summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.mailmap2
-rw-r--r--Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml2
-rw-r--r--Documentation/devicetree/bindings/input/gpio-keys.yaml2
-rw-r--r--Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml14
-rw-r--r--Documentation/devicetree/bindings/net/ethernet-phy.yaml8
-rw-r--r--Documentation/devicetree/bindings/power/supply/bq25980.yaml2
-rw-r--r--MAINTAINERS2
-rw-r--r--Makefile10
-rw-r--r--block/fops.c3
-rw-r--r--block/ioprio.c3
-rw-r--r--drivers/clk/imx/clk-imx8qxp-lpcg.c2
-rw-r--r--drivers/clk/imx/clk-imx8qxp.c2
-rw-r--r--drivers/clk/qcom/clk-alpha-pll.c9
-rw-r--r--drivers/clk/qcom/clk-regmap-mux.c2
-rw-r--r--drivers/clk/qcom/common.c12
-rw-r--r--drivers/clk/qcom/common.h2
-rw-r--r--drivers/clk/qcom/gcc-sm6125.c4
-rw-r--r--drivers/clk/versatile/clk-icst.c2
-rw-r--r--drivers/i2c/busses/i2c-mpc.c2
-rw-r--r--drivers/i2c/busses/i2c-virtio.c32
-rw-r--r--drivers/md/md.c4
-rw-r--r--drivers/nvme/host/core.c23
-rw-r--r--drivers/nvme/host/multipath.c3
-rw-r--r--drivers/nvme/host/nvme.h2
-rw-r--r--drivers/nvme/host/zns.c5
-rw-r--r--drivers/nvme/target/tcp.c9
-rw-r--r--drivers/of/irq.c27
-rw-r--r--fs/io-wq.c29
-rw-r--r--fs/io_uring.c6
-rw-r--r--include/linux/delay.h14
-rw-r--r--include/uapi/linux/resource.h13
-rw-r--r--kernel/time/timer.c16
-rw-r--r--mm/backing-dev.c7
-rw-r--r--mm/damon/core.c20
-rw-r--r--mm/damon/dbgfs.c4
-rw-r--r--mm/damon/vaddr-test.h79
-rw-r--r--mm/damon/vaddr.c1
-rw-r--r--mm/filemap.c2
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/memcontrol.c106
-rw-r--r--mm/slub.c15
-rw-r--r--tools/testing/selftests/damon/.gitignore2
-rw-r--r--tools/testing/selftests/damon/Makefile7
-rw-r--r--tools/testing/selftests/damon/_debugfs_common.sh52
-rw-r--r--tools/testing/selftests/damon/debugfs_attrs.sh73
-rw-r--r--tools/testing/selftests/damon/debugfs_empty_targets.sh13
-rw-r--r--tools/testing/selftests/damon/debugfs_huge_count_read_write.sh22
-rw-r--r--tools/testing/selftests/damon/debugfs_schemes.sh19
-rw-r--r--tools/testing/selftests/damon/debugfs_target_ids.sh19
-rw-r--r--tools/testing/selftests/damon/huge_count_read_write.c39
50 files changed, 474 insertions, 276 deletions
diff --git a/.mailmap b/.mailmap
index 6277bb27b4bf..b344067e0acb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -126,6 +126,8 @@ Greg Kroah-Hartman <gregkh@suse.de>
Greg Kroah-Hartman <greg@kroah.com>
Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com>
+Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
diff --git a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
index c65921e66dc1..81c87295912c 100644
--- a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
@@ -136,7 +136,7 @@ examples:
samsung,syscon-phandle = <&pmu_system_controller>;
/* NTC thermistor is a hwmon device */
- ncp15wb473 {
+ thermistor {
compatible = "murata,ncp15wb473";
pullup-uv = <1800000>;
pullup-ohm = <47000>;
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index 060a309ff8e7..dbe7ecc19ccb 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -142,7 +142,7 @@ examples:
down {
label = "GPIO Key DOWN";
linux,code = <108>;
- interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+ interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
};
};
diff --git a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
index 877183cf4278..1ef849dc74d7 100644
--- a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
+++ b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
@@ -79,6 +79,8 @@ properties:
properties:
data-lanes:
+ description:
+ Note that 'fsl,imx7-mipi-csi2' only supports up to 2 data lines.
items:
minItems: 1
maxItems: 4
@@ -91,18 +93,6 @@ properties:
required:
- data-lanes
- allOf:
- - if:
- properties:
- compatible:
- contains:
- const: fsl,imx7-mipi-csi2
- then:
- properties:
- data-lanes:
- items:
- maxItems: 2
-
port@1:
$ref: /schemas/graph.yaml#/properties/port
description:
diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 2766fe45bb98..ee42328a109d 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -91,6 +91,14 @@ properties:
compensate for the board being designed with the lanes
swapped.
+ enet-phy-lane-no-swap:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ If set, indicates that PHY will disable swap of the
+ TX/RX lanes. This property allows the PHY to work correcly after
+ e.g. wrong bootstrap configuration caused by issues in PCB
+ layout design.
