leading to xfstest failures for generic/430,431,432,433,565.
v2: changing cache_validity needs to be protected by the i_lock.
Reported-by: Murphy Zhou <jencce.kernel@xxxxxxxxx>
Fixes: 2e72448b07dc ("NFS: Add COPY nfs operation")
Signed-off-by: Olga Kornievskaia <kolga@xxxxxxxxxx>
Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
---
fs/nfs/nfs42proc.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 142225f0af59..2b2211d1234e 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -356,7 +356,15 @@ static ssize_t _nfs42_proc_copy(struct file *src,
truncate_pagecache_range(dst_inode, pos_dst,
pos_dst + res->write_res.count);
-
+ spin_lock(&dst_inode->i_lock);
+ NFS_I(dst_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
+ NFS_INO_REVAL_FORCED | NFS_INO_INVALID_SIZE |
+ NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA);
+ spin_unlock(&dst_inode->i_lock);
+ spin_lock(&src_inode->i_lock);
+ NFS_I(src_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
+ NFS_INO_REVAL_FORCED | NFS_INO_INVALID_ATIME);
+ spin_unlock(&src_inode->i_lock);
status = res->write_res.count;
out:
if (args->sync)
--
GitLab
>From 8bb283e93dd98b27e2a88c623c2f6be889c82ad1 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@xxxxxxxxxx>
Date: Thu, 10 Sep 2020 13:34:03 -0400
Subject: [PATCH 021/126] RHMAINTAINERS: update for unassigned kernel areas
These areas are unassigned in the kernel
- lib/
- drivers/phy
- init/
- drivers/input
- drivers/clk
- drivers/tty
- drivers/misc
- drivers/soc
- mm/
Also fix an out-of-order entry (MMC).
v2: Remove darcari from SYSTEM ON CHIP (darcari)
v3: Helps to actually send the right version of the patch.
RH-Acked-by: David Arcari <darcari@xxxxxxxxxx>
RH-Acked-by: John W. Linville <linville@xxxxxxxxxx>
RH-Acked-by: Tony Camuso <tcamuso@xxxxxxxxxx>
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: prarit@xxxxxxxxxx
Cc: linville@xxxxxxxxxx
Cc: darcari@xxxxxxxxxx
Cc: tcamuso@xxxxxxxxxx
Cc: msalter@xxxxxxxxxx
Cc: aquini@xxxxxxxxxx
---
redhat/rhdocs/MAINTAINERS/RHMAINTAINERS | 78 +++++++++++++++++++++++--
1 file changed, 73 insertions(+), 5 deletions(-)
diff --git a/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS b/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
index ccc77ee4679d..a7bf575a4d1d 100644
--- a/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
+++ b/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
@@ -440,6 +440,13 @@ S: Maintained
F: Documentation/filesystems/ceph.txt
F: fs/ceph/
+CHAR and MISC DRIVERS
+M: John Linville <linville@xxxxxxxxxx>
+S: Maintained
+F: drivers/char/
+F: drivers/misc/
+F: include/linux/miscdevice.h
+
CIFS FILESYSTEM
L: kernel-patches@xxxxxxxxxx
S: Maintained
@@ -455,6 +462,15 @@ M: Chris Leech <cleech@xxxxxxxxxx>
S: Maintained
F: drivers/scsi/fnic/
+COMMON CLK FRAMEWORK
+M: Mark Salter <msalter@xxxxxxxxxx>
+S: Maintained
+F: Documentation/devicetree/bindings/clock/
+F: drivers/clk/
+F: include/linux/clk-pr*
+F: include/linux/clk/
+F: include/linux/of_clk.h
+
CONFIGFS
M: Bob Peterson <rpeterso@xxxxxxxxxx>
F: fs/configfs/
@@ -654,6 +670,13 @@ F: kernel/futex.c
F: tools/perf/bench/futex*
F: tools/testing/selftests/futex/
+GENERIC PHY FRAMEWORK
+M: John Linville <linville@xxxxxxxxxx>
+S: Maintained
+F: Documentation/devicetree/bindings/phy/
+F: drivers/phy
+F: include/linux/phy
+
GFS2 FILE SYSTEM
M: Bob Peterson <rpeterso@xxxxxxxxxx>
M: Andreas Gruenbacher <agruenba@xxxxxxxxxx>
@@ -682,6 +705,23 @@ F: include/linux/i2c-*.h
F: include/uapi/linux/i2c.h
F: include/uapi/linux/i2c-*.h
+INIT
+M: Prarit Bhargava <prarit@xxxxxxxxxx>
+S: Maintained
+F: init/
+
+INPUT (KEYBOARD, MOUSE, JOYSTICK, TOUCHSCREEN) DRIVERS
+M: Tony Camuso <tcamuso@xxxxxxxxxx>
+S: Maintained
+F: Documentation/devicetree/bindings/input/
+F: Documentation/devicetree/bindings/serio/
+F: Documentation/input/
+F: drivers/input/
+F: include/linux/input.h
+F: include/linux/input/
+F: include/uapi/linux/input-event-codes.h
+F: include/uapi/linux/input.h
+
INTEGRITY SUBSYSTEM
M: Bruno Meneguele <bmeneg@xxxxxxxxxx>
S: Maintained
@@ -927,12 +967,10 @@ M: Tony Camuso <tcamuso@xxxxxxxxxx>
S: Maintained
F: drivers/i2c/busses/i2c-ismt.c
-MMC LAYER
-M: Gopal Tiwari <gtiwari@xxxxxxxxxx>
+LIB
+M: Prarit Bhargava <prarit@xxxxxxxxxx>
S: Maintained
-F: Documentation/mmc/
-F: include/linux/mmc/
-F: drivers/mmc/
+F: lib/
LIVE PATCHING / KPATCH
M: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
@@ -999,6 +1037,11 @@ MEMORY MANAGEMENT
M: Rafael Aquini <aquini@xxxxxxxxxx>
S: Maintained
F: include/linux/mm.h
+F: include/linux/gfp.h
+F: include/linux/memory_hotplug.h
+F: include/linux/mm.h
+F: include/linux/mmzone.h
+F: include/linux/vmalloc.h
F: mm/
MEMORY HOTPLUG
@@ -1011,6 +1054,13 @@ S: Maintained
F: drivers/block/mtip32xx/mtip32xx.c
F: drivers/block/mtip32xx/mtip32xx.h
+MMC LAYER
+M: Gopal Tiwari <gtiwari@xxxxxxxxxx>
+S: Maintained
+F: Documentation/mmc/
+F: include/linux/mmc/
+F: drivers/mmc/
+
MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
M: Jarod Wilson <jarod@xxxxxxxxxx>
S: Maintained
@@ -1428,6 +1478,12 @@ F: Documentation/networking/switchdev.txt
F: include/net/switchdev.h
F: net/switchdev/
+SYSTEM ON CHIP
+M: Mark Salter <msalter@xxxxxxxxxx>
+S: Maintained
+F: drivers/soc/
+F: include/linux/soc
+
TC subsystem
M: Ivan Vecera <ivecera@xxxxxxxxxx>
S: Maintained
@@ -1459,6 +1515,18 @@ F: include/uapi/linux/tipc_netlink.h
F: include/uapi/linux/tipc_config.h
F: include/uapi/linux/tipc_socket_diag.h
+TTY LAYER
+M: John Linville <linville@xxxxxxxxxx>
+S: Supported
+F: drivers/tty/
+F: drivers/tty/serial/serial_core.c
+F: include/linux/serial.h
+F: include/linux/serial_core.h
+F: include/linux/tty.h
+F: include/uapi/linux/serial.h
+F: include/uapi/linux/serial_core.h
+F: include/uapi/linux/tty.h
+
X86 ARCHITECTURE
M: David Arcari <darcari@xxxxxxxxxx>
M: Prarit Bhargava <prarit@xxxxxxxxxx>
--
GitLab
>From 94cc89eb8fa5039fcb6e3e3d50f929ddcccee095 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@xxxxxxxxxxxxxxxxxxxxx>
Date: Thu, 17 Sep 2020 13:08:28 +0100
Subject: [PATCH 022/126] regmap: debugfs: Fix handling of name string for
debugfs init delays
In regmap_debugfs_init the initialisation of the debugfs is delayed
if the root node isn't ready yet. Most callers of regmap_debugfs_init
pass the name from the regmap_config, which is considered temporary
ie. may be unallocated after the regmap_init call returns. This leads
to a potential use after free, where config->name has been freed by
the time it is used in regmap_debugfs_initcall.
This situation can be seen on Zynq, where the architecture init_irq
callback registers a syscon device, using a local variable for the
regmap_config. As init_irq is very early in the platform bring up the
regmap debugfs root isn't ready yet. Although this doesn't crash it
does result in the debugfs entry not having the correct name.
Regmap already sets map->name from config->name on the regmap_init
path and the fact that a separate field is used to pass the name
to regmap_debugfs_init appears to be an artifact of the debugfs
name being added before the map name. As such this patch updates
regmap_debugfs_init to use map->name, which is already duplicated from
the config avoiding the issue.
This does however leave two lose ends, both regmap_attach_dev and
regmap_reinit_cache can be called after a regmap is registered and
would have had the effect of applying a new name to the debugfs
entries. In both of these cases it was chosen to update the map
name. In the case of regmap_attach_dev there are 3 users that
currently use this function to update the name, thus doing so avoids
changes for those users and it seems reasonable that attaching
a device would want to set the name of the map. In the case of
regmap_reinit_cache the primary use-case appears to be devices that
need some register access to identify the device (for example devices
in the same family) and then update the cache to match the exact
hardware. Whilst no users do currently update the name here, given the
use-case it seemed reasonable the name might want to be updated once
the device is better identified.
Signed-off-by: Charles Keepax <ckeepax@xxxxxxxxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200917120828.12987-1-ckeepax@xxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/base/regmap/internal.h | 4 +--
drivers/base/regmap/regmap-debugfs.c | 7 ++---
drivers/base/regmap/regmap.c | 44 +++++++++++++++++++++-------
3 files changed, 38 insertions(+), 17 deletions(-)
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 3d80c4b43f72..e0ff8e90ebdc 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -217,7 +217,7 @@ struct regmap_field {
#ifdef CONFIG_DEBUG_FS
extern void regmap_debugfs_initcall(void);
-extern void regmap_debugfs_init(struct regmap *map, const char *name);
+extern void regmap_debugfs_init(struct regmap *map);
extern void regmap_debugfs_exit(struct regmap *map);
static inline void regmap_debugfs_disable(struct regmap *map)
@@ -227,7 +227,7 @@ static inline void regmap_debugfs_disable(struct regmap *map)
#else
static inline void regmap_debugfs_initcall(void) { }
-static inline void regmap_debugfs_init(struct regmap *map, const char *name) { }
+static inline void regmap_debugfs_init(struct regmap *map) { }
static inline void regmap_debugfs_exit(struct regmap *map) { }
static inline void regmap_debugfs_disable(struct regmap *map) { }
#endif
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index f58baff2be0a..b6d63ef16b44 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -17,7 +17,6 @@
struct regmap_debugfs_node {
struct regmap *map;
- const char *name;
struct list_head link;
};
@@ -544,11 +543,12 @@ static const struct file_operations regmap_cache_bypass_fops = {
.write = regmap_cache_bypass_write_file,
};
-void regmap_debugfs_init(struct regmap *map, const char *name)
+void regmap_debugfs_init(struct regmap *map)
{
struct rb_node *next;
struct regmap_range_node *range_node;
const char *devname = "dummy";
+ const char *name = map->name;
/*
* Userspace can initiate reads from the hardware over debugfs.
@@ -569,7 +569,6 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
if (!node)
return;
node->map = map;
- node->name = name;
mutex_lock(®map_debugfs_early_lock);
list_add(&node->link, ®map_debugfs_early_list);
mutex_unlock(®map_debugfs_early_lock);
@@ -679,7 +678,7 @@ void regmap_debugfs_initcall(void)
mutex_lock(®map_debugfs_early_lock);
list_for_each_entry_safe(node, tmp, ®map_debugfs_early_list, link) {
- regmap_debugfs_init(node->map, node->name);
+ regmap_debugfs_init(node->map);
list_del(&node->link);
kfree(node);
}
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e93700af7e6e..e22c21affebd 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -581,14 +581,34 @@ static void regmap_range_exit(struct regmap *map)
kfree(map->selector_work_buf);
}
+static int regmap_set_name(struct regmap *map, const struct regmap_config *config)
+{
+ if (config->name) {
+ const char *name = kstrdup_const(config->name, GFP_KERNEL);
+
+ if (!name)
+ return -ENOMEM;
+
+ kfree_const(map->name);
+ map->name = name;
+ }
+
+ return 0;
+}
+
int regmap_attach_dev(struct device *dev, struct regmap *map,
const struct regmap_config *config)
{
struct regmap **m;
+ int ret;
map->dev = dev;
- regmap_debugfs_init(map, config->name);
+ ret = regmap_set_name(map, config);
+ if (ret)
+ return ret;
+
+ regmap_debugfs_init(map);
/* Add a devres resource for dev_get_regmap() */
m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL);
@@ -674,9 +694,9 @@ struct regmap *__regmap_init(struct device *dev,
const char *lock_name)
{
struct regmap *map;
- int ret = -EINVAL;
enum regmap_endian reg_endian, val_endian;
int i, j;
+ int ret;
if (!config)
goto err;
@@ -687,13 +707,9 @@ struct regmap *__regmap_init(struct device *dev,
goto err;
}
- if (config->name) {
- map->name = kstrdup_const(config->name, GFP_KERNEL);
- if (!map->name) {
- ret = -ENOMEM;
- goto err_map;
- }
- }
+ ret = regmap_set_name(map, config);
+ if (ret)
+ goto err_map;
if (config->disable_locking) {
map->lock = map->unlock = regmap_lock_unlock_none;
@@ -1137,7 +1153,7 @@ struct regmap *__regmap_init(struct device *dev,
if (ret != 0)
goto err_regcache;
} else {
- regmap_debugfs_init(map, config->name);
+ regmap_debugfs_init(map);
}
return map;
@@ -1297,6 +1313,8 @@ EXPORT_SYMBOL_GPL(regmap_field_free);
*/
int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
{
+ int ret;
+
regcache_exit(map);
regmap_debugfs_exit(map);
@@ -1309,7 +1327,11 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
map->readable_noinc_reg = config->readable_noinc_reg;
map->cache_type = config->cache_type;
- regmap_debugfs_init(map, config->name);
+ ret = regmap_set_name(map, config);
+ if (ret)
+ return ret;
+
+ regmap_debugfs_init(map);
map->cache_bypass = false;
map->cache_only = false;
--
GitLab
>From d36cb0205f034e943aa29e35b59c6a441f0056b5 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@xxxxxxxxxxxxxxxxxxxxx>
Date: Fri, 18 Sep 2020 12:20:02 +0100
Subject: [PATCH 023/126] regmap: debugfs: Add back in erroneously removed
initialisation of ret
Fixes: 94cc89eb8fa5 ("regmap: debugfs: Fix handling of name string for debugfs init delays")
Reported-by: kernel test robot <lkp@xxxxxxxxx>
Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Signed-off-by: Charles Keepax <ckeepax@xxxxxxxxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200918112002.15216-1-ckeepax@xxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/base/regmap/regmap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e22c21affebd..388ff8a6816c 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -694,9 +694,9 @@ struct regmap *__regmap_init(struct device *dev,
const char *lock_name)
{
struct regmap *map;
+ int ret = -EINVAL;
enum regmap_endian reg_endian, val_endian;
int i, j;
- int ret;
if (!config)
goto err;
--
GitLab
>From ee15c7b53e52fb04583f734461244c4dcca828fa Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Date: Fri, 18 Sep 2020 08:58:58 -0400
Subject: [PATCH 024/126] pNFS/flexfiles: Ensure we initialise the mirror
bsizes correctly on read
While it is true that reading from an unmirrored source always uses
index 0, that is no longer true for mirrored sources when we fail over.
Fixes: 563c53e73b8b ("NFS: Fix flexfiles read failover")
Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index ff8965d1a4d4..1edeebd51937 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -838,6 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
int ds_idx;
+ u32 i;
retry:
ff_layout_pg_check_layout(pgio, req);
@@ -863,14 +864,14 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
goto retry;
}
- mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
+ for (i = 0; i < pgio->pg_mirror_count; i++) {
+ mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
+ pgm = &pgio->pg_mirrors[i];
+ pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
+ }
pgio->pg_mirror_idx = ds_idx;
- /* read always uses only one mirror - idx 0 for pgio layer */
- pgm = &pgio->pg_mirrors[0];
- pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
-
if (NFS_SERVER(pgio->pg_inode)->flags &
(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
pgio->pg_maxretrans = io_maxretrans;
--
GitLab
>From b9df46d08a8d098ea2124cb9e3b84458a474b4d4 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Date: Fri, 18 Sep 2020 09:19:43 -0400
Subject: [PATCH 025/126] pNFS/flexfiles: Be consistent about mirror index
types
A mirror index is always of type u32.
Signed-off-by: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
---
fs/nfs/flexfilelayout/flexfilelayout.c | 34 +++++++++++++-------------
include/linux/nfs_xdr.h | 4 +--
2 files changed, 19 insertions(+), 19 deletions(-)
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 1edeebd51937..a163533446fa 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
}
static void
-ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx)
{
struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
}
static void
-ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx)
{
struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
static struct nfs4_pnfs_ds *
ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx, int *best_idx,
+ u32 start_idx, u32 *best_idx,
bool check_device)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
bool fail_return = false;
- int idx;
+ u32 idx;
/* mirrors are initially sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
@@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
static struct nfs4_pnfs_ds *
ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx, int *best_idx)
+ u32 start_idx, u32 *best_idx)
{
return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
}
static struct nfs4_pnfs_ds *
ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx, int *best_idx)
+ u32 start_idx, u32 *best_idx)
{
return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
}
static struct nfs4_pnfs_ds *
ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx, int *best_idx)
+ u32 start_idx, u32 *best_idx)
{
struct nfs4_pnfs_ds *ds;
@@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
}
static struct nfs4_pnfs_ds *
-ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx)
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
+ u32 *best_idx)
{
struct pnfs_layout_segment *lseg = pgio->pg_lseg;
struct nfs4_pnfs_ds *ds;
@@ -837,8 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_pgio_mirror *pgm;
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
- int ds_idx;
- u32 i;
+ u32 ds_idx, i;
retry:
ff_layout_pg_check_layout(pgio, req);
@@ -895,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs4_ff_layout_mirror *mirror;
struct nfs_pgio_mirror *pgm;
struct nfs4_pnfs_ds *ds;
- int i;
+ u32 i;
retry:
ff_layout_pg_check_layout(pgio, req);
@@ -1039,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
{
u32 idx = hdr->pgio_mirror_idx + 1;
- int new_idx = 0;
+ u32 new_idx = 0;
if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx))
ff_layout_send_layouterror(hdr->lseg);
@@ -1076,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
struct nfs4_state *state,
struct nfs_client *clp,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
struct pnfs_layout_hdr *lo = lseg->pls_layout;
struct inode *inode = lo->plh_inode;
@@ -1150,7 +1150,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
static int ff_layout_async_handle_error_v3(struct rpc_task *task,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -1185,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
struct nfs4_state *state,
struct nfs_client *clp,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
int vers = clp->cl_nfs_mod->rpc_vers->number;
@@ -1212,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
}
static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
- int idx, u64 offset, u64 length,
+ u32 idx, u64 offset, u64 length,
u32 *op_status, int opnum, int error)
{
struct nfs4_ff_layout_mirror *mirror;
@@ -1810,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
loff_t offset = hdr->args.offset;
int vers;
struct nfs_fh *fh;
- int idx = hdr->pgio_mirror_idx;
+ u32 idx = hdr->pgio_mirror_idx;
mirror = FF_LAYOUT_COMP(lseg, idx);
ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9408f3252c8e..69cb46f7b8d2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1611,8 +1611,8 @@ struct nfs_pgio_header {
__u64 mds_offset; /* Filelayout dense stripe */
struct nfs_page_array page_array;
struct nfs_client *ds_clp; /* pNFS data server */
- int ds_commit_idx; /* ds index if ds_clp is set */
- int pgio_mirror_idx;/* mirror index in pgio layer */
+ u32 ds_commit_idx; /* ds index if ds_clp is set */
+ u32 pgio_mirror_idx;/* mirror index in pgio layer */
};
struct nfs_mds_commit_info {
--
GitLab
>From 472eb39103e885f302fd8fd6eff104fcf5503f1b Mon Sep 17 00:00:00 2001
From: Tom Rix <trix@xxxxxxxxxx>
Date: Sun, 13 Sep 2020 09:52:30 -0700
Subject: [PATCH 026/126] ALSA: asihpi: fix iounmap in error handler
clang static analysis flags this problem
hpioctl.c:513:7: warning: Branch condition evaluates to
a garbage value
if (pci.ap_mem_base[idx]) {
^~~~~~~~~~~~~~~~~~~~
If there is a failure in the middle of the memory space loop,
only some of the memory spaces need to be cleaned up.
At the error handler, idx holds the number of successful
memory spaces mapped. So rework the handler loop to use the
old idx.
There is a second problem, the memory space loop conditionally
iomaps()/sets the mem_base so it is necessay to initize pci.
Fixes: 719f82d3987a ("ALSA: Add support of AudioScience ASI boards")
Signed-off-by: Tom Rix <trix@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200913165230.17166-1-trix@xxxxxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/pci/asihpi/hpioctl.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index 496dcde9715d..9790f5108a16 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -343,7 +343,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
struct hpi_message hm;
struct hpi_response hr;
struct hpi_adapter adapter;
- struct hpi_pci pci;
+ struct hpi_pci pci = { 0 };
memset(&adapter, 0, sizeof(adapter));
@@ -499,7 +499,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
return 0;
err:
- for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) {
+ while (--idx >= 0) {
if (pci.ap_mem_base[idx]) {
iounmap(pci.ap_mem_base[idx]);
pci.ap_mem_base[idx] = NULL;
--
GitLab
>From 3f74249057827c5f6676c41c18f6be12ce1469ce Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@xxxxxxxxxxxxx>
Date: Mon, 14 Sep 2020 14:51:18 +0800
Subject: [PATCH 027/126] ALSA: hda/realtek - Couldn't detect Mic if booting
with headset plugged
We found a Mic detection issue on many Lenovo laptops, those laptops
belong to differnt models and they have different audio design like
internal mic connects to the codec or PCH, they all have this problem,
the problem is if plugging a headset before powerup/reboot the
machine, after booting up, the headphone could be detected but Mic
couldn't. If we plug out and plug in the headset, both headphone and
Mic could be detected then.
Through debugging we found the codec on those laptops are same, it is
alc257, and if we don't disable the 3k pulldown in alc256_shutup(),
the issue will be fixed. So far there is no pop noise or power
consumption regression on those laptops after this change.
Cc: Kailang Yang <kailang@xxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Hui Wang <hui.wang@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200914065118.19238-1-hui.wang@xxxxxxxxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/pci/hda/patch_realtek.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 85e207173f5d..b6dc47da1d7b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3428,7 +3428,11 @@ static void alc256_shutup(struct hda_codec *codec)
/* 3k pull low control for Headset jack. */
/* NOTE: call this before clearing the pin, otherwise codec stalls */
- alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
+ /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly
+ * when booting with headset plugged. So skip setting it for the codec alc257
+ */
+ if (codec->core.vendor_id != 0x10ec0257)
+ alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
if (!spec->no_shutup_pins)
snd_hda_codec_write(codec, hp_pin, 0,
--
GitLab
>From f73bbf639b32acb6b409e188fdde5644b301978f Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
Date: Mon, 14 Sep 2020 15:02:29 +0800
Subject: [PATCH 028/126] ALSA: hda/realtek: Enable front panel headset LED on
Lenovo ThinkStation P520
On Lenovo P520, the front panel headset LED isn't lit up right now.
Realtek states that the LED needs to be enabled by ALC233's GPIO2, so
let's do it accordingly to light the LED up.
Signed-off-by: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
Acked-by: Hui Wang <hui.wang@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200914070231.13192-1-kai.heng.feng@xxxxxxxxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/pci/hda/patch_realtek.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b6dc47da1d7b..c4d615cf8de1 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6055,6 +6055,7 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec,
#include "hp_x360_helper.c"
enum {
+ ALC269_FIXUP_GPIO2,
ALC269_FIXUP_SONY_VAIO,
ALC275_FIXUP_SONY_VAIO_GPIO2,
ALC269_FIXUP_DELL_M101Z,
@@ -6236,6 +6237,10 @@ enum {
};
static const struct hda_fixup alc269_fixups[] = {
+ [ALC269_FIXUP_GPIO2] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_gpio2,
+ },
[ALC269_FIXUP_SONY_VAIO] = {
.type = HDA_FIXUP_PINCTLS,
.v.pins = (const struct hda_pintbl[]) {
@@ -7055,6 +7060,8 @@ static const struct hda_fixup alc269_fixups[] = {
[ALC233_FIXUP_LENOVO_MULTI_CODECS] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc233_alc662_fixup_lenovo_dual_codecs,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_GPIO2
},
[ALC233_FIXUP_ACER_HEADSET_MIC] = {
.type = HDA_FIXUP_VERBS,
--
GitLab
>From 315c7ad7a701baba28c628c4c5426b3d9617ceed Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@xxxxxxxxxxxx>
Date: Thu, 10 Sep 2020 10:53:28 +0200
Subject: [PATCH 029/126] ALSA: usb-audio: Add delay quirk for H570e USB
headsets
Needs the same delay as H650e
Signed-off-by: Joakim Tjernlund <joakim.tjernlund@xxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20200910085328.19188-1-joakim.tjernlund@xxxxxxxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/usb/quirks.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 75bbdc691243..892296df131d 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1678,12 +1678,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
&& (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
msleep(20);
- /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny
- * delay here, otherwise requests like get/set frequency return as
- * failed despite actually succeeding.
+ /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX
+ * needs a tiny delay here, otherwise requests like get/set
+ * frequency return as failed despite actually succeeding.
*/
if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
chip->usb_id == USB_ID(0x046d, 0x0a46) ||
+ chip->usb_id == USB_ID(0x046d, 0x0a56) ||
chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
(requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
--
GitLab
>From 19a508bd1ad8e444de86873bf2f2b2ab8edd6552 Mon Sep 17 00:00:00 2001
From: Charan Teja Reddy <charante@xxxxxxxxxxxxxx>
Date: Fri, 18 Sep 2020 16:02:31 +0530
Subject: [PATCH 030/126] dmabuf: fix NULL pointer dereference in
dma_buf_release()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
NULL pointer dereference is observed while exporting the dmabuf but
failed to allocate the 'struct file' which results into the dropping of
the allocated dentry corresponding to this file in the dmabuf fs, which
is ending up in dma_buf_release() and accessing the uninitialzed
dentry->d_fsdata.
Call stack on 5.4 is below:
dma_buf_release+0x2c/0x254 drivers/dma-buf/dma-buf.c:88
__dentry_kill+0x294/0x31c fs/dcache.c:584
dentry_kill fs/dcache.c:673 [inline]
dput+0x250/0x380 fs/dcache.c:859
path_put+0x24/0x40 fs/namei.c:485
alloc_file_pseudo+0x1a4/0x200 fs/file_table.c:235
dma_buf_getfile drivers/dma-buf/dma-buf.c:473 [inline]
dma_buf_export+0x25c/0x3ec drivers/dma-buf/dma-buf.c:585
Fix this by checking for the valid pointer in the dentry->d_fsdata.
Fixes: 4ab59c3c638c ("dma-buf: Move dma_buf_release() from fops to dentry_ops")
Cc: <stable@xxxxxxxxxxxxxxx> [5.7+]
Signed-off-by: Charan Teja Reddy <charante@xxxxxxxxxxxxxx>
Reviewed-by: Christian König <christian.koenig@xxxxxxx>
Link: https://patchwork.freedesktop.org/patch/391319/
Signed-off-by: Christian König <christian.koenig@xxxxxxx>
---
drivers/dma-buf/dma-buf.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 58564d82a3a2..844967f98866 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -59,6 +59,8 @@ static void dma_buf_release(struct dentry *dentry)
struct dma_buf *dmabuf;
dmabuf = dentry->d_fsdata;
+ if (unlikely(!dmabuf))
+ return;
BUG_ON(dmabuf->vmapping_counter);
--
GitLab
>From 8f8bf00b1c00b37ef5c32a642e5c3e0a364182b6 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@xxxxxxx>
Date: Mon, 21 Sep 2020 12:26:32 +0200
Subject: [PATCH 031/126] Revert "ALSA: hda - Fix silent audio output and
corrupted input on MSI X570-A PRO"
This reverts commit 15cbff3fbbc6 ("ALSA: hda - Fix silent audio output
and corrupted input on MSI X570-A PRO").
A regression reported by a Fedora user for MSI X570-A PRO mobo.
Until the correct solution is found out, let's revert the quirk as a
quick workaround.
