* Persistent Reservation API V3
From: Christoph Hellwig @ 2015-08-26 16:03 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
This series adds support for a simplified Persistent Reservation API
to the block layer. The intent is that both in-kernel and userspace
consumers can use the API instead of having to hand craft SCSI or NVMe
command through the various pass through interfaces. It also adds
DM support as getting reservations through dm-multipath is a major
pain with the current scheme.
NVMe support currently isn't included as I don't have a multihost
NVMe setup to test on, but Keith offered to test it and I'll have
a patch for it shortly.
The ioctl API is documented in Documentation/block/pr.txt, but to
fully understand the concept you'll have to read up the SPC spec,
PRs are too complicated that trying to rephrase them into different
terminology is just going to create confusion.
Note that Mike wants to include the DM patches so through the DM
tree, so they are only included for reference.
I also have a set of simple test tools available at:
git://git.infradead.org/users/hch/pr-tests.git
Changes since V2:
- added an ignore flag to the reserve opertion as well, and redid
the ioctl API to have general flags fields
- rebased on top of the latest block layer tree updates
Changes since V1:
- rename DM ->ioctl to ->prepare_ioctl
- rename dm_get_ioctl_table to dm_get_live_table_for_ioctl
- merge two DM patches into one
- various spelling fixes
^ permalink raw reply
* [PATCH 1/5] block: cleanup blkdev_ioctl
From: Christoph Hellwig @ 2015-08-26 16:03 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
In-Reply-To: <1440604998-10597-1-git-send-email-hch@lst.de>
Split out helpers for all non-trivial ioctls to make this function simpler,
and also start passing around a pointer version of the argument, as that's
what most ioctl handlers actually need.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/ioctl.c | 227 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..df62b47 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -193,10 +193,20 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
-static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
- uint64_t len, int secure)
+static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
{
- unsigned long flags = 0;
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
if (start & 511)
return -EINVAL;
@@ -207,14 +217,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
- if (secure)
- flags |= BLKDEV_DISCARD_SECURE;
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
-static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
- uint64_t len)
+static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+ unsigned long arg)
{
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
+
if (start & 511)
return -EINVAL;
if (len & 511)
@@ -295,89 +315,115 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}
-/*
- * always keep this in sync with compat_blkdev_ioctl()
- */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
{
- struct gendisk *disk = bdev->bd_disk;
- struct backing_dev_info *bdi;
- loff_t size;
- int ret, n;
- unsigned int max_sectors;
+ int ret;
- switch(cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
- fsync_bdev(bdev);
- invalidate_bdev(bdev);
- return 0;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
- case BLKROSET:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (get_user(n, (int __user *)(arg)))
- return -EFAULT;
- set_device_ro(bdev, n);
- return 0;
+ fsync_bdev(bdev);
+ invalidate_bdev(bdev);
+ return 0;
+}
- case BLKDISCARD:
- case BLKSECDISCARD: {
- uint64_t range[2];
+static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
+{
+ int ret, n;
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (get_user(n, (int __user *)arg))
+ return -EFAULT;
+ set_device_ro(bdev, n);
+ return 0;
+}
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+static int blkdev_getgeo(struct block_device *bdev,
+ struct hd_geometry __user *argp)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct hd_geometry geo;
+ int ret;
- return blk_ioctl_discard(bdev, range[0], range[1],
- cmd == BLKSECDISCARD);
- }
- case BLKZEROOUT: {
- uint64_t range[2];
+ if (!argp)
+ return -EINVAL;
+ if (!disk->fops->getgeo)
+ return -ENOTTY;
+
+ /*
+ * We need to set the startsect first, the driver may
+ * want to override it.
+ */
+ memset(&geo, 0, sizeof(geo));
+ geo.start = get_start_sect(bdev);
+ ret = disk->fops->getgeo(bdev, &geo);
+ if (ret)
+ return ret;
+ if (copy_to_user(argp, &geo, sizeof(geo)))
+ return -EFAULT;
+ return 0;
+}
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+/* set the logical block size */
+static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+ int __user *argp)
+{
+ int ret, n;
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (!argp)
+ return -EINVAL;
+ if (get_user(n, argp))
+ return -EFAULT;
- return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
}
- case HDIO_GETGEO: {
- struct hd_geometry geo;
+ ret = set_blocksize(bdev, n);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
+ return ret;
+}
- if (!arg)
- return -EINVAL;
- if (!disk->fops->getgeo)
- return -ENOTTY;
-
- /*
- * We need to set the startsect first, the driver may
- * want to override it.
- */
- memset(&geo, 0, sizeof(geo));
- geo.start = get_start_sect(bdev);
- ret = disk->fops->getgeo(bdev, &geo);
- if (ret)
- return ret;
- if (copy_to_user((struct hd_geometry __user *)arg, &geo,
- sizeof(geo)))
- return -EFAULT;
- return 0;
- }
+/*
+ * always keep this in sync with compat_blkdev_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+ unsigned long arg)
+{
+ struct backing_dev_info *bdi;
+ void __user *argp = (void __user *)arg;
+ loff_t size;
+ unsigned int max_sectors;
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ return blkdev_flushbuf(bdev, mode, cmd, arg);
+ case BLKROSET:
+ return blkdev_roset(bdev, mode, cmd, arg);
+ case BLKDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg, 0);
+ case BLKSECDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg,
+ BLKDEV_DISCARD_SECURE);
+ case BLKZEROOUT:
+ return blk_ioctl_zeroout(bdev, mode, arg);
+ case HDIO_GETGEO:
+ return blkdev_getgeo(bdev, argp);
case BLKRAGET:
case BLKFRAGET:
if (!arg)
@@ -414,28 +460,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
- /* set the logical block size */
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (!arg)
- return -EINVAL;
- if (get_user(n, (int __user *) arg))
- return -EFAULT;
- if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
- }
- ret = set_blocksize(bdev, n);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
- return ret;
+ return blkdev_bszset(bdev, mode, argp);
case BLKPG:
- ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
- break;
+ return blkpg_ioctl(bdev, argp);
case BLKRRPART:
- ret = blkdev_reread_part(bdev);
- break;
+ return blkdev_reread_part(bdev);
case BLKGETSIZE:
size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
@@ -447,11 +476,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
- ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
- break;
+ return blk_trace_ioctl(bdev, cmd, argp);
default:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
--
1.9.1
^ permalink raw reply related
* Persistent Reservation API V3
From: Christoph Hellwig @ 2015-08-26 16:06 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
This series adds support for a simplified Persistent Reservation API
to the block layer. The intent is that both in-kernel and userspace
consumers can use the API instead of having to hand craft SCSI or NVMe
command through the various pass through interfaces. It also adds
DM support as getting reservations through dm-multipath is a major
pain with the current scheme.