+
eee-broken-100tx:
$ref: /schemas/types.yaml#/definitions/flag
description:
diff --git a/Documentation/devicetree/bindings/power/supply/bq25980.yaml b/Documentation/devicetree/bindings/power/supply/bq25980.yaml
index 06eca6667f67..8367a1fd4057 100644
--- a/Documentation/devicetree/bindings/power/supply/bq25980.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq25980.yaml
@@ -105,7 +105,7 @@ examples:
reg = <0x65>;
interrupt-parent = <&gpio1>;
interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
- ti,watchdog-timer = <0>;
+ ti,watchdog-timeout-ms = <0>;
ti,sc-ocp-limit-microamp = <2000000>;
ti,sc-ovp-limit-microvolt = <17800000>;
monitored-battery = <&bat>;
diff --git a/MAINTAINERS b/MAINTAINERS
index 8691c531e297..cf77835aea35 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10279,9 +10279,9 @@ F: lib/Kconfig.kcsan
F: scripts/Makefile.kcsan
KDUMP
-M: Dave Young <dyoung@redhat.com>
M: Baoquan He <bhe@redhat.com>
R: Vivek Goyal <vgoyal@redhat.com>
+R: Dave Young <dyoung@redhat.com>
L: kexec@lists.infradead.org
S: Maintained
W: http://lse.sourceforge.net/kdump/
diff --git a/Makefile b/Makefile
index ef967a26bcd3..bce58275257a 100644
--- a/Makefile
+++ b/Makefile
@@ -1374,17 +1374,17 @@ endif
ifneq ($(dtstree),)
-%.dtb: dt_binding_check include/config/kernel.release scripts_dtc
- $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtb: include/config/kernel.release scripts_dtc
+ $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
-%.dtbo: dt_binding_check include/config/kernel.release scripts_dtc
- $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtbo: include/config/kernel.release scripts_dtc
+ $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
PHONY += dtbs dtbs_install dtbs_check
dtbs: include/config/kernel.release scripts_dtc
$(Q)$(MAKE) $(build)=$(dtstree)
-ifneq ($(filter dtbs_check %.dtb %.dtbo, $(MAKECMDGOALS)),)
+ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),)
export CHECK_DTBS=y
dtbs: dt_binding_check
endif
diff --git a/block/fops.c b/block/fops.c
index 3cb1e81929bc..0da147edbd18 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -341,8 +341,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
} else {
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
+ bio_put(bio);
return ret;
}
}
diff --git a/block/ioprio.c b/block/ioprio.c
index 313c14a70bbd..6f01d35a5145 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -220,6 +220,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
tmpio = get_task_ioprio(p);
if (tmpio < 0)
@@ -229,6 +230,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
else
ret = ioprio_best(ret, tmpio);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
+
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c
index d3e905cf867d..b23758083ce5 100644
--- a/drivers/clk/imx/clk-imx8qxp-lpcg.c
+++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c
@@ -370,7 +370,7 @@ static struct platform_driver imx8qxp_lpcg_clk_driver = {
.probe = imx8qxp_lpcg_clk_probe,
};
-builtin_platform_driver(imx8qxp_lpcg_clk_driver);
+module_platform_driver(imx8qxp_lpcg_clk_driver);
MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
MODULE_DESCRIPTION("NXP i.MX8QXP LPCG clock driver");
diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
index c53a688d8ccc..40a2efb1329b 100644
--- a/drivers/clk/imx/clk-imx8qxp.c
+++ b/drivers/clk/imx/clk-imx8qxp.c
@@ -308,7 +308,7 @@ static struct platform_driver imx8qxp_clk_driver = {
},
.probe = imx8qxp_clk_probe,
};
-builtin_platform_driver(imx8qxp_clk_driver);
+module_platform_driver(imx8qxp_clk_driver);
MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
MODULE_DESCRIPTION("NXP i.MX8QXP clock driver");
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index eaedcceb766f..8f65b9bdafce 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -1429,6 +1429,15 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops);
void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
const struct alpha_pll_config *config)
{
+ /*
+ * If the bootloader left the PLL enabled it's likely that there are
+ * RCGs that will lock up if we disable the PLL below.