Fixes: 15cbff3fbbc6 ("ALSA: hda - Fix silent audio output and corrupted input on MSI X570-A PRO")
Reported-by: Hans de Goede <hdegoede@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Cc: Dan Crawford <dnlcrwfrd@xxxxxxxxx>
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1879277
Link: https://lore.kernel.org/r/7efd2fe5-bf38-7f85-891a-eee3845d1493@xxxxxxxxxx
Link: https://lore.kernel.org/r/20200921102632.31139-1-tiwai@xxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/pci/hda/patch_realtek.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c4d615cf8de1..d4f17b465892 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2475,7 +2475,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
- SND_PCI_QUIRK(0x1462, 0x9c37, "MSI X570-A PRO", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
--
GitLab
>From 35be8851d172c6e3db836c0f28c19087b10c9e00 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
Date: Mon, 21 Sep 2020 16:57:14 +0900
Subject: [PATCH 032/126] btrfs: fix overflow when copying corrupt csums for a
message
Syzkaller reported a buffer overflow in btree_readpage_end_io_hook()
when loop mounting a crafted image:
detected buffer overflow in memcpy
------------[ cut here ]------------
kernel BUG at lib/string.c:1129!
invalid opcode: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 26 Comm: kworker/u4:2 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: btrfs-endio-meta btrfs_work_helper
RIP: 0010:fortify_panic+0xf/0x20 lib/string.c:1129
RSP: 0018:ffffc90000e27980 EFLAGS: 00010286
RAX: 0000000000000022 RBX: ffff8880a80dca64 RCX: 0000000000000000
RDX: ffff8880a90860c0 RSI: ffffffff815dba07 RDI: fffff520001c4f22
RBP: ffff8880a80dca00 R08: 0000000000000022 R09: ffff8880ae7318e7
R10: 0000000000000000 R11: 0000000000077578 R12: 00000000ffffff6e
R13: 0000000000000008 R14: ffffc90000e27a40 R15: 1ffff920001c4f3c
FS: 0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000557335f440d0 CR3: 000000009647d000 CR4: 00000000001506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
memcpy include/linux/string.h:405 [inline]
btree_readpage_end_io_hook.cold+0x206/0x221 fs/btrfs/disk-io.c:642
end_bio_extent_readpage+0x4de/0x10c0 fs/btrfs/extent_io.c:2854
bio_endio+0x3cf/0x7f0 block/bio.c:1449
end_workqueue_fn+0x114/0x170 fs/btrfs/disk-io.c:1695
btrfs_work_helper+0x221/0xe20 fs/btrfs/async-thread.c:318
process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
kthread+0x3b5/0x4a0 kernel/kthread.c:292
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
Modules linked in:
---[ end trace b68924293169feef ]---
RIP: 0010:fortify_panic+0xf/0x20 lib/string.c:1129
RSP: 0018:ffffc90000e27980 EFLAGS: 00010286
RAX: 0000000000000022 RBX: ffff8880a80dca64 RCX: 0000000000000000
RDX: ffff8880a90860c0 RSI: ffffffff815dba07 RDI: fffff520001c4f22
RBP: ffff8880a80dca00 R08: 0000000000000022 R09: ffff8880ae7318e7
R10: 0000000000000000 R11: 0000000000077578 R12: 00000000ffffff6e
R13: 0000000000000008 R14: ffffc90000e27a40 R15: 1ffff920001c4f3c
FS: 0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f95b7c4d008 CR3: 000000009647d000 CR4: 00000000001506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
The overflow happens, because in btree_readpage_end_io_hook() we assume
that we have found a 4 byte checksum instead of the real possible 32
bytes we have for the checksums.
With the fix applied:
[ 35.726623] BTRFS: device fsid 815caf9a-dc43-4d2a-ac54-764b8333d765 devid 1 transid 5 /dev/loop0 scanned by syz-repro (215)
[ 35.738994] BTRFS info (device loop0): disk space caching is enabled
[ 35.738998] BTRFS info (device loop0): has skinny extents
[ 35.743337] BTRFS warning (device loop0): loop0 checksum verify failed on 1052672 wanted 0xf9c035fc8d239a54 found 0x67a25c14b7eabcf9 level 0
[ 35.743420] BTRFS error (device loop0): failed to read chunk root
[ 35.745899] BTRFS error (device loop0): open_ctree failed
Reported-by: syzbot+e864a35d361e1d4e29a5@xxxxxxxxxxxxxxxxxxxxxxxxx
Fixes: d5178578bcd4 ("btrfs: directly call into crypto framework for checksumming")
CC: stable@xxxxxxxxxxxxxxx # 5.4+
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
Signed-off-by: David Sterba <dsterba@xxxxxxxx>
---
fs/btrfs/disk-io.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9fe9ec6aab71..93d3bb8989df 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -636,16 +636,15 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
csum_tree_block(eb, result);
if (memcmp_extent_buffer(eb, result, 0, csum_size)) {
- u32 val;
- u32 found = 0;
-
- memcpy(&found, result, csum_size);
+ u8 val[BTRFS_CSUM_SIZE] = { 0 };
read_extent_buffer(eb, &val, 0, csum_size);
btrfs_warn_rl(fs_info,
- "%s checksum verify failed on %llu wanted %x found %x level %d",
+ "%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d",
fs_info->sb->s_id, eb->start,
- val, found, btrfs_header_level(eb));
+ CSUM_FMT_VALUE(csum_size, val),
+ CSUM_FMT_VALUE(csum_size, result),
+ btrfs_header_level(eb));
ret = -EUCLEAN;
goto err;
}
--
GitLab
>From 3ad1c8ef083bef96ec922688966484be1039e6b5 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@xxxxxxx>
Date: Mon, 21 Sep 2020 12:31:36 +0200
Subject: [PATCH 033/126] rcu/tree: Export rcu_idle_{enter,exit} to modules
Fix this link error:
ERROR: modpost: "rcu_idle_enter" [drivers/acpi/processor.ko] undefined!
ERROR: modpost: "rcu_idle_exit" [drivers/acpi/processor.ko] undefined!
when CONFIG_ACPI_PROCESSOR is built as module. PeterZ says that in light
of ARM needing those soon too, they should simply be exported.
Fixes: 1fecfdbb7acc ("ACPI: processor: Take over RCU-idle for C3-BM idle")
Reported-by: Sven Joachim <svenjoac@xxxxxx>
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Paul E. McKenney <paulmckrcu@xxxxxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
---
kernel/rcu/tree.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8ce77d9ac716..f78ee759af9c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -673,6 +673,7 @@ void rcu_idle_enter(void)
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -886,6 +887,7 @@ void rcu_idle_exit(void)
rcu_eqs_exit(false);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
#ifdef CONFIG_NO_HZ_FULL
/**
--
GitLab
>From 36050d8984ab743f9990a2eb97a0062fdc3d7bbd Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
Date: Fri, 4 Sep 2020 08:47:05 +0200
Subject: [PATCH 034/126] cpuidle: psci: Fix suspicious RCU usage
The commit eb1f00237aca ("lockdep,trace: Expose tracepoints"), started to
expose us for tracepoints. This lead to the following RCU splat on an ARM64
Qcom board.
[ 5.529634] WARNING: suspicious RCU usage
[ 5.537307] sdhci-pltfm: SDHCI platform and OF driver helper
[ 5.541092] 5.9.0-rc3 #86 Not tainted
[ 5.541098] -----------------------------
[ 5.541105] ../include/trace/events/lock.h:37 suspicious rcu_dereference_check() usage!
[ 5.541110]
[ 5.541110] other info that might help us debug this:
[ 5.541110]
[ 5.541116]
[ 5.541116] rcu_scheduler_active = 2, debug_locks = 1
[ 5.541122] RCU used illegally from extended quiescent state!
[ 5.541129] no locks held by swapper/0/0.
[ 5.541134]
[ 5.541134] stack backtrace:
[ 5.541143] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.9.0-rc3 #86
[ 5.541149] Hardware name: Qualcomm Technologies, Inc. APQ 8016 SBC (DT)
[ 5.541157] Call trace:
[ 5.568185] sdhci_msm 7864900.sdhci: Got CD GPIO
[ 5.574186] dump_backtrace+0x0/0x1c8
[ 5.574206] show_stack+0x14/0x20
[ 5.574229] dump_stack+0xe8/0x154
[ 5.574250] lockdep_rcu_suspicious+0xd4/0xf8
[ 5.574269] lock_acquire+0x3f0/0x460
[ 5.574292] _raw_spin_lock_irqsave+0x80/0xb0
[ 5.574314] __pm_runtime_suspend+0x4c/0x188
[ 5.574341] psci_enter_domain_idle_state+0x40/0xa0
[ 5.574362] cpuidle_enter_state+0xc0/0x610
[ 5.646487] cpuidle_enter+0x38/0x50
[ 5.650651] call_cpuidle+0x18/0x40
[ 5.654467] do_idle+0x228/0x278
[ 5.657678] cpu_startup_entry+0x24/0x70
[ 5.661153] rest_init+0x1a4/0x278
[ 5.665061] arch_call_rest_init+0xc/0x14
[ 5.668272] start_kernel+0x508/0x540
Following the path in pm_runtime_put_sync_suspend() from
psci_enter_domain_idle_state(), it seems like we end up using the RCU.
Therefore, let's simply silence the splat by informing the RCU about it
with RCU_NONIDLE.
Note that, this is a temporary solution. Instead we should strive to avoid
using RCU_NONIDLE (and similar), but rather push rcu_idle_enter|exit()
further down, closer to the arch specific code. However, as the CPU PM
notifiers are also using the RCU, additional rework is needed.
Reported-by: Naresh Kamboju <naresh.kamboju@xxxxxxxxxx>
Signed-off-by: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
---
drivers/cpuidle/cpuidle-psci.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c
index 74463841805f..d928b37718bd 100644
--- a/drivers/cpuidle/cpuidle-psci.c
+++ b/drivers/cpuidle/cpuidle-psci.c
@@ -66,7 +66,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
return -1;
/* Do runtime PM to manage a hierarchical CPU toplogy. */
- pm_runtime_put_sync_suspend(pd_dev);
+ RCU_NONIDLE(pm_runtime_put_sync_suspend(pd_dev));
state = psci_get_domain_state();
if (!state)
@@ -74,7 +74,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev,
ret = psci_cpu_suspend_enter(state) ? -1 : idx;
- pm_runtime_get_sync(pd_dev);
+ RCU_NONIDLE(pm_runtime_get_sync(pd_dev));
cpu_pm_exit();
--
GitLab
>From 13a9a9d74d4d9689ad65938966dbc66386063648 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@xxxxxxxxxx>
Date: Sun, 20 Sep 2020 13:46:25 -0400
Subject: [PATCH 035/126] SUNRPC: Fix svc_flush_dcache()
On platforms that implement flush_dcache_page(), a large NFS WRITE
triggers the WARN_ONCE in bvec_iter_advance():
Sep 20 14:01:05 klimt.1015granger.net kernel: Attempted to advance past end of bvec iter
Sep 20 14:01:05 klimt.1015granger.net kernel: WARNING: CPU: 0 PID: 1032 at include/linux/bvec.h:101 bvec_iter_advance.isra.0+0xa7/0x158 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: Call Trace:
Sep 20 14:01:05 klimt.1015granger.net kernel: svc_tcp_recvfrom+0x60c/0x12c7 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? bvec_iter_advance.isra.0+0x158/0x158 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? del_timer_sync+0x4b/0x55
Sep 20 14:01:05 klimt.1015granger.net kernel: ? test_bit+0x1d/0x27 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: svc_recv+0x1193/0x15e4 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? try_to_freeze.isra.0+0x6f/0x6f [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? refcount_sub_and_test.constprop.0+0x13/0x40 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? svc_xprt_put+0x1e/0x29f [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? svc_send+0x39f/0x3c1 [sunrpc]
Sep 20 14:01:05 klimt.1015granger.net kernel: nfsd+0x282/0x345 [nfsd]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? __kthread_parkme+0x74/0xba
Sep 20 14:01:05 klimt.1015granger.net kernel: kthread+0x2ad/0x2bc
Sep 20 14:01:05 klimt.1015granger.net kernel: ? nfsd_destroy+0x124/0x124 [nfsd]
Sep 20 14:01:05 klimt.1015granger.net kernel: ? test_bit+0x1d/0x27
Sep 20 14:01:05 klimt.1015granger.net kernel: ? kthread_mod_delayed_work+0x115/0x115
Sep 20 14:01:05 klimt.1015granger.net kernel: ret_from_fork+0x22/0x30
Reported-by: He Zhe <zhe.he@xxxxxxxxxxxxx>
Fixes: ca07eda33e01 ("SUNRPC: Refactor svc_recvfrom()")
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
---
net/sunrpc/svcsock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index d5805fa1d066..c2752e2b9ce3 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -228,7 +228,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek)
{
struct bvec_iter bi = {
- .bi_size = size,
+ .bi_size = size + seek,
};
struct bio_vec bv;
--
GitLab
>From 4003324856311faebb46cbd56a1616bd3f3b67c2 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
Date: Thu, 17 Sep 2020 18:34:04 +0300
Subject: [PATCH 036/126] regmap: fix page selection for noinc reads
Non-incrementing reads can fail if register + length crosses page
border. However for non-incrementing reads we should not check for page
border crossing. Fix this by passing additional flag to _regmap_raw_read
and passing length to _regmap_select_page basing on the flag.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
Fixes: 74fe7b551f33 ("regmap: Add regmap_noinc_read API")
Link: https://lore.kernel.org/r/20200917153405.3139200-1-dmitry.baryshkov@xxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/base/regmap/regmap.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 388ff8a6816c..e2822dc21022 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -2472,7 +2472,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg,
EXPORT_SYMBOL_GPL(regmap_raw_write_async);
static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
- unsigned int val_len)
+ unsigned int val_len, bool noinc)
{
struct regmap_range_node *range;
int ret;
@@ -2485,7 +2485,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
range = _regmap_range_lookup(map, reg);
if (range) {
ret = _regmap_select_page(map, ®, range,
- val_len / map->format.val_bytes);
+ noinc ? 1 : val_len / map->format.val_bytes);
if (ret != 0)
return ret;
}
@@ -2523,7 +2523,7 @@ static int _regmap_bus_read(void *context, unsigned int reg,
if (!map->format.parse_val)
return -EINVAL;
- ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes);
+ ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false);
if (ret == 0)
*val = map->format.parse_val(work_val);
@@ -2639,7 +2639,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
/* Read bytes that fit into whole chunks */
for (i = 0; i < chunk_count; i++) {
- ret = _regmap_raw_read(map, reg, val, chunk_bytes);
+ ret = _regmap_raw_read(map, reg, val, chunk_bytes, false);
if (ret != 0)
goto out;
@@ -2650,7 +2650,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
/* Read remaining bytes */
if (val_len) {
- ret = _regmap_raw_read(map, reg, val, val_len);
+ ret = _regmap_raw_read(map, reg, val, val_len, false);
if (ret != 0)
goto out;
}
@@ -2725,7 +2725,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg,
read_len = map->max_raw_read;
else
read_len = val_len;
- ret = _regmap_raw_read(map, reg, val, read_len);
+ ret = _regmap_raw_read(map, reg, val, read_len, true);
if (ret)
goto out_unlock;
val = ((u8 *)val) + read_len;
--
GitLab
>From 05669b63170771d554854c0e465b76dc98fc7c84 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
Date: Thu, 17 Sep 2020 18:34:05 +0300
Subject: [PATCH 037/126] regmap: fix page selection for noinc writes
Non-incrementing writes can fail if register + length crosses page
border. However for non-incrementing writes we should not check for page
border crossing. Fix this by passing additional flag to _regmap_raw_write
and passing length to _regmap_select_page basing on the flag.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
Fixes: cdf6b11daa77 ("regmap: Add regmap_noinc_write API")
Link: https://lore.kernel.org/r/20200917153405.3139200-2-dmitry.baryshkov@xxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/base/regmap/internal.h | 2 +-
drivers/base/regmap/regcache.c | 2 +-
drivers/base/regmap/regmap.c | 21 +++++++++++----------
3 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index e0ff8e90ebdc..7be2fcfeea52 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -259,7 +259,7 @@ bool regcache_set_val(struct regmap *map, void *base, unsigned int idx,
int regcache_lookup_reg(struct regmap *map, unsigned int reg);
int _regmap_raw_write(struct regmap *map, unsigned int reg,
- const void *val, size_t val_len);
+ const void *val, size_t val_len, bool noinc);
void regmap_async_complete_cb(struct regmap_async *async, int ret);
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index a93cafd7be4f..7f4b3b62492c 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -717,7 +717,7 @@ static int regcache_sync_block_raw_flush(struct regmap *map, const void **data,
map->cache_bypass = true;
- ret = _regmap_raw_write(map, base, *data, count * val_bytes);
+ ret = _regmap_raw_write(map, base, *data, count * val_bytes, false);
if (ret)
dev_err(map->dev, "Unable to sync registers %#x-%#x. %d\n",
base, cur - map->reg_stride, ret);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e2822dc21022..b71f9ecddff5 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1486,7 +1486,7 @@ static void regmap_set_work_buf_flag_mask(struct regmap *map, int max_bytes,
}
static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
- const void *val, size_t val_len)
+ const void *val, size_t val_len, bool noinc)
{
struct regmap_range_node *range;
unsigned long flags;
@@ -1545,7 +1545,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
win_residue, val_len / map->format.val_bytes);
ret = _regmap_raw_write_impl(map, reg, val,
win_residue *
- map->format.val_bytes);
+ map->format.val_bytes, noinc);
if (ret != 0)
return ret;
@@ -1559,7 +1559,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
win_residue = range->window_len - win_offset;
}
- ret = _regmap_select_page(map, ®, range, val_num);
+ ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_num);
if (ret != 0)
return ret;
}
@@ -1767,7 +1767,8 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg,
map->work_buf +
map->format.reg_bytes +
map->format.pad_bytes,
- map->format.val_bytes);
+ map->format.val_bytes,
+ false);
}
static inline void *_regmap_map_get_context(struct regmap *map)
@@ -1861,7 +1862,7 @@ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val)
EXPORT_SYMBOL_GPL(regmap_write_async);
int _regmap_raw_write(struct regmap *map, unsigned int reg,
- const void *val, size_t val_len)
+ const void *val, size_t val_len, bool noinc)
{
size_t val_bytes = map->format.val_bytes;
size_t val_count = val_len / val_bytes;
@@ -1882,7 +1883,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
/* Write as many bytes as possible with chunk_size */
for (i = 0; i < chunk_count; i++) {
- ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes);
+ ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes, noinc);
if (ret)
return ret;
@@ -1893,7 +1894,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
/* Write remaining bytes */
if (val_len)
- ret = _regmap_raw_write_impl(map, reg, val, val_len);
+ ret = _regmap_raw_write_impl(map, reg, val, val_len, noinc);
return ret;
}
@@ -1926,7 +1927,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
map->lock(map->lock_arg);
- ret = _regmap_raw_write(map, reg, val, val_len);
+ ret = _regmap_raw_write(map, reg, val, val_len, false);
map->unlock(map->lock_arg);
@@ -1984,7 +1985,7 @@ int regmap_noinc_write(struct regmap *map, unsigned int reg,
write_len = map->max_raw_write;
else
write_len = val_len;
- ret = _regmap_raw_write(map, reg, val, write_len);
+ ret = _regmap_raw_write(map, reg, val, write_len, true);
if (ret)
goto out_unlock;
val = ((u8 *)val) + write_len;
@@ -2461,7 +2462,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg,
map->async = true;
- ret = _regmap_raw_write(map, reg, val, val_len);
+ ret = _regmap_raw_write(map, reg, val, val_len, false);
map->async = false;
--
GitLab
>From b867eef4cf548cd9541225aadcdcee644669b9e1 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@xxxxxxxxxxxxxxxxxxx>
Date: Fri, 4 Sep 2020 12:28:12 +1200
Subject: [PATCH 038/126] spi: fsl-espi: Only process interrupts for expected
events
The SPIE register contains counts for the TX FIFO so any time the irq
handler was invoked we would attempt to process the RX/TX fifos. Use the
SPIM value to mask the events so that we only process interrupts that
were expected.
This was a latent issue exposed by commit 3282a3da25bd ("powerpc/64:
Implement soft interrupt replay in C").
Signed-off-by: Chris Packham <chris.packham@xxxxxxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200904002812.7300-1-chris.packham@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/spi/spi-fsl-espi.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index e60581283a24..6d148ab70b93 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -564,13 +564,14 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events)
static irqreturn_t fsl_espi_irq(s32 irq, void *context_data)
{
struct fsl_espi *espi = context_data;
- u32 events;
+ u32 events, mask;
spin_lock(&espi->lock);
/* Get interrupt events(tx/rx) */
events = fsl_espi_read_reg(espi, ESPI_SPIE);
- if (!events) {
+ mask = fsl_espi_read_reg(espi, ESPI_SPIM);
+ if (!(events & mask)) {
spin_unlock(&espi->lock);
return IRQ_NONE;
}
--
GitLab
>From ee1dfad5325ff1cfb2239e564cd411b3bfe8667a Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@xxxxxxxxxx>
Date: Mon, 14 Sep 2020 13:04:19 -0400
Subject: [PATCH 039/126] dm: fix bio splitting and its bio completion order
for regular IO
dm_queue_split() is removed because __split_and_process_bio() _must_
handle splitting bios to ensure proper bio submission and completion
ordering as a bio is split.
Otherwise, multiple recursive calls to ->submit_bio will cause multiple
split bios to be allocated from the same ->bio_split mempool at the same
time. This would result in deadlock in low memory conditions because no
progress could be made (only one bio is available in ->bio_split
mempool).
This fix has been verified to still fix the loss of performance, due
to excess splitting, that commit 120c9257f5f1 provided.
Fixes: 120c9257f5f1 ("Revert "dm: always call blk_queue_split() in dm_process_bio()"")
Cc: stable@xxxxxxxxxxxxxxx # 5.0+, requires custom backport due to 5.9 changes
Reported-by: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
drivers/md/dm.c | 23 ++---------------------
1 file changed, 2 insertions(+), 21 deletions(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4a40df8af7d3..d948cd522431 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1724,23 +1724,6 @@ static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
return ret;
}
-static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struct bio **bio)
-{
- unsigned len, sector_count;
-
- sector_count = bio_sectors(*bio);
- len = min_t(sector_t, max_io_len((*bio)->bi_iter.bi_sector, ti), sector_count);
-
- if (sector_count > len) {
- struct bio *split = bio_split(*bio, len, GFP_NOIO, &md->queue->bio_split);
-
- bio_chain(split, *bio);
- trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector);
- submit_bio_noacct(*bio);
- *bio = split;
- }
-}
-
static blk_qc_t dm_process_bio(struct mapped_device *md,
struct dm_table *map, struct bio *bio)
{
@@ -1768,14 +1751,12 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
if (current->bio_list) {
if (is_abnormal_io(bio))
blk_queue_split(&bio);
- else
- dm_queue_split(md, ti, &bio);
+ /* regular IO is split by __split_and_process_bio */
}
if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
return __process_bio(md, map, bio, ti);
- else
- return __split_and_process_bio(md, map, bio);
+ return __split_and_process_bio(md, map, bio);
}
static blk_qc_t dm_submit_bio(struct bio *bio)
--
GitLab
>From cf9c37865557d39292d82da29e9ebda1dbc584b3 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 19:08:30 -0400
Subject: [PATCH 040/126] dm: fix comment in dm_process_bio()
Refer to the correct function (->submit_bio instead of ->queue_bio).
Also, add details about why using blk_queue_split() isn't needed for
dm_wq_work()'s call to dm_process_bio().
Fixes: c62b37d96b6eb ("block: move ->make_request_fn to struct block_device_operations")
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
drivers/md/dm.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index d948cd522431..6ed05ca65a0f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1744,9 +1744,11 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
}
/*
- * If in ->queue_bio we need to use blk_queue_split(), otherwise
+ * If in ->submit_bio we need to use blk_queue_split(), otherwise
* queue_limits for abnormal requests (e.g. discard, writesame, etc)
* won't be imposed.
+ * If called from dm_wq_work() for deferred bio processing, bio
+ * was already handled by following code with previous ->submit_bio.
*/
if (current->bio_list) {
if (is_abnormal_io(bio))
--
GitLab
>From ead1e19ad905b97261f0ad7a98bb64abb9323b2b Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 18:44:42 +0900
Subject: [PATCH 041/126] lib/bootconfig: Fix a bug of breaking existing tree
nodes
Fix a bug of breaking existing tree nodes by parsing the second
and subsequent braces. Since the bootconfig parser uses the
node.next field as a flag of current parent node, but this will
break the existing tree if the same key node is specified again
in the bootconfig.
For example, the following bootconfig should be foo.buz and bar.
foo
bar
foo { buz }
However, when parsing the brace "{", it breaks foo->bar link
by marking open-brace node. So the bootconfig unlinks bar
from the bootconfig internal tree.
This introduces a stack outside of the tree and record the
last open-brace on the stack instead of using node.next field.
Link: https://lkml.kernel.org/r/160068148267.1088739.8264704338030168660.stgit@devnote2
Fixes: 76db5a27a827 ("bootconfig: Add Extra Boot Config support")
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
lib/bootconfig.c | 36 +++++++++++++++++++++++-------------
1 file changed, 23 insertions(+), 13 deletions(-)
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 2c905a91d4eb..b44bba0f1583 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -31,6 +31,8 @@ static size_t xbc_data_size __initdata;
static struct xbc_node *last_parent __initdata;
static const char *xbc_err_msg __initdata;
static int xbc_err_pos __initdata;
+static int open_brace[XBC_DEPTH_MAX] __initdata;
+static int brace_index __initdata;
static int __init xbc_parse_error(const char *msg, const char *p)
{
@@ -431,27 +433,27 @@ static char *skip_spaces_until_newline(char *p)
return p;
}
-static int __init __xbc_open_brace(void)
+static int __init __xbc_open_brace(char *p)
{
- /* Mark the last key as open brace */
- last_parent->next = XBC_NODE_MAX;
+ /* Push the last key as open brace */
+ open_brace[brace_index++] = xbc_node_index(last_parent);
+ if (brace_index >= XBC_DEPTH_MAX)
+ return xbc_parse_error("Exceed max depth of braces", p);
return 0;
}
static int __init __xbc_close_brace(char *p)
{
- struct xbc_node *node;
-
- if (!last_parent || last_parent->next != XBC_NODE_MAX)
+ brace_index--;
+ if (!last_parent || brace_index < 0 ||
+ (open_brace[brace_index] != xbc_node_index(last_parent)))
return xbc_parse_error("Unexpected closing brace", p);
- node = last_parent;
- node->next = 0;
- do {
- node = xbc_node_get_parent(node);
- } while (node && node->next != XBC_NODE_MAX);
- last_parent = node;
+ if (brace_index == 0)
+ last_parent = NULL;
+ else
+ last_parent = &xbc_nodes[open_brace[brace_index - 1]];
return 0;
}
@@ -661,7 +663,7 @@ static int __init xbc_open_brace(char **k, char *n)
return ret;
*k = n;
- return __xbc_open_brace();
+ return __xbc_open_brace(n - 1);
}
static int __init xbc_close_brace(char **k, char *n)
@@ -681,6 +683,13 @@ static int __init xbc_verify_tree(void)
int i, depth, len, wlen;
struct xbc_node *n, *m;
+ /* Brace closing */
+ if (brace_index) {
+ n = &xbc_nodes[open_brace[brace_index]];
+ return xbc_parse_error("Brace is not closed",
+ xbc_node_get_data(n));
+ }
+
/* Empty tree */
if (xbc_node_num == 0) {
xbc_parse_error("Empty config", xbc_data);
@@ -745,6 +754,7 @@ void __init xbc_destroy_all(void)
xbc_node_num = 0;
memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX);
xbc_nodes = NULL;
+ brace_index = 0;
}
/**
--
GitLab
>From c7af4ecdffe1537ba8aeed0ac12c3326f908df43 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 18:44:51 +0900
Subject: [PATCH 042/126] lib/bootconfig: Fix to remove tailing spaces after
value
Fix to remove tailing spaces after value. If there is a space
after value, the bootconfig failed to remove it because it
applies strim() before replacing the delimiter with null.
For example,
foo = var # comment
was parsed as below.
foo="var "
but user will expect
foo="var"
This fixes it by applying strim() after removing the delimiter.
Link: https://lkml.kernel.org/r/160068149134.1088739.8868306567670058853.stgit@devnote2
Fixes: 76db5a27a827 ("bootconfig: Add Extra Boot Config support")
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
lib/bootconfig.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index b44bba0f1583..649ed44f199c 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -494,8 +494,8 @@ static int __init __xbc_parse_value(char **__v, char **__n)
break;
}
if (strchr(",;\n#}", c)) {
- v = strim(v);
*p++ = '\0';
+ v = strim(v);
break;
}
}
--
GitLab
>From 1d210c166b693c3a659abbac4b58385c2d4cf887 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 18:45:02 +0900
Subject: [PATCH 043/126] tools/bootconfig: Add testcases for repeated key with
brace
Add a testcase for repeated key with brace parsing issue.
Link: https://lkml.kernel.org/r/160068150176.1088739.409481347784771987.stgit@devnote2
Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
tools/bootconfig/test-bootconfig.sh | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 56284b98d8f0..95eec768b503 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -137,6 +137,18 @@ $BOOTCONF $INITRD > $TEMPCONF
cat $TEMPCONF
xpass grep \'\"string\"\' $TEMPCONF
+echo "Repeat same-key tree"
+cat > $TEMPCONF << EOF
+foo
+bar
+foo { buz }
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xpass grep -q "bar" $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
--
GitLab
>From 2f5fb555637eff4a3e5579f2323cd358c77efdc8 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 18:45:11 +0900
Subject: [PATCH 044/126] tools/bootconfig: Add testcase for tailing space
Add testcases for removing/keeping tailing space
in the value.