NVMe support currently isn't included as I don't have a multihost
NVMe setup to test on, but Keith offered to test it and I'll have
a patch for it shortly.
The ioctl API is documented in Documentation/block/pr.txt, but to
fully understand the concept you'll have to read up the SPC spec,
PRs are too complicated that trying to rephrase them into different
terminology is just going to create confusion.
Note that Mike wants to include the DM patches so through the DM
tree, so they are only included for reference.
I also have a set of simple test tools available at:
git://git.infradead.org/users/hch/pr-tests.git
Changes since V2:
- added an ignore flag to the reserve opertion as well, and redid
the ioctl API to have general flags fields
- rebased on top of the latest block layer tree updates
Changes since V1:
- rename DM ->ioctl to ->prepare_ioctl
- rename dm_get_ioctl_table to dm_get_live_table_for_ioctl
- merge two DM patches into one
- various spelling fixes
^ permalink raw reply
* Re: Persistent Reservation API V3
From: Christoph Hellwig @ 2015-08-26 16:10 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Jens Axboe, linux-scsi, linux-nvme, dm-devel, linux-api,
linux-kernel
In-Reply-To: <1440605167-10769-1-git-send-email-hch@lst.de>
Meh, looks like the train wifi is too bad to send out a whole patch
series. I'll resend once I've arrived..
^ permalink raw reply
* Re: [RFC][PATCH 1/2] dt-bindings: drm/mediatek: Add Mediatek DRM dts binding
From: Philipp Zabel @ 2015-08-26 16:34 UTC (permalink / raw)
To: CK Hu
Cc: Mark Rutland, Catalin Marinas, Will Deacon, dri-devel,
Rob Herring, Cawa Cheng, YT Shen, devicetree, Jitao Shi,
Pawel Moll, Ian Campbell, Grant Likely, Rob Herring,
linux-mediatek, Matthias Brugger, linux-arm-kernel,
Graeme Gregory, srv_heupstream, linux-api, linux-kernel,
Ashwin Chaugule, Sascha Hauer, Kumar Gala
In-Reply-To: <1431530626-31493-2-git-send-email-ck.hu@mediatek.com>
Hi,
overall it looks to me like this binding is modeled after the Linux DRM
abstractions. Instead, the device nodes should be modeled after the
hardware.
Describing each function block as a separate device node is probably not
the best choice, as would be combining all devices in the mmsys range
into a single device node. So a somewhat arbitrary decision has to be
made what to group together. See my comments below:
Am Mittwoch, den 13.05.2015, 23:23 +0800 schrieb CK Hu:
> This patch includes
> 1. Mediatek DRM Device binding
> 2. Mediatek DSI Device binding
> 3. Mediatek CRTC Main Device binding
> 4. Mediatek DDP Device binding
>
> Signed-off-by: CK Hu <ck.hu@mediatek.com>
> ---
> .../bindings/drm/mediatek/mediatek,crtc-main.txt | 38 ++++++++++++++++++++++
> .../bindings/drm/mediatek/mediatek,ddp.txt | 22 +++++++++++++
> .../bindings/drm/mediatek/mediatek,drm.txt | 27 +++++++++++++++
> .../bindings/drm/mediatek/mediatek,dsi.txt | 20 ++++++++++++
> 4 files changed, 107 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/drm/mediatek/mediatek,crtc-main.txt
> create mode 100644 Documentation/devicetree/bindings/drm/mediatek/mediatek,ddp.txt
> create mode 100644 Documentation/devicetree/bindings/drm/mediatek/mediatek,drm.txt
> create mode 100644 Documentation/devicetree/bindings/drm/mediatek/mediatek,dsi.txt
>
> diff --git a/Documentation/devicetree/bindings/drm/mediatek/mediatek,crtc-main.txt b/Documentation/devicetree/bindings/drm/mediatek/mediatek,crtc-main.txt
> new file mode 100644
> index 0000000..5c6c420
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/drm/mediatek/mediatek,crtc-main.txt
> @@ -0,0 +1,38 @@
> +Mediatek CRTC Main Device
> +================================
> +
> +The Mediatek CRTC Main device is a crtc device of DRM system.
"crtc" does not belong in the device tree. There is no crtc hardware.
What this node describes is a useful, but fixed configuration of a part
of the DISP subsystem function blocks.
In my opinion, it would be better to not describe the separate display
pipes in the device tree at all if they are dynamically configurable.
What for example if you model two separate fixed pipelines in the device
tree and then in the future you want to support the MERGE or SPLIT
blocks (I'm not sure what MERGE does, SPLIT seems to be needed for
8-lane DSI)?