+ */
+ if (trion_pll_is_enabled(pll, regmap)) {
+ pr_debug("Trion PLL is already enabled, skipping configuration\n");
+ return;
+ }
+
clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
diff --git a/drivers/clk/qcom/clk-regmap-mux.c b/drivers/clk/qcom/clk-regmap-mux.c
index b2d00b451963..45d9cca28064 100644
--- a/drivers/clk/qcom/clk-regmap-mux.c
+++ b/drivers/clk/qcom/clk-regmap-mux.c
@@ -28,7 +28,7 @@ static u8 mux_get_parent(struct clk_hw *hw)
val &= mask;
if (mux->parent_map)
- return qcom_find_src_index(hw, mux->parent_map, val);
+ return qcom_find_cfg_index(hw, mux->parent_map, val);
return val;
}
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index 0932e019dd12..75f09e6e057e 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -69,6 +69,18 @@ int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map, u8 src)
}
EXPORT_SYMBOL_GPL(qcom_find_src_index);
+int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map, u8 cfg)
+{
+ int i, num_parents = clk_hw_get_num_parents(hw);
+
+ for (i = 0; i < num_parents; i++)
+ if (cfg == map[i].cfg)
+ return i;
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(qcom_find_cfg_index);
+
struct regmap *
qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc)
{
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index bb39a7e106d8..9c8f7b798d9f 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -49,6 +49,8 @@ extern void
qcom_pll_set_fsm_mode(struct regmap *m, u32 reg, u8 bias_count, u8 lock_count);
extern int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map,
u8 src);
+extern int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map,
+ u8 cfg);
extern int qcom_cc_register_board_clk(struct device *dev, const char *path,
const char *name, unsigned long rate);
diff --git a/drivers/clk/qcom/gcc-sm6125.c b/drivers/clk/qcom/gcc-sm6125.c
index 543cfab7561f..431b55bb0d2f 100644
--- a/drivers/clk/qcom/gcc-sm6125.c
+++ b/drivers/clk/qcom/gcc-sm6125.c
@@ -1121,7 +1121,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = {
.name = "gcc_sdcc1_apps_clk_src",
.parent_data = gcc_parent_data_1,
.num_parents = ARRAY_SIZE(gcc_parent_data_1),
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_floor_ops,
},
};
@@ -1143,7 +1143,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = {
.name = "gcc_sdcc1_ice_core_clk_src",
.parent_data = gcc_parent_data_0,
.num_parents = ARRAY_SIZE(gcc_parent_data_0),
- .ops = &clk_rcg2_floor_ops,
+ .ops = &clk_rcg2_ops,
},
};
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index d52f976dc875..d5cb372f0901 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -543,8 +543,8 @@ static void __init of_syscon_icst_setup(struct device_node *np)
regclk = icst_clk_setup(NULL, &icst_desc, name, parent_name, map, ctype);
if (IS_ERR(regclk)) {
- kfree(name);
pr_err("error setting up syscon ICST clock %s\n", name);
+ kfree(name);
return;
}
of_clk_add_provider(np, of_clk_src_simple_get, regclk);
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index a6ea1eb1394e..53b8da6dbb23 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -636,7 +636,7 @@ static irqreturn_t mpc_i2c_isr(int irq, void *dev_id)
status = readb(i2c->base + MPC_I2C_SR);
if (status & CSR_MIF) {
/* Wait up to 100us for transfer to properly complete */
- readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100);
+ readb_poll_timeout_atomic(i2c->base + MPC_I2C_SR, status, status & CSR_MCF, 0, 100);
writeb(0, i2c->base + MPC_I2C_SR);
mpc_i2c_do_intr(i2c, status);
return IRQ_HANDLED;
diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c
index 95378780da6d..41eb0dcc3204 100644
--- a/drivers/i2c/busses/i2c-virtio.c
+++ b/drivers/i2c/busses/i2c-virtio.c
@@ -22,24 +22,24 @@
/**
* struct virtio_i2c - virtio I2C data
* @vdev: virtio device for this controller
- * @completion: completion of virtio I2C message
* @adap: I2C adapter for this controller
* @vq: the virtio virtqueue for communication
*/
struct virtio_i2c {
struct virtio_device *vdev;
- struct completion completion;
struct i2c_adapter adap;
struct virtqueue *vq;
};
/**
* struct virtio_i2c_req - the virtio I2C request structure
+ * @completion: completion of virtio I2C message
* @out_hdr: the OUT header of the virtio I2C message
* @buf: the buffer into which data is read, or from which it's written
* @in_hdr: the IN header of the virtio I2C message
*/
struct virtio_i2c_req {
+ struct completion completion;
struct virtio_i2c_out_hdr out_hdr ____cacheline_aligned;
uint8_t *buf ____cacheline_aligned;
struct virtio_i2c_in_hdr in_hdr ____cacheline_aligned;
@@ -47,9 +47,11 @@ struct virtio_i2c_req {
static void virtio_i2c_msg_done(struct virtqueue *vq)
{
- struct virtio_i2c *vi = vq->vdev->priv;
+ struct virtio_i2c_req *req;
+ unsigned int len;
- complete(&vi->completion);
+ while ((req = virtqueue_get_buf(vq, &len)))
+ complete(&req->completion);
}
static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
@@ -62,6 +64,8 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
for (i = 0; i < num; i++) {
int outcnt = 0, incnt = 0;
+ init_completion(&reqs[i].completion);
+
/*
* Only 7-bit mode supported for this moment. For the address
* format, Please check the Virtio I2C Specification.
@@ -106,21 +110,15 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq,
struct virtio_i2c_req *reqs,
struct i2c_msg *msgs, int num)
{
- struct virtio_i2c_req *req;
bool failed = false;
- unsigned int len;
int i, j = 0;
for (i = 0; i < num; i++) {
- /* Detach the ith request from the vq */
- req = virtqueue_get_buf(vq, &len);
+ struct virtio_i2c_req *req = &reqs[i];
- /*
- * Condition req == &reqs[i] should always meet since we have
- * total num requests in the vq. reqs[i] can never be NULL here.