Link: https://lkml.kernel.org/r/160068151151.1088739.3469541807296024227.stgit@devnote2
Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
tools/bootconfig/test-bootconfig.sh | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 95eec768b503..d295e406a756 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -149,6 +149,19 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD
$BOOTCONF $INITRD > $OUTFILE
xpass grep -q "bar" $OUTFILE
+
+echo "Remove/keep tailing spaces"
+cat > $TEMPCONF << EOF
+foo = val # comment
+bar = "val2 " # comment
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xfail grep -q val[[:space:]] $OUTFILE
+xpass grep -q val2[[:space:]] $OUTFILE
+
echo "=== expected failure cases ==="
for i in samples/bad-* ; do
xfail $BOOTCONF -a $i $INITRD
--
GitLab
>From d0254f82d702a1d0d92e42f87676111de88846cf Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@xxxxxxxxxx>
Date: Sat, 12 Sep 2020 12:30:45 +0200
Subject: [PATCH 045/126] media: dt-bindings: media: imx274: Convert to
json-schema
Convert the imx274 bindings document to json-schema and update
the MAINTAINERS file accordingly.
Reviewed-by: Luca Ceresoli <luca@xxxxxxxxxxxxxxxx>
Reviewed-by: Laurent Pinchart <laurent.pinchart@xxxxxxxxxxxxxxxx>
Signed-off-by: Jacopo Mondi <jacopo+renesas@xxxxxxxxxx>
Reviewed-by: Rob Herring <robh@xxxxxxxxxx>
Signed-off-by: Sakari Ailus <sakari.ailus@xxxxxxxxxxxxxxx>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@xxxxxxxxxx>
---
.../devicetree/bindings/media/i2c/imx274.txt | 38 ----------
.../bindings/media/i2c/sony,imx274.yaml | 76 +++++++++++++++++++
MAINTAINERS | 2 +-
3 files changed, 77 insertions(+), 39 deletions(-)
delete mode 100644 Documentation/devicetree/bindings/media/i2c/imx274.txt
create mode 100644 Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
diff --git a/Documentation/devicetree/bindings/media/i2c/imx274.txt b/Documentation/devicetree/bindings/media/i2c/imx274.txt
deleted file mode 100644
index 0727079d2410..000000000000
--- a/Documentation/devicetree/bindings/media/i2c/imx274.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Sony 1/2.5-Inch 8.51Mp CMOS Digital Image Sensor
-
-The Sony imx274 is a 1/2.5-inch CMOS active pixel digital image sensor with
-an active array size of 3864H x 2202V. It is programmable through I2C
-interface. The I2C address is fixed to 0x1a as per sensor data sheet.
-Image data is sent through MIPI CSI-2, which is configured as 4 lanes
-at 1440 Mbps.
-
-
-Required Properties:
-- compatible: value should be "sony,imx274" for imx274 sensor
-- reg: I2C bus address of the device
-
-Optional Properties:
-- reset-gpios: Sensor reset GPIO
-- clocks: Reference to the input clock.
-- clock-names: Should be "inck".
-- VANA-supply: Sensor 2.8v analog supply.
-- VDIG-supply: Sensor 1.8v digital core supply.
-- VDDL-supply: Sensor digital IO 1.2v supply.
-
-The imx274 device node should contain one 'port' child node with
-an 'endpoint' subnode. For further reading on port node refer to
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Example:
- sensor@1a {
- compatible = "sony,imx274";
- reg = <0x1a>;
- #address-cells = <1>;
- #size-cells = <0>;
- reset-gpios = <&gpio_sensor 0 0>;
- port {
- sensor_out: endpoint {
- remote-endpoint = <&csiss_in>;
- };
- };
- };
diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
new file mode 100644
index 000000000000..f697e1a20beb
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/i2c/sony,imx274.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sony 1/2.5-Inch 8.51MP CMOS Digital Image Sensor
+
+maintainers:
+ - Leon Luo <leonl@xxxxxxxxxxxxxxxxxx>
+
+description: |
+ The Sony IMX274 is a 1/2.5-inch CMOS active pixel digital image sensor with an
+ active array size of 3864H x 2202V. It is programmable through I2C interface.
+ Image data is sent through MIPI CSI-2, which is configured as 4 lanes at 1440
+ Mbps.
+
+properties:
+ compatible:
+ const: sony,imx274
+
+ reg:
+ const: 0x1a
+
+ reset-gpios:
+ maxItems: 1
+
+ clocks:
+ maxItems: 1
+
+ clock-names:
+ const: inck
+
+ vana-supply:
+ description: Sensor 2.8 V analog supply.
+ maxItems: 1
+
+ vdig-supply:
+ description: Sensor 1.8 V digital core supply.
+ maxItems: 1
+
+ vddl-supply:
+ description: Sensor digital IO 1.2 V supply.
+ maxItems: 1
+
+ port:
+ type: object
+ description: Output video port. See ../video-interfaces.txt.
+
+required:
+ - compatible
+ - reg
+ - port
+
+additionalProperties: false
+
+examples:
+ - |
+ i2c0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ imx274: camera-sensor@1a {
+ compatible = "sony,imx274";
+ reg = <0x1a>;
+ reset-gpios = <&gpio_sensor 0 0>;
+
+ port {
+ sensor_out: endpoint {
+ remote-endpoint = <&csiss_in>;
+ };
+ };
+ };
+ };
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index f0068bceeb61..ba1a4d2238cc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16125,7 +16125,7 @@ M: Leon Luo <leonl@xxxxxxxxxxxxxxxxxx>
L: linux-media@xxxxxxxxxxxxxxx
S: Maintained
T: git git://linuxtv.org/media_tree.git
-F: Documentation/devicetree/bindings/media/i2c/imx274.txt
+F: Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
F: drivers/media/i2c/imx274.c
SONY IMX290 SENSOR DRIVER
--
GitLab
>From 01ce6d4d2c8157b076425e3dd8319948652583c5 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@xxxxxxxxxx>
Date: Mon, 24 Aug 2020 15:44:03 +0800
Subject: [PATCH 046/126] MIPS: Loongson-3: Fix fp register access if MSA
enabled
If MSA is enabled, FPU_REG_WIDTH is 128 rather than 64, then get_fpr64()
/set_fpr64() in the original unaligned instruction emulation code access
the wrong fp registers. This is because the current code doesn't specify
the correct index field, so fix it.
Fixes: f83e4f9896eff614d0f2547a ("MIPS: Loongson-3: Add some unaligned instructions emulation")
Signed-off-by: Huacai Chen <chenhc@xxxxxxxxxx>
Signed-off-by: Pei Huang <huangpei@xxxxxxxxxxx>
Signed-off-by: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
---
arch/mips/loongson64/cop2-ex.c | 24 ++++++++----------------
1 file changed, 8 insertions(+), 16 deletions(-)
diff --git a/arch/mips/loongson64/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c
index f130f62129b8..00055d4b6042 100644
--- a/arch/mips/loongson64/cop2-ex.c
+++ b/arch/mips/loongson64/cop2-ex.c
@@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
if (res)
goto fault;
- set_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lswc2_format.rt, value);
- set_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lswc2_format.rq, value_next);
+ set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value);
+ set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next);
compute_return_epc(regs);
own_fpu(1);
}
@@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
goto sigbus;
lose_fpu(1);
- value_next = get_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lswc2_format.rq);
+ value_next = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0);
StoreDW(addr + 8, value_next, res);
if (res)
goto fault;
- value = get_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lswc2_format.rt);
+ value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0);
StoreDW(addr, value, res);
if (res)
@@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
if (res)
goto fault;
- set_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lsdc2_format.rt, value);
+ set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
compute_return_epc(regs);
own_fpu(1);
@@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
if (res)
goto fault;
- set_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lsdc2_format.rt, value);
+ set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
compute_return_epc(regs);
own_fpu(1);
break;
@@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
goto sigbus;
lose_fpu(1);
- value = get_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lsdc2_format.rt);
+ value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
StoreW(addr, value, res);
if (res)
@@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
goto sigbus;
lose_fpu(1);
- value = get_fpr64(current->thread.fpu.fpr,
- insn.loongson3_lsdc2_format.rt);
+ value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
StoreDW(addr, value, res);
if (res)
--
GitLab
>From b5ddcffa37778244d5e786fe32f778edf2bfc93e Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@xxxxxxxxxx>
Date: Sat, 5 Sep 2020 01:34:21 +0800
Subject: [PATCH 047/126] btrfs: fix put of uninitialized kobject after seed
device delete
The following test case leads to NULL kobject free error:
mount seed /mnt
add sprout to /mnt
umount /mnt
mount sprout to /mnt
delete seed
kobject: '(null)' (00000000dd2b87e4): is not initialized, yet kobject_put() is being called.
WARNING: CPU: 1 PID: 15784 at lib/kobject.c:736 kobject_put+0x80/0x350
RIP: 0010:kobject_put+0x80/0x350
::
Call Trace:
btrfs_sysfs_remove_devices_dir+0x6e/0x160 [btrfs]
btrfs_rm_device.cold+0xa8/0x298 [btrfs]
btrfs_ioctl+0x206c/0x22a0 [btrfs]
ksys_ioctl+0xe2/0x140
__x64_sys_ioctl+0x1e/0x29
do_syscall_64+0x96/0x150
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f4047c6288b
::
This is because, at the end of the seed device-delete, we try to remove
the seed's devid sysfs entry. But for the seed devices under the sprout
fs, we don't initialize the devid kobject yet. So add a kobject state
check, which takes care of the bug.
Fixes: 668e48af7a94 ("btrfs: sysfs, add devid/dev_state kobject and device attributes")
CC: stable@xxxxxxxxxxxxxxx # 5.6+
Signed-off-by: Anand Jain <anand.jain@xxxxxxxxxx>
Reviewed-by: David Sterba <dsterba@xxxxxxxx>
Signed-off-by: David Sterba <dsterba@xxxxxxxx>
---
fs/btrfs/sysfs.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c8df2edafd85..5be30066563c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1170,10 +1170,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices,
disk_kobj->name);
}
- kobject_del(&one_device->devid_kobj);
- kobject_put(&one_device->devid_kobj);
+ if (one_device->devid_kobj.state_initialized) {
+ kobject_del(&one_device->devid_kobj);
+ kobject_put(&one_device->devid_kobj);
- wait_for_completion(&one_device->kobj_unregister);
+ wait_for_completion(&one_device->kobj_unregister);
+ }
return 0;
}
@@ -1186,10 +1188,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices,
sysfs_remove_link(fs_devices->devices_kobj,
disk_kobj->name);
}
- kobject_del(&one_device->devid_kobj);
- kobject_put(&one_device->devid_kobj);
+ if (one_device->devid_kobj.state_initialized) {
+ kobject_del(&one_device->devid_kobj);
+ kobject_put(&one_device->devid_kobj);
- wait_for_completion(&one_device->kobj_unregister);
+ wait_for_completion(&one_device->kobj_unregister);
+ }
}
return 0;
--
GitLab
>From ce65d55f92a67e247f4d799e581cf9fed677871c Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@xxxxxxx>
Date: Tue, 22 Sep 2020 14:58:45 +0300
Subject: [PATCH 048/126] dmaengine: dmatest: Prevent to run on misconfigured
channel
Andy reported that commit 6b41030fdc79 ("dmaengine: dmatest:
Restore default for channel") broke his scripts for the case
where "busy" channel is used for configuration with expectation
that run command would do nothing. Instead, behavior was
(unintentionally) changed to treat such case as under-configuration
and progress with defaults, i.e. run command would start a test
with default setting for channel (which would use all channels).
Restore original behavior with tracking status of channel setter
so we can distinguish between misconfigured and under-configured
cases in run command and act accordingly.
Fixes: 6b41030fdc79 ("dmaengine: dmatest: Restore default for channel")
Reported-by: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
Tested-by: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
Signed-off-by: Vladimir Murzin <vladimir.murzin@xxxxxxx>
Tested-by: Peter Ujfalusi <peter.ujfalusi@xxxxxx>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200922115847.30100-1-andriy.shevchenko@xxxxxxxxxxxxxxx
Signed-off-by: Vinod Koul <vkoul@xxxxxxxxxx>
---
drivers/dma/dmatest.c | 26 +++++++++++++++++++++-----
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 45d4d92e91db..a819611b8892 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -129,6 +129,7 @@ struct dmatest_params {
* @nr_channels: number of channels under test
* @lock: access protection to the fields of this structure
* @did_init: module has been initialized completely
+ * @last_error: test has faced configuration issues
*/
static struct dmatest_info {
/* Test parameters */
@@ -137,6 +138,7 @@ static struct dmatest_info {
/* Internal state */
struct list_head channels;
unsigned int nr_channels;
+ int last_error;
struct mutex lock;
bool did_init;
} test_info = {
@@ -1184,10 +1186,22 @@ static int dmatest_run_set(const char *val, const struct kernel_param *kp)
return ret;
} else if (dmatest_run) {
if (!is_threaded_test_pending(info)) {
- pr_info("No channels configured, continue with any\n");
- if (!is_threaded_test_run(info))
- stop_threaded_test(info);
- add_threaded_test(info);
+ /*
+ * We have nothing to run. This can be due to:
+ */
+ ret = info->last_error;
+ if (ret) {
+ /* 1) Misconfiguration */
+ pr_err("Channel misconfigured, can't continue\n");
+ mutex_unlock(&info->lock);
+ return ret;
+ } else {
+ /* 2) We rely on defaults */
+ pr_info("No channels configured, continue with any\n");
+ if (!is_threaded_test_run(info))
+ stop_threaded_test(info);
+ add_threaded_test(info);
+ }
}
start_threaded_tests(info);
} else {
@@ -1204,7 +1218,7 @@ static int dmatest_chan_set(const char *val, const struct kernel_param *kp)
struct dmatest_info *info = &test_info;
struct dmatest_chan *dtc;
char chan_reset_val[20];
- int ret = 0;
+ int ret;
mutex_lock(&info->lock);
ret = param_set_copystring(val, kp);
@@ -1259,12 +1273,14 @@ static int dmatest_chan_set(const char *val, const struct kernel_param *kp)
goto add_chan_err;
}
+ info->last_error = ret;
mutex_unlock(&info->lock);
return ret;
add_chan_err:
param_set_copystring(chan_reset_val, kp);
+ info->last_error = ret;
mutex_unlock(&info->lock);
return ret;
--
GitLab
>From c413c3102703a453c1312ce2160c6b7ffd55403e Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
Date: Tue, 15 Sep 2020 18:39:23 +0800
Subject: [PATCH 049/126] Revert "ALSA: usb-audio: Disable Lenovo P620 Rear
line-in volume control"
This reverts commit 34dedd2a83b241ba6aeb290260313c65dc58660e.
According to Realtek, volume FU works for line-in.
I can confirm volume control works after device firmware is updated.
Fixes: 34dedd2a83b2 ("ALSA: usb-audio: Disable Lenovo P620 Rear line-in volume control")
Signed-off-by: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200915103925.12777-1-kai.heng.feng@xxxxxxxxxxxxx
Signed-off-by: Takashi Iwai <tiwai@xxxxxxx>
---
sound/usb/mixer_maps.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 5b43e9e40e49..c369c81e74c4 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -371,7 +371,6 @@ static const struct usbmix_name_map asus_rog_map[] = {
};
static const struct usbmix_name_map lenovo_p620_rear_map[] = {
- { 19, NULL, 2 }, /* FU, Volume */
{ 19, NULL, 12 }, /* FU, Input Gain Pad */
{}
};
--
GitLab
>From 59e330f8ff7ada7aa64fa422f6adf22a45152a7e Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@xxxxxxxxxx>
Date: Thu, 17 Sep 2020 08:50:25 -0700
Subject: [PATCH 050/126] nvme: return errors for hwmon init
Initializing the nvme hwmon retrieves a log from the controller. If the
controller is broken, we need to return the appropriate error so that
subsequent initialization doesn't attempt to continue.
Reported-by: Tong Zhang <ztong0001@xxxxxxxxx>
Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/nvme/host/core.c | 7 +++++--
drivers/nvme/host/hwmon.c | 14 ++++++--------
drivers/nvme/host/nvme.h | 7 +++++--
3 files changed, 16 insertions(+), 12 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c013eb52fdc8..4cea14c18a6d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3236,8 +3236,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
if (ret < 0)
return ret;
- if (!ctrl->identified)
- nvme_hwmon_init(ctrl);
+ if (!ctrl->identified) {
+ ret = nvme_hwmon_init(ctrl);
+ if (ret < 0)
+ return ret;
+ }
ctrl->identified = true;
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index 412a6c97c0d8..552dbc04567b 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -59,12 +59,8 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
{
- int ret;
-
- ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+ return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
-
- return ret <= 0 ? ret : -EIO;
}
static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
@@ -225,7 +221,7 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = {
.info = nvme_hwmon_info,
};
-void nvme_hwmon_init(struct nvme_ctrl *ctrl)
+int nvme_hwmon_init(struct nvme_ctrl *ctrl)
{
struct device *dev = ctrl->dev;
struct nvme_hwmon_data *data;
@@ -234,7 +230,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl)
data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
if (!data)
- return;
+ return 0;
data->ctrl = ctrl;
mutex_init(&data->read_lock);
@@ -244,7 +240,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl)
dev_warn(ctrl->device,
"Failed to read smart log (error %d)\n", err);
devm_kfree(dev, data);
- return;
+ return err;
}
hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data,
@@ -254,4 +250,6 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl)
dev_warn(dev, "Failed to instantiate hwmon device\n");
devm_kfree(dev, data);
}
+
+ return 0;
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9fd45ff656da..2aaedfa43ed8 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -827,9 +827,12 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
}
#ifdef CONFIG_NVME_HWMON
-void nvme_hwmon_init(struct nvme_ctrl *ctrl);
+int nvme_hwmon_init(struct nvme_ctrl *ctrl);
#else
-static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { }
+static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl)
+{
+ return 0;
+}
#endif
u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
--
GitLab
>From 50b7c24390a53c78de546215282fb52980f1d7b7 Mon Sep 17 00:00:00 2001
From: Xianting Tian <tian.xianting@xxxxxxx>
Date: Tue, 22 Sep 2020 14:25:17 +0800
Subject: [PATCH 051/126] nvme-pci: fix NULL req in completion handler
Currently, we use nvmeq->q_depth as the upper limit for a valid tag in
nvme_handle_cqe(), it is not correct. Because the available tag number
is recorded in tagset, which is not equal to nvmeq->q_depth.
The nvme driver registers interrupts for queues before initializing the
tagset, because it uses the number of successful request_irq() calls to
configure the tagset parameters. This allows a race condition with the
current tag validity check if the controller happens to produce an
interrupt with a corrupted CQE before the tagset is initialized.
Replace the driver's indirect tag check with the one already provided by
the block layer.
Signed-off-by: Xianting Tian <tian.xianting@xxxxxxx>
Reviewed-by: Keith Busch <kbusch@xxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/nvme/host/pci.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d31e298669a9..d286c267869d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -940,13 +940,6 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
struct nvme_completion *cqe = &nvmeq->cqes[idx];
struct request *req;
- if (unlikely(cqe->command_id >= nvmeq->q_depth)) {
- dev_warn(nvmeq->dev->ctrl.device,
- "invalid id %d completed on queue %d\n",
- cqe->command_id, le16_to_cpu(cqe->sq_id));
- return;
- }
-
/*
* AEN requests are special as they don't time out and can
* survive any kind of queue freeze and often don't respond to
@@ -960,6 +953,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
}
req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
+ if (unlikely(!req)) {
+ dev_warn(nvmeq->dev->ctrl.device,
+ "invalid id %d completed on queue %d\n",
+ cqe->command_id, le16_to_cpu(cqe->sq_id));
+ return;
+ }
+
trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
if (!nvme_try_complete_req(req, cqe->status, cqe->result))
nvme_pci_complete_rq(req);
--
GitLab
>From 9e0e8dac985d4bd07d9e62922b9d189d3ca2fccf Mon Sep 17 00:00:00 2001
From: James Smart <james.smart@xxxxxxxxxxxx>
Date: Thu, 17 Sep 2020 13:33:22 -0700
Subject: [PATCH 052/126] nvme-fc: fail new connections to a deleted host or
remote port
The lldd may have made calls to delete a remote port or local port and
the delete is in progress when the cli then attempts to create a new
controller. Currently, this proceeds without error although it can't be
very successful.
Fix this by validating that both the host port and remote port are
present when a new controller is to be created.
Signed-off-by: James Smart <james.smart@xxxxxxxxxxxx>
Reviewed-by: Himanshu Madhani <himanshu.madhani@xxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/nvme/host/fc.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e8ef42b9d50c..e2e09e25c056 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3671,12 +3671,14 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts)
spin_lock_irqsave(&nvme_fc_lock, flags);
list_for_each_entry(lport, &nvme_fc_lport_list, port_list) {
if (lport->localport.node_name != laddr.nn ||
- lport->localport.port_name != laddr.pn)
+ lport->localport.port_name != laddr.pn ||
+ lport->localport.port_state != FC_OBJSTATE_ONLINE)
continue;
list_for_each_entry(rport, &lport->endp_list, endp_list) {
if (rport->remoteport.node_name != raddr.nn ||
- rport->remoteport.port_name != raddr.pn)
+ rport->remoteport.port_name != raddr.pn ||
+ rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
continue;
/* if fail to get reference fall through. Will error */
--
GitLab
>From 4a5caa4af0df5cd8f1c7f0c2f871d382662b022e Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@xxxxxxxxx>
Date: Thu, 20 Aug 2020 19:45:38 +0200
Subject: [PATCH 053/126] dm crypt: document new no_workqueue flags
Commit 39d42fa96ba1 ("dm crypt: add flags to optionally bypass kcryptd
workqueues") introduced new dm-crypt 'no_read_workqueue' and
'no_write_workqueue' flags.
Add documentation to admin guide for them.
Fixes: 39d42fa96ba1 ("dm crypt: add flags to optionally bypass kcryptd workqueues")
Signed-off-by: Milan Broz <gmazyland@xxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
Documentation/admin-guide/device-mapper/dm-crypt.rst | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst
index 8f4a3f889d43..40dc2df58cd5 100644
--- a/Documentation/admin-guide/device-mapper/dm-crypt.rst
+++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst
@@ -121,6 +121,14 @@ submit_from_crypt_cpus
thread because it benefits CFQ to have writes submitted using the
same context.
+no_read_workqueue
+ Bypass dm-crypt internal workqueue and process read requests synchronously.
+
+no_write_workqueue
+ Bypass dm-crypt internal workqueue and process write requests synchronously.
+ This option is automatically enabled for host-managed zoned block devices
+ (e.g. host-managed SMR hard-disks).
+
integrity:<bytes>:<type>
The device requires additional <bytes> metadata per-sector stored
in per-bio integrity structure. This metadata must by provided
--
GitLab
>From 4c07ae0ad493b7b2d3dd3e53870e594f136ce8a5 Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@xxxxxxxxx>
Date: Thu, 20 Aug 2020 21:20:26 +0200
Subject: [PATCH 054/126] dm crypt: document encrypted keyring key option
Commit 27f5411a718c4 ("dm crypt: support using encrypted keys")
introduced support for encrypted keyring type.
Fix documentation in admin guide to mention this type.
Fixes: 27f5411a718c4 ("dm crypt: support using encrypted keys")
Signed-off-by: Milan Broz <gmazyland@xxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
---
Documentation/admin-guide/device-mapper/dm-crypt.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst
index 40dc2df58cd5..bc28a9527ee5 100644
--- a/Documentation/admin-guide/device-mapper/dm-crypt.rst
+++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst
@@ -67,7 +67,7 @@ Parameters::
the value passed in <key_size>.
<key_type>
- Either 'logon' or 'user' kernel key type.
+ Either 'logon', 'user' or 'encrypted' kernel key type.
<key_description>
The kernel keyring key description crypt target should look for
--
GitLab
>From bd805274577457f301bf826f86543f550cf5c1ef Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
Date: Tue, 22 Sep 2020 11:15:50 +0200
Subject: [PATCH 055/126] cpuidle: Drop misleading comments about RCU usage
The commit 1098582a0f6c ("sched,idle,rcu: Push rcu_idle deeper into the
idle path"), moved the calls rcu_idle_enter|exit() into the cpuidle core.
However, it forgot to remove a couple of comments in enter_s2idle_proper()
about why RCU_NONIDLE earlier was needed. So, let's drop them as they have
become a bit misleading.
Fixes: 1098582a0f6c ("sched,idle,rcu: Push rcu_idle deeper into the idle path")
Signed-off-by: Ulf Hansson <ulf.hansson@xxxxxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
---
drivers/cpuidle/cpuidle.c | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 6c7e5621cf9a..29e84687f3c3 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -142,11 +142,6 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
time_start = ns_to_ktime(local_clock());
- /*
- * trace_suspend_resume() called by tick_freeze() for the last CPU
- * executing it contains RCU usage regarded as invalid in the idle
- * context, so tell RCU about that.
- */
tick_freeze();
/*
* The state used here cannot be a "coupled" one, because the "coupled"
@@ -159,11 +154,6 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv,
target_state->enter_s2idle(dev, drv, index);
if (WARN_ON_ONCE(!irqs_disabled()))
local_irq_disable();
- /*
- * timekeeping_resume() that will be called by tick_unfreeze() for the
- * first CPU executing it calls functions containing RCU read-side
- * critical sections, so tell RCU about that.
- */
if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE))
rcu_idle_exit();
tick_unfreeze();
--
GitLab
>From a7b3474cbb2864d5500d5e4f48dd57c903975cab Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Date: Tue, 22 Sep 2020 09:58:52 +0200
Subject: [PATCH 056/126] x86/irq: Make run_on_irqstack_cond() typesafe
Sami reported that run_on_irqstack_cond() requires the caller to cast
functions to mismatching types, which trips indirect call Control-Flow
Integrity (CFI) in Clang.
Instead of disabling CFI on that function, provide proper helpers for
the three call variants. The actual ASM code stays the same as that is
out of reach.
[ bp: Fix __run_on_irqstack() prototype to match. ]
Fixes: 931b94145981 ("x86/entry: Provide helpers for executing on the irqstack")
Reported-by: Nathan Chancellor <natechancellor@xxxxxxxxx>
Reported-by: Sami Tolvanen <samitolvanen@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Tested-by: Sami Tolvanen <samitolvanen@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://github.com/ClangBuiltLinux/linux/issues/1052
Link: https://lkml.kernel.org/r/87pn6eb5tv.fsf@xxxxxxxxxxxxxxxxxxxxxxx
---
arch/x86/entry/common.c | 2 +-
arch/x86/entry/entry_64.S | 2 +
arch/x86/include/asm/idtentry.h | 2 +-
arch/x86/include/asm/irq_stack.h | 69 ++++++++++++++++++++++++++++----
arch/x86/kernel/irq.c | 2 +-
arch/x86/kernel/irq_64.c | 2 +-
6 files changed, 67 insertions(+), 12 deletions(-)
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 2f84c7ca74ea..870efeec8bda 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -299,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
old_regs = set_irq_regs(regs);
instrumentation_begin();
- run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs);
+ run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
instrumentation_begin();
set_irq_regs(old_regs);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 70dea9337816..d977079a7d02 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs)
* rdx: Function argument (can be NULL if none)
*/
SYM_FUNC_START(asm_call_on_stack)
+SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL)
+SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL)
/*
* Save the frame pointer unconditionally. This allows the ORC
* unwinder to handle the stack switch.