As far as I currently understand, there are five source function blocks
that can read from memory (OVL0, OVL1, RDMA0, RDMA1, RDMA2) and three
sink function blocks (DSI0, DSI1, DPI0) that can be connected to panels,
or encoder bridges. How these map to the crtcs doesn't necessarily have
to be described in the device tree.
How about a single node that contains all of the DISP functional blocks
that don't need their own node (like DSI, which has to be connectable to
bridges or panels):
disp: disp@0x1400c000 {
compatible = "mediatek,mt8173-disp";
interrupts = <GIC_SPI 180 IRQ_TYPE_LEVEL_LOW>, /* OVL0 */
<GIC_SPI 181 IRQ_TYPE_LEVEL_LOW>; /* OVL1 */
interrupt-names = "ovl0", "ovl1";
reg = <0 0x1400c000 0 0x1000>, /* OVL0 */
<0 0x1400d000 0 0x1000>, /* OVL1 */
<0 0x1400e000 0 0x1000>, /* RDMA0 */
<0 0x1400f000 0 0x1000>, /* RDMA1 */
<0 0x14010000 0 0x1000>, /* RDMA2 */
<0 0x14013000 0 0x1000>, /* COLOR0 */
<0 0x14014000 0 0x1000>, /* COLOR1 */
<0 0x14015000 0 0x1000>, /* AAL */
<0 0x14016000 0 0x1000>, /* GAMMA */
<0 0x14017000 0 0x1000>, /* MERGE */
<0 0x14018000 0 0x1000>, /* SPLIT0 */
<0 0x14019000 0 0x1000>, /* SPLIT1 */
<0 0x1401a000 0 0x1000>, /* UFOE */
<0 0x14020000 0 0x1000>; /* MUTEX */
<0 0x14023000 0 0x1000>; /* OD */
reg-names = "ovl0", "ovl1", "rdma0", "rdma1", "rdma2",
"color0", "color1", "aal", "gamma", "merge",
"split0", "split1", "ufoe", "mutex", "od";
clocks = <&mmsys CLK_MM_DISP_OVL0>,
<&mmsys CLK_MM_DISP_OVL1>,
<&mmsys CLK_MM_DISP_RDMA0>,
<&mmsys CLK_MM_DISP_RDMA1>,
<&mmsys CLK_MM_DISP_RDMA2>,
<&mmsys CLK_MM_DISP_COLOR0>,
<&mmsys CLK_MM_DISP_COLOR1>,
<&mmsys CLK_MM_DISP_AAL>,
<&mmsys CLK_MM_DISP_GAMMA>,
<&mmsys CLK_MM_DISP_MERGE>,
<&mmsys CLK_MM_DISP_SPLIT0>,
<&mmsys CLK_MM_DISP_SPLIT1>,
<&mmsys CLK_MM_DISP_UFOE>,
<&mmsys CLK_MM_MUTEX_32K>,
<&mmsys CLK_MM_DISP_OD>;
clock-names = "ovl0", "ovl1", "rdma0", "rdma1", "rdma2",
"color0", "color1", "aal", "gamma", "merge",
"split0", "split1", "ufoe", "mutex", "od";
power-domains = <&scpsys MT8173_POWER_DOMAIN_DIS>;
config = <&mmsys>; /* syscon */
};
How the muxes in the config area are set up to connect those blocks
could be determined by the driver.
> +Required properties:
> +- compatible: "mediatek,<chip>-crtc-main"
> +- interrupts: The interrupt signal from the CRTC Main block.
> +- reg: Physical base address and length of the controller's registers
> +- clocks: device clocks
> + See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
> +- ddp: phandle of ddp device which control display data path.
> +
> +Example:
> +
> +crtc_main: crtc@1400c000 {
> + compatible = "mediatek,mt8173-crtc-main";
> + interrupts = <GIC_SPI 196 IRQ_TYPE_LEVEL_LOW>;
Should it be mentioned that this is the interrupt of the source of the
pipeline (OVL0/1)?
> + reg = <0 0x1400c000 0 0x1000>, /* OVL0 */
> + <0 0x1400e000 0 0x1000>, /* RDMA0 */
> + <0 0x14013000 0 0x1000>, /* COLOR0 */
> + <0 0x14015000 0 0x1000>, /* AAL */
> + <0 0x1401a000 0 0x1000>, /* UFOE */
> + <0 0x14023000 0 0x1000>; /* OD */
With the amount of register ranges and given the symmetry with the
clocks, better use reg-names instead of position to determine the
register space for each function block.
reg-names = "ovl0", "rdma0", "color0", "aal", "ufoe", "od";
> + clocks = <&mmsys MM_DISP_OVL0>,
> + <&mmsys MM_DISP_RDMA0>,
> + <&mmsys MM_DISP_COLOR0>,
> + <&mmsys MM_DISP_AAL>,
> + <&mmsys MM_DISP_UFOE>,
> + <&mmsys MM_DISP_OD>;
> + clock-names = "ovl0_disp",
> + "rdma0_disp",
> + "color0_disp",
> + "aal_disp",
> + "ufoe_disp",
> + "od_disp";
I'd drop the disp suffix from the clock input names.
clock-names = "ovl0", "rdma0", "color0", "aal", "ufoe", "od";
> + ddp = <&ddp>;
> +};
> \ No newline at end of file
> diff --git a/Documentation/devicetree/bindings/drm/mediatek/mediatek,ddp.txt b/Documentation/devicetree/bindings/drm/mediatek/mediatek,ddp.txt
> new file mode 100644
> index 0000000..77cf630
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/drm/mediatek/mediatek,ddp.txt
> @@ -0,0 +1,22 @@
> +Mediatek DDP Device
> +================================
> +
> +The Mediatek DDP device control the display data path.
This is not a real device either. There is nothing wrong with having a
ddp driver, but I don't think it is right to describe this driver in the
device tree. What we really have here is the mutex function block and
some registers in the mmsys config region, which already can be accessed
via the mmsys syscon.