- */
- if (!failed && (WARN_ON(req != &reqs[i]) ||
- req->in_hdr.status != VIRTIO_I2C_MSG_OK))
+ wait_for_completion(&req->completion);
+
+ if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK)
failed = true;
i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed);
@@ -156,12 +154,8 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
* remote here to clear the virtqueue, so we can try another set of
* messages later on.
*/
-
- reinit_completion(&vi->completion);
virtqueue_kick(vq);
- wait_for_completion(&vi->completion);
-
count = virtio_i2c_complete_reqs(vq, reqs, msgs, count);
err_free:
@@ -210,8 +204,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev)
vdev->priv = vi;
vi->vdev = vdev;
- init_completion(&vi->completion);
-
ret = virtio_i2c_setup_vqs(vi);
if (ret)
return ret;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5111ed966947..41d6e2383517 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2189,6 +2189,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
if (!num_sectors || num_sectors > max_sectors)
num_sectors = max_sectors;
+ rdev->sb_start = sb_start;
}
sb = page_address(rdev->sb_page);
sb->data_size = cpu_to_le64(num_sectors);
@@ -6270,7 +6271,8 @@ static void __md_stop(struct mddev *mddev)
spin_lock(&mddev->lock);
mddev->pers = NULL;
spin_unlock(&mddev->lock);
- pers->free(mddev, mddev->private);
+ if (mddev->private)
+ pers->free(mddev, mddev->private);
mddev->private = NULL;
if (pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4c63564adeaa..1af8a4513708 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -666,6 +666,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
struct request *rq)
{
if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+ ctrl->state != NVME_CTRL_DELETING &&
ctrl->state != NVME_CTRL_DEAD &&
!test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
@@ -1749,9 +1750,20 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
*/
if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
return -EINVAL;
- if (ctrl->max_integrity_segments)
- ns->features |=
- (NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+
+ ns->features |= NVME_NS_EXT_LBAS;
+
+ /*
+ * The current fabrics transport drivers support namespace
+ * metadata formats only if nvme_ns_has_pi() returns true.
+ * Suppress support for all other formats so the namespace will
+ * have a 0 capacity and not be usable through the block stack.
+ *
+ * Note, this check will need to be modified if any drivers
+ * gain the ability to use other metadata formats.
+ */
+ if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+ ns->features |= NVME_NS_METADATA_SUPPORTED;
} else {
/*
* For PCIe controllers, we can't easily remap the separate
@@ -2696,8 +2708,9 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
if (tmp->cntlid == ctrl->cntlid) {
dev_err(ctrl->device,
- "Duplicate cntlid %u with %s, rejecting\n",
- ctrl->cntlid, dev_name(tmp->device));
+ "Duplicate cntlid %u with %s, subsys %s, rejecting\n",
+ ctrl->cntlid, dev_name(tmp->device),
+ subsys->subnqn);
return false;
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 7f2071f2460c..13e5d503ed07 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -866,7 +866,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
}
if (ana_log_size > ctrl->ana_log_size) {
nvme_mpath_stop(ctrl);
- kfree(ctrl->ana_log_buf);
+ nvme_mpath_uninit(ctrl);
ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
if (!ctrl->ana_log_buf)
return -ENOMEM;
@@ -886,4 +886,5 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
{
kfree(ctrl->ana_log_buf);
ctrl->ana_log_buf = NULL;
+ ctrl->ana_log_size = 0;
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b334af8aa264..9b095ee01364 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -709,7 +709,7 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
return true;
if (ctrl->ops->flags & NVME_F_FABRICS &&
ctrl->state == NVME_CTRL_DELETING)
- return true;
+ return queue_live;
return __nvme_check_ready(ctrl, rq, queue_live);
}
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index bfc259e0d7b8..9f81beb4df4e 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -166,7 +166,10 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
zone.len = ns->zsze;
zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
- zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+ if (zone.cond == BLK_ZONE_COND_FULL)
+ zone.wp = zone.start + zone.len;
+ else
+ zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
return cb(&zone, idx, data);
}
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index cb6a473c3eaf..7c1c43ce466b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -922,7 +922,14 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
int ret;
- if (!nvme_is_write(cmd->req.cmd) ||
+ /*
+ * This command has not been processed yet, hence we are trying to
+ * figure out if there is still pending data left to receive. If
+ * we don't, we can simply prepare for the next pdu and bail out,
+ * otherwise we will need to prepare a buffer and receive the
+ * stale data before continuing forward.
+ */
+ if (!nvme_is_write(cmd->req.cmd) || !data_len ||
data_len > cmd->req.port->inline_data_size) {
nvmet_prepare_receive_pdu(queue);
return;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index b10f015b2e37..2b07677a386b 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -76,6 +76,26 @@ struct device_node *of_irq_find_parent(struct device_node *child)
}
EXPORT_SYMBOL_GPL(of_irq_find_parent);
+/*
+ * These interrupt controllers abuse interrupt-map for unspeakable
+ * reasons and rely on the core code to *ignore* it (the drivers do
+ * their own parsing of the property).
+ *
+ * If you think of adding to the list for something *new*, think
+ * again. There is a high chance that you will be sent back to the
+ * drawing board.