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index a43366191212..a0638640f1ed 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs) \
instrumentation_begin(); \
irq_enter_rcu(); \
kvm_set_cpu_l1tf_flush_l1d(); \
- run_on_irqstack_cond(__##func, regs, regs); \
+ run_sysvec_on_irqstack_cond(__##func, regs); \
irq_exit_rcu(); \
instrumentation_end(); \
irqentry_exit(regs, state); \
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 4ae66f097101..775816965c6a 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void)
return __this_cpu_read(irq_count) != -1;
}
-void asm_call_on_stack(void *sp, void *func, void *arg);
+void asm_call_on_stack(void *sp, void (*func)(void), void *arg);
+void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs),
+ struct pt_regs *regs);
+void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc),
+ struct irq_desc *desc);
-static __always_inline void __run_on_irqstack(void *func, void *arg)
+static __always_inline void __run_on_irqstack(void (*func)(void))
{
void *tos = __this_cpu_read(hardirq_stack_ptr);
__this_cpu_add(irq_count, 1);
- asm_call_on_stack(tos - 8, func, arg);
+ asm_call_on_stack(tos - 8, func, NULL);
+ __this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+ struct pt_regs *regs)
+{
+ void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+ __this_cpu_add(irq_count, 1);
+ asm_call_sysvec_on_stack(tos - 8, func, regs);
+ __this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+ struct irq_desc *desc)
+{
+ void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+ __this_cpu_add(irq_count, 1);
+ asm_call_irq_on_stack(tos - 8, func, desc);
__this_cpu_sub(irq_count, 1);
}
#else /* CONFIG_X86_64 */
static inline bool irqstack_active(void) { return false; }
-static inline void __run_on_irqstack(void *func, void *arg) { }
+static inline void __run_on_irqstack(void (*func)(void)) { }
+static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+ struct pt_regs *regs) { }
+static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+ struct irq_desc *desc) { }
#endif /* !CONFIG_X86_64 */
static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
@@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
return !user_mode(regs) && !irqstack_active();
}
-static __always_inline void run_on_irqstack_cond(void *func, void *arg,
+
+static __always_inline void run_on_irqstack_cond(void (*func)(void),
struct pt_regs *regs)
{
- void (*__func)(void *arg) = func;
+ lockdep_assert_irqs_disabled();
+
+ if (irq_needs_irq_stack(regs))
+ __run_on_irqstack(func);
+ else
+ func();
+}
+
+static __always_inline void
+run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs),
+ struct pt_regs *regs)
+{
+ lockdep_assert_irqs_disabled();
+ if (irq_needs_irq_stack(regs))
+ __run_sysvec_on_irqstack(func, regs);
+ else
+ func(regs);
+}
+
+static __always_inline void
+run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc,
+ struct pt_regs *regs)
+{
lockdep_assert_irqs_disabled();
if (irq_needs_irq_stack(regs))
- __run_on_irqstack(__func, arg);
+ __run_irq_on_irqstack(func, desc);
else
- __func(arg);
+ func(desc);
}
#endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 181060247e3c..c5dd50369e2f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -227,7 +227,7 @@ static __always_inline void handle_irq(struct irq_desc *desc,
struct pt_regs *regs)
{
if (IS_ENABLED(CONFIG_X86_64))
- run_on_irqstack_cond(desc->handle_irq, desc, regs);
+ run_irq_on_irqstack_cond(desc->handle_irq, desc, regs);
else
__handle_irq(desc, regs);
}
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1b4fe93a86c5..440eed558558 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu)
void do_softirq_own_stack(void)
{
- run_on_irqstack_cond(__do_softirq, NULL, NULL);
+ run_on_irqstack_cond(__do_softirq, NULL);
}
--
GitLab
>From 0c309ed17c50e7eeaf3c66102b475198064e80da Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@xxxxxxxxxxx>
Date: Tue, 8 Sep 2020 19:57:07 +0900
Subject: [PATCH 057/126] PM / devfreq: Add timer type to devfreq_summary
debugfs
The commit 4dc3bab8687f ("PM / devfreq: Add support delayed timer for
polling mode") supports the delayed timer but this commit missed
the adding the timer type to devfreq_summary debugfs node.
Add the timer type to devfreq_summary debugfs.
Fixes: 4dc3bab8687f ("PM / devfreq: Add support delayed timer for polling mode")
Signed-off-by: Chanwoo Choi <cw00.choi@xxxxxxxxxxx>
---
drivers/devfreq/devfreq.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 561d91b2d3bf..071b59fe84d2 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1766,20 +1766,23 @@ static int devfreq_summary_show(struct seq_file *s, void *data)
struct devfreq *p_devfreq = NULL;
unsigned long cur_freq, min_freq, max_freq;
unsigned int polling_ms;
+ unsigned int timer;
- seq_printf(s, "%-30s %-30s %-15s %10s %12s %12s %12s\n",
+ seq_printf(s, "%-30s %-30s %-15s %-10s %10s %12s %12s %12s\n",
"dev",
"parent_dev",
"governor",
+ "timer",
"polling_ms",
"cur_freq_Hz",
"min_freq_Hz",
"max_freq_Hz");
- seq_printf(s, "%30s %30s %15s %10s %12s %12s %12s\n",
+ seq_printf(s, "%30s %30s %15s %10s %10s %12s %12s %12s\n",
"------------------------------",
"------------------------------",
"---------------",
"----------",
+ "----------",
"------------",
"------------",
"------------");
@@ -1803,13 +1806,15 @@ static int devfreq_summary_show(struct seq_file *s, void *data)
cur_freq = devfreq->previous_freq;
get_freq_range(devfreq, &min_freq, &max_freq);
polling_ms = devfreq->profile->polling_ms;
+ timer = devfreq->profile->timer;
mutex_unlock(&devfreq->lock);
seq_printf(s,
- "%-30s %-30s %-15s %10d %12ld %12ld %12ld\n",
+ "%-30s %-30s %-15s %-10s %10d %12ld %12ld %12ld\n",
dev_name(&devfreq->dev),
p_devfreq ? dev_name(&p_devfreq->dev) : "null",
devfreq->governor_name,
+ polling_ms ? timer_name[timer] : "null",
polling_ms,
cur_freq,
min_freq,
--
GitLab
>From 6bf560766a8ef5afe4faa3244220cf5b3a934549 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Date: Tue, 8 Sep 2020 10:25:57 +0300
Subject: [PATCH 058/126] PM / devfreq: tegra30: Disable clock on error in
probe
This error path needs to call clk_disable_unprepare().
Fixes: 7296443b900e ("PM / devfreq: tegra30: Handle possible round-rate error")
Signed-off-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Reviewed-by: Dmitry Osipenko <digetx@xxxxxxxxx>
Signed-off-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Signed-off-by: Chanwoo Choi <cw00.choi@xxxxxxxxxxx>
---
drivers/devfreq/tegra30-devfreq.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c
index e94a27804c20..dedd39de7367 100644
--- a/drivers/devfreq/tegra30-devfreq.c
+++ b/drivers/devfreq/tegra30-devfreq.c
@@ -836,7 +836,8 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
rate = clk_round_rate(tegra->emc_clock, ULONG_MAX);
if (rate < 0) {
dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate);
- return rate;
+ err = rate;
+ goto disable_clk;
}
tegra->max_freq = rate / KHZ;
@@ -897,6 +898,7 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
dev_pm_opp_remove_all_dynamic(&pdev->dev);
reset_control_reset(tegra->reset);
+disable_clk:
clk_disable_unprepare(tegra->clock);
return err;
--
GitLab
>From 16cce04cdb200ba905d1241b425ac48da5a9ace5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Date: Wed, 16 Sep 2020 11:50:22 +0100
Subject: [PATCH 059/126] drm/i915/selftests: Push the fake iommu device from
the stack to data
Since we store a pointer to the fake iommu device that is allocated on
the stack, as soon as we leave the function it goes out of scope and any
future dereference is undefined behaviour. Just in case we may need to
look at the fake iommu device after initialiation, move the allocation
from the stack into the data.
Fixes: 01b9d4e21148 ("iommu/vt-d: Use dev_iommu_priv_get/set()")
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Matthew Auld <matthew.auld@xxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20200916105022.28316-2-chris@xxxxxxxxxxxxxxxxxx
(cherry picked from commit 9f9f4101fc98db56714e71676d5a1e2d27e01f7e)
Signed-off-by: Jani Nikula <jani.nikula@xxxxxxxxx>
---
drivers/gpu/drm/i915/selftests/mock_gem_device.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index f127e633f7ca..397c313a8b69 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = {
struct drm_i915_private *mock_gem_device(void)
{
- struct drm_i915_private *i915;
- struct pci_dev *pdev;
#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
- struct dev_iommu iommu;
+ static struct dev_iommu fake_iommu = { .priv = (void *)-1 };
#endif
+ struct drm_i915_private *i915;
+ struct pci_dev *pdev;
int err;
pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
@@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void)
dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
- /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */
- memset(&iommu, 0, sizeof(iommu));
- iommu.priv = (void *)-1;
- pdev->dev.iommu = &iommu;
+ /* HACK to disable iommu for the fake device; force identity mapping */
+ pdev->dev.iommu = &fake_iommu;
#endif
pci_set_drvdata(pdev, i915);
--
GitLab
>From 955921289dcdbc49b46a731ec07978fb7d4e1fc7 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@xxxxxxxxx>
Date: Wed, 23 Sep 2020 13:50:12 +0200
Subject: [PATCH 060/126] ACPI: processor: Fix build for
ARCH_APICTIMER_STOPS_ON_C3 unset
Fix the lapic_timer_needs_broadcast() stub for
ARCH_APICTIMER_STOPS_ON_C3 unset to actually return
a value.
Fixes: aa6b43d57f99 ("ACPI: processor: Use CPUIDLE_FLAG_TIMER_STOP")
Reported-by: Guenter Roeck <linux@xxxxxxxxxxxx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
---
drivers/acpi/processor_idle.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 7ecb90e90afd..f66236cff69b 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -176,6 +176,7 @@ static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { }
static bool lapic_timer_needs_broadcast(struct acpi_processor *pr,
struct acpi_processor_cx *cx)
{
+ return false;
}
#endif
--
GitLab
>From b13812ddea615b6507beef24f76540c0c1143c5c Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx>
Date: Wed, 23 Sep 2020 18:33:12 +0800
Subject: [PATCH 061/126] MIPS: Loongson2ef: Disable Loongson MMI instructions
It was missed when I was forking Loongson2ef from Loongson64 but
should be applied to Loongson2ef as march=loongson2f
will also enable Loongson MMI in GCC-9+.
Signed-off-by: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx>
Fixes: 71e2f4dd5a65 ("MIPS: Fork loongson2ef from loongson64")
Reported-by: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # v5.8+
Signed-off-by: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
---
arch/mips/loongson2ef/Platform | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform
index 4ab55f1123a0..ae023b9a1c51 100644
--- a/arch/mips/loongson2ef/Platform
+++ b/arch/mips/loongson2ef/Platform
@@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
endif
endif
+# Some -march= flags enable MMI instructions, and GCC complains about that
+# support being enabled alongside -msoft-float. Thus explicitly disable MMI.
+cflags-y += $(call cc-option,-mno-loongson-mmi)
+
#
# Loongson Machines' Support
#
--
GitLab
>From e393fbe6fa27af23f78df6e16a8fd2963578a8c4 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@xxxxxxxxxx>
Date: Wed, 23 Sep 2020 14:53:12 +0800
Subject: [PATCH 062/126] MIPS: Add the missing 'CPU_1074K' into
__get_cpu_type()
Commit 442e14a2c55e ("MIPS: Add 1074K CPU support explicitly.") split
1074K from the 74K as an unique CPU type, while it missed to add the
'CPU_1074K' in __get_cpu_type(). So let's add it back.
Fixes: 442e14a2c55e ("MIPS: Add 1074K CPU support explicitly.")
Signed-off-by: Wei Li <liwei391@xxxxxxxxxx>
Signed-off-by: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
---
arch/mips/include/asm/cpu-type.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index 75a7a382da09..3288cef4b168 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type)
case CPU_34K:
case CPU_1004K:
case CPU_74K:
+ case CPU_1074K:
case CPU_M14KC:
case CPU_M14KEC:
case CPU_INTERAPTIV:
--
GitLab
>From be090fa62080d8501a5651a73cb954721966b125 Mon Sep 17 00:00:00 2001
From: Wei Li <liwei391@xxxxxxxxxx>
Date: Wed, 23 Sep 2020 14:53:26 +0800
Subject: [PATCH 063/126] MIPS: BCM47XX: Remove the needless check with the
1074K
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
As there is no known soc powered by mips 1074K in bcm47xx series,
the check with 1074K is needless. So just remove it.
Link: https://wireless.wiki.kernel.org/en/users/Drivers/b43/soc
Fixes: 442e14a2c55e ("MIPS: Add 1074K CPU support explicitly.")
Signed-off-by: Wei Li <liwei391@xxxxxxxxxx>
Acked-by: Rafał Miłecki <rafal@xxxxxxxxxx>
Signed-off-by: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
---
arch/mips/bcm47xx/setup.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 82627c264964..01427bde2397 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -148,7 +148,7 @@ void __init plat_mem_setup(void)
{
struct cpuinfo_mips *c = ¤t_cpu_data;
- if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) {
+ if (c->cputype == CPU_74K) {
pr_info("Using bcma bus\n");
#ifdef CONFIG_BCM47XX_BCMA
bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA;
--
GitLab
>From b96e6506c2ea7c8e3ef0860169b6d0ba2f1aca9f Mon Sep 17 00:00:00 2001
From: Mohammed Gamal <mgamal@xxxxxxxxxx>
Date: Thu, 3 Sep 2020 16:11:22 +0200
Subject: [PATCH 064/126] KVM: x86: VMX: Make smaller physical guest address
space support user-configurable
This patch exposes allow_smaller_maxphyaddr to the user as a module parameter.
Since smaller physical address spaces are only supported on VMX, the
parameter is only exposed in the kvm_intel module.
For now disable support by default, and let the user decide if they want
to enable it.
Modifications to VMX page fault and EPT violation handling will depend
on whether that parameter is enabled.
Signed-off-by: Mohammed Gamal <mgamal@xxxxxxxxxx>
Message-Id: <20200903141122.72908-1-mgamal@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/vmx/vmx.c | 15 ++++++++++-----
arch/x86/kvm/vmx/vmx.h | 5 ++++-
arch/x86/kvm/x86.c | 2 +-
3 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 75cd720c9e8c..f0384e93548a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1;
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
#endif
+extern bool __read_mostly allow_smaller_maxphyaddr;
+module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
+
#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
#define KVM_VM_CR0_ALWAYS_ON \
@@ -4803,6 +4806,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
* EPT will cause page fault only if we need to
* detect illegal GPAs.
*/
+ WARN_ON_ONCE(!allow_smaller_maxphyaddr);
kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code);
return 1;
} else
@@ -5331,7 +5335,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
* would also use advanced VM-exit information for EPT violations to
* reconstruct the page fault error code.
*/
- if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+ if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa)))
return kvm_emulate_instruction(vcpu, 0);
return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -8305,11 +8309,12 @@ static int __init vmx_init(void)
vmx_check_vmcs12_offsets();
/*
- * Intel processors don't have problems with
- * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable
- * it for VMX by default
+ * Shadow paging doesn't have a (further) performance penalty
+ * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
+ * by default
*/
- allow_smaller_maxphyaddr = true;
+ if (!enable_ept)
+ allow_smaller_maxphyaddr = true;
return 0;
}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a2f82127c170..a0e47720f60c 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
{
- return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+ if (!enable_ept)
+ return true;
+
+ return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
}
void dump_vmcs(void);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e3de0fe5af37..67362607e396 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs;
u64 __read_mostly host_efer;
EXPORT_SYMBOL_GPL(host_efer);
-bool __read_mostly allow_smaller_maxphyaddr;
+bool __read_mostly allow_smaller_maxphyaddr = 0;
EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
static u64 __read_mostly host_xss;
--
GitLab
>From 18391e5e9cf59226354a864e5befa3c764eb8903 Mon Sep 17 00:00:00 2001
From: Yang Weijiang <weijiang.yang@xxxxxxxxx>
Date: Wed, 26 Aug 2020 09:55:24 +0800
Subject: [PATCH 065/126] selftests: kvm: Fix assert failure in single-step
test
This is a follow-up patch to fix an issue left in commit:
98b0bf02738004829d7e26d6cb47b2e469aaba86
selftests: kvm: Use a shorter encoding to clear RAX
With the change in the commit, we also need to modify "xor" instruction
length from 3 to 2 in array ss_size accordingly to pass below check:
for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) {
target_rip += ss_size[i];
CLEAR_DEBUG();
debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
debug.arch.debugreg[7] = 0x00000400;
APPLY_DEBUG();
vcpu_run(vm, VCPU_ID);
TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG &&
run->debug.arch.exception == DB_VECTOR &&
run->debug.arch.pc == target_rip &&
run->debug.arch.dr6 == target_dr6,
"SINGLE_STEP[%d]: exit %d exception %d rip 0x%llx "
"(should be 0x%llx) dr6 0x%llx (should be 0x%llx)",
i, run->exit_reason, run->debug.arch.exception,
run->debug.arch.pc, target_rip, run->debug.arch.dr6,
target_dr6);
}
Reported-by: kernel test robot <rong.a.chen@xxxxxxxxx>
Signed-off-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
Message-Id: <20200826015524.13251-1-weijiang.yang@xxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
tools/testing/selftests/kvm/x86_64/debug_regs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index b8d14f9db5f9..2fc6b3af81a1 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -73,7 +73,7 @@ int main(void)
int i;
/* Instruction lengths starting at ss_start */
int ss_size[4] = {
- 3, /* xor */
+ 2, /* xor */
2, /* cpuid */
5, /* mov */
2, /* rdmsr */
--
GitLab
>From fbb5a79d2fe7b01c6424fbbc04368373b1672d61 Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <icenowy@xxxxxxx>
Date: Wed, 23 Sep 2020 08:51:42 +0800
Subject: [PATCH 066/126] regulator: axp20x: fix LDO2/4 description
Currently we wrongly set the mask of value of LDO2/4 both to the mask of
LDO2, and the LDO4 voltage configuration is left untouched. This leads
to conflict when LDO2/4 are both in use.
Fix this issue by setting different vsel_mask to both regulators.
Fixes: db4a555f7c4c ("regulator: axp20x: use defines for masks")
Signed-off-by: Icenowy Zheng <icenowy@xxxxxxx>
Link: https://lore.kernel.org/r/20200923005142.147135-1-icenowy@xxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/regulator/axp20x-regulator.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index fbc95cadaf53..126649c172e1 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -42,8 +42,9 @@
#define AXP20X_DCDC2_V_OUT_MASK GENMASK(5, 0)
#define AXP20X_DCDC3_V_OUT_MASK GENMASK(7, 0)
-#define AXP20X_LDO24_V_OUT_MASK GENMASK(7, 4)
+#define AXP20X_LDO2_V_OUT_MASK GENMASK(7, 4)
#define AXP20X_LDO3_V_OUT_MASK GENMASK(6, 0)
+#define AXP20X_LDO4_V_OUT_MASK GENMASK(3, 0)
#define AXP20X_LDO5_V_OUT_MASK GENMASK(7, 4)
#define AXP20X_PWR_OUT_EXTEN_MASK BIT_MASK(0)
@@ -542,14 +543,14 @@ static const struct regulator_desc axp20x_regulators[] = {
AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_DCDC3_MASK),
AXP_DESC_FIXED(AXP20X, LDO1, "ldo1", "acin", 1300),
AXP_DESC(AXP20X, LDO2, "ldo2", "ldo24in", 1800, 3300, 100,
- AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK,
+ AXP20X_LDO24_V_OUT, AXP20X_LDO2_V_OUT_MASK,
AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO2_MASK),
AXP_DESC(AXP20X, LDO3, "ldo3", "ldo3in", 700, 3500, 25,
AXP20X_LDO3_V_OUT, AXP20X_LDO3_V_OUT_MASK,
AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO3_MASK),
AXP_DESC_RANGES(AXP20X, LDO4, "ldo4", "ldo24in",
axp20x_ldo4_ranges, AXP20X_LDO4_V_OUT_NUM_VOLTAGES,
- AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK,
+ AXP20X_LDO24_V_OUT, AXP20X_LDO4_V_OUT_MASK,
AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO4_MASK),
AXP_DESC_IO(AXP20X, LDO5, "ldo5", "ldo5in", 1800, 3300, 100,
AXP20X_LDO5_V_OUT, AXP20X_LDO5_V_OUT_MASK,
--
GitLab
>From 530b5affc675ade5db4a03f04ed7cd66806c8a1a Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>
Date: Wed, 23 Sep 2020 15:10:26 +0200
Subject: [PATCH 067/126] spi: fsl-dspi: fix use-after-free in remove path
spi_unregister_controller() not only unregisters the controller, but
also frees the controller. This will free the driver data with it, so
we must not access it later dspi_remove().
Solve this by allocating the driver data separately from the SPI
controller.
Signed-off-by: Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200923131026.20707-1-s.hauer@xxxxxxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/spi/spi-fsl-dspi.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 283f2468a2f4..127323a4b27c 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1273,11 +1273,14 @@ static int dspi_probe(struct platform_device *pdev)
void __iomem *base;
bool big_endian;
- ctlr = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi));
+ dspi = devm_kzalloc(&pdev->dev, sizeof(*dspi), GFP_KERNEL);
+ if (!dspi)
+ return -ENOMEM;
+
+ ctlr = spi_alloc_master(&pdev->dev, 0);
if (!ctlr)
return -ENOMEM;
- dspi = spi_controller_get_devdata(ctlr);
dspi->pdev = pdev;
dspi->ctlr = ctlr;
@@ -1414,7 +1417,7 @@ static int dspi_probe(struct platform_device *pdev)
if (dspi->devtype_data->trans_mode != DSPI_DMA_MODE)
ctlr->ptp_sts_supported = true;
- platform_set_drvdata(pdev, ctlr);
+ platform_set_drvdata(pdev, dspi);
ret = spi_register_controller(ctlr);
if (ret != 0) {
@@ -1437,8 +1440,7 @@ static int dspi_probe(struct platform_device *pdev)
static int dspi_remove(struct platform_device *pdev)
{
- struct spi_controller *ctlr = platform_get_drvdata(pdev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = platform_get_drvdata(pdev);
/* Disconnect from the SPI framework */
spi_unregister_controller(dspi->ctlr);
--
GitLab
>From df3a57d1f6072d07978bafa7dbd9904cdf8f3e13 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Wed, 23 Sep 2020 09:56:59 -0700
Subject: [PATCH 068/126] mm: split out the non-present case from
copy_one_pte()
This is a purely mechanical split of the copy_one_pte() function. It's
not immediately obvious when looking at the diff because of the
indentation change, but the way to see what is going on in this commit
is to use the "-w" flag to not show pure whitespace changes, and you see
how the first part of copy_one_pte() is simply lifted out into a
separate function.
And since the non-present case is marked unlikely, don't make the new
function be inlined. Not that gcc really seems to care, since it looks
like it will inline it anyway due to the whole "single callsite for
static function" logic. In fact, code generation with the function
split is almost identical to before. But not marking it inline is the
right thing to do.
This is pure prep-work and cleanup for subsequent changes.
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 146 ++++++++++++++++++++++++++++------------------------
1 file changed, 79 insertions(+), 67 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 469af373ae76..31a3ab7d9aa3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -695,85 +695,98 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
* covered by this vma.
*/
-static inline unsigned long
-copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+static unsigned long
+copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr, int *rss)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(pte);
+
+ if (likely(!non_swap_entry(entry))) {
+ if (swap_duplicate(entry) < 0)
+ return entry.val;
+
+ /* make sure dst_mm is on swapoff's mmlist. */
+ if (unlikely(list_empty(&dst_mm->mmlist))) {
+ spin_lock(&mmlist_lock);
+ if (list_empty(&dst_mm->mmlist))
+ list_add(&dst_mm->mmlist,
+ &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ rss[MM_SWAPENTS]++;
+ } else if (is_migration_entry(entry)) {
+ page = migration_entry_to_page(entry);
- /* pte contains position in swap or file, so copy. */
- if (unlikely(!pte_present(pte))) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
- if (likely(!non_swap_entry(entry))) {
- if (swap_duplicate(entry) < 0)
- return entry.val;
-
- /* make sure dst_mm is on swapoff's mmlist. */
- if (unlikely(list_empty(&dst_mm->mmlist))) {
- spin_lock(&mmlist_lock);
- if (list_empty(&dst_mm->mmlist))
- list_add(&dst_mm->mmlist,
- &src_mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- rss[MM_SWAPENTS]++;
- } else if (is_migration_entry(entry)) {
- page = migration_entry_to_page(entry);
-
- rss[mm_counter(page)]++;
-
- if (is_write_migration_entry(entry) &&
- is_cow_mapping(vm_flags)) {
- /*
- * COW mappings require pages in both
- * parent and child to be set to read.
- */
- make_migration_entry_read(&entry);
- pte = swp_entry_to_pte(entry);
- if (pte_swp_soft_dirty(*src_pte))
- pte = pte_swp_mksoft_dirty(pte);
- if (pte_swp_uffd_wp(*src_pte))
- pte = pte_swp_mkuffd_wp(pte);
- set_pte_at(src_mm, addr, src_pte, pte);
- }
- } else if (is_device_private_entry(entry)) {
- page = device_private_entry_to_page(entry);
+ rss[mm_counter(page)]++;
+ if (is_write_migration_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
/*
- * Update rss count even for unaddressable pages, as
- * they should treated just like normal pages in this
- * respect.
- *
- * We will likely want to have some new rss counters
- * for unaddressable pages, at some point. But for now
- * keep things as they are.
+ * COW mappings require pages in both
+ * parent and child to be set to read.
*/
- get_page(page);
- rss[mm_counter(page)]++;
- page_dup_rmap(page, false);
+ make_migration_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(*src_pte))
+ pte = pte_swp_mksoft_dirty(pte);
+ if (pte_swp_uffd_wp(*src_pte))
+ pte = pte_swp_mkuffd_wp(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
+ }
+ } else if (is_device_private_entry(entry)) {
+ page = device_private_entry_to_page(entry);
- /*
- * We do not preserve soft-dirty information, because so
- * far, checkpoint/restore is the only feature that
- * requires that. And checkpoint/restore does not work
- * when a device driver is involved (you cannot easily
- * save and restore device driver state).
- */
- if (is_write_device_private_entry(entry) &&
- is_cow_mapping(vm_flags)) {
- make_device_private_entry_read(&entry);
- pte = swp_entry_to_pte(entry);
- if (pte_swp_uffd_wp(*src_pte))
- pte = pte_swp_mkuffd_wp(pte);
- set_pte_at(src_mm, addr, src_pte, pte);
- }
+ /*
+ * Update rss count even for unaddressable pages, as
+ * they should treated just like normal pages in this
+ * respect.
+ *
+ * We will likely want to have some new rss counters
+ * for unaddressable pages, at some point. But for now
+ * keep things as they are.
+ */
+ get_page(page);
+ rss[mm_counter(page)]++;
+ page_dup_rmap(page, false);
+
+ /*
+ * We do not preserve soft-dirty information, because so
+ * far, checkpoint/restore is the only feature that
+ * requires that. And checkpoint/restore does not work
+ * when a device driver is involved (you cannot easily
+ * save and restore device driver state).
+ */
+ if (is_write_device_private_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
+ make_device_private_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_uffd_wp(*src_pte))
+ pte = pte_swp_mkuffd_wp(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
}
- goto out_set_pte;
}
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return 0;
+}
+
+static inline unsigned long
+copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
+ unsigned long addr, int *rss)
+{
+ unsigned long vm_flags = vma->vm_flags;
+ pte_t pte = *src_pte;
+ struct page *page;
+
+ /* pte contains position in swap or file, so copy. */
+ if (unlikely(!pte_present(pte)))
+ return copy_nonpresent_pte(dst_mm, src_mm,
+ dst_pte, src_pte, vma,
+ addr, rss);
/*
* If it's a COW mapping, write protect it both
@@ -807,7 +820,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
rss[mm_counter(page)]++;
}
-out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
--
GitLab
>From 79a1971c5f14ea3a6e2b0c4caf73a1760db7cab8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Wed, 23 Sep 2020 10:04:16 -0700
Subject: [PATCH 069/126] mm: move the copy_one_pte() pte_present check into
the caller
This completes the split of the non-present and present pte cases by
moving the check for the source pte being present into the single
caller, which also means that we clearly separate out the very different
return value case for a non-present pte.
The present pte case currently always succeeds.
This is a pure code re-organization with no semantic change: the intent
is to make it much easier to add a new return case to the present pte
case for when we do early COW at page table copy time.
This was split out from the previous commit simply to make it easy to
visually see that there were no semantic changes from this code
re-organization.
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 31a3ab7d9aa3..e315b1f1ef08 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -773,8 +773,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
return 0;
}
-static inline unsigned long
-copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+static inline void
+copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr, int *rss)
{
@@ -782,12 +782,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t pte = *src_pte;
struct page *page;
- /* pte contains position in swap or file, so copy. */
- if (unlikely(!pte_present(pte)))
- return copy_nonpresent_pte(dst_mm, src_mm,
- dst_pte, src_pte, vma,
- addr, rss);
-
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
@@ -821,7 +815,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
}
set_pte_at(dst_mm, addr, dst_pte, pte);
- return 0;
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -863,10 +856,17 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
progress++;
continue;
}
- entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
+ if (unlikely(!pte_present(*src_pte))) {
+ entry.val = copy_nonpresent_pte(dst_mm, src_mm,
+ dst_pte, src_pte,
vma, addr, rss);
- if (entry.val)
- break;
+ if (entry.val)
+ break;
+ progress += 8;
+ continue;
+ }
+ copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
+ vma, addr, rss);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
--
GitLab
>From 46d2613eae51d527ecaf0e8248a9bfcc0b92aa7e Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@xxxxxxx>
Date: Tue, 22 Sep 2020 12:49:38 -0700
Subject: [PATCH 070/126] nvme-core: don't use NVME_NSID_ALL for command
effects and supported log
In the function nvme_get_effects_log() it uses NVME_NSID_ALL which has
namespace scope. The command effect log page is controller specific.
Replace NVME_NSID_ALL with 0x00 which specifies the controller scope
instead of namespace scope.