With a single disp device node including the mutex and power domain
phandle this node would not be necessary.
> +Required properties:
> +- compatible: "mediatek,<chip>-ddp"
> +- reg: Physical base address and length of the controller's registers
> +- power-domains: a phandle to DDP power domain node.
> +- clocks: device clocks
> + See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
> +
> +Example:
> +
> +ddp: ddp@14000000 {
> + compatible = "mediatek,mt8173-ddp";
> + reg = <0 0x14000000 0 0x100>, /* CONFIG */
This remaps part of the mmsys register space, which is already a syscon.
Why not use syscon to access it?
> + <0 0x14020000 0 0x1000>; /* MUTEX */
> + power-domains = <&scpsys MT8173_POWER_DOMAIN_DIS>;
> + clocks = <&mmsys MM_MUTEX_32K>;
> + clock-names = "mutex_disp";
> +};
> \ No newline at end of file
> diff --git a/Documentation/devicetree/bindings/drm/mediatek/mediatek,drm.txt b/Documentation/devicetree/bindings/drm/mediatek/mediatek,drm.txt
> new file mode 100644
> index 0000000..c4a5702
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/drm/mediatek/mediatek,drm.txt
> @@ -0,0 +1,27 @@
> +Mediatek DRM Device
> +================================
> +
> +The Mediatek DRM device is a device needed to list all
> +display component nodes that comprise the display subsystem.
> +And it list the memory-related interface.
"drm" does not belong in the device tree. There is no "drm" hardware.
Other SoCs use the "display-subsystem" name for this node, it would be
better to follow that.
> +Required properties:
> +- compatible: "mediatek,<chip>-drm"
> +- larb: Should contain a list of phandles pointing to larb device.
> + larb definitions as defined in
> + Documentation/devicetree/bindings/soc/mediatek/mediatek,smi-larb.txt
> +- iommus: required a iommu node
> +- connectors: Should contain a list of phandles pointing to connector device.
> + connector device should be one component of this master.
> +- crtcs: Should contain a list of phandles pointing to crtc device.
> + crtc device should be one component of this master.
"connectors" and "crtcs" as used here are DRM concepts, not hardware
devices that should exist in the device tree. Ideally you would use
something recognizable from the datasheet, like "sinks" or from the
device tree, like "ports" if of-graph bindings are used, or just
"components" if this also were to include things like the ddp.
Another possibility would be to even merge the
> +
> +Example:
> +
> +drm0: drm {
> + compatible = "mediatek,mt8173-drm";
> + larb = <&larb0>;
> + iommus = <&iommu M4U_PORT_DISP_OVL0>;
> + connectors = <&dsi>;
> + crtcs = <&crtc_main>;
> +};
> \ No newline at end of file
> diff --git a/Documentation/devicetree/bindings/drm/mediatek/mediatek,dsi.txt b/Documentation/devicetree/bindings/drm/mediatek/mediatek,dsi.txt
> new file mode 100644
> index 0000000..16e3eb3
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/drm/mediatek/mediatek,dsi.txt
> @@ -0,0 +1,20 @@
> +Mediatek DSI Device
> +================================
> +
> +The Mediatek DSI device is a connector device of DRM system.
> +
> +Required properties:
> +- compatible: "mediatek,<chip>-dsi"
> +- reg: Physical base address and length of the controller's registers
> +- clocks: device clocks
> + See Documentation/devicetree/bindings/clock/clock-bindings.txt for details.
Will this use the
Documentation/devicetree/bindings/mipi/dsi/mipi-dsi-bus.txt
bindings to connect panels controlled via the DSI command channel
or the
Documentation/devicetree/bindings/graph.txt
bindings to connect panels controlled via I2C or other control buses?
If so, this should be documented here.
> +Example:
> +
> +dsi: dsi@10215000 {
> + compatible = "mediatek,mt8173-dsi";
> + reg = <0 0x1401B000 0 0x1000>, /* DSI0 */
> + <0 0x10215000 0 0x1000>; /* MIPITX */
> + clocks = <&mmsys MM_DSI0_ENGINE>, <&mmsys MM_DSI0_DIGITAL>;
> + clock-names = "dsi0_engine_disp_ck", "dsi0_digital_disp_ck";
Maybe shorten the clock names to "engine" and "digital" ?
And add an example of panel or bridge connected to the DSI sink.
What about DSI1 and the DPI sink?
best regards
Philipp
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel
^ permalink raw reply
* Persistent Reservation API V3
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA,
linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
This series adds support for a simplified Persistent Reservation API
to the block layer. The intent is that both in-kernel and userspace
consumers can use the API instead of having to hand craft SCSI or NVMe
command through the various pass through interfaces. It also adds
DM support as getting reservations through dm-multipath is a major
pain with the current scheme.
NVMe support currently isn't included as I don't have a multihost
NVMe setup to test on, but Keith offered to test it and I'll have
a patch for it shortly.
The ioctl API is documented in Documentation/block/pr.txt, but to
fully understand the concept you'll have to read up the SPC spec,
PRs are too complicated that trying to rephrase them into different
terminology is just going to create confusion.
Note that Mike wants to include the DM patches so through the DM
tree, so they are only included for reference.