+ */
+static const char * const of_irq_imap_abusers[] = {
+ "CBEA,platform-spider-pic",
+ "sti,platform-spider-pic",
+ "realtek,rtl-intc",
+ "fsl,ls1021a-extirq",
+ "fsl,ls1043a-extirq",
+ "fsl,ls1088a-extirq",
+ "renesas,rza1-irqc",
+ NULL,
+};
+
/**
* of_irq_parse_raw - Low level interrupt tree parsing
* @addr: address specifier (start of "reg" property of the device) in be32 format
@@ -159,12 +179,15 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
/*
* Now check if cursor is an interrupt-controller and
* if it is then we are done, unless there is an
- * interrupt-map which takes precedence.
+ * interrupt-map which takes precedence except on one
+ * of these broken platforms that want to parse
+ * interrupt-map themselves for $reason.
*/
bool intc = of_property_read_bool(ipar, "interrupt-controller");
imap = of_get_property(ipar, "interrupt-map", &imaplen);
- if (imap == NULL && intc) {
+ if (intc &&
+ (!imap || of_device_compatible_match(ipar, of_irq_imap_abusers))) {
pr_debug(" -> got it !\n");
return 0;
}
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 50cf9f92da36..8d2bb818a3bb 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -142,6 +142,7 @@ static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
struct io_wqe_acct *acct,
struct io_cb_cancel_data *match);
static void create_worker_cb(struct callback_head *cb);
+static void io_wq_cancel_tw_create(struct io_wq *wq);
static bool io_worker_get(struct io_worker *worker)
{
@@ -357,12 +358,22 @@ static bool io_queue_worker_create(struct io_worker *worker,
test_and_set_bit_lock(0, &worker->create_state))
goto fail_release;
+ atomic_inc(&wq->worker_refs);
init_task_work(&worker->create_work, func);
worker->create_index = acct->index;
if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
- clear_bit_unlock(0, &worker->create_state);
+ /*
+ * EXIT may have been set after checking it above, check after
+ * adding the task_work and remove any creation item if it is
+ * now set. wq exit does that too, but we can have added this
+ * work item after we canceled in io_wq_exit_workers().
+ */
+ if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
+ io_wq_cancel_tw_create(wq);
+ io_worker_ref_put(wq);
return true;
}
+ io_worker_ref_put(wq);
clear_bit_unlock(0, &worker->create_state);
fail_release:
io_worker_release(worker);
@@ -1198,13 +1209,9 @@ void io_wq_exit_start(struct io_wq *wq)
set_bit(IO_WQ_BIT_EXIT, &wq->state);
}
-static void io_wq_exit_workers(struct io_wq *wq)
+static void io_wq_cancel_tw_create(struct io_wq *wq)
{
struct callback_head *cb;
- int node;
-
- if (!wq->task)
- return;
while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
struct io_worker *worker;
@@ -1212,6 +1219,16 @@ static void io_wq_exit_workers(struct io_wq *wq)
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
}
+}
+
+static void io_wq_exit_workers(struct io_wq *wq)
+{
+ int node;
+
+ if (!wq->task)
+ return;
+
+ io_wq_cancel_tw_create(wq);
rcu_read_lock();
for_each_node(node) {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c4f217613f56..d5ab0e9a3f29 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9824,7 +9824,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
+ * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
*/
static __cold void io_uring_cancel_generic(bool cancel_all,
struct io_sq_data *sqd)
@@ -9866,8 +9866,10 @@ static __cold void io_uring_cancel_generic(bool cancel_all,
cancel_all);
}
- prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
+ io_run_task_work();
io_uring_drop_tctx_refs(current);
+
/*
* If we've seen completions, retry without waiting. This
* avoids a race where a completion comes in before we did
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8eacf67eb212..039e7e0c7378 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -20,6 +20,7 @@
*/
#include <linux/math.h>
+#include <linux/sched.h>
extern unsigned long loops_per_jiffy;
@@ -58,7 +59,18 @@ void calibrate_delay(void);
void __attribute__((weak)) calibration_delay_done(void);
void msleep(unsigned int msecs);
unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+ unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+ usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+ usleep_range_state(min, max, TASK_IDLE);
+}
static inline void ssleep(unsigned int seconds)
{
diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h
index 74ef57b38f9f..ac5d6a3031db 100644
--- a/include/uapi/linux/resource.h
+++ b/include/uapi/linux/resource.h
@@ -66,10 +66,17 @@ struct rlimit64 {
#define _STK_LIM (8*1024*1024)
/*
- * GPG2 wants 64kB of mlocked memory, to make sure pass phrases
- * and other sensitive information are never written to disk.
+ * Limit the amount of locked memory by some sane default:
+ * root can always increase this limit if needed.
+ *
+ * The main use-cases are (1) preventing sensitive memory
+ * from being swapped; (2) real-time operations; (3) via
+ * IOURING_REGISTER_BUFFERS.
+ *
+ * The first two don't need much. The latter will take as
+ * much as it can get. 8MB is a reasonably sane default.