Fixes: 84fef62d135b ("nvme: check admin passthru command effects")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=209287
Reported-by: Huai-Cheng Kuo <hh81478072@xxxxxxxxx>
Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@xxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
drivers/nvme/host/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4cea14c18a6d..53c93836c7c6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3041,7 +3041,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
if (!cel)
return -ENOMEM;
- ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi,
+ ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi,
&cel->log, sizeof(cel->log), 0);
if (ret) {
kfree(cel);
--
GitLab
>From 86a82ae0b5095ea24c55898a3f025791e7958b21 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Date: Wed, 23 Sep 2020 17:46:20 +0200
Subject: [PATCH 071/126] x86/ioapic: Unbreak check_timer()
Several people reported in the kernel bugzilla that between v4.12 and v4.13
the magic which works around broken hardware and BIOSes to find the proper
timer interrupt delivery mode stopped working for some older affected
platforms which need to fall back to ExtINT delivery mode.
The reason is that the core code changed to keep track of the masked and
disabled state of an interrupt line more accurately to avoid the expensive
hardware operations.
That broke an assumption in i8259_make_irq() which invokes
disable_irq_nosync();
irq_set_chip_and_handler();
enable_irq();
Up to v4.12 this worked because enable_irq() unconditionally unmasked the
interrupt line, but after the state tracking improvements this is not
longer the case because the IO/APIC uses lazy disabling. So the line state
is unmasked which means that enable_irq() does not call into the new irq
chip to unmask it.
In principle this is a shortcoming of the core code, but it's more than
unclear whether the core code should try to reset state. At least this
cannot be done unconditionally as that would break other existing use cases
where the chip type is changed, e.g. when changing the trigger type, but
the callers expect the state to be preserved.
As the way how check_timer() is switching the delivery modes is truly
unique, the obvious fix is to simply unmask the i8259 manually after
changing the mode to ExtINT delivery and switching the irq chip to the
legacy PIC.
Note, that the fixes tag is not really precise, but identifies the commit
which broke the assumptions in the IO/APIC and i8259 code and that's the
kernel version to which this needs to be backported.
Fixes: bf22ff45bed6 ("genirq: Avoid unnecessary low level irq function calls")
Reported-by: p_c_chan@xxxxxxxxxxx
Reported-by: ecm4@xxxxxxxx
Reported-by: perdigao1@xxxxxxxxx
Reported-by: matzes@xxxxxxxxxxxxxxxxxxxxx
Reported-by: rvelascog@xxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Tested-by: p_c_chan@xxxxxxxxxxx
Tested-by: matzes@xxxxxxxxxxxxxxxxxxxxx
Cc: stable@xxxxxxxxxxxxxxx
Link: https://bugzilla.kernel.org/show_bug.cgi?id=197769
---
arch/x86/kernel/apic/io_apic.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 779a89e31c4c..21f9c7f11779 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2243,6 +2243,7 @@ static inline void __init check_timer(void)
legacy_pic->init(0);
legacy_pic->make_irq(0);
apic_write(APIC_LVT0, APIC_DM_EXTINT);
+ legacy_pic->unmask(0);
unlock_ExtINT_logic();
--
GitLab
>From 8bedc98f668110019c7c8aa13fe2faa189d5f8b8 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Thu, 24 Sep 2020 04:28:20 +0000
Subject: [PATCH 072/126] [redhat]
kernel-5.9.0-0.rc6.20200924gitc9c9e6a49f89.14.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 16 ++++++++++++++++
redhat/marker | 2 +-
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index e4f22ec46f1e..c11ed05e1444 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 14
+RHEL_RELEASE = 15
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index fcc8bb116141..33240850fc7e 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,19 @@
+* Thu Sep 24 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200924gitc9c9e6a49f89.14.test]
+- c9c9e6a49f89 rebase
+- mm: move the copy_one_pte() pte_present check into the caller (Linus Torvalds)
+- mm: split out the non-present case from copy_one_pte() (Linus Torvalds)
+- Updated changelog for the release based on 805c6d3c1921 (Fedora Kernel Team)
+- dm crypt: document encrypted keyring key option (Milan Broz)
+- dm crypt: document new no_workqueue flags (Milan Broz)
+- btrfs: fix put of uninitialized kobject after seed device delete (Anand Jain)
+- tools/bootconfig: Add testcase for tailing space (Masami Hiramatsu)
+- tools/bootconfig: Add testcases for repeated key with brace (Masami Hiramatsu)
+- lib/bootconfig: Fix to remove tailing spaces after value (Masami Hiramatsu)
+- lib/bootconfig: Fix a bug of breaking existing tree nodes (Masami Hiramatsu)
+- dm: fix comment in dm_process_bio() (Mike Snitzer)
+- dm: fix bio splitting and its bio completion order for regular IO (Mike Snitzer)
+- btrfs: fix overflow when copying corrupt csums for a message (Johannes Thumshirn)
+
* Wed Sep 23 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200923git805c6d3c1921.14]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index 00b038405d0a..68954b9460d2 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-805c6d3c1921
+c9c9e6a49f89
--
GitLab
>From b7c8976585b780595f02e861b847c19ff9b580b4 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Thu, 24 Sep 2020 04:32:58 +0000
Subject: [PATCH 073/126] Updated changelog for the release based on
c9c9e6a49f89
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 33240850fc7e..b7e1d20b422f 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Thu Sep 24 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200924gitc9c9e6a49f89.15]
+- Merge ark-patches
+
* Thu Sep 24 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200924gitc9c9e6a49f89.14.test]
- c9c9e6a49f89 rebase
- mm: move the copy_one_pte() pte_present check into the caller (Linus Torvalds)
--
GitLab
>From f7e80983f0cf470bb82036e73bff4d5a7daf8fc2 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 12:48:36 +0200
Subject: [PATCH 074/126] s390/zcrypt: Fix ZCRYPT_PERDEV_REQCNT ioctl
reqcnt is an u32 pointer but we do copy sizeof(reqcnt) which is the
size of the pointer. This means we only copy 8 byte. Let us copy
the full monty.
Signed-off-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Harald Freudenberger <freude@xxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Fixes: af4a72276d49 ("s390/zcrypt: Support up to 256 crypto adapters.")
Reviewed-by: Harald Freudenberger <freude@xxxxxxxxxxxxx>
Signed-off-by: Vasily Gorbik <gor@xxxxxxxxxxxxx>
---
drivers/s390/crypto/zcrypt_api.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 4dbbfd88262c..f314936b5462 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -1449,7 +1449,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
if (!reqcnt)
return -ENOMEM;
zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES);
- if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt)))
+ if (copy_to_user((int __user *) arg, reqcnt,
+ sizeof(u32) * AP_DEVICES))
rc = -EFAULT;
kfree(reqcnt);
return rc;
--
GitLab
>From 71c548c26de20334cf0d52217de0b02471442e6a Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@xxxxxxxxxxxx>
Date: Tue, 30 Jun 2020 08:29:25 +0300
Subject: [PATCH 075/126] vhost: Fix documentation
Fix documentation to match actual function prototypes
"end" used instead of "last". Fix that.
Signed-off-by: Eli Cohen <eli@xxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20200630052925.GA157062@xxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
drivers/vhost/iotlb.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c
index 34aec4ba331e..0fd3f87e913c 100644
--- a/drivers/vhost/iotlb.c
+++ b/drivers/vhost/iotlb.c
@@ -149,7 +149,7 @@ EXPORT_SYMBOL_GPL(vhost_iotlb_free);
* vhost_iotlb_itree_first - return the first overlapped range
* @iotlb: the IOTLB
* @start: start of IOVA range
- * @end: end of IOVA range
+ * @last: last byte in IOVA range
*/
struct vhost_iotlb_map *
vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last)
@@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first);
* vhost_iotlb_itree_next - return the next overlapped range
* @map: the starting map node
* @start: start of IOVA range
- * @end: end of IOVA range
+ * @last: last byte IOVA range
*/
struct vhost_iotlb_map *
vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last)
--
GitLab
>From a127c5bbb6a8eee851cbdec254424c480b8edd75 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@xxxxxxxxxx>
Date: Mon, 7 Sep 2020 18:43:43 +0800
Subject: [PATCH 076/126] vhost-vdpa: fix backend feature ioctls
Commit 653055b9acd4 ("vhost-vdpa: support get/set backend features")
introduces two malfunction backend features ioctls:
1) the ioctls was blindly added to vring ioctl instead of vdpa device
ioctl
2) vhost_set_backend_features() was called when dev mutex has already
been held which will lead a deadlock
This patch fixes the above issues.
Cc: Eli Cohen <elic@xxxxxxxxxx>
Reported-by: Zhu Lingshan <lingshan.zhu@xxxxxxxxx>
Fixes: 653055b9acd4 ("vhost-vdpa: support get/set backend features")
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200907104343.31141-1-jasowang@xxxxxxxxxx
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
drivers/vhost/vdpa.c | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 3fab94f88894..796fe979f997 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -353,8 +353,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
struct vdpa_callback cb;
struct vhost_virtqueue *vq;
struct vhost_vring_state s;
- u64 __user *featurep = argp;
- u64 features;
u32 idx;
long r;
@@ -381,18 +379,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
vq->last_avail_idx = vq_state.avail_index;
break;
- case VHOST_GET_BACKEND_FEATURES:
- features = VHOST_VDPA_BACKEND_FEATURES;
- if (copy_to_user(featurep, &features, sizeof(features)))
- return -EFAULT;
- return 0;
- case VHOST_SET_BACKEND_FEATURES:
- if (copy_from_user(&features, featurep, sizeof(features)))
- return -EFAULT;
- if (features & ~VHOST_VDPA_BACKEND_FEATURES)
- return -EOPNOTSUPP;
- vhost_set_backend_features(&v->vdev, features);
- return 0;
}
r = vhost_vring_ioctl(&v->vdev, cmd, argp);
@@ -440,8 +426,20 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
struct vhost_vdpa *v = filep->private_data;
struct vhost_dev *d = &v->vdev;
void __user *argp = (void __user *)arg;
+ u64 __user *featurep = argp;
+ u64 features;
long r;
+ if (cmd == VHOST_SET_BACKEND_FEATURES) {
+ r = copy_from_user(&features, featurep, sizeof(features));
+ if (r)
+ return r;
+ if (features & ~VHOST_VDPA_BACKEND_FEATURES)
+ return -EOPNOTSUPP;
+ vhost_set_backend_features(&v->vdev, features);
+ return 0;
+ }
+
mutex_lock(&d->mutex);
switch (cmd) {
@@ -476,6 +474,10 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
case VHOST_VDPA_SET_CONFIG_CALL:
r = vhost_vdpa_set_config_call(v, argp);
break;
+ case VHOST_GET_BACKEND_FEATURES:
+ features = VHOST_VDPA_BACKEND_FEATURES;
+ r = copy_to_user(featurep, &features, sizeof(features));
+ break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
if (r == -ENOIOCTLCMD)
--
GitLab
>From 00fb259c618ea1198fc51b53a6167aa0d78672a9 Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@xxxxxxxxxxxx>
Date: Thu, 10 Sep 2020 08:25:38 -0700
Subject: [PATCH 077/126] spi: bcm-qspi: Fix probe regression on iProc
platforms
iProc chips have QSPI controller that does not have the MSPI_REV
offset. Reading from that offset will cause a bus error. Fix it by
having MSPI_REV query disabled in the generic compatible string.
Fixes: 3a01f04d74ef ("spi: bcm-qspi: Handle lack of MSPI_REV offset")
Link: https://lore.kernel.org/linux-arm-kernel/20200909211857.4144718-1-f.fainelli@xxxxxxxxx/T/#u
Signed-off-by: Ray Jui <ray.jui@xxxxxxxxxxxx>
Acked-by: Florian Fainelli <f.fainelli@xxxxxxxxx>
Link: https://lore.kernel.org/r/20200910152539.45584-3-ray.jui@xxxxxxxxxxxx
Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
---
drivers/spi/spi-bcm-qspi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 681d09085175..9cfa15ec8b08 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1295,7 +1295,7 @@ static const struct of_device_id bcm_qspi_of_match[] = {
},
{
.compatible = "brcm,spi-bcm-qspi",
- .data = &bcm_qspi_rev_data,
+ .data = &bcm_qspi_no_rev_data,
},
{
.compatible = "brcm,spi-bcm7216-qspi",
--
GitLab
>From be068f29034fb00530a053d18b8cf140c32b12b3 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Thu, 24 Sep 2020 08:41:32 -0700
Subject: [PATCH 078/126] mm: fix misplaced unlock_page in do_wp_page()
Commit 09854ba94c6a ("mm: do_wp_page() simplification") reorganized all
the code around the page re-use vs copy, but in the process also moved
the final unlock_page() around to after the wp_page_reuse() call.
That normally doesn't matter - but it means that the unlock_page() is
now done after releasing the page table lock. Again, not a big deal,
you'd think.
But it turns out that it's very wrong indeed, because once we've
released the page table lock, we've basically lost our only reference to
the page - the page tables - and it could now be free'd at any time. We
do hold the mmap_sem, so no actual unmap() can happen, but madvise can
come in and a MADV_DONTNEED will zap the page range - and free the page.
So now the page may be free'd just as we're unlocking it, which in turn
will usually trigger a "Bad page state" error in the freeing path. To
make matters more confusing, by the time the debug code prints out the
page state, the unlock has typically completed and everything looks fine
again.
This all doesn't happen in any normal situations, but it does trigger
with the dirtyc0w_child LTP test. And it seems to trigger much more
easily (but not expclusively) on s390 than elsewhere, probably because
s390 doesn't do the "batch pages up for freeing after the TLB flush"
that gives the unlock_page() more time to complete and makes the race
harder to hit.
Fixes: 09854ba94c6a ("mm: do_wp_page() simplification")
Link: https://lore.kernel.org/lkml/a46e9bbef2ed4e17778f5615e818526ef848d791.camel@xxxxxxxxxx/
Link: https://lore.kernel.org/linux-mm/c41149a8-211e-390b-af1d-d5eee690fecb@xxxxxxxxxxxxxxxxx/
Reported-by: Qian Cai <cai@xxxxxxxxxx>
Reported-by: Alex Shi <alex.shi@xxxxxxxxxxxxxxxxx>
Bisected-and-analyzed-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Tested-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/memory.c b/mm/memory.c
index e315b1f1ef08..f3eb55975902 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2967,8 +2967,8 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
* page count reference, and the page is locked,
* it's dark out, and we're wearing sunglasses. Hit it.
*/
- wp_page_reuse(vmf);
unlock_page(page);
+ wp_page_reuse(vmf);
return VM_FAULT_WRITE;
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))) {
--
GitLab
>From 516d980f85415d76ae3d0d2a871eb20243f46c95 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@xxxxxxxxxx>
Date: Wed, 23 Sep 2020 02:48:56 +0900
Subject: [PATCH 079/126] scripts/kallsyms: skip ppc compiler stub
*.long_branch.* / *.plt_branch.*
PowerPC allmodconfig often fails to build as follows:
LD .tmp_vmlinux.kallsyms1
KSYM .tmp_vmlinux.kallsyms1.o
LD .tmp_vmlinux.kallsyms2
KSYM .tmp_vmlinux.kallsyms2.o
LD .tmp_vmlinux.kallsyms3
KSYM .tmp_vmlinux.kallsyms3.o
LD vmlinux
SORTTAB vmlinux
SYSMAP System.map
Inconsistent kallsyms data
Try make KALLSYMS_EXTRA_PASS=1 as a workaround
make[2]: *** [../Makefile:1162: vmlinux] Error 1
Setting KALLSYMS_EXTRA_PASS=1 does not help.
This is caused by the compiler inserting stubs such as *.long_branch.*
and *.plt_branch.*
$ powerpc-linux-nm -n .tmp_vmlinux.kallsyms2
[ snip ]
c00000000210c010 t 00000075.plt_branch.da9:19
c00000000210c020 t 00000075.plt_branch.1677:5
c00000000210c030 t 00000075.long_branch.memmove
c00000000210c034 t 00000075.plt_branch.9e0:5
c00000000210c044 t 00000075.plt_branch.free_initrd_mem
...
Actually, the problem mentioned in scripts/link-vmlinux.sh comments;
"In theory it's possible this results in even more stubs, but unlikely"
is happening here, and ends up with another kallsyms step required.
scripts/kallsyms.c already ignores various compiler stubs. Let's do
similar to make kallsysms for PowerPC always succeed in 2 steps.
Reported-by: Guenter Roeck <linux@xxxxxxxxxxxx>
Signed-off-by: Masahiro Yamada <masahiroy@xxxxxxxxxx>
Tested-by: Guenter Roeck <linux@xxxxxxxxxxxx>
---
scripts/kallsyms.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 0096cd965332..7ecd2ccba531 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -82,6 +82,7 @@ static char *sym_name(const struct sym_entry *s)
static bool is_ignored_symbol(const char *name, char type)
{
+ /* Symbol names that exactly match to the following are ignored.*/
static const char * const ignored_symbols[] = {
/*
* Symbols which vary between passes. Passes 1 and 2 must have
@@ -104,6 +105,7 @@ static bool is_ignored_symbol(const char *name, char type)
NULL
};
+ /* Symbol names that begin with the following are ignored.*/
static const char * const ignored_prefixes[] = {
"$", /* local symbols for ARM, MIPS, etc. */
".LASANPC", /* s390 kasan local symbols */
@@ -113,6 +115,7 @@ static bool is_ignored_symbol(const char *name, char type)
NULL
};
+ /* Symbol names that end with the following are ignored.*/
static const char * const ignored_suffixes[] = {
"_from_arm", /* arm */
"_from_thumb", /* arm */
@@ -120,9 +123,15 @@ static bool is_ignored_symbol(const char *name, char type)
NULL
};
+ /* Symbol names that contain the following are ignored.*/
+ static const char * const ignored_matches[] = {
+ ".long_branch.", /* ppc stub */
+ ".plt_branch.", /* ppc stub */
+ NULL
+ };
+
const char * const *p;
- /* Exclude symbols which vary between passes. */
for (p = ignored_symbols; *p; p++)
if (!strcmp(name, *p))
return true;
@@ -138,6 +147,11 @@ static bool is_ignored_symbol(const char *name, char type)
return true;
}
+ for (p = ignored_matches; *p; p++) {
+ if (strstr(name, *p))
+ return true;
+ }
+
if (type == 'U' || type == 'u')
return true;
/* exclude debugging symbols */
--
GitLab
>From ee6fa053019478918ca15eadaa93e516ddb9da8d Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Date: Mon, 21 Sep 2020 13:38:05 +0300
Subject: [PATCH 080/126] KVM: x86: fix MSR_IA32_TSC read for nested migration
MSR reads/writes should always access the L1 state, since the (nested)
hypervisor should intercept all the msrs it wants to adjust, and these
that it doesn't should be read by the guest as if the host had read it.
However IA32_TSC is an exception. Even when not intercepted, guest still
reads the value + TSC offset.
The write however does not take any TSC offset into account.
This is documented in Intel's SDM and seems also to happen on AMD as well.
This creates a problem when userspace wants to read the IA32_TSC value and then
write it. (e.g for migration)
In this case it reads L2 value but write is interpreted as an L1 value.
To fix this make the userspace initiated reads of IA32_TSC return L1 value
as well.
Huge thanks to Dave Gilbert for helping me understand this very confusing
semantic of MSR writes.
Signed-off-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Message-Id: <20200921103805.9102-2-mlevitsk@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/x86.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 67362607e396..e3fe1d126cc3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3224,9 +3224,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_POWER_CTL:
msr_info->data = vcpu->arch.msr_ia32_power_ctl;
break;
- case MSR_IA32_TSC:
- msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+ case MSR_IA32_TSC: {
+ /*
+ * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
+ * even when not intercepted. AMD manual doesn't explicitly
+ * state this but appears to behave the same.
+ *
+ * On userspace reads and writes, however, we unconditionally
+ * operate L1's TSC value to ensure backwards-compatible
+ * behavior for migration.
+ */
+ u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
+ vcpu->arch.tsc_offset;
+
+ msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset;
break;
+ }
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
--
GitLab
>From af5d6c1016487ef4b5aa780062fa000f802580d4 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 04:28:32 +0000
Subject: [PATCH 081/126] [redhat]
kernel-5.9.0-0.rc6.20200925git171d4ff79f96.15.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 15 +++++++++++++++
redhat/marker | 2 +-
3 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index c11ed05e1444..98f70a2f0f06 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 15
+RHEL_RELEASE = 16
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index b7e1d20b422f..21a5f7b65085 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,18 @@
+* Fri Sep 25 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200925git171d4ff79f96.15.test]
+- 171d4ff79f96 rebase
+- mm: fix misplaced unlock_page in do_wp_page() (Linus Torvalds)
+- Updated changelog for the release based on c9c9e6a49f89 (Fedora Kernel Team)
+- Revert "ALSA: usb-audio: Disable Lenovo P620 Rear line-in volume control" (Kai-Heng Feng)
+- media: dt-bindings: media: imx274: Convert to json-schema (Jacopo Mondi)
+- Revert "ALSA: hda - Fix silent audio output and corrupted input on MSI X570-A PRO" (Takashi Iwai)
+- ALSA: usb-audio: Add delay quirk for H570e USB headsets (Joakim Tjernlund)
+- ALSA: hda/realtek: Enable front panel headset LED on Lenovo ThinkStation P520 (Kai-Heng Feng)
+- ALSA: hda/realtek - Couldn't detect Mic if booting with headset plugged (Hui Wang)
+- ALSA: asihpi: fix iounmap in error handler (Tom Rix)
+- media: media/v4l2: remove V4L2_FLAG_MEMORY_NON_CONSISTENT flag (Sergey Senozhatsky)
+- mmc: mmc_spi: Fix mmc_spi_dma_alloc() return type for !HAS_DMA (Geert Uytterhoeven)
+- media: cec-adap.c: don't use flush_scheduled_work() (Hans Verkuil)
+
* Thu Sep 24 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200924gitc9c9e6a49f89.15]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index 68954b9460d2..783055722c2a 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-c9c9e6a49f89
+171d4ff79f96
--
GitLab
>From 7e9806012360a38e4d61366aa12729bbd03419d1 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 04:33:20 +0000
Subject: [PATCH 082/126] Updated changelog for the release based on
171d4ff79f96
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 21a5f7b65085..74300d4ea7aa 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Fri Sep 25 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200925git171d4ff79f96.16]
+- Merge ark-patches
+
* Fri Sep 25 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200925git171d4ff79f96.15.test]
- 171d4ff79f96 rebase
- mm: fix misplaced unlock_page in do_wp_page() (Linus Torvalds)
--
GitLab
>From 8d214c481611b29458a57913bd786f0ac06f0605 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Date: Wed, 23 Sep 2020 14:53:52 -0700
Subject: [PATCH 083/126] KVM: x86: Reset MMU context if guest toggles CR4.SMAP
or CR4.PKE
Reset the MMU context during kvm_set_cr4() if SMAP or PKE is toggled.
Recent commits to (correctly) not reload PDPTRs when SMAP/PKE are
toggled inadvertantly skipped the MMU context reset due to the mask
of bits that triggers PDPTR loads also being used to trigger MMU context
resets.
Fixes: 427890aff855 ("kvm: x86: Toggling CR4.SMAP does not load PDPTEs in PAE mode")
Fixes: cb957adb4ea4 ("kvm: x86: Toggling CR4.PKE does not load PDPTEs in PAE mode")
Cc: Jim Mattson <jmattson@xxxxxxxxxx>
Cc: Peter Shier <pshier@xxxxxxxxxx>
Cc: Oliver Upton <oupton@xxxxxxxxxx>
Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Message-Id: <20200923215352.17756-1-sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/x86.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e3fe1d126cc3..58fa354b1446 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
X86_CR4_SMEP;
+ unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
if (kvm_valid_cr4(vcpu, cr4))
return 1;
@@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if (kvm_x86_ops.set_cr4(vcpu, cr4))
return 1;
- if (((cr4 ^ old_cr4) & pdptr_bits) ||
+ if (((cr4 ^ old_cr4) & mmu_role_bits) ||
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
--
GitLab
>From f3cd4850504ff612d0ea77a0aaf29b66c98fcefe Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@xxxxxxxxx>
Date: Thu, 24 Sep 2020 14:55:54 -0600
Subject: [PATCH 084/126] io_uring: ensure open/openat2 name is cleaned on
cancelation
If we cancel these requests, we'll leak the memory associated with the
filename. Add them to the table of ops that need cleaning, if
REQ_F_NEED_CLEANUP is set.
Cc: stable@xxxxxxxxxxxxxxx
Fixes: e62753e4e292 ("io_uring: call statx directly")
Reviewed-by: Stefano Garzarella <sgarzare@xxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e6004b92e553..0ab16df31288 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5671,6 +5671,11 @@ static void __io_clean_op(struct io_kiocb *req)
io_put_file(req, req->splice.file_in,
(req->splice.flags & SPLICE_F_FD_IN_FIXED));
break;
+ case IORING_OP_OPENAT:
+ case IORING_OP_OPENAT2:
+ if (req->open.filename)
+ putname(req->open.filename);
+ break;
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
--
GitLab
>From 3aab91774bbd8e571cfaddaf839aafd07718333c Mon Sep 17 00:00:00 2001
From: Jeffle Xu <jefflexu@xxxxxxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 14:00:31 +0800
Subject: [PATCH 085/126] block: remove unused BLK_QC_T_EAGAIN flag
commit 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE") removed the
REQ_NOWAIT_INLINE related code, but the diff wasn't applied to
blk_types.h somehow.
Then commit 2771cefeac49 ("block: remove the REQ_NOWAIT_INLINE flag")
removed the REQ_NOWAIT_INLINE flag while the BLK_QC_T_EAGAIN flag still
remains.
Fixes: 7b6620d7db56 ("block: remove REQ_NOWAIT_INLINE")
Signed-off-by: Jeffle Xu <jefflexu@xxxxxxxxxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
include/linux/blk_types.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4ecf4fed171f..b3fc5d3dd8ea 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -497,13 +497,12 @@ static inline int op_stat_group(unsigned int op)
typedef unsigned int blk_qc_t;
#define BLK_QC_T_NONE -1U
-#define BLK_QC_T_EAGAIN -2U
#define BLK_QC_T_SHIFT 16
#define BLK_QC_T_INTERNAL (1U << 31)
static inline bool blk_qc_t_valid(blk_qc_t cookie)
{
- return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN;
+ return cookie != BLK_QC_T_NONE;
}
static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
--
GitLab
>From 62c774ed483174b994c79e0c9f596b315f1ddfaf Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@xxxxxxxxx>
Date: Fri, 25 Sep 2020 09:01:53 -0600
Subject: [PATCH 086/126] io_uring: don't unconditionally set plug->nowait =
true
This causes all the bios to be submitted with REQ_NOWAIT, which can be
problematic on either btrfs or on file systems that otherwise use a mix
of block devices where only some of them support it.
For now, just remove the setting of plug->nowait = true.
Reported-by: Dan Melnic <dmm@xxxxxx>
Reported-by: Brian Foster <bfoster@xxxxxxxxxx>
Fixes: b63534c41e20 ("io_uring: re-issue block requests that failed because of resources")
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0ab16df31288..ad828fa19af4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6353,9 +6353,6 @@ static void io_submit_state_start(struct io_submit_state *state,
struct io_ring_ctx *ctx, unsigned int max_ios)
{
blk_start_plug(&state->plug);
-#ifdef CONFIG_BLOCK
- state->plug.nowait = true;
-#endif
state->comp.nr = 0;
INIT_LIST_HEAD(&state->comp.list);
state->comp.ctx = ctx;
--
GitLab
>From 4bb05f30483fd21ea5413eaf1182768f251cf625 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@xxxxxxx>
Date: Thu, 24 Sep 2020 13:41:57 -0500
Subject: [PATCH 087/126] KVM: SVM: Add a dedicated INVD intercept routine
The INVD instruction intercept performs emulation. Emulation can't be done
on an SEV guest because the guest memory is encrypted.
Provide a dedicated intercept routine for the INVD intercept. And since
the instruction is emulated as a NOP, just skip it instead.
Fixes: 1654efcbc431 ("KVM: SVM: Add KVM_SEV_INIT command")
Signed-off-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
Message-Id: <a0b9a19ffa7fef86a3cc700c7ea01cb2731e04e5.1600972918.git.thomas.lendacky@xxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/svm/svm.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5764b87379cf..d4e18bda19c7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm)
return 1;
}
+static int invd_interception(struct vcpu_svm *svm)
+{
+ /* Treat an INVD instruction as a NOP and just skip it. */
+ return kvm_skip_emulated_instruction(&svm->vcpu);
+}
+
static int invlpg_interception(struct vcpu_svm *svm)
{
if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
@@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_RDPMC] = rdpmc_interception,
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
- [SVM_EXIT_INVD] = emulate_on_interception,
+ [SVM_EXIT_INVD] = invd_interception,
[SVM_EXIT_PAUSE] = pause_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
--
GitLab
>From cb91cb092b51196cffb69867f0d638c38e5ad7d1 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@xxxxxxxxxx>
Date: Thu, 24 Sep 2020 17:38:29 -0400
Subject: [PATCH 088/126] Merge Upstream script fixes
As part of splitting the merge-upstream and release stages apart,
the merge upstream wasn't working quite right. These are cleanup
fixes to fix that.
The main change is to drop the ark rebase patches script. Running
that through a Makefile through gitlab CI creates a funky environment
where the next script (update-configs.sh) no longer exists because
of the git checkout changes. Keep rebase-patches in the gitlab-ci
script for now.
That will be removed soon enough. No effect on normal workflow.