I also have a set of simple test tools available at:
git://git.infradead.org/users/hch/pr-tests.git
Changes since V2:
- added an ignore flag to the reserve opertion as well, and redid
the ioctl API to have general flags fields
- rebased on top of the latest block layer tree updates
Changes since V1:
- rename DM ->ioctl to ->prepare_ioctl
- rename dm_get_ioctl_table to dm_get_live_table_for_ioctl
- merge two DM patches into one
- various spelling fixes
^ permalink raw reply
* [PATCH 1/5] block: cleanup blkdev_ioctl
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
In-Reply-To: <1440608214-14497-1-git-send-email-hch@lst.de>
Split out helpers for all non-trivial ioctls to make this function simpler,
and also start passing around a pointer version of the argument, as that's
what most ioctl handlers actually need.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
block/ioctl.c | 227 ++++++++++++++++++++++++++++++++--------------------------
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/block/ioctl.c b/block/ioctl.c
index 8061eba..df62b47 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -193,10 +193,20 @@ int blkdev_reread_part(struct block_device *bdev)
}
EXPORT_SYMBOL(blkdev_reread_part);
-static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
- uint64_t len, int secure)
+static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
+ unsigned long arg, unsigned long flags)
{
- unsigned long flags = 0;
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
if (start & 511)
return -EINVAL;
@@ -207,14 +217,24 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
if (start + len > (i_size_read(bdev->bd_inode) >> 9))
return -EINVAL;
- if (secure)
- flags |= BLKDEV_DISCARD_SECURE;
return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
}
-static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
- uint64_t len)
+static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
+ unsigned long arg)
{
+ uint64_t range[2];
+ uint64_t start, len;
+
+ if (!(mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+ return -EFAULT;
+
+ start = range[0];
+ len = range[1];
+
if (start & 511)
return -EINVAL;
if (len & 511)
@@ -295,89 +315,115 @@ static inline int is_unrecognized_ioctl(int ret)
ret == -ENOIOCTLCMD;
}
-/*
- * always keep this in sync with compat_blkdev_ioctl()
- */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
- unsigned long arg)
+static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
{
- struct gendisk *disk = bdev->bd_disk;
- struct backing_dev_info *bdi;
- loff_t size;
- int ret, n;
- unsigned int max_sectors;
+ int ret;
- switch(cmd) {
- case BLKFLSBUF:
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
-
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
- fsync_bdev(bdev);
- invalidate_bdev(bdev);
- return 0;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
- case BLKROSET:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
- if (!is_unrecognized_ioctl(ret))
- return ret;
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (get_user(n, (int __user *)(arg)))
- return -EFAULT;
- set_device_ro(bdev, n);
- return 0;
+ fsync_bdev(bdev);
+ invalidate_bdev(bdev);
+ return 0;
+}
- case BLKDISCARD:
- case BLKSECDISCARD: {
- uint64_t range[2];
+static int blkdev_roset(struct block_device *bdev, fmode_t mode,
+ unsigned cmd, unsigned long arg)
+{
+ int ret, n;
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+ ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (!is_unrecognized_ioctl(ret))
+ return ret;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (get_user(n, (int __user *)arg))
+ return -EFAULT;
+ set_device_ro(bdev, n);
+ return 0;
+}
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+static int blkdev_getgeo(struct block_device *bdev,
+ struct hd_geometry __user *argp)
+{
+ struct gendisk *disk = bdev->bd_disk;
+ struct hd_geometry geo;
+ int ret;
- return blk_ioctl_discard(bdev, range[0], range[1],
- cmd == BLKSECDISCARD);
- }
- case BLKZEROOUT: {
- uint64_t range[2];
+ if (!argp)
+ return -EINVAL;
+ if (!disk->fops->getgeo)
+ return -ENOTTY;
+
+ /*
+ * We need to set the startsect first, the driver may
+ * want to override it.
+ */
+ memset(&geo, 0, sizeof(geo));
+ geo.start = get_start_sect(bdev);
+ ret = disk->fops->getgeo(bdev, &geo);
+ if (ret)
+ return ret;
+ if (copy_to_user(argp, &geo, sizeof(geo)))
+ return -EFAULT;
+ return 0;
+}
- if (!(mode & FMODE_WRITE))
- return -EBADF;
+/* set the logical block size */
+static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
+ int __user *argp)
+{
+ int ret, n;
- if (copy_from_user(range, (void __user *)arg, sizeof(range)))
- return -EFAULT;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (!argp)
+ return -EINVAL;
+ if (get_user(n, argp))
+ return -EFAULT;
- return blk_ioctl_zeroout(bdev, range[0], range[1]);
+ if (!(mode & FMODE_EXCL)) {
+ bdgrab(bdev);
+ if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
+ return -EBUSY;
}
- case HDIO_GETGEO: {
- struct hd_geometry geo;
+ ret = set_blocksize(bdev, n);
+ if (!(mode & FMODE_EXCL))
+ blkdev_put(bdev, mode | FMODE_EXCL);
+ return ret;
+}
- if (!arg)
- return -EINVAL;
- if (!disk->fops->getgeo)
- return -ENOTTY;
-
- /*
- * We need to set the startsect first, the driver may
- * want to override it.