*/
-#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024)
+#define MLOCK_LIMIT (8*1024*1024)
/*
* Due to binary compatibility, the actual resource numbers
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e3d2c23c413d..85f1021ad459 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs)
EXPORT_SYMBOL(msleep_interruptible);
/**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min: Minimum time in usecs to sleep
+ * @max: Maximum time in usecs to sleep
+ * @state: State of the current task that will be while sleeping
*
* In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay(). The sleep improves responsiveness
+ * usleep_range_state() instead of udelay(). The sleep improves responsiveness
* by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
* power usage by allowing hrtimers to take advantage of an already-
* scheduled interrupt instead of scheduling a new one just for this sleep.
*/
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+ unsigned int state)
{
ktime_t exp = ktime_add_us(ktime_get(), min);
u64 delta = (u64)(max - min) * NSEC_PER_USEC;
for (;;) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(state);
/* Do not return before the requested sleep time has elapsed */
if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
break;
}
}
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1eead4761011..eae96dfe0261 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_info *bdi)
wb_shutdown(&bdi->wb);
cgwb_bdi_unregister(bdi);
+ /*
+ * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+ * update the global bdi_min_ratio.
+ */
+ if (bdi->min_ratio)
+ bdi_set_min_ratio(bdi, 0);
+
if (bdi->dev) {
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c381b3c525d0..e92497895202 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *ctx,
for (i = 0; i < nr_ids; i++) {
t = damon_new_target(ids[i]);
if (!t) {
- pr_err("Failed to alloc damon_target\n");
/* The caller should do cleanup of the ids itself */
damon_for_each_target_safe(t, next, ctx)
damon_destroy_target(t);
@@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
unsigned long aggr_int, unsigned long primitive_upd_int,
unsigned long min_nr_reg, unsigned long max_nr_reg)
{
- if (min_nr_reg < 3) {
- pr_err("min_nr_regions (%lu) must be at least 3\n",
- min_nr_reg);
+ if (min_nr_reg < 3)
return -EINVAL;
- }
- if (min_nr_reg > max_nr_reg) {
- pr_err("invalid nr_regions. min (%lu) > max (%lu)\n",
- min_nr_reg, max_nr_reg);
+ if (min_nr_reg > max_nr_reg)
return -EINVAL;
- }
ctx->sample_interval = sample_int;
ctx->aggr_interval = aggr_int;
@@ -980,10 +973,11 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme)
static void kdamond_usleep(unsigned long usecs)
{
- if (usecs > 100 * 1000)
- schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+ /* See Documentation/timers/timers-howto.rst for the thresholds */
+ if (usecs > 20 * USEC_PER_MSEC)
+ schedule_timeout_idle(usecs_to_jiffies(usecs));
else
- usleep_range(usecs, usecs + 1);
+ usleep_idle_range(usecs, usecs + 1);
}
/* Returns negative error code if it's not activated but should return */
@@ -1038,7 +1032,7 @@ static int kdamond_fn(void *data)
ctx->callback.after_sampling(ctx))
done = true;
- usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+ kdamond_usleep(ctx->sample_interval);
if (ctx->primitive.check_accesses)
max_nr_accesses = ctx->primitive.check_accesses(ctx);
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index 9b520bb4a3e7..1efac0022e9a 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -210,10 +210,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
&wmarks.low, &parsed);
if (ret != 18)
break;
- if (!damos_action_valid(action)) {
- pr_err("wrong action %d\n", action);
+ if (!damos_action_valid(action))
goto fail;
- }
pos += parsed;
scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index ecfd0b2ed222..6a1b9272ea12 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -135,7 +135,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
struct damon_addr_range *three_regions,
unsigned long *expected, int nr_expected)
{
- struct damon_ctx *ctx = damon_new_ctx();
struct damon_target *t;
struct damon_region *r;
int i;
@@ -145,7 +144,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
damon_add_region(r, t);
}
- damon_add_target(ctx, t);
damon_va_apply_three_regions(t, three_regions);
@@ -154,8 +152,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
}
-
- damon_destroy_ctx(ctx);
}
/*
@@ -252,60 +248,59 @@ static void damon_test_apply_three_regions4(struct kunit *test)
new_three_regions, expected, ARRAY_SIZE(expected));
}
-static void damon_test_split_evenly(struct kunit *test)
+static void damon_test_split_evenly_fail(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
{
- struct damon_ctx *c = damon_new_ctx();
- struct damon_target *t;
- struct damon_region *r;
- unsigned long i;
-
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
- -EINVAL);
-
- t = damon_new_target(42);
- r = damon_new_region(0, 100);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
- i = 0;
damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
- KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
}
+
damon_free_target(t);
+}
+
+static void damon_test_split_evenly_succ(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
+{
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
+ unsigned long expected_width = (end - start) / nr_pieces;
+ unsigned long i = 0;
- t = damon_new_target(42);
- r = damon_new_region(5, 59);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), 0);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces);
- i = 0;
damon_for_each_region(r, t) {
- if (i == 4)
+ if (i == nr_pieces - 1)
break;
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
- KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+ KUNIT_EXPECT_EQ(test,
+ r->ar.start, start + i++ * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width);
}