The other fixes are self-explanatory.
Signed-off-by: Don Zickus <dzickus@xxxxxxxxxx>
---
redhat/Makefile | 5 ++---
redhat/scripts/ci/ark-rebase-patches.sh | 4 ++--
redhat/scripts/ci/ark-update-configs.sh | 2 +-
3 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/redhat/Makefile b/redhat/Makefile
index bfc9cd63df60..27d2cd94e78f 100644
--- a/redhat/Makefile
+++ b/redhat/Makefile
@@ -327,11 +327,10 @@ dist-merge-upstream: git-tree-check
fi;
@# If TAG is empty, script defaults to master:HEAD
- @$(REDHAT)/scripts/ci/ark-rebase-patches.sh $(TAG) || exit 1
git checkout $(DIST_BRANCH)
@$(REDHAT)/scripts/ci/ark-update-configs.sh $(TAG)
-dist-merge-upstream-push: DIST_PUSH="1"
+dist-merge-upstream-push: export DIST_PUSH="1"
dist-merge-upstream-push: dist-merge-upstream
dist-fedora-release: git-tree-check
@@ -340,7 +339,7 @@ dist-fedora-release: git-tree-check
@cd ..; $(REDHAT)/scripts/ci/ark-create-release.sh $(TAG) || \
(echo "Unable to create release tag"; exit 1)
-dist-fedora-release-push: DIST_PUSH="1"
+dist-fedora-release-push: export DIST_PUSH="1"
dist-fedora-release-push: dist-fedora-release
.PHONY: dist-brew dist-koji
diff --git a/redhat/scripts/ci/ark-rebase-patches.sh b/redhat/scripts/ci/ark-rebase-patches.sh
index ef2183ecc799..2e64b90ac277 100755
--- a/redhat/scripts/ci/ark-rebase-patches.sh
+++ b/redhat/scripts/ci/ark-rebase-patches.sh
@@ -99,7 +99,7 @@ fi
if $CLEAN_REBASE; then
if test -n "$DIST_PUSH"; then
- echo "Pushing branch ark-patches to $(get remote get-url gitlab)"
+ echo "Pushing branch ark-patches to $(git remote get-url gitlab)"
git push -f gitlab ark-patches
else
printf "You can safely update ark-patches with 'git push -f <remote> ark-patches'\n"
@@ -114,7 +114,7 @@ if git tag -v "$UPSTREAM_REF" > /dev/null 2>&1; then
printf "Creating branch \"ark/patches/%s\"\n" "$UPSTREAM_REF"
git branch ark/patches/"$UPSTREAM_REF"
if test -n "$DIST_PUSH"; then
- echo "Pushing branch ark/patches to $(get remote get-url gitlab)"
+ echo "Pushing branch ark/patches to $(git remote get-url gitlab)"
git push gitlab ark/patches/"$UPSTREAM_REF"
else
printf "Don't forget to run 'git push <remote> ark/patches/%s'\n" "$UPSTREAM_REF"
diff --git a/redhat/scripts/ci/ark-update-configs.sh b/redhat/scripts/ci/ark-update-configs.sh
index 22dcead23f88..e8baacdb929e 100755
--- a/redhat/scripts/ci/ark-update-configs.sh
+++ b/redhat/scripts/ci/ark-update-configs.sh
@@ -67,7 +67,7 @@ else
fi
if test -n "$DIST_PUSH"; then
- echo "Pushing branch $(git branch --show-current) to $(get remote get-url gitlab)"
+ echo "Pushing branch $(git branch --show-current) to $(git remote get-url gitlab)"
git push gitlab HEAD
echo "Pushing config update branches"
--
GitLab
>From f38c7e3abfba9a9e180b34f642254c43782e7ffe Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@xxxxxxxxx>
Date: Fri, 25 Sep 2020 15:23:43 -0600
Subject: [PATCH 089/126] io_uring: ensure async buffered read-retry is setup
properly
A previous commit for fixing up short reads botched the async retry
path, so we ended up going to worker threads more often than we should.
Fix this up, so retries work the way they originally were intended to.
Fixes: 227c0c9673d8 ("io_uring: internally retry short reads")
Reported-by: Hao_Xu <haoxu@xxxxxxxxxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/io_uring.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index ad828fa19af4..11b8e428300d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3172,10 +3172,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
goto done;
/* some cases will consume bytes even on error returns */
iov_iter_revert(iter, iov_count - iov_iter_count(iter));
- ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
- if (ret)
- goto out_free;
- return -EAGAIN;
+ ret = 0;
+ goto copy_iov;
} else if (ret < 0) {
/* make sure -ERESTARTSYS -> -EINTR is done */
goto done;
--
GitLab
>From fc45ae7370c5576427d3767b9d6575bc19a8e050 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 18:16:45 -0400
Subject: [PATCH 090/126] Filter out upstream commits from changelog
I updated the release code to include more changelog info
in the os-build branch. This resulted in adding upstream
merge commits. This is not interesting for a Fedora tree
as it is covered by a generic 'merge' entry.
Use a simple git trick to filter those upstream commits out, "^master".
See 'man gitrevisions' for more tricks.
Signed-off-by: Don Zickus <dzickus@xxxxxxxxxx>
---
redhat/genspec.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/redhat/genspec.sh b/redhat/genspec.sh
index fbe275f6f4e7..ab135b1a2a1e 100755
--- a/redhat/genspec.sh
+++ b/redhat/genspec.sh
@@ -49,7 +49,7 @@ if [ -z "$lasttag" ]; then
lasttag=$MARKER
fi
echo "Gathering new log entries since $lasttag"
-git format-patch --no-renames -k --stdout ${lasttag}.. -- ":!/redhat/rhdocs" | awk '
+git format-patch --no-renames -k --stdout ^master ${lasttag}.. -- ":!/redhat/rhdocs" | awk '
BEGIN{TYPE="PATCHJUNK"; }
# add an entry to changelog
function changelog(subjectline, nameline, zstream)
--
GitLab
>From 15f68d44f9123ebc54604e833ec3d9411d96cd9c Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 14:02:19 -0400
Subject: [PATCH 091/126] Create Patchlist.changelog file
A source git tree's workflow and Fedora's separation of upstream and distro
contributions don't overlap well.
A source git tree is always merging upstream content and downstream content
while avoiding a rebase. By separating the tarballs and patches out, this
effectively causes a rebase. This 'rebase' causes patches to not apply
correctly as git took care of it previously.
This patch creates a Patchlist.changelog file that lists all the SHAs that
are added to the upstream tree.
The goal is to create a useful file such that the source git tree can
create a single tarball and use the Patchlist.changelog file to adhere
to the spirit of the Fedora's separation rules.
No technical changes, just a new file added to the srpm.
Signed-off-by: Don Zickus <dzickus@xxxxxxxxxx>
---
redhat/genspec.sh | 8 ++++++++
redhat/kernel.spec.template | 1 +
2 files changed, 9 insertions(+)
diff --git a/redhat/genspec.sh b/redhat/genspec.sh
index fbe275f6f4e7..308db0182954 100755
--- a/redhat/genspec.sh
+++ b/redhat/genspec.sh
@@ -273,6 +273,14 @@ if [ "$SINGLE_TARBALL" = 0 ]; then
done
fi
+# generate Patchlist.changelog file that holds the shas and commits not
+# included upstream.
+git log --no-merges --pretty=oneline --no-decorate master.. \
+ ":(exclude,top).gitlab-ci.yml" \
+ ":(exclude,top)makefile" \
+ ":(exclude,top)Makefile.rhelver" \
+ ":(exclude,top)redhat" > $plistf.changelog
+
sed -i "s/%%PATCHLIST%%//" $SPECFILE
sed -i "s/%%APPLYPATCH%%//" $SPECFILE
diff --git a/redhat/kernel.spec.template b/redhat/kernel.spec.template
index 6f591e11bd71..bc12211a7d6b 100644
--- a/redhat/kernel.spec.template
+++ b/redhat/kernel.spec.template
@@ -708,6 +708,7 @@ Source2001: cpupower.config
Source3000: merge.pl
Source3001: kernel-local
Source3002: Patchlist
+Source3003: Patchlist.changelog
Source4000: README.rst
--
GitLab
>From 54cd0a71284033df1aef6c15c8b69c2564d22103 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Sat, 26 Sep 2020 04:28:03 +0000
Subject: [PATCH 092/126] [redhat]
kernel-5.9.0-0.rc6.20200926git7c7ec3226f5f.16.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 6 ++++++
redhat/marker | 2 +-
3 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index 98f70a2f0f06..350b1c0db268 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 16
+RHEL_RELEASE = 17
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 74300d4ea7aa..57fc51ebebc3 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,9 @@
+* Sat Sep 26 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200926git7c7ec3226f5f.16.test]
+- 7c7ec3226f5f rebase
+- Filter out upstream commits from changelog (Don Zickus)
+- Merge Upstream script fixes (Don Zickus)
+- Updated changelog for the release based on 171d4ff79f96 (Fedora Kernel Team)
+
* Fri Sep 25 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200925git171d4ff79f96.16]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index 783055722c2a..02e1e4b6abb0 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-171d4ff79f96
+7c7ec3226f5f
--
GitLab
>From 256de6a50ef1a7e1303a7e1732fca657f672cda3 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Sat, 26 Sep 2020 04:32:57 +0000
Subject: [PATCH 093/126] Updated changelog for the release based on
7c7ec3226f5f
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 57fc51ebebc3..5857c0547754 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Sat Sep 26 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200926git7c7ec3226f5f.17]
+- Merge ark-patches
+
* Sat Sep 26 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200926git7c7ec3226f5f.16.test]
- 7c7ec3226f5f rebase
- Filter out upstream commits from changelog (Don Zickus)
--
GitLab
>From e30d694c3381b565e043cf74b0bed059db1b4ac9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@xxxxxxxxx>
Date: Fri, 25 Sep 2020 08:21:14 -0700
Subject: [PATCH 094/126] Documentation/llvm: Fix clang target examples
clang --target=<triple> is how we can specify a particular toolchain
triple to be use, fix the two occurences in the documentation.
Fixes: fcf1b6a35c16 ("Documentation/llvm: add documentation on building w/ Clang/LLVM")
Signed-off-by: Florian Fainelli <f.fainelli@xxxxxxxxx>
Reviewed-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
Reviewed-by: Nathan Chancellor <natechancellor@xxxxxxxxx>
Signed-off-by: Masahiro Yamada <masahiroy@xxxxxxxxxx>
---
Documentation/kbuild/llvm.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst
index 334df758dce3..dae90c21aed3 100644
--- a/Documentation/kbuild/llvm.rst
+++ b/Documentation/kbuild/llvm.rst
@@ -39,10 +39,10 @@ which can help simplify cross compiling. ::
ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang
``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead
-``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For
+``CROSS_COMPILE`` is used to set a command line flag: ``--target=<triple>``. For
example: ::
- clang --target aarch64-linux-gnu foo.c
+ clang --target=aarch64-linux-gnu foo.c
LLVM Utilities
--------------
--
GitLab
>From 678ff6a7afccc43d352c1b8c94b6d8c0ee1464ad Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@xxxxxxxxxx>
Date: Sat, 26 Sep 2020 07:13:41 -0700
Subject: [PATCH 095/126] mm: slab: fix potential double free in ___cache_free
With the commit 10befea91b61 ("mm: memcg/slab: use a single set of
kmem_caches for all allocations"), it becomes possible to call kfree()
from the slabs_destroy().
The functions cache_flusharray() and do_drain() calls slabs_destroy() on
array_cache of the local CPU without updating the size of the
array_cache. This enables the kfree() call from the slabs_destroy() to
recursively call cache_flusharray() which can potentially call
free_block() on the same elements of the array_cache of the local CPU
and causing double free and memory corruption.
To fix the issue, simply update the local CPU array_cache cache before
calling slabs_destroy().
Fixes: 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations")
Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Reviewed-by: Roman Gushchin <guro@xxxxxx>
Tested-by: Ming Lei <ming.lei@xxxxxxxxxx>
Reported-by: kernel test robot <rong.a.chen@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Ted Ts'o <tytso@xxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/slab.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/mm/slab.c b/mm/slab.c
index 3160dff6fd76..f658e86ec8ce 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1632,6 +1632,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page)
kmem_cache_free(cachep->freelist_cache, freelist);
}
+/*
+ * Update the size of the caches before calling slabs_destroy as it may
+ * recursively call kfree.
+ */
static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
{
struct page *page, *n;
@@ -2153,8 +2157,8 @@ static void do_drain(void *arg)
spin_lock(&n->list_lock);
free_block(cachep, ac->entry, ac->avail, node, &list);
spin_unlock(&n->list_lock);
- slabs_destroy(cachep, &list);
ac->avail = 0;
+ slabs_destroy(cachep, &list);
}
static void drain_cpu_caches(struct kmem_cache *cachep)
@@ -3402,9 +3406,9 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
}
#endif
spin_unlock(&n->list_lock);
- slabs_destroy(cachep, &list);
ac->avail -= batchcount;
memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
+ slabs_destroy(cachep, &list);
}
/*
--
GitLab
>From 41663430588c737dd735bad5a0d1ba325dcabd59 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:01 -0700
Subject: [PATCH 096/126] mm, THP, swap: fix allocating cluster for swapfile by
mistake
SWP_FS is used to make swap_{read,write}page() go through the
filesystem, and it's only used for swap files over NFS. So, !SWP_FS
means non NFS for now, it could be either file backed or device backed.
Something similar goes with legacy SWP_FILE.
So in order to achieve the goal of the original patch, SWP_BLKDEV should
be used instead.
FS corruption can be observed with SSD device + XFS + fragmented
swapfile due to CONFIG_THP_SWAP=y.
I reproduced the issue with the following details:
Environment:
QEMU + upstream kernel + buildroot + NVMe (2 GB)
Kernel config:
CONFIG_BLK_DEV_NVME=y
CONFIG_THP_SWAP=y
Some reproducible steps:
mkfs.xfs -f /dev/nvme0n1
mkdir /tmp/mnt
mount /dev/nvme0n1 /tmp/mnt
bs="32k"
sz="1024m" # doesn't matter too much, I also tried 16m
xfs_io -f -c "pwrite -R -b $bs 0 $sz" -c "fdatasync" /tmp/mnt/sw
xfs_io -f -c "pwrite -R -b $bs 0 $sz" -c "fdatasync" /tmp/mnt/sw
xfs_io -f -c "pwrite -R -b $bs 0 $sz" -c "fdatasync" /tmp/mnt/sw
xfs_io -f -c "pwrite -F -S 0 -b $bs 0 $sz" -c "fdatasync" /tmp/mnt/sw
xfs_io -f -c "pwrite -R -b $bs 0 $sz" -c "fsync" /tmp/mnt/sw
mkswap /tmp/mnt/sw
swapon /tmp/mnt/sw
stress --vm 2 --vm-bytes 600M # doesn't matter too much as well
Symptoms:
- FS corruption (e.g. checksum failure)
- memory corruption at: 0xd2808010
- segfault
Fixes: f0eea189e8e9 ("mm, THP, swap: Don't allocate huge cluster for file backed swap device")
Fixes: 38d8b4e6bdc8 ("mm, THP, swap: delay splitting THP during swap out")
Signed-off-by: Gao Xiang <hsiangkao@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Reviewed-by: Yang Shi <shy828301@xxxxxxxxx>
Acked-by: Rafael Aquini <aquini@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Carlos Maiolino <cmaiolino@xxxxxxxxxx>
Cc: Eric Sandeen <esandeen@xxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200820045323.7809-1-hsiangkao@xxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/swapfile.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 12f59e641b5e..debc94155f74 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1078,7 +1078,7 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
goto nextsi;
}
if (size == SWAPFILE_CLUSTER) {
- if (!(si->flags & SWP_FS))
+ if (si->flags & SWP_BLKDEV)
n_ret = swap_alloc_cluster(si, swp_entries);
} else
n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
--
GitLab
>From 8d3fe09d8d6645dcbbe2413cde58f51ceb6545a6 Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:05 -0700
Subject: [PATCH 097/126] mm: memcontrol: fix missing suffix of
workingset_restore
We forget to add the suffix to the workingset_restore string, so fix it.
And also update the documentation of cgroup-v2.rst.
Fixes: 170b04b7ae49 ("mm/workingset: prepare the workingset detection infrastructure for anon LRU")
Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200916100030.71698-1-songmuchun@xxxxxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/admin-guide/cgroup-v2.rst | 25 ++++++++++++++++++-------
mm/memcontrol.c | 4 ++--
2 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 6be43781ec7f..baa07b30845e 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1324,15 +1324,26 @@ PAGE_SIZE multiple when read back.
pgmajfault
Number of major page faults incurred
- workingset_refault
- Number of refaults of previously evicted pages
+ workingset_refault_anon
+ Number of refaults of previously evicted anonymous pages.
- workingset_activate
- Number of refaulted pages that were immediately activated
+ workingset_refault_file
+ Number of refaults of previously evicted file pages.
- workingset_restore
- Number of restored pages which have been detected as an active
- workingset before they got reclaimed.
+ workingset_activate_anon
+ Number of refaulted anonymous pages that were immediately
+ activated.
+
+ workingset_activate_file
+ Number of refaulted file pages that were immediately activated.
+
+ workingset_restore_anon
+ Number of restored anonymous pages which have been detected as
+ an active workingset before they got reclaimed.
+
+ workingset_restore_file
+ Number of restored file pages which have been detected as an
+ active workingset before they got reclaimed.
workingset_nodereclaim
Number of times a shadow node has been reclaimed
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cfa6cbad21d5..6877c765b8d0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1538,9 +1538,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON));
seq_buf_printf(&s, "workingset_activate_file %lu\n",
memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE));
- seq_buf_printf(&s, "workingset_restore %lu\n",
+ seq_buf_printf(&s, "workingset_restore_anon %lu\n",
memcg_page_state(memcg, WORKINGSET_RESTORE_ANON));
- seq_buf_printf(&s, "workingset_restore %lu\n",
+ seq_buf_printf(&s, "workingset_restore_file %lu\n",
memcg_page_state(memcg, WORKINGSET_RESTORE_FILE));
seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
--
GitLab
>From d3f7b1bb204099f2f7306318896223e8599bb6a2 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:10 -0700
Subject: [PATCH 098/126] mm/gup: fix gup_fast with dynamic page table folding
Currently to make sure that every page table entry is read just once
gup_fast walks perform READ_ONCE and pass pXd value down to the next
gup_pXd_range function by value e.g.:
static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
...
pudp = pud_offset(&p4d, addr);
This function passes a reference on that local value copy to pXd_offset,
and might get the very same pointer in return. This happens when the
level is folded (on most arches), and that pointer should not be
iterated.
On s390 due to the fact that each task might have different 5,4 or
3-level address translation and hence different levels folded the logic
is more complex and non-iteratable pointer to a local copy leads to
severe problems.
Here is an example of what happens with gup_fast on s390, for a task
with 3-level paging, crossing a 2 GB pud boundary:
// addr = 0x1007ffff000, end = 0x10080001000
static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
// pud_offset returns &p4d itself (a pointer to a value on stack)
pudp = pud_offset(&p4d, addr);
do {
// on second iteratation reading "random" stack value
pud_t pud = READ_ONCE(*pudp);
// next = 0x10080000000, due to PUD_SIZE/MASK != PGDIR_SIZE/MASK on s390
next = pud_addr_end(addr, end);
...
} while (pudp++, addr = next, addr != end); // pudp++ iterating over stack
return 1;
}
This happens since s390 moved to common gup code with commit
d1874a0c2805 ("s390/mm: make the pxd_offset functions more robust") and
commit 1a42010cdc26 ("s390/mm: convert to the generic
get_user_pages_fast code").
s390 tried to mimic static level folding by changing pXd_offset
primitives to always calculate top level page table offset in pgd_offset
and just return the value passed when pXd_offset has to act as folded.
What is crucial for gup_fast and what has been overlooked is that
PxD_SIZE/MASK and thus pXd_addr_end should also change correspondingly.
And the latter is not possible with dynamic folding.
To fix the issue in addition to pXd values pass original pXdp pointers
down to gup_pXd_range functions. And introduce pXd_offset_lockless
helpers, which take an additional pXd entry value parameter. This has
already been discussed in
https://lkml.kernel.org/r/20190418100218.0a4afd51@mschwideX1
Fixes: 1a42010cdc26 ("s390/mm: convert to the generic get_user_pages_fast code")
Signed-off-by: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Reviewed-by: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Reviewed-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Reviewed-by: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Jeff Dike <jdike@xxxxxxxxxxx>
Cc: Richard Weinberger <richard@xxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Claudio Imbrenda <imbrenda@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [5.2+]
Link: https://lkml.kernel.org/r/patch.git-943f1e5dcff2.your-ad-here.call-01599856292-ext-8676@work.hours
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
arch/s390/include/asm/pgtable.h | 42 +++++++++++++++++++++++----------
include/linux/pgtable.h | 10 ++++++++
mm/gup.c | 18 +++++++-------
3 files changed, 49 insertions(+), 21 deletions(-)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7eb01a5459cd..b55561cc8786 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
{
- if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
- return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
- return (p4d_t *) pgd;
+ if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+ return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+ return (p4d_t *) pgdp;
}
+#define p4d_offset_lockless p4d_offset_lockless
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
{
- if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
- return (pud_t *) p4d_deref(*p4d) + pud_index(address);
- return (pud_t *) p4d;
+ return p4d_offset_lockless(pgdp, *pgdp, address);
+}
+
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
+{
+ if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+ return (pud_t *) p4d_deref(p4d) + pud_index(address);
+ return (pud_t *) p4dp;
+}
+#define pud_offset_lockless pud_offset_lockless
+
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
+{
+ return pud_offset_lockless(p4dp, *p4dp, address);
}
#define pud_offset pud_offset
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
+{
+ if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+ return (pmd_t *) pud_deref(pud) + pmd_index(address);
+ return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
{
- if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
- return (pmd_t *) pud_deref(*pud) + pmd_index(address);
- return (pmd_t *) pud;
+ return pmd_offset_lockless(pudp, *pudp, address);
}
#define pmd_offset pmd_offset
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e8cbc2e795d5..90654cb63e9e 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,6 +1427,16 @@ typedef unsigned int pgtbl_mod_mask;
#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED)
#endif
+#ifndef p4d_offset_lockless
+#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address)
+#endif
+#ifndef pud_offset_lockless
+#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address)
+#endif
+#ifndef pmd_offset_lockless
+#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address)
+#endif
+
/*
* p?d_leaf() - true if this entry is a final mapping to a physical address.
* This differs from p?d_huge() by the fact that they are always available (if
diff --git a/mm/gup.c b/mm/gup.c
index e5739a1974d5..578bf5bd8bf8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2485,13 +2485,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
return 1;
}
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pmd_t *pmdp;
- pmdp = pmd_offset(&pud, addr);
+ pmdp = pmd_offset_lockless(pudp, pud, addr);
do {
pmd_t pmd = READ_ONCE(*pmdp);
@@ -2528,13 +2528,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
return 1;
}
-static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
+static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
- pudp = pud_offset(&p4d, addr);
+ pudp = pud_offset_lockless(p4dp, p4d, addr);
do {
pud_t pud = READ_ONCE(*pudp);
@@ -2549,20 +2549,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
PUD_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr))
+ } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr))
return 0;
} while (pudp++, addr = next, addr != end);
return 1;
}
-static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
+static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end,
unsigned int flags, struct page **pages, int *nr)
{
unsigned long next;
p4d_t *p4dp;
- p4dp = p4d_offset(&pgd, addr);
+ p4dp = p4d_offset_lockless(pgdp, pgd, addr);
do {
p4d_t p4d = READ_ONCE(*p4dp);
@@ -2574,7 +2574,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end,
if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr,
P4D_SHIFT, next, flags, pages, nr))
return 0;
- } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr))
+ } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr))
return 0;
} while (p4dp++, addr = next, addr != end);
@@ -2602,7 +2602,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end,
if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
PGDIR_SHIFT, next, flags, pages, nr))
return;
- } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr))
+ } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr))
return;
} while (pgdp++, addr = next, addr != end);
}
--
GitLab
>From 6c5c7b9f3352728af490183f71d350bb658ffb75 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:14 -0700
Subject: [PATCH 099/126] mm/migrate: correct thp migration stats
PageTransHuge returns true for both thp and hugetlb, so thp stats was
counting both thp and hugetlb migrations. Exclude hugetlb migration by
setting is_thp variable right.
Clean up thp handling code too when we are there.
Fixes: 1a5bae25e3cf ("mm/vmstat: add events for THP migration without split")
Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
Link: https://lkml.kernel.org/r/20200917210413.1462975-1-zi.yan@xxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/migrate.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index aecb1433cf3c..04a98bb2f568 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1446,7 +1446,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
* Capture required information that might get lost
* during migration.
*/
- is_thp = PageTransHuge(page);
+ is_thp = PageTransHuge(page) && !PageHuge(page);
nr_subpages = thp_nr_pages(page);
cond_resched();
@@ -1472,7 +1472,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
* we encounter them after the rest of the list
* is processed.
*/
- if (PageTransHuge(page) && !PageHuge(page)) {
+ if (is_thp) {
lock_page(page);
rc = split_huge_page_to_list(page, from);
unlock_page(page);
@@ -1481,8 +1481,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
nr_thp_split++;
goto retry;
}
- }
- if (is_thp) {
+
nr_thp_failed++;
nr_failed += nr_subpages;
goto out;
--
GitLab
>From 1e1b6d63d6340764e00356873e5794225a2a03ea Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:18 -0700
Subject: [PATCH 100/126] lib/string.c: implement stpcpy
LLVM implemented a recent "libcall optimization" that lowers calls to
`sprintf(dest, "%s", str)` where the return value is used to
`stpcpy(dest, str) - dest`.
This generally avoids the machinery involved in parsing format strings.
`stpcpy` is just like `strcpy` except it returns the pointer to the new
tail of `dest`. This optimization was introduced into clang-12.
Implement this so that we don't observe linkage failures due to missing
symbol definitions for `stpcpy`.
Similar to last year's fire drill with: commit 5f074f3e192f
("lib/string.c: implement a basic bcmp")
The kernel is somewhere between a "freestanding" environment (no full
libc) and "hosted" environment (many symbols from libc exist with the
same type, function signature, and semantics).
As Peter Anvin notes, there's not really a great way to inform the
compiler that you're targeting a freestanding environment but would like
to opt-in to some libcall optimizations (see pr/47280 below), rather
than opt-out.
Arvind notes, -fno-builtin-* behaves slightly differently between GCC
and Clang, and Clang is missing many __builtin_* definitions, which I
consider a bug in Clang and am working on fixing.
Masahiro summarizes the subtle distinction between compilers justly:
To prevent transformation from foo() into bar(), there are two ways in
Clang to do that; -fno-builtin-foo, and -fno-builtin-bar. There is
only one in GCC; -fno-buitin-foo.
(Any difference in that behavior in Clang is likely a bug from a missing
__builtin_* definition.)
Masahiro also notes:
We want to disable optimization from foo() to bar(),
but we may still benefit from the optimization from
foo() into something else. If GCC implements the same transform, we
would run into a problem because it is not -fno-builtin-bar, but
-fno-builtin-foo that disables that optimization.
In this regard, -fno-builtin-foo would be more future-proof than
-fno-built-bar, but -fno-builtin-foo is still potentially overkill. We
may want to prevent calls from foo() being optimized into calls to
bar(), but we still may want other optimization on calls to foo().
It seems that compilers today don't quite provide the fine grain control
over which libcall optimizations pseudo-freestanding environments would
prefer.
Finally, Kees notes that this interface is unsafe, so we should not
encourage its use. As such, I've removed the declaration from any
header, but it still needs to be exported to avoid linkage errors in
modules.
Reported-by: Sami Tolvanen <samitolvanen@xxxxxxxxxx>
Suggested-by: Andy Lavr <andy.lavr@xxxxxxxxx>
Suggested-by: Arvind Sankar <nivedita@xxxxxxxxxxxx>
Suggested-by: Joe Perches <joe@xxxxxxxxxxx>
Suggested-by: Kees Cook <keescook@xxxxxxxxxxxx>
Suggested-by: Masahiro Yamada <masahiroy@xxxxxxxxxx>
Suggested-by: Rasmus Villemoes <linux@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Tested-by: Nathan Chancellor <natechancellor@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200914161643.938408-1-ndesaulniers@xxxxxxxxxx
Link: https://bugs.llvm.org/show_bug.cgi?id=47162
Link: https://bugs.llvm.org/show_bug.cgi?id=47280
Link: https://github.com/ClangBuiltLinux/linux/issues/1126
Link: https://man7.org/linux/man-pages/man3/stpcpy.3.html
Link: https://pubs.opengroup.org/onlinepubs/9699919799/functions/stpcpy.html
Link: https://reviews.llvm.org/D85963
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
lib/string.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/lib/string.c b/lib/string.c
index 6012c385fb31..4288e0158d47 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const char *src, size_t count)
}
EXPORT_SYMBOL(strscpy_pad);
+/**
+ * stpcpy - copy a string from src to dest returning a pointer to the new end
+ * of dest, including src's %NUL-terminator. May overrun dest.
+ * @dest: pointer to end of string being copied into. Must be large enough
+ * to receive copy.