- */
- memset(&geo, 0, sizeof(geo));
- geo.start = get_start_sect(bdev);
- ret = disk->fops->getgeo(bdev, &geo);
- if (ret)
- return ret;
- if (copy_to_user((struct hd_geometry __user *)arg, &geo,
- sizeof(geo)))
- return -EFAULT;
- return 0;
- }
+/*
+ * always keep this in sync with compat_blkdev_ioctl()
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+ unsigned long arg)
+{
+ struct backing_dev_info *bdi;
+ void __user *argp = (void __user *)arg;
+ loff_t size;
+ unsigned int max_sectors;
+
+ switch (cmd) {
+ case BLKFLSBUF:
+ return blkdev_flushbuf(bdev, mode, cmd, arg);
+ case BLKROSET:
+ return blkdev_roset(bdev, mode, cmd, arg);
+ case BLKDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg, 0);
+ case BLKSECDISCARD:
+ return blk_ioctl_discard(bdev, mode, arg,
+ BLKDEV_DISCARD_SECURE);
+ case BLKZEROOUT:
+ return blk_ioctl_zeroout(bdev, mode, arg);
+ case HDIO_GETGEO:
+ return blkdev_getgeo(bdev, argp);
case BLKRAGET:
case BLKFRAGET:
if (!arg)
@@ -414,28 +460,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
- /* set the logical block size */
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (!arg)
- return -EINVAL;
- if (get_user(n, (int __user *) arg))
- return -EFAULT;
- if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0)
- return -EBUSY;
- }
- ret = set_blocksize(bdev, n);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
- return ret;
+ return blkdev_bszset(bdev, mode, argp);
case BLKPG:
- ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
- break;
+ return blkpg_ioctl(bdev, argp);
case BLKRRPART:
- ret = blkdev_reread_part(bdev);
- break;
+ return blkdev_reread_part(bdev);
case BLKGETSIZE:
size = i_size_read(bdev->bd_inode);
if ((size >> 9) > ~0UL)
@@ -447,11 +476,9 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
- ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
- break;
+ return blk_trace_ioctl(bdev, cmd, argp);
default:
- ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
- return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);
--
1.9.1
^ permalink raw reply related
* [PATCH 2/5] block: add an API for Persistent Reservations
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
In-Reply-To: <1440608214-14497-1-git-send-email-hch@lst.de>
This commits adds a driver API and ioctls for controlling Persistent
Reservations s/genericly/generically/ at the block layer. Persistent
Reservations are supported by SCSI and NVMe and allow controlling who gets
access to a device in a shared storage setup.
Note that we add a pr_ops structure to struct block_device_operations
instead of adding the members directly to avoid bloating all instances
of devices that will never support Persistent Reservations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
Documentation/block/pr.txt | 119 +++++++++++++++++++++++++++++++++++++++++++++
block/ioctl.c | 93 +++++++++++++++++++++++++++++++++++
include/linux/blkdev.h | 2 +
include/linux/pr.h | 18 +++++++
include/uapi/linux/pr.h | 48 ++++++++++++++++++
5 files changed, 280 insertions(+)
create mode 100644 Documentation/block/pr.txt
create mode 100644 include/linux/pr.h
create mode 100644 include/uapi/linux/pr.h
diff --git a/Documentation/block/pr.txt b/Documentation/block/pr.txt
new file mode 100644
index 0000000..d3eb1ca
--- /dev/null
+++ b/Documentation/block/pr.txt
@@ -0,0 +1,119 @@
+
+Block layer support for Persistent Reservations
+===============================================
+
+The Linux kernel supports a user space interface for simplified
+Persistent Reservations which map to block devices that support
+these (like SCSI). Persistent Reservations allow restricting
+access to block devices to specific initiators in a shared storage
+setup.
+
+This document gives a general overview of the support ioctl commands.
+For a more detailed reference please refer the the SCSI Primary
+Commands standard, specifically the section on Reservations and the
+"PERSISTENT RESERVE IN" and "PERSISTENT RESERVE OUT" commands.
+
+All implementations are expected to ensure the reservations survive
+a power loss and cover all connections in a multi path environment.
+These behaviors are optional in SPC but will be automatically applied
+by Linux.
+
+
+The following types of reservations are supported:
+--------------------------------------------------
+
+ - PR_WRITE_EXCLUSIVE
+
+ Only the initiator that owns the reservation can write to the
+ device. Any initiator can read from the device.
+
+ - PR_EXCLUSIVE_ACCESS
+
+ Only the initiator that owns the reservation can access the
+ device.
+
+ - PR_WRITE_EXCLUSIVE_REG_ONLY
+
+ Only initiators with a registered key can write to the device,
+ Any initiator can read from the device.
+
+ - PR_EXCLUSIVE_ACCESS_REG_ONLY
+
+ Only initiators with a registered key can access the device.
+
+ - PR_WRITE_EXCLUSIVE_ALL_REGS
+
+ Only initiators with a registered key can write to the device,
+ Any initiator can read from the device.
+ All initiators with a registered key are considered reservation
+ holders.
+ Please reference the SPC spec on the meaning of a reservation
+ holder if you want to use this type.
+
+ - PR_EXCLUSIVE_ACCESS_ALL_REGS
+
+ Only initiators with a registered key can access the device.
+ All initiators with a registered key are considered reservation
+ holders.
+ Please reference the SPC spec on the meaning of a reservation
+ holder if you want to use this type.
+
+
+The following ioctl are supported:
+----------------------------------
+
+1. IOC_PR_REGISTER
+
+This ioctl command registers a new reservation if the new_key argument
+is non-null. If no existing reservation exists old_key must be zero,
+if an existing reservation should be replaced old_key must contain
+the old reservation key.
+
+If the new_key argument is 0 it unregisters the existing reservation passed
+in old_key.
+
+
+2. IOC_PR_RESERVE
+
+This ioctl command reserves the device and thus restricts access for other
+devices based on the type argument. The key argument must be the existing
+reservation key for the device as acquired by the IOC_PR_REGISTER,
+IOC_PR_REGISTER_IGNORE, IOC_PR_PREEMPT or IOC_PR_PREEMPT_ABORT commands.
+
+
+3. IOC_PR_RELEASE
+
+This ioctl command releases the reservation specified by key and flags
+and thus removes any access restriction implied by it.
+
+
+4. IOC_PR_PREEMPT
+
+This ioctl command releases the existing reservation referred to by
+old_key and replaces it with a a new reservation of type for the
+reservation key new_key.
+
+
+5. IOC_PR_PREEMPT_ABORT
+
+This ioctl command works like IOC_PR_PREEMPT except that it also aborts
+any outstanding command sent over a connection identified by old_key.
+
+6. IOC_PR_CLEAR
+
+This ioctl command unregisters both key and any other reservation key
+registered with the device and drops any existing reservation.