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
- KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
damon_free_target(t);
+}
- t = damon_new_target(42);
- r = damon_new_region(5, 6);
- damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+static void damon_test_split_evenly(struct kunit *test)
+{
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+ -EINVAL);
- damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
- KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
- }
- damon_free_target(t);
- damon_destroy_ctx(c);
+ damon_test_split_evenly_fail(test, 0, 100, 0);
+ damon_test_split_evenly_succ(test, 0, 100, 10);
+ damon_test_split_evenly_succ(test, 5, 59, 5);
+ damon_test_split_evenly_fail(test, 5, 6, 2);
}
static struct kunit_case damon_test_cases[] = {
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 47f47f60440e..20a9a9d69eb1 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -627,7 +627,6 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
case DAMOS_STAT:
return 0;
default:
- pr_warn("Wrong action %d\n", scheme->action);
return -EINVAL;
}
diff --git a/mm/filemap.c b/mm/filemap.c
index daa0e23a6ee6..39c4c46c6133 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(struct page *page,
goto skip;
if (!PageUptodate(page) || PageReadahead(page))
goto skip;
- if (PageHWPoison(page))
- goto skip;
if (!trylock_page(page))
goto skip;
if (page->mapping != mapping)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index abcd1785c629..a1baa198519a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2973,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
struct huge_bootmem_page *m = NULL; /* initialize for clang */
int nr_nodes, node;
- if (nid >= nr_online_nodes)
+ if (nid != NUMA_NO_NODE && nid >= nr_online_nodes)
return 0;
/* do node specific alloc */
if (nid != NUMA_NO_NODE) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6863a834ed42..2ed5f2a0879d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
rcu_read_unlock();
}
-/*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
-static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
- struct pglist_data *pgdat,
- enum node_stat_item idx, int nr)
-{
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
-
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- mod_memcg_lruvec_state(lruvec, idx, nr);
- rcu_read_unlock();
-}
-
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
@@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
}
#endif
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
- struct memcg_stock_pcp *stock;
-
- if (likely(in_task())) {
- *pflags = 0UL;
- preempt_disable();
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->task_obj;
- }
-
- local_irq_save(*pflags);
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
- if (likely(in_task()))
- preempt_enable();
- else
- local_irq_restore(flags);
-}
-
/**
* consume_stock: Try to consume stocked charge on this cpu.
* @memcg: memcg to consume from.
@@ -2816,6 +2763,59 @@ retry:
*/
#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+/*
+ * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
+ * sequence used in this case to access content from object stock is slow.
+ * To optimize for user context access, there are now two object stocks for
+ * task context and interrupt context access respectively.
+ *
+ * The task context object stock can be accessed by disabling preemption only
+ * which is cheap in non-preempt kernel. The interrupt context object stock
+ * can only be accessed after disabling interrupt. User context code can
+ * access interrupt object stock, but not vice versa.
+ */
+static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
+{
+ struct memcg_stock_pcp *stock;
+
+ if (likely(in_task())) {
+ *pflags = 0UL;
+ preempt_disable();
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->task_obj;
+ }
+
+ local_irq_save(*pflags);
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->irq_obj;
+}
+
+static inline void put_obj_stock(unsigned long flags)
+{
+ if (likely(in_task()))
+ preempt_enable();
+ else
+ local_irq_restore(flags);
+}
+
+/*
+ * mod_objcg_mlstate() may be called with irq enabled, so
+ * mod_memcg_lruvec_state() should be used.
+ */
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+ struct pglist_data *pgdat,
+ enum node_stat_item idx, int nr)
+{
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+ memcg = obj_cgroup_memcg(objcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ mod_memcg_lruvec_state(lruvec, idx, nr);
+ rcu_read_unlock();
+}
+
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
gfp_t gfp, bool new_page)
{
diff --git a/mm/slub.c b/mm/slub.c
index a8626825a829..abe7db581d68 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5081,6 +5081,7 @@ struct loc_track {
unsigned long max;
unsigned long count;
struct location *loc;
+ loff_t idx;
};
static struct dentry *slab_debugfs_root;
@@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init);
#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
static int slab_debugfs_show(struct seq_file *seq, void *v)
{
-
- struct location *l;
- unsigned int idx = *(unsigned int *)v;
struct loc_track *t = seq->private;
+ struct location *l;
+ unsigned long idx;
+ idx = (unsigned long) t->idx;
if (idx < t->count) {
l = &t->loc[idx];
@@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
{
struct loc_track *t = seq->private;
- v = ppos;
- ++*ppos;
+ t->idx = ++(*ppos);
if (*ppos <= t->count)
- return v;
+ return ppos;
return NULL;
}
static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
{
+ struct loc_track *t = seq->private;
+
+ t->idx = *ppos;
return ppos;
}
diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore
new file mode 100644
index 000000000000..c6c2965a6607
--- /dev/null
+++ b/tools/testing/selftests/damon/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+huge_count_read_write