+ * @src: pointer to the beginning of string being copied from. Must not overlap
+ * dest.
+ *
+ * stpcpy differs from strcpy in a key way: the return value is a pointer
+ * to the new %NUL-terminating character in @dest. (For strcpy, the return
+ * value is a pointer to the start of @dest). This interface is considered
+ * unsafe as it doesn't perform bounds checking of the inputs. As such it's
+ * not recommended for usage. Instead, its definition is provided in case
+ * the compiler lowers other libcalls to stpcpy.
+ */
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src);
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src)
+{
+ while ((*dest++ = *src++) != '\0')
+ /* nothing */;
+ return --dest;
+}
+EXPORT_SYMBOL(stpcpy);
+
#ifndef __HAVE_ARCH_STRCAT
/**
* strcat - Append one %NUL-terminated string to another
--
GitLab
>From ffa550cd691b8ba6c6117ce986516635afe03c13 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:21 -0700
Subject: [PATCH 101/126] lib/memregion.c: include memregion.h
This addresses the following sparse warning:
lib/memregion.c:8:5: warning: symbol 'memregion_alloc' was not declared. Should it be static?
lib/memregion.c:14:6: warning: symbol 'memregion_free' was not declared. Should it be static?
Reported-by: Hulk Robot <hulkci@xxxxxxxxxx>
Signed-off-by: Jason Yan <yanaijie@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200921142852.875312-1-yanaijie@xxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
lib/memregion.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/memregion.c b/lib/memregion.c
index 77c85b5251da..be5cfa5a3b57 100644
--- a/lib/memregion.c
+++ b/lib/memregion.c
@@ -2,6 +2,7 @@
/* identifiers for device / performance-differentiated memory regions */
#include <linux/idr.h>
#include <linux/types.h>
+#include <linux/memregion.h>
static DEFINE_IDA(memregion_ids);
--
GitLab
>From a1cd6c2ae47ee10ff21e62475685d5b399e2ed4a Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:24 -0700
Subject: [PATCH 102/126] arch/x86/lib/usercopy_64.c: fix
__copy_user_flushcache() cache writeback
If we copy less than 8 bytes and if the destination crosses a cache
line, __copy_user_flushcache would invalidate only the first cache line.
This patch makes it invalidate the second cache line as well.
Fixes: 0aed55af88345b ("x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations")
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Dan Williams <dan.j.wiilliams@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/alpine.LRH.2.02.2009161451140.21915@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/lib/usercopy_64.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b0dfac3d3df7..1847e993ac63 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
*/
if (size < 8) {
if (!IS_ALIGNED(dest, 4) || size != 4)
- clean_cache_range(dst, 1);
+ clean_cache_range(dst, size);
} else {
if (!IS_ALIGNED(dest, 8)) {
dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
--
GitLab
>From c1d0da83358a2316d9be7f229f26126dbaa07468 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@xxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:28 -0700
Subject: [PATCH 103/126] mm: replace memmap_context by meminit_context
Patch series "mm: fix memory to node bad links in sysfs", v3.
Sometimes, firmware may expose interleaved memory layout like this:
Early memory node ranges
node 1: [mem 0x0000000000000000-0x000000011fffffff]
node 2: [mem 0x0000000120000000-0x000000014fffffff]
node 1: [mem 0x0000000150000000-0x00000001ffffffff]
node 0: [mem 0x0000000200000000-0x000000048fffffff]
node 2: [mem 0x0000000490000000-0x00000007ffffffff]
In that case, we can see memory blocks assigned to multiple nodes in
sysfs:
$ ls -l /sys/devices/system/memory/memory21
total 0
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2
-rw-r--r-- 1 root root 65536 Aug 24 05:27 online
-r--r--r-- 1 root root 65536 Aug 24 05:27 phys_device
-r--r--r-- 1 root root 65536 Aug 24 05:27 phys_index
drwxr-xr-x 2 root root 0 Aug 24 05:27 power
-r--r--r-- 1 root root 65536 Aug 24 05:27 removable
-rw-r--r-- 1 root root 65536 Aug 24 05:27 state
lrwxrwxrwx 1 root root 0 Aug 24 05:25 subsystem -> ../../../../bus/memory
-rw-r--r-- 1 root root 65536 Aug 24 05:25 uevent
-r--r--r-- 1 root root 65536 Aug 24 05:27 valid_zones
The same applies in the node's directory with a memory21 link in both
the node1 and node2's directory.
This is wrong but doesn't prevent the system to run. However when
later, one of these memory blocks is hot-unplugged and then hot-plugged,
the system is detecting an inconsistency in the sysfs layout and a
BUG_ON() is raised:
kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084!
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4
CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25
Call Trace:
add_memory_resource+0x23c/0x340 (unreliable)
__add_memory+0x5c/0xf0
dlpar_add_lmb+0x1b4/0x500
dlpar_memory+0x1f8/0xb80
handle_dlpar_errorlog+0xc0/0x190
dlpar_store+0x198/0x4a0
kobj_attr_store+0x30/0x50
sysfs_kf_write+0x64/0x90
kernfs_fop_write+0x1b0/0x290
vfs_write+0xe8/0x290
ksys_write+0xdc/0x130
system_call_exception+0x160/0x270
system_call_common+0xf0/0x27c
This has been seen on PowerPC LPAR.
The root cause of this issue is that when node's memory is registered,
the range used can overlap another node's range, thus the memory block
is registered to multiple nodes in sysfs.
There are two issues here:
(a) The sysfs memory and node's layouts are broken due to these
multiple links
(b) The link errors in link_mem_sections() should not lead to a system
panic.
To address (a) register_mem_sect_under_node should not rely on the
system state to detect whether the link operation is triggered by a hot
plug operation or not. This is addressed by the patches 1 and 2 of this
series.
Issue (b) will be addressed separately.
This patch (of 2):
The memmap_context enum is used to detect whether a memory operation is
due to a hot-add operation or happening at boot time.
Make it general to the hotplug operation and rename it as
meminit_context.
There is no functional change introduced by this patch
Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: "Rafael J . Wysocki" <rafael@xxxxxxxxxx>
Cc: Nathan Lynch <nathanl@xxxxxxxxxxxxx>
Cc: Scott Cheloha <cheloha@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200915094143.79181-1-ldufour@xxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/20200915132624.9723-1-ldufour@xxxxxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
arch/ia64/mm/init.c | 6 +++---
include/linux/mm.h | 2 +-
include/linux/mmzone.h | 11 ++++++++---
mm/memory_hotplug.c | 2 +-
mm/page_alloc.c | 10 +++++-----
5 files changed, 18 insertions(+), 13 deletions(-)
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 0b3fb4c7af29..8e7b8c6c576e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
if (map_start < map_end)
memmap_init_zone((unsigned long)(map_end - map_start),
args->nid, args->zone, page_to_pfn(map_start),
- MEMMAP_EARLY, NULL);
+ MEMINIT_EARLY, NULL);
return 0;
}
@@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
unsigned long start_pfn)
{
if (!vmem_map) {
- memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY,
- NULL);
+ memmap_init_zone(size, nid, zone, start_pfn,
+ MEMINIT_EARLY, NULL);
} else {
struct page *start;
struct memmap_init_callback_data args;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b2f370f0b420..48614513eb66 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2416,7 +2416,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
extern void set_dma_reserve(unsigned long new_dma_reserve);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
- enum memmap_context, struct vmem_altmap *);
+ enum meminit_context, struct vmem_altmap *);
extern void setup_per_zone_wmarks(void);
extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 8379432f4f2f..0f7a4ff4b059 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -824,10 +824,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order,
unsigned int alloc_flags);
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
unsigned long mark, int highest_zoneidx);
-enum memmap_context {
- MEMMAP_EARLY,
- MEMMAP_HOTPLUG,
+/*
+ * Memory initialization context, use to differentiate memory added by
+ * the platform statically or via memory hotplug interface.
+ */
+enum meminit_context {
+ MEMINIT_EARLY,
+ MEMINIT_HOTPLUG,
};
+
extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
unsigned long size);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b11a269e2356..345308a8bd15 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -729,7 +729,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
* are reserved so nobody should be touching them so we should be safe
*/
memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
- MEMMAP_HOTPLUG, altmap);
+ MEMINIT_HOTPLUG, altmap);
set_zone_contiguous(zone);
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fab5e97dc9ca..5661fa164f13 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5975,7 +5975,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
* done. Non-atomic initialization, single-pass.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
- unsigned long start_pfn, enum memmap_context context,
+ unsigned long start_pfn, enum meminit_context context,
struct vmem_altmap *altmap)
{
unsigned long pfn, end_pfn = start_pfn + size;
@@ -6007,7 +6007,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
- if (context == MEMMAP_EARLY) {
+ if (context == MEMINIT_EARLY) {
if (overlap_memmap_init(zone, &pfn))
continue;
if (defer_init(nid, pfn, end_pfn))
@@ -6016,7 +6016,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid);
- if (context == MEMMAP_HOTPLUG)
+ if (context == MEMINIT_HOTPLUG)
__SetPageReserved(page);
/*
@@ -6099,7 +6099,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
* check here not to call set_pageblock_migratetype() against
* pfn out of zone.
*
- * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+ * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
* because this is done early in section_activate()
*/
if (!(pfn & (pageblock_nr_pages - 1))) {
@@ -6137,7 +6137,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
if (end_pfn > start_pfn) {
size = end_pfn - start_pfn;
memmap_init_zone(size, nid, zone, start_pfn,
- MEMMAP_EARLY, NULL);
+ MEMINIT_EARLY, NULL);
}
}
}
--
GitLab
>From f85086f95fa36194eb0db5cd5c12e56801b98523 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@xxxxxxxxxxxxx>
Date: Fri, 25 Sep 2020 21:19:31 -0700
Subject: [PATCH 104/126] mm: don't rely on system state to detect hot-plug
operations
In register_mem_sect_under_node() the system_state's value is checked to
detect whether the call is made during boot time or during an hot-plug
operation. Unfortunately, that check against SYSTEM_BOOTING is wrong
because regular memory is registered at SYSTEM_SCHEDULING state. In
addition, memory hot-plug operation can be triggered at this system
state by the ACPI [1]. So checking against the system state is not
enough.
The consequence is that on system with interleaved node's ranges like this:
Early memory node ranges
node 1: [mem 0x0000000000000000-0x000000011fffffff]
node 2: [mem 0x0000000120000000-0x000000014fffffff]
node 1: [mem 0x0000000150000000-0x00000001ffffffff]
node 0: [mem 0x0000000200000000-0x000000048fffffff]
node 2: [mem 0x0000000490000000-0x00000007ffffffff]
This can be seen on PowerPC LPAR after multiple memory hot-plug and
hot-unplug operations are done. At the next reboot the node's memory
ranges can be interleaved and since the call to link_mem_sections() is
made in topology_init() while the system is in the SYSTEM_SCHEDULING
state, the node's id is not checked, and the sections registered to
multiple nodes:
$ ls -l /sys/devices/system/memory/memory21/node*
total 0
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node1 -> ../../node/node1
lrwxrwxrwx 1 root root 0 Aug 24 05:27 node2 -> ../../node/node2
In that case, the system is able to boot but if later one of theses
memory blocks is hot-unplugged and then hot-plugged, the sysfs
inconsistency is detected and this is triggering a BUG_ON():
kernel BUG at /Users/laurent/src/linux-ppc/mm/memory_hotplug.c:1084!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in: rpadlpar_io rpaphp pseries_rng rng_core vmx_crypto gf128mul binfmt_misc ip_tables x_tables xfs libcrc32c crc32c_vpmsum autofs4
CPU: 8 PID: 10256 Comm: drmgr Not tainted 5.9.0-rc1+ #25
Call Trace:
add_memory_resource+0x23c/0x340 (unreliable)
__add_memory+0x5c/0xf0
dlpar_add_lmb+0x1b4/0x500
dlpar_memory+0x1f8/0xb80
handle_dlpar_errorlog+0xc0/0x190
dlpar_store+0x198/0x4a0
kobj_attr_store+0x30/0x50
sysfs_kf_write+0x64/0x90
kernfs_fop_write+0x1b0/0x290
vfs_write+0xe8/0x290
ksys_write+0xdc/0x130
system_call_exception+0x160/0x270
system_call_common+0xf0/0x27c
This patch addresses the root cause by not relying on the system_state
value to detect whether the call is due to a hot-plug operation. An
extra parameter is added to link_mem_sections() detailing whether the
operation is due to a hot-plug operation.
[1] According to Oscar Salvador, using this qemu command line, ACPI
memory hotplug operations are raised at SYSTEM_SCHEDULING state:
$QEMU -enable-kvm -machine pc -smp 4,sockets=4,cores=1,threads=1 -cpu host -monitor pty \
-m size=$MEM,slots=255,maxmem=4294967296k \
-numa node,nodeid=0,cpus=0-3,mem=512 -numa node,nodeid=1,mem=512 \
-object memory-backend-ram,id=memdimm0,size=134217728 -device pc-dimm,node=0,memdev=memdimm0,id=dimm0,slot=0 \
-object memory-backend-ram,id=memdimm1,size=134217728 -device pc-dimm,node=0,memdev=memdimm1,id=dimm1,slot=1 \
-object memory-backend-ram,id=memdimm2,size=134217728 -device pc-dimm,node=0,memdev=memdimm2,id=dimm2,slot=2 \
-object memory-backend-ram,id=memdimm3,size=134217728 -device pc-dimm,node=0,memdev=memdimm3,id=dimm3,slot=3 \
-object memory-backend-ram,id=memdimm4,size=134217728 -device pc-dimm,node=1,memdev=memdimm4,id=dimm4,slot=4 \
-object memory-backend-ram,id=memdimm5,size=134217728 -device pc-dimm,node=1,memdev=memdimm5,id=dimm5,slot=5 \
-object memory-backend-ram,id=memdimm6,size=134217728 -device pc-dimm,node=1,memdev=memdimm6,id=dimm6,slot=6 \
Fixes: 4fbce633910e ("mm/memory_hotplug.c: make register_mem_sect_under_node() a callback of walk_memory_range()")
Signed-off-by: Laurent Dufour <ldufour@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
Cc: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Cc: Nathan Lynch <nathanl@xxxxxxxxxxxxx>
Cc: Scott Cheloha <cheloha@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200915094143.79181-3-ldufour@xxxxxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
drivers/base/node.c | 85 ++++++++++++++++++++++++++++----------------
include/linux/node.h | 11 +++---
mm/memory_hotplug.c | 3 +-
3 files changed, 64 insertions(+), 35 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..50af16e68d98 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
return pfn_to_nid(pfn);
}
+static int do_register_memory_block_under_node(int nid,
+ struct memory_block *mem_blk)
+{
+ int ret;
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node.
+ */
+ mem_blk->nid = nid;
+
+ ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+ &mem_blk->dev.kobj,
+ kobject_name(&mem_blk->dev.kobj));
+ if (ret)
+ return ret;
+
+ return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+ &node_devices[nid]->dev.kobj,
+ kobject_name(&node_devices[nid]->dev.kobj));
+}
+
/* register memory section under specified node if it spans that node */
-static int register_mem_sect_under_node(struct memory_block *mem_blk,
- void *arg)
+static int register_mem_block_under_node_early(struct memory_block *mem_blk,
+ void *arg)
{
unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
- int ret, nid = *(int *)arg;
+ int nid = *(int *)arg;
unsigned long pfn;
for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
@@ -785,38 +807,33 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
}
/*
- * We need to check if page belongs to nid only for the boot
- * case, during hotplug we know that all pages in the memory
- * block belong to the same node.
- */
- if (system_state == SYSTEM_BOOTING) {
- page_nid = get_nid_for_pfn(pfn);
- if (page_nid < 0)
- continue;
- if (page_nid != nid)
- continue;
- }
-
- /*
- * If this memory block spans multiple nodes, we only indicate
- * the last processed node.
+ * We need to check if page belongs to nid only at the boot
+ * case because node's ranges can be interleaved.
*/
- mem_blk->nid = nid;
-
- ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
- &mem_blk->dev.kobj,
- kobject_name(&mem_blk->dev.kobj));
- if (ret)
- return ret;
+ page_nid = get_nid_for_pfn(pfn);
+ if (page_nid < 0)
+ continue;
+ if (page_nid != nid)
+ continue;
- return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
- &node_devices[nid]->dev.kobj,
- kobject_name(&node_devices[nid]->dev.kobj));
+ return do_register_memory_block_under_node(nid, mem_blk);
}
/* mem section does not span the specified node */
return 0;
}
+/*
+ * During hotplug we know that all pages in the memory block belong to the same
+ * node.
+ */
+static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
+ void *arg)
+{
+ int nid = *(int *)arg;
+
+ return do_register_memory_block_under_node(nid, mem_blk);
+}
+
/*
* Unregister a memory block device under the node it spans. Memory blocks
* with multiple nodes cannot be offlined and therefore also never be removed.
@@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum meminit_context context)
{
+ walk_memory_blocks_func_t func;
+
+ if (context == MEMINIT_HOTPLUG)
+ func = register_mem_block_under_node_hotplug;
+ else
+ func = register_mem_block_under_node_early;
+
return walk_memory_blocks(PFN_PHYS(start_pfn),
PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
- register_mem_sect_under_node);
+ func);
}
#ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/node.h b/include/linux/node.h
index 4866f32a02d8..014ba3ab2efd 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,11 +99,13 @@ extern struct node *node_devices[];
typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn);
+int link_mem_sections(int nid, unsigned long start_pfn,
+ unsigned long end_pfn,
+ enum meminit_context context);
#else
static inline int link_mem_sections(int nid, unsigned long start_pfn,
- unsigned long end_pfn)
+ unsigned long end_pfn,
+ enum meminit_context context)
{
return 0;
}
@@ -128,7 +130,8 @@ static inline int register_one_node(int nid)
if (error)
return error;
/* link memory sections under this node */
- error = link_mem_sections(nid, start_pfn, end_pfn);
+ error = link_mem_sections(nid, start_pfn, end_pfn,
+ MEMINIT_EARLY);
}
return error;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 345308a8bd15..ce3e73e3a5c1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
}
/* link memory sections under this node.*/
- ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
+ ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+ MEMINIT_HOTPLUG);
BUG_ON(ret);
/* create new memmap entry */
--
GitLab
>From ce2684254bd4818ca3995c0d021fb62c4cf10a19 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@xxxxxxxxxx>
Date: Mon, 14 Sep 2020 23:32:15 -0700
Subject: [PATCH 105/126] mm: validate pmd after splitting
syzbot reported the following KASAN splat:
general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
CPU: 1 PID: 6826 Comm: syz-executor142 Not tainted 5.9.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__lock_acquire+0x84/0x2ae0 kernel/locking/lockdep.c:4296
Code: ff df 8a 04 30 84 c0 0f 85 e3 16 00 00 83 3d 56 58 35 08 00 0f 84 0e 17 00 00 83 3d 25 c7 f5 07 00 74 2c 4c 89 e8 48 c1 e8 03 <80> 3c 30 00 74 12 4c 89 ef e8 3e d1 5a 00 48 be 00 00 00 00 00 fc
RSP: 0018:ffffc90004b9f850 EFLAGS: 00010006
Call Trace:
lock_acquire+0x140/0x6f0 kernel/locking/lockdep.c:5006
__raw_spin_lock include/linux/spinlock_api_smp.h:142 [inline]
_raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:151
spin_lock include/linux/spinlock.h:354 [inline]
madvise_cold_or_pageout_pte_range+0x52f/0x25c0 mm/madvise.c:389
walk_pmd_range mm/pagewalk.c:89 [inline]
walk_pud_range mm/pagewalk.c:160 [inline]
walk_p4d_range mm/pagewalk.c:193 [inline]
walk_pgd_range mm/pagewalk.c:229 [inline]
__walk_page_range+0xe7b/0x1da0 mm/pagewalk.c:331
walk_page_range+0x2c3/0x5c0 mm/pagewalk.c:427
madvise_pageout_page_range mm/madvise.c:521 [inline]
madvise_pageout mm/madvise.c:557 [inline]
madvise_vma mm/madvise.c:946 [inline]
do_madvise+0x12d0/0x2090 mm/madvise.c:1145
__do_sys_madvise mm/madvise.c:1171 [inline]
__se_sys_madvise mm/madvise.c:1169 [inline]
__x64_sys_madvise+0x76/0x80 mm/madvise.c:1169
do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The backing vma was shmem.
In case of split page of file-backed THP, madvise zaps the pmd instead
of remapping of sub-pages. So we need to check pmd validity after
split.
Reported-by: syzbot+ecf80462cb7d5d552bc7@xxxxxxxxxxxxxxxxxxxxxxxxx
Fixes: 1a4e58cce84e ("mm: introduce MADV_PAGEOUT")
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/madvise.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/madvise.c b/mm/madvise.c
index d4aa5f776543..0e0d61003fc6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -381,9 +381,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
return 0;
}
+regular_page:
if (pmd_trans_unstable(pmd))
return 0;
-regular_page:
#endif
tlb_change_page_size(tlb, PAGE_SIZE);
orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
--
GitLab
>From 41dd876ad95312bf2c718704d098b9e8b8b3344d Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Sun, 27 Sep 2020 04:32:44 +0000
Subject: [PATCH 106/126] [redhat]
kernel-5.9.0-0.rc6.20200927gita1bffa48745a.17.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 5 +++++
redhat/marker | 2 +-
3 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index 350b1c0db268..7633b2faaba4 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 17
+RHEL_RELEASE = 18
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 5857c0547754..4af9953b8366 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,8 @@
+* Sun Sep 27 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200927gita1bffa48745a.17.test]
+- a1bffa48745a rebase
+- Updated changelog for the release based on 7c7ec3226f5f (Fedora Kernel Team)
+- Create Patchlist.changelog file (Don Zickus)
+
* Sat Sep 26 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200926git7c7ec3226f5f.17]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index 02e1e4b6abb0..f6cade62a796 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-7c7ec3226f5f
+a1bffa48745a
--
GitLab
>From b6510359a70347d2379ad38feafdf9ae31317e32 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Sun, 27 Sep 2020 04:37:24 +0000
Subject: [PATCH 107/126] Updated changelog for the release based on
a1bffa48745a
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 4af9953b8366..d1f557eef4df 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Sun Sep 27 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200927gita1bffa48745a.18]
+- Merge ark-patches
+
* Sun Sep 27 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200927gita1bffa48745a.17.test]
- a1bffa48745a rebase
- Updated changelog for the release based on 7c7ec3226f5f (Fedora Kernel Team)
--
GitLab
>From 008cfe4418b3dbda2ff820cdd7b1a5ce458ae444 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 18:25:57 -0400
Subject: [PATCH 108/126] mm: Introduce mm_struct.has_pinned
(Commit message majorly collected from Jason Gunthorpe)
Reduce the chance of false positive from page_maybe_dma_pinned() by
keeping track if the mm_struct has ever been used with pin_user_pages().
This allows cases that might drive up the page ref_count to avoid any
penalty from handling dma_pinned pages.
Future work is planned, to provide a more sophisticated solution, likely
to turn it into a real counter. For now, make it atomic_t but use it as
a boolean for simplicity.
Suggested-by: Jason Gunthorpe <jgg@xxxxxxxx>
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm_types.h | 10 ++++++++++
kernel/fork.c | 1 +
mm/gup.c | 6 ++++++
3 files changed, 17 insertions(+)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 496c3ff97cce..ed028af3cb19 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -436,6 +436,16 @@ struct mm_struct {
*/
atomic_t mm_count;
+ /**
+ * @has_pinned: Whether this mm has pinned any pages. This can
+ * be either replaced in the future by @pinned_vm when it
+ * becomes stable, or grow into a counter on its own. We're
+ * aggresive on this bit now - even if the pinned pages were
+ * unpinned later on, we'll still keep this bit set for the
+ * lifecycle of this mm just for simplicity.
+ */
+ atomic_t has_pinned;
+
#ifdef CONFIG_MMU
atomic_long_t pgtables_bytes; /* PTE page table pages */
#endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 49677d668de4..e65d8192d080 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
+ atomic_set(&mm->has_pinned, 0);
atomic64_set(&mm->pinned_vm, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
diff --git a/mm/gup.c b/mm/gup.c
index 578bf5bd8bf8..dfe781d2ad4c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1255,6 +1255,9 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
BUG_ON(*locked != 1);
}
+ if (flags & FOLL_PIN)
+ atomic_set(¤t->mm->has_pinned, 1);
+
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
* is to set FOLL_GET if the caller wants pages[] filled in (but has
@@ -2660,6 +2663,9 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
FOLL_FAST_ONLY)))
return -EINVAL;
+ if (gup_flags & FOLL_PIN)
+ atomic_set(¤t->mm->has_pinned, 1);
+
if (!(gup_flags & FOLL_FAST_ONLY))
might_lock_read(¤t->mm->mmap_lock);
--
GitLab
>From 7a4830c380f3a8b3425f6383deff58e65b2557b5 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 18:25:58 -0400
Subject: [PATCH 109/126] mm/fork: Pass new vma pointer into copy_page_range()
This prepares for the future work to trigger early cow on pinned pages
during fork().
No functional change intended.
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 2 +-
kernel/fork.c | 2 +-
mm/memory.c | 14 +++++++++-----
3 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 48614513eb66..16b799a0522c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1646,7 +1646,7 @@ struct mmu_notifier_range;
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
unsigned long end, unsigned long floor, unsigned long ceiling);
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma);
+ struct vm_area_struct *vma, struct vm_area_struct *new);
int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
struct mmu_notifier_range *range,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
diff --git a/kernel/fork.c b/kernel/fork.c
index e65d8192d080..da8d360fb032 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
- retval = copy_page_range(mm, oldmm, mpnt);
+ retval = copy_page_range(mm, oldmm, mpnt, tmp);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
diff --git a/mm/memory.c b/mm/memory.c
index f3eb55975902..d56178721452 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -819,6 +819,7 @@ copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
+ struct vm_area_struct *new,
unsigned long addr, unsigned long end)
{
pte_t *orig_src_pte, *orig_dst_pte;
@@ -889,6 +890,7 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
+ struct vm_area_struct *new,
unsigned long addr, unsigned long end)
{
pmd_t *src_pmd, *dst_pmd;
@@ -915,7 +917,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
if (pmd_none_or_clear_bad(src_pmd))
continue;
if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
- vma, addr, next))
+ vma, new, addr, next))
return -ENOMEM;
} while (dst_pmd++, src_pmd++, addr = next, addr != end);
return 0;
@@ -923,6 +925,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
+ struct vm_area_struct *new,
unsigned long addr, unsigned long end)
{
pud_t *src_pud, *dst_pud;
@@ -949,7 +952,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
if (pud_none_or_clear_bad(src_pud))
continue;
if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
- vma, addr, next))
+ vma, new, addr, next))
return -ENOMEM;
} while (dst_pud++, src_pud++, addr = next, addr != end);
return 0;
@@ -957,6 +960,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+ struct vm_area_struct *new,
unsigned long addr, unsigned long end)
{
p4d_t *src_p4d, *dst_p4d;
@@ -971,14 +975,14 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src
if (p4d_none_or_clear_bad(src_p4d))
continue;
if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
- vma, addr, next))
+ vma, new, addr, next))
return -ENOMEM;
} while (dst_p4d++, src_p4d++, addr = next, addr != end);
return 0;
}
int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
- struct vm_area_struct *vma)
+ struct vm_area_struct *vma, struct vm_area_struct *new)
{
pgd_t *src_pgd, *dst_pgd;
unsigned long next;
@@ -1033,7 +1037,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
if (pgd_none_or_clear_bad(src_pgd))
continue;
if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
- vma, addr, next))) {
+ vma, new, addr, next))) {
ret = -ENOMEM;
break;
}
--
GitLab
>From 70e806e4e645019102d0e09d4933654fb5fb58ce Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 18:25:59 -0400
Subject: [PATCH 110/126] mm: Do early cow for pinned pages during fork() for
ptes
This allows copy_pte_range() to do early cow if the pages were pinned on
the source mm.
Currently we don't have an accurate way to know whether a page is pinned
or not. The only thing we have is page_maybe_dma_pinned(). However
that's good enough for now. Especially, with the newly added
mm->has_pinned flag to make sure we won't affect processes that never
pinned any pages.
It would be easier if we can do GFP_KERNEL allocation within
copy_one_pte(). Unluckily, we can't because we're with the page table
locks held for both the parent and child processes. So the page
allocation needs to be done outside copy_one_pte().
Some trick is there in copy_present_pte(), majorly the wrprotect trick
to block concurrent fast-gup. Comments in the function should explain
better in place.
Oleg Nesterov reported a (probably harmless) bug during review that we
didn't reset entry.val properly in copy_pte_range() so that potentially
there's chance to call add_swap_count_continuation() multiple times on
the same swp entry. However that should be harmless since even if it
happens, the same function (add_swap_count_continuation()) will return
directly noticing that there're enough space for the swp counter. So
instead of a standalone stable patch, it is touched up in this patch
directly.
Link: https://lore.kernel.org/lkml/20200914143829.GA1424636@xxxxxxxxxx/
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory.c | 205 ++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 189 insertions(+), 16 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index d56178721452..fcfc4ca36eba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -773,15 +773,142 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
return 0;
}
-static inline void
+/*
+ * Copy a present and normal page if necessary.