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 8a3f2cd9fec0..937d36ae9a69 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -1,7 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for damon selftests
-TEST_FILES = _chk_dependency.sh
-TEST_PROGS = debugfs_attrs.sh
+TEST_GEN_FILES += huge_count_read_write
+
+TEST_FILES = _chk_dependency.sh _debugfs_common.sh
+TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
+TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
include ../lib.mk
diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh
new file mode 100644
index 000000000000..48989d4813ae
--- /dev/null
+++ b/tools/testing/selftests/damon/_debugfs_common.sh
@@ -0,0 +1,52 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+test_write_result() {
+ file=$1
+ content=$2
+ orig_content=$3
+ expect_reason=$4
+ expected=$5
+
+ echo "$content" > "$file"
+ if [ $? -ne "$expected" ]
+ then
+ echo "writing $content to $file doesn't return $expected"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+test_write_succ() {
+ test_write_result "$1" "$2" "$3" "$4" 0
+}
+
+test_write_fail() {
+ test_write_result "$1" "$2" "$3" "$4" 1
+}
+
+test_content() {
+ file=$1
+ orig_content=$2
+ expected=$3
+ expect_reason=$4
+
+ content=$(cat "$file")
+ if [ "$content" != "$expected" ]
+ then
+ echo "reading $file expected $expected but $content"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+source ./_chk_dependency.sh
+
+damon_onoff="$DBGFS/monitor_on"
+if [ $(cat "$damon_onoff") = "on" ]
+then
+ echo "monitoring is on"
+ exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index 196b6640bf37..902e312bca89 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -1,48 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-test_write_result() {
- file=$1
- content=$2
- orig_content=$3
- expect_reason=$4
- expected=$5
-
- echo "$content" > "$file"
- if [ $? -ne "$expected" ]
- then
- echo "writing $content to $file doesn't return $expected"
- echo "expected because: $expect_reason"
- echo "$orig_content" > "$file"
- exit 1
- fi
-}
-
-test_write_succ() {
- test_write_result "$1" "$2" "$3" "$4" 0
-}
-
-test_write_fail() {
- test_write_result "$1" "$2" "$3" "$4" 1
-}
-
-test_content() {
- file=$1
- orig_content=$2
- expected=$3
- expect_reason=$4
-
- content=$(cat "$file")
- if [ "$content" != "$expected" ]
- then
- echo "reading $file expected $expected but $content"
- echo "expected because: $expect_reason"
- echo "$orig_content" > "$file"
- exit 1
- fi
-}
-
-source ./_chk_dependency.sh
+source _debugfs_common.sh
# Test attrs file
# ===============
@@ -56,33 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
"min_nr_regions > max_nr_regions"
test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
echo "$orig_content" > "$file"
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
- "$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-echo "$orig_content" > "$file"
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
-
-echo "PASS"
diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh
new file mode 100644
index 000000000000..87aff8083822
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test empty targets case
+# =======================
+
+orig_target_ids=$(cat "$DBGFS/target_ids")
+echo "" > "$DBGFS/target_ids"
+orig_monitor_on=$(cat "$DBGFS/monitor_on")
+test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
+echo "$orig_target_ids" > "$DBGFS/target_ids"
diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
new file mode 100644
index 000000000000..922cadac2950
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test huge count read write
+# ==========================
+
+dmesg -C
+
+for file in "$DBGFS/"*
+do
+ ./huge_count_read_write "$file"
+done
+
+if dmesg | grep -q WARNING
+then
+ dmesg
+ exit 1
+else
+ exit 0
+fi
diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh
new file mode 100644
index 000000000000..5b39ab44731c
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_schemes.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test schemes file
+# =================
+
+file="$DBGFS/schemes"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
+ "$orig_content" "valid input"
+test_write_fail "$file" "1 2
+3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
+test_write_succ "$file" "" "$orig_content" "disabling"
+test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
+ "$orig_content" "wrong condition ranges"
+echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh
new file mode 100644
index 000000000000..49aeabdb0aae
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_target_ids.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test target_ids file
+# ====================
+
+file="$DBGFS/target_ids"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
+test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
+test_content "$file" "$orig_content" "1 2" "non-integer was there"
+test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
+test_content "$file" "$orig_content" "" "wrong input written"
+test_write_succ "$file" "" "$orig_content" "empty input"
+test_content "$file" "$orig_content" "" "empty input written"
+echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
new file mode 100644
index 000000000000..ad7a6b4cf338
--- /dev/null
+++ b/tools/testing/selftests/damon/huge_count_read_write.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+
+void write_read_with_huge_count(char *file)
+{
+ int filedesc = open(file, O_RDWR);
+ char buf[25];
+ int ret;
+
+ printf("%s %s\n", __func__, file);
+ if (filedesc < 0) {
+ fprintf(stderr, "failed opening %s\n", file);
+ exit(1);
+ }
+
+ write(filedesc, "", 0xfffffffful);
+ perror("after write: ");
+ ret = read(filedesc, buf, 0xfffffffful);
+ perror("after read: ");
+ close(filedesc);
+}
+
+int main(int argc, char *argv[])
+{
+ if (argc != 2) {
+ fprintf(stderr, "Usage: %s <file>\n", argv[0]);
+ exit(1);
+ }
+ write_read_with_huge_count(argv[1]);
+
+ return 0;
+}