+ *
+ * NOTE! The usual case is that this doesn't need to do
+ * anything, and can just return a positive value. That
+ * will let the caller know that it can just increase
+ * the page refcount and re-use the pte the traditional
+ * way.
+ *
+ * But _if_ we need to copy it because it needs to be
+ * pinned in the parent (and the child should get its own
+ * copy rather than just a reference to the same page),
+ * we'll do that here and return zero to let the caller
+ * know we're done.
+ *
+ * And if we need a pre-allocated page but don't yet have
+ * one, return a negative error to let the preallocation
+ * code know so that it can do so outside the page table
+ * lock.
+ */
+static inline int
+copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pte_t *dst_pte, pte_t *src_pte,
+ struct vm_area_struct *vma, struct vm_area_struct *new,
+ unsigned long addr, int *rss, struct page **prealloc,
+ pte_t pte, struct page *page)
+{
+ struct page *new_page;
+
+ if (!is_cow_mapping(vma->vm_flags))
+ return 1;
+
+ /*
+ * The trick starts.
+ *
+ * What we want to do is to check whether this page may
+ * have been pinned by the parent process. If so,
+ * instead of wrprotect the pte on both sides, we copy
+ * the page immediately so that we'll always guarantee
+ * the pinned page won't be randomly replaced in the
+ * future.
+ *
+ * To achieve this, we do the following:
+ *
+ * 1. Write-protect the pte if it's writable. This is
+ * to protect concurrent write fast-gup with
+ * FOLL_PIN, so that we'll fail the fast-gup with
+ * the write bit removed.
+ *
+ * 2. Check page_maybe_dma_pinned() to see whether this
+ * page may have been pinned.
+ *
+ * The order of these steps is important to serialize
+ * against the fast-gup code (gup_pte_range()) on the
+ * pte check and try_grab_compound_head(), so that
+ * we'll make sure either we'll capture that fast-gup
+ * so we'll copy the pinned page here, or we'll fail
+ * that fast-gup.
+ *
+ * NOTE! Even if we don't end up copying the page,
+ * we won't undo this wrprotect(), because the normal
+ * reference copy will need it anyway.
+ */
+ if (pte_write(pte))
+ ptep_set_wrprotect(src_mm, addr, src_pte);
+
+ /*
+ * These are the "normally we can just copy by reference"
+ * checks.
+ */
+ if (likely(!atomic_read(&src_mm->has_pinned)))
+ return 1;
+ if (likely(!page_maybe_dma_pinned(page)))
+ return 1;
+
+ /*
+ * Uhhuh. It looks like the page might be a pinned page,
+ * and we actually need to copy it. Now we can set the
+ * source pte back to being writable.
+ */
+ if (pte_write(pte))
+ set_pte_at(src_mm, addr, src_pte, pte);
+
+ new_page = *prealloc;
+ if (!new_page)
+ return -EAGAIN;
+
+ /*
+ * We have a prealloc page, all good! Take it
+ * over and copy the page & arm it.
+ */
+ *prealloc = NULL;
+ copy_user_highpage(new_page, page, addr, vma);
+ __SetPageUptodate(new_page);
+ page_add_new_anon_rmap(new_page, new, addr, false);
+ lru_cache_add_inactive_or_unevictable(new_page, new);
+ rss[mm_counter(new_page)]++;
+
+ /* All done, just insert the new page copy in the child */
+ pte = mk_pte(new_page, new->vm_page_prot);
+ pte = maybe_mkwrite(pte_mkdirty(pte), new);
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return 0;
+}
+
+/*
+ * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page
+ * is required to copy this pte.
+ */
+static inline int
copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
- unsigned long addr, int *rss)
+ struct vm_area_struct *new,
+ unsigned long addr, int *rss, struct page **prealloc)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
+ page = vm_normal_page(vma, addr, pte);
+ if (page) {
+ int retval;
+
+ retval = copy_present_page(dst_mm, src_mm,
+ dst_pte, src_pte,
+ vma, new,
+ addr, rss, prealloc,
+ pte, page);
+ if (retval <= 0)
+ return retval;
+
+ get_page(page);
+ page_dup_rmap(page, false);
+ rss[mm_counter(page)]++;
+ }
+
/*
* If it's a COW mapping, write protect it both
* in the parent and the child
@@ -807,14 +934,27 @@ copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
if (!(vm_flags & VM_UFFD_WP))
pte = pte_clear_uffd_wp(pte);
- page = vm_normal_page(vma, addr, pte);
- if (page) {
- get_page(page);
- page_dup_rmap(page, false);
- rss[mm_counter(page)]++;
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return 0;
+}
+
+static inline struct page *
+page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct page *new_page;
+
+ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr);
+ if (!new_page)
+ return NULL;
+
+ if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) {
+ put_page(new_page);
+ return NULL;
}
+ cgroup_throttle_swaprate(new_page, GFP_KERNEL);
- set_pte_at(dst_mm, addr, dst_pte, pte);
+ return new_page;
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
@@ -825,16 +965,20 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *orig_src_pte, *orig_dst_pte;
pte_t *src_pte, *dst_pte;
spinlock_t *src_ptl, *dst_ptl;
- int progress = 0;
+ int progress, ret = 0;
int rss[NR_MM_COUNTERS];
swp_entry_t entry = (swp_entry_t){0};
+ struct page *prealloc = NULL;
again:
+ progress = 0;
init_rss_vec(rss);
dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
- if (!dst_pte)
- return -ENOMEM;
+ if (!dst_pte) {
+ ret = -ENOMEM;
+ goto out;
+ }
src_pte = pte_offset_map(src_pmd, addr);
src_ptl = pte_lockptr(src_mm, src_pmd);
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -866,8 +1010,25 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
progress += 8;
continue;
}
- copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
- vma, addr, rss);
+ /* copy_present_pte() will clear `*prealloc' if consumed */
+ ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
+ vma, new, addr, rss, &prealloc);
+ /*
+ * If we need a pre-allocated page for this pte, drop the
+ * locks, allocate, and try again.
+ */
+ if (unlikely(ret == -EAGAIN))
+ break;
+ if (unlikely(prealloc)) {
+ /*
+ * pre-alloc page cannot be reused by next time so as
+ * to strictly follow mempolicy (e.g., alloc_page_vma()
+ * will allocate page according to address). This
+ * could only happen if one pinned pte changed.
+ */
+ put_page(prealloc);
+ prealloc = NULL;
+ }
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
@@ -879,13 +1040,25 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
cond_resched();
if (entry.val) {
- if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
+ if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ entry.val = 0;
+ } else if (ret) {
+ WARN_ON_ONCE(ret != -EAGAIN);
+ prealloc = page_copy_prealloc(src_mm, vma, addr);
+ if (!prealloc)
return -ENOMEM;
- progress = 0;
+ /* We've captured and resolved the error. Reset, try again. */
+ ret = 0;
}
if (addr != end)
goto again;
- return 0;
+out:
+ if (unlikely(prealloc))
+ put_page(prealloc);
+ return ret;
}
static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
--
GitLab
>From d042035eaf5f9009ad927dc4d3ce848381ccdeed Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 18:26:00 -0400
Subject: [PATCH 111/126] mm/thp: Split huge pmds/puds if they're pinned when
fork()
Pinned pages shouldn't be write-protected when fork() happens, because
follow up copy-on-write on these pages could cause the pinned pages to
be replaced by random newly allocated pages.
For huge PMDs, we split the huge pmd if pinning is detected. So that
future handling will be done by the PTE level (with our latest changes,
each of the small pages will be copied). We can achieve this by let
copy_huge_pmd() return -EAGAIN for pinned pages, so that we'll
fallthrough in copy_pmd_range() and finally land the next
copy_pte_range() call.
Huge PUDs will be even more special - so far it does not support
anonymous pages. But it can actually be done the same as the huge PMDs
even if the split huge PUDs means to erase the PUD entries. It'll
guarantee the follow up fault ins will remap the same pages in either
parent/child later.
This might not be the most efficient way, but it should be easy and
clean enough. It should be fine, since we're tackling with a very rare
case just to make sure userspaces that pinned some thps will still work
even without MADV_DONTFORK and after they fork()ed.
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index faadc449cca5..da397779a6d4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1074,6 +1074,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
src_page = pmd_page(pmd);
VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
+
+ /*
+ * If this page is a potentially pinned page, split and retry the fault
+ * with smaller page size. Normally this should not happen because the
+ * userspace should use MADV_DONTFORK upon pinned regions. This is a
+ * best effort that the pinned pages won't be replaced by another
+ * random page during the coming copy-on-write.
+ */
+ if (unlikely(is_cow_mapping(vma->vm_flags) &&
+ atomic_read(&src_mm->has_pinned) &&
+ page_maybe_dma_pinned(src_page))) {
+ pte_free(dst_mm, pgtable);
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ __split_huge_pmd(vma, src_pmd, addr, false, NULL);
+ return -EAGAIN;
+ }
+
get_page(src_page);
page_dup_rmap(src_page, true);
add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
@@ -1177,6 +1195,16 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
/* No huge zero pud yet */
}
+ /* Please refer to comments in copy_huge_pmd() */
+ if (unlikely(is_cow_mapping(vma->vm_flags) &&
+ atomic_read(&src_mm->has_pinned) &&
+ page_maybe_dma_pinned(pud_page(pud)))) {
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ __split_huge_pud(vma, src_pud, addr);
+ return -EAGAIN;
+ }
+
pudp_set_wrprotect(src_mm, addr, src_pud);
pud = pud_mkold(pud_wrprotect(pud));
set_pud_at(dst_mm, addr, dst_pud, pud);
--
GitLab
>From a1b8638ba1320e6684aa98233c15255eb803fac7 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Sun, 27 Sep 2020 14:38:10 -0700
Subject: [PATCH 112/126] Linux 5.9-rc7
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index 2b66d3398878..992d24467ca0 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
--
GitLab
>From 91870415d7072513052a21fdb9b0f1393b5ba89f Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Mon, 28 Sep 2020 04:25:58 +0000
Subject: [PATCH 113/126] [redhat] kernel-5.9.0-0.rc7.18.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 4 ++++
redhat/marker | 2 +-
3 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index 7633b2faaba4..85efc4f45c49 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 18
+RHEL_RELEASE = 19
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index d1f557eef4df..0776dd2a5a09 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,7 @@
+* Mon Sep 28 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.18.test]
+- v5.9-rc7 rebase
+- Updated changelog for the release based on a1bffa48745a (Fedora Kernel Team)
+
* Sun Sep 27 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc6.20200927gita1bffa48745a.18]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index f6cade62a796..ab4ad51a233a 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-a1bffa48745a
+v5.9-rc7
--
GitLab
>From ec835ea8eae96eb831b3cc0529e53bdfa28058f8 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Mon, 28 Sep 2020 04:30:46 +0000
Subject: [PATCH 114/126] Updated changelog for the release based on v5.9-rc7
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 0776dd2a5a09..9b005b3fea3d 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Mon Sep 28 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.19]
+- Merge ark-patches
+
* Mon Sep 28 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.18.test]
- v5.9-rc7 rebase
- Updated changelog for the release based on a1bffa48745a (Fedora Kernel Team)
--
GitLab
>From 6a7548305a04ae0cd9e9f062c050f265d4bf2d2e Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@xxxxxxxxxx>
Date: Thu, 24 Sep 2020 10:26:42 +0200
Subject: [PATCH 115/126] ARM: dts: bcm2835: Change firmware compatible from
simple-bus to simple-mfd
The current binding for the RPi firmware uses the simple-bus compatible as
a fallback to benefit from its automatic probing of child nodes.
However, simple-bus also comes with some constraints, like having the ranges,
our case.
Let's switch to simple-mfd that provides the same probing logic without
those constraints.
Signed-off-by: Maxime Ripard <maxime@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200924082642.18144-1-maxime@xxxxxxxxxx
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
.../bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml | 4 ++--
arch/arm/boot/dts/bcm2835-rpi.dtsi | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
index 17e4f20c8d39..6834f5e8df5f 100644
--- a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
@@ -23,7 +23,7 @@ properties:
compatible:
items:
- const: raspberrypi,bcm2835-firmware
- - const: simple-bus
+ - const: simple-mfd
mboxes:
$ref: '/schemas/types.yaml#/definitions/phandle'
@@ -57,7 +57,7 @@ required:
examples:
- |
firmware {
- compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+ compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
mboxes = <&mailbox>;
firmware_clocks: clocks {
diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi
index f7ae5a4530b8..d94357b21f7e 100644
--- a/arch/arm/boot/dts/bcm2835-rpi.dtsi
+++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi
@@ -13,7 +13,7 @@ act {
soc {
firmware: firmware {
- compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+ compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
#address-cells = <1>;
#size-cells = <1>;
--
GitLab
>From 5cada726c70e5d5f034e41b913d8bfb7628f2dbe Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@xxxxxxxxxx>
Date: Mon, 28 Sep 2020 08:58:54 -0400
Subject: [PATCH 116/126] Re-enable CONFIG_IR_SERIAL on Fedora
The serial IR driver is needed for Fedora media-centers.
Re-enable the serial IR module for Fedora.
Suggested-by: Craig Gelowitz <craig@xxxxxxxxxxxx>
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: jbastian@xxxxxxxxxx
---
redhat/configs/fedora/generic/CONFIG_IR_SERIAL | 1 +
1 file changed, 1 insertion(+)
create mode 100644 redhat/configs/fedora/generic/CONFIG_IR_SERIAL
diff --git a/redhat/configs/fedora/generic/CONFIG_IR_SERIAL b/redhat/configs/fedora/generic/CONFIG_IR_SERIAL
new file mode 100644
index 000000000000..53c7f1d81e8e
--- /dev/null
+++ b/redhat/configs/fedora/generic/CONFIG_IR_SERIAL
@@ -0,0 +1 @@
+CONFIG_IR_SERIAL=m
--
GitLab
>From 749543316e90704b0d6ea769cd3bda384e090ee2 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@xxxxxxxxxx>
Date: Fri, 25 Sep 2020 19:18:14 -0400
Subject: [PATCH 117/126] Separate merge-upstream and release stages
Now that the merge-upstream stage is separated and working, let's
remove it from the release stage. These scripts are already excuted by the
'merge-upstream' stage. This changes just removes the duplication. Trivial
change.
Signed-off-by: Don Zickus <dzickus@xxxxxxxxxx>
---
redhat/scripts/ci/ark-create-release.sh | 3 ---
1 file changed, 3 deletions(-)
diff --git a/redhat/scripts/ci/ark-create-release.sh b/redhat/scripts/ci/ark-create-release.sh
index 0d4cfd9181e5..aeb3696f5caf 100755
--- a/redhat/scripts/ci/ark-create-release.sh
+++ b/redhat/scripts/ci/ark-create-release.sh
@@ -33,9 +33,6 @@ if [ -n "$BASE_RELEASE" ]; then
fi
git checkout os-build
-./redhat/scripts/ci/ark-rebase-patches.sh "$UPSTREAM_REF" "$PROJECT_ID"
-git checkout os-build
-./redhat/scripts/ci/ark-update-configs.sh "$UPSTREAM_REF" "$PROJECT_ID"
make dist-release
if git tag -v "$UPSTREAM_REF" > /dev/null 2>&1; then
--
GitLab
>From a4d63c3732f1a0c91abcf5b7f32b4ef7dcd82025 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@xxxxxxxxx>
Date: Mon, 28 Sep 2020 12:35:07 +0200
Subject: [PATCH 118/126] mm: do not rely on mm == current->mm in
__get_user_pages_locked
It seems likely this block was pasted from internal_get_user_pages_fast,
which is not passed an mm struct and therefore uses current's. But
__get_user_pages_locked is passed an explicit mm, and current->mm is not
always valid. This was hit when being called from i915, which uses:
pin_user_pages_remote->
__get_user_pages_remote->
__gup_longterm_locked->
__get_user_pages_locked
Before, this would lead to an OOPS:
BUG: kernel NULL pointer dereference, address: 0000000000000064
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
CPU: 10 PID: 1431 Comm: kworker/u33:1 Tainted: P S U O 5.9.0-rc7+ #140
Hardware name: LENOVO 20QTCTO1WW/20QTCTO1WW, BIOS N2OET47W (1.34 ) 08/06/2020
Workqueue: i915-userptr-acquire __i915_gem_userptr_get_pages_worker [i915]
RIP: 0010:__get_user_pages_remote+0xd7/0x310
Call Trace:
__i915_gem_userptr_get_pages_worker+0xc8/0x260 [i915]
process_one_work+0x1ca/0x390
worker_thread+0x48/0x3c0
kthread+0x114/0x130
ret_from_fork+0x1f/0x30
CR2: 0000000000000064
This commit fixes the problem by using the mm pointer passed to the
function rather than the bogus one in current.
Fixes: 008cfe4418b3 ("mm: Introduce mm_struct.has_pinned")
Tested-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Reported-by: Harald Arnesen <harald@xxxxxxxxxxx>
Reviewed-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Reviewed-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/gup.c b/mm/gup.c
index dfe781d2ad4c..e869c634cc9a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1256,7 +1256,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
}
if (flags & FOLL_PIN)
- atomic_set(¤t->mm->has_pinned, 1);
+ atomic_set(&mm->has_pinned, 1);
/*
* FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
--
GitLab
>From 9949189a72d0eeb2d308a41ed6f941bc0a254271 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@xxxxxxxxxx>
Date: Thu, 17 Sep 2020 08:55:36 -0400
Subject: [PATCH 119/126] RHMAINTAINERS: Reassign FIREWIRE
Reassign FIREWIRE to Jarod.
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: jarod@xxxxxxxxxx
---
redhat/rhdocs/MAINTAINERS/RHMAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS b/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
index a7bf575a4d1d..2ee6d6986ee6 100644
--- a/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
+++ b/redhat/rhdocs/MAINTAINERS/RHMAINTAINERS
@@ -637,7 +637,7 @@ F: include/linux/dax.h
F: include/trace/events/fs_dax.h
FIREWIRE SUBSYSTEM
-L: kernel-patches@xxxxxxxxxx
+M: Jarod Wilson <jarod@xxxxxxxxxx>
S: Maintained
F: drivers/firewire/
F: include/linux/firewire*.h
--
GitLab
>From d09f5fc4b844b59c74cfc6a662615bb2575b0dc3 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Tue, 29 Sep 2020 04:26:27 +0000
Subject: [PATCH 120/126] [redhat] kernel-5.9.0-0.rc7.19.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 5 +++++
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index 85efc4f45c49..07fdee0572fb 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 19
+RHEL_RELEASE = 20
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 9b005b3fea3d..2af5ed2c10e1 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,8 @@
+* Tue Sep 29 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.19.test]
+- Separate merge-upstream and release stages (Don Zickus)
+- Re-enable CONFIG_IR_SERIAL on Fedora (Prarit Bhargava)
+- Updated changelog for the release based on v5.9-rc7 (Fedora Kernel Team)
+
* Mon Sep 28 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.19]
- Merge ark-patches
--
GitLab
>From ed718bcee0fd3c084f8c5f20af02fefff64cc912 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Tue, 29 Sep 2020 04:31:18 +0000
Subject: [PATCH 121/126] Updated changelog for the release based on v5.9-rc7
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index 2af5ed2c10e1..cadeeacd8bfb 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Tue Sep 29 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.20]
+- Merge ark-patches
+
* Tue Sep 29 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.19.test]
- Separate merge-upstream and release stages (Don Zickus)
- Re-enable CONFIG_IR_SERIAL on Fedora (Prarit Bhargava)
--
GitLab
>From 64ff609b551914d8c2c51d828920f2ffc5237de7 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@xxxxxxxxxx>
Date: Mon, 28 Sep 2020 10:22:56 -0500
Subject: [PATCH 122/126] dt-bindings: Fix 'reg' size issues in zynqmp examples
The default sizes in examples for 'reg' are 1 cell each. Fix the
incorrect sizes in zynqmp examples:
Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.example.dt.yaml: example-0: dma-controller@fd4c0000:reg:0: [0, 4249616384, 0, 4096] is too long
From schema: /usr/local/lib/python3.8/dist-packages/dtschema/schemas/reg.yaml
Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.example.dt.yaml: example-0: display@fd4a0000:reg:0: [0, 4249485312, 0, 4096] is too long
From schema: /usr/local/lib/python3.8/dist-packages/dtschema/schemas/reg.yaml
Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.example.dt.yaml: example-0: display@fd4a0000:reg:1: [0, 4249526272, 0, 4096] is too long
From schema: /usr/local/lib/python3.8/dist-packages/dtschema/schemas/reg.yaml
Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.example.dt.yaml: example-0: display@fd4a0000:reg:2: [0, 4249530368, 0, 4096] is too long
From schema: /usr/local/lib/python3.8/dist-packages/dtschema/schemas/reg.yaml
Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.example.dt.yaml: example-0: display@fd4a0000:reg:3: [0, 4249534464, 0, 4096] is too long
From schema: /usr/local/lib/python3.8/dist-packages/dtschema/schemas/reg.yaml
Cc: Hyun Kwon <hyun.kwon@xxxxxxxxxx>
Cc: Laurent Pinchart <laurent.pinchart@xxxxxxxxxxxxxxxx>
Cc: Vinod Koul <vkoul@xxxxxxxxxx>
Cc: dri-devel@xxxxxxxxxxxxxxxxxxxxx
Cc: dmaengine@xxxxxxxxxxxxxxx
Acked-by: Michal Simek <michal.simek@xxxxxxxxxx>
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
.../bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml | 8 ++++----
.../devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml | 2 +-
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
index 52a939cade3b..7b9d468c3e52 100644
--- a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
+++ b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
@@ -145,10 +145,10 @@ examples:
display@fd4a0000 {
compatible = "xlnx,zynqmp-dpsub-1.7";
- reg = <0x0 0xfd4a0000 0x0 0x1000>,
- <0x0 0xfd4aa000 0x0 0x1000>,
- <0x0 0xfd4ab000 0x0 0x1000>,
- <0x0 0xfd4ac000 0x0 0x1000>;
+ reg = <0xfd4a0000 0x1000>,
+ <0xfd4aa000 0x1000>,
+ <0xfd4ab000 0x1000>,
+ <0xfd4ac000 0x1000>;
reg-names = "dp", "blend", "av_buf", "aud";
interrupts = <0 119 4>;
interrupt-parent = <&gic>;
diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
index 5de510f8c88c..2a595b18ff6c 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
+++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
@@ -57,7 +57,7 @@ examples:
dma: dma-controller@fd4c0000 {
compatible = "xlnx,zynqmp-dpdma";
- reg = <0x0 0xfd4c0000 0x0 0x1000>;
+ reg = <0xfd4c0000 0x1000>;
interrupts = <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
clocks = <&dpdma_clk>;
--
GitLab
>From efe84d408bf41975db8506d3a1cc02e794e2309c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@xxxxxxxxxxxxxx>
Date: Sat, 19 Sep 2020 16:39:22 +0200
Subject: [PATCH 123/126] scripts/dtc: only append to HOST_EXTRACFLAGS instead
of overwriting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When building with
$ HOST_EXTRACFLAGS=-g make
the expectation is that host tools are built with debug informations.
This however doesn't happen if the Makefile assigns a new value to the
HOST_EXTRACFLAGS instead of appending to it. So use += instead of := for
the first assignment.
Fixes: e3fd9b5384f3 ("scripts/dtc: consolidate include path options in Makefile")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@xxxxxxxxxxxxxx>
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
scripts/dtc/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile
index a698ece43fff..4852bf44e913 100644
--- a/scripts/dtc/Makefile
+++ b/scripts/dtc/Makefile
@@ -9,7 +9,7 @@ dtc-objs := dtc.o flattree.o fstree.o data.o livetree.o treesource.o \
dtc-objs += dtc-lexer.lex.o dtc-parser.tab.o
# Source files need to get at the userspace version of libfdt_env.h to compile
-HOST_EXTRACFLAGS := -I $(srctree)/$(src)/libfdt
+HOST_EXTRACFLAGS += -I $(srctree)/$(src)/libfdt
ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),)
ifneq ($(CHECK_DT_BINDING)$(CHECK_DTBS),)
--
GitLab
>From 90fb702791bf99b959006972e8ee7bb4609f441b Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Date: Tue, 29 Sep 2020 17:18:34 -0700
Subject: [PATCH 124/126] autofs: use __kernel_write() for the autofs pipe
writing
autofs got broken in some configurations by commit 13c164b1a186
("autofs: switch to kernel_write") because there is now an extra LSM
permission check done by security_file_permission() in rw_verify_area().
autofs is one if the few places that really does want the much more
limited __kernel_write(), because the write is an internal kernel one
that shouldn't do any user permission checks (it also doesn't need the
file_start_write/file_end_write logic, since it's just a pipe).
There are a couple of other cases like that - accounting, core dumping,
and splice - but autofs stands out because it can be built as a module.
As a result, we need to export this internal __kernel_write() function
again.
We really don't want any other module to use this, but we don't have a
"EXPORT_SYMBOL_FOR_AUTOFS_ONLY()". But we can mark it GPL-only to at
least approximate that "internal use only" for licensing.
While in this area, make autofs pass in NULL for the file position
pointer, since it's always a pipe, and we now use a NULL file pointer
for streaming file descriptors (see file_ppos() and commit 438ab720c675:
"vfs: pass ppos=NULL to .read()/.write() of FMODE_STREAM files")
This effectively reverts commits 9db977522449 ("fs: unexport
__kernel_write") and 13c164b1a186 ("autofs: switch to kernel_write").
Fixes: 13c164b1a186 ("autofs: switch to kernel_write")
Reported-by: Ondrej Mosnacek <omosnace@xxxxxxxxxx>
Acked-by: Christoph Hellwig <hch@xxxxxx>
Acked-by: Acked-by: Ian Kent <raven@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
fs/autofs/waitq.c | 2 +-
fs/read_write.c | 8 ++++++++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index 74c886f7c51c..5ced859dac53 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi,
mutex_lock(&sbi->pipe_mutex);
while (bytes) {
- wr = kernel_write(file, data, bytes, &file->f_pos);
+ wr = __kernel_write(file, data, bytes, NULL);
if (wr <= 0)
break;
data += wr;
diff --git a/fs/read_write.c b/fs/read_write.c
index 5db58b8c78d0..d3428189f36b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -538,6 +538,14 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
inc_syscw(current);
return ret;
}
+/*
+ * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()",
+ * but autofs is one of the few internal kernel users that actually
+ * wants this _and_ can be built as a module. So we need to export
+ * this symbol for autofs, even though it really isn't appropriate
+ * for any other kernel modules.
+ */
+EXPORT_SYMBOL_GPL(__kernel_write);
ssize_t kernel_write(struct file *file, const void *buf, size_t count,
loff_t *pos)
--
GitLab
>From a47f675eac24fa68106356972d94dc759f9fecc8 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Wed, 30 Sep 2020 04:26:38 +0000
Subject: [PATCH 125/126] [redhat]
kernel-5.9.0-0.rc7.20200930gitfb0155a09b02.20.test
Signed-off-by: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
---
Makefile.rhelver | 2 +-
redhat/kernel.changelog-8.99 | 3 +++
redhat/marker | 2 +-
3 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/Makefile.rhelver b/Makefile.rhelver
index 07fdee0572fb..165fd682816c 100644
--- a/Makefile.rhelver
+++ b/Makefile.rhelver
@@ -12,7 +12,7 @@ RHEL_MINOR = 99
#
# Use this spot to avoid future merge conflicts.
# Do not trim this comment.
-RHEL_RELEASE = 20
+RHEL_RELEASE = 21
#
# Early y+1 numbering
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index cadeeacd8bfb..b875c35aff21 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Wed Sep 30 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.20200930gitfb0155a09b02.20.test]
+- fb0155a09b02 rebase
+
* Tue Sep 29 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.20]
- Merge ark-patches
diff --git a/redhat/marker b/redhat/marker
index ab4ad51a233a..234a5040e110 100644
--- a/redhat/marker
+++ b/redhat/marker
@@ -1 +1 @@
-v5.9-rc7
+fb0155a09b02
--
GitLab
>From 97492496b430e0293e815028719121eff83c7038 Mon Sep 17 00:00:00 2001
From: Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx>
Date: Wed, 30 Sep 2020 04:31:29 +0000
Subject: [PATCH 126/126] Updated changelog for the release based on
fb0155a09b02
---
redhat/kernel.changelog-8.99 | 3 +++
1 file changed, 3 insertions(+)
diff --git a/redhat/kernel.changelog-8.99 b/redhat/kernel.changelog-8.99
index b875c35aff21..528244659c85 100644
--- a/redhat/kernel.changelog-8.99
+++ b/redhat/kernel.changelog-8.99
@@ -1,3 +1,6 @@
+* Wed Sep 30 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.20200930gitfb0155a09b02.21]
+- Merge ark-patches
+
* Wed Sep 30 2020 Fedora Kernel Team <kernel-team@xxxxxxxxxxxxxxxxx> [5.9.0-0.rc7.20200930gitfb0155a09b02.20.test]
- fb0155a09b02 rebase
--
GitLab
_______________________________________________
kernel mailing list -- kernel@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to kernel-leave@xxxxxxxxxxxxxxxxxxxxxxx
Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: https://lists.fedoraproject.org/archives/list/kernel@xxxxxxxxxxxxxxxxxxxxxxx