+
+
+Flags
+-----
+
+All the ioctls have a flag field. Currently only one flag is supported:
+
+ - PR_FL_IGNORE_KEY
+
+ Ignore the existing reservation key. This is commonly supported for
+ IOC_PR_REGISTER, and some implementation may support the flag for
+ IOC_PR_RESERVE.
+
+For all unknown flags the kernel will return -EOPNOTSUPP.
diff --git a/block/ioctl.c b/block/ioctl.c
index df62b47..9c83e72 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -7,6 +7,7 @@
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/blktrace_api.h>
+#include <linux/pr.h>
#include <asm/uaccess.h>
static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
@@ -295,6 +296,86 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
*/
EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
+static int blkdev_pr_register(struct block_device *bdev,
+ struct pr_registration __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_registration reg;
+
+ if (!ops || !ops->pr_register)
+ return -EOPNOTSUPP;
+ if (copy_from_user(®, arg, sizeof(reg)))
+ return -EFAULT;
+
+ if (reg.flags & ~PR_FL_IGNORE_KEY)
+ return -EOPNOTSUPP;
+ return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);
+}
+
+static int blkdev_pr_reserve(struct block_device *bdev,
+ struct pr_reservation __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_reservation rsv;
+
+ if (!ops || !ops->pr_reserve)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&rsv, arg, sizeof(rsv)))
+ return -EFAULT;
+
+ if (rsv.flags & ~PR_FL_IGNORE_KEY)
+ return -EOPNOTSUPP;
+ return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);
+}
+
+static int blkdev_pr_release(struct block_device *bdev,
+ struct pr_reservation __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_reservation rsv;
+
+ if (!ops || !ops->pr_release)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&rsv, arg, sizeof(rsv)))
+ return -EFAULT;
+
+ if (rsv.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_release(bdev, rsv.key, rsv.type);
+}
+
+static int blkdev_pr_preempt(struct block_device *bdev,
+ struct pr_preempt __user *arg, bool abort)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_preempt p;
+
+ if (!ops || !ops->pr_preempt)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&p, arg, sizeof(p)))
+ return -EFAULT;
+
+ if (p.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);
+}
+
+static int blkdev_pr_clear(struct block_device *bdev,
+ struct pr_clear __user *arg)
+{
+ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+ struct pr_clear c;
+
+ if (!ops || !ops->pr_clear)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&c, arg, sizeof(c)))
+ return -EFAULT;
+
+ if (c.flags)
+ return -EOPNOTSUPP;
+ return ops->pr_clear(bdev, c.key);
+}
+
/*
* Is it an unrecognized ioctl? The correct returns are either
* ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a
@@ -477,6 +558,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
return blk_trace_ioctl(bdev, cmd, argp);
+ case IOC_PR_REGISTER:
+ return blkdev_pr_register(bdev, argp);
+ case IOC_PR_RESERVE:
+ return blkdev_pr_reserve(bdev, argp);
+ case IOC_PR_RELEASE:
+ return blkdev_pr_release(bdev, argp);
+ case IOC_PR_PREEMPT:
+ return blkdev_pr_preempt(bdev, argp, false);
+ case IOC_PR_PREEMPT_ABORT:
+ return blkdev_pr_preempt(bdev, argp, true);
+ case IOC_PR_CLEAR:
+ return blkdev_pr_clear(bdev, argp);
default:
return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a622f27..70b185e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -35,6 +35,7 @@ struct sg_io_hdr;
struct bsg_job;
struct blkcg_gq;
struct blk_flush_queue;
+struct pr_ops;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
@@ -1581,6 +1582,7 @@ struct block_device_operations {
/* this callback is with swap_lock and sometimes page table lock held */
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
struct module *owner;
+ const struct pr_ops *pr_ops;
};
extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
diff --git a/include/linux/pr.h b/include/linux/pr.h
new file mode 100644
index 0000000..65c01c1
--- /dev/null
+++ b/include/linux/pr.h
@@ -0,0 +1,18 @@
+#ifndef LINUX_PR_H
+#define LINUX_PR_H
+
+#include <uapi/linux/pr.h>
+
+struct pr_ops {
+ int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags);
+ int (*pr_reserve)(struct block_device *bdev, u64 key,
+ enum pr_type type, u32 flags);
+ int (*pr_release)(struct block_device *bdev, u64 key,
+ enum pr_type type);
+ int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort);
+ int (*pr_clear)(struct block_device *bdev, u64 key);
+};
+
+#endif /* LINUX_PR_H */
diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h
new file mode 100644
index 0000000..57d7c0f
--- /dev/null
+++ b/include/uapi/linux/pr.h
@@ -0,0 +1,48 @@
+#ifndef _UAPI_PR_H
+#define _UAPI_PR_H
+
+enum pr_type {
+ PR_WRITE_EXCLUSIVE = 1,
+ PR_EXCLUSIVE_ACCESS = 2,
+ PR_WRITE_EXCLUSIVE_REG_ONLY = 3,
+ PR_EXCLUSIVE_ACCESS_REG_ONLY = 4,
+ PR_WRITE_EXCLUSIVE_ALL_REGS = 5,
+ PR_EXCLUSIVE_ACCESS_ALL_REGS = 6,
+};
+
+struct pr_reservation {
+ __u64 key;
+ __u32 type;
+ __u32 flags;
+};
+
+struct pr_registration {
+ __u64 old_key;
+ __u64 new_key;
+ __u32 flags;
+ __u32 __pad;
+};
+
+struct pr_preempt {
+ __u64 old_key;
+ __u64 new_key;
+ __u32 type;
+ __u32 flags;
+};
+
+struct pr_clear {
+ __u64 key;
+ __u32 flags;
+ __u32 __pad;
+};
+
+#define PR_FL_IGNORE_KEY (1 << 0) /* ignore existing key */
+
+#define IOC_PR_REGISTER _IOW('p', 200, struct pr_registration)
+#define IOC_PR_RESERVE _IOW('p', 201, struct pr_reservation)
+#define IOC_PR_RELEASE _IOW('p', 202, struct pr_reservation)
+#define IOC_PR_PREEMPT _IOW('p', 203, struct pr_preempt)
+#define IOC_PR_PREEMPT_ABORT _IOW('p', 204, struct pr_preempt)
+#define IOC_PR_CLEAR _IOW('p', 205, struct pr_clear)
+
+#endif /* _UAPI_PR_H */
--
1.9.1
^ permalink raw reply related
* [PATCH 3/5] sd: implement the Persistent Reservation API
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA,
linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA, linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1440608214-14497-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
This is a mostly trivial mapping to the PERSISTENT RESERVE IN/OUT
commands.
Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
drivers/scsi/sd.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 94 insertions(+)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 160e44e..df8e667 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -51,6 +51,7 @@
#include <linux/async.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
+#include <linux/pr.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
@@ -1535,6 +1536,98 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
}
#endif
+static char sd_pr_type(enum pr_type type)
+{
+ switch (type) {
+ case PR_WRITE_EXCLUSIVE:
+ return 0x01;
+ case PR_EXCLUSIVE_ACCESS:
+ return 0x03;
+ case PR_WRITE_EXCLUSIVE_REG_ONLY:
+ return 0x05;
+ case PR_EXCLUSIVE_ACCESS_REG_ONLY:
+ return 0x06;
+ case PR_WRITE_EXCLUSIVE_ALL_REGS:
+ return 0x07;
+ case PR_EXCLUSIVE_ACCESS_ALL_REGS:
+ return 0x08;
+ default:
+ return 0;
+ }
+};
+
+static int sd_pr_command(struct block_device *bdev, u8 sa,
+ u64 key, u64 sa_key, u8 type, u8 flags)
+{
+ struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
+ struct scsi_sense_hdr sshdr;
+ int result;
+ u8 cmd[16] = { 0, };
+ u8 data[24] = { 0, };
+
+ cmd[0] = PERSISTENT_RESERVE_OUT;
+ cmd[1] = sa;
+ cmd[2] = type;
+ put_unaligned_be32(sizeof(data), &cmd[5]);
+
+ put_unaligned_be64(key, &data[0]);
+ put_unaligned_be64(sa_key, &data[8]);
+ data[20] = flags;
+
+ result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
+ &sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
+
+ if ((driver_byte(result) & DRIVER_SENSE) &&
+ (scsi_sense_valid(&sshdr))) {
+ sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
+ scsi_print_sense_hdr(sdev, NULL, &sshdr);
+ }
+
+ return result;
+}
+
+static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags)
+{
+ return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
+ old_key, new_key, 0,
+ (1 << 0) /* APTPL */ |
+ (1 << 2) /* ALL_TG_PT */);
+}
+
+static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
+ u32 flags)
+{
+ if (flags)
+ return -EOPNOTSUPP;
+ return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+ return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
+}
+
+static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort)
+{
+ return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
+ sd_pr_type(type), 0);
+}
+
+static int sd_pr_clear(struct block_device *bdev, u64 key)
+{
+ return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
+}
+
+static const struct pr_ops sd_pr_ops = {
+ .pr_register = sd_pr_register,
+ .pr_reserve = sd_pr_reserve,
+ .pr_release = sd_pr_release,
+ .pr_preempt = sd_pr_preempt,
+ .pr_clear = sd_pr_clear,
+};
+
static const struct block_device_operations sd_fops = {
.owner = THIS_MODULE,
.open = sd_open,
@@ -1547,6 +1640,7 @@ static const struct block_device_operations sd_fops = {
.check_events = sd_check_events,
.revalidate_disk = sd_revalidate_disk,
.unlock_native_capacity = sd_unlock_native_capacity,
+ .pr_ops = &sd_pr_ops,
};
/**
--
1.9.1
^ permalink raw reply related
* [PATCH 4/5] dm: refactor ioctl handling
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
In-Reply-To: <1440608214-14497-1-git-send-email-hch@lst.de>
This moves the call to blkdev_ioctl and the argument checking to core code,
and only leaves a callout to find the block device to operate on it the
targets. This will simplifies the code and will allow us to pass through
ioctl-like command using other methods in the next patch.
Also split out a helper around calling the prepare_ioctl method that will
be reused for persistent reservation handling.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/dm-flakey.c | 16 +++++++-------
drivers/md/dm-linear.c | 14 ++++++------
drivers/md/dm-log-writes.c | 13 ++++++-----
drivers/md/dm-mpath.c | 32 +++++++++++----------------
drivers/md/dm-switch.c | 21 ++++++++----------
drivers/md/dm-verity.c | 15 ++++++-------
drivers/md/dm.c | 50 ++++++++++++++++++++++++++++++++-----------
include/linux/device-mapper.h | 6 +++---
8 files changed, 89 insertions(+), 78 deletions(-)
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index afab13b..c177d88 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -371,20 +371,20 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
}
}
-static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long arg)
+static int flakey_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct flakey_c *fc = ti->private;
- struct dm_dev *dev = fc->dev;
- int r = 0;
+
+ *bdev = fc->dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (fc->start ||
- ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return 0;
}
static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
@@ -403,7 +403,7 @@ static struct target_type flakey_target = {
.map = flakey_map,
.end_io = flakey_end_io,
.status = flakey_status,
- .ioctl = flakey_ioctl,
+ .prepare_ioctl = flakey_prepare_ioctl,
.iterate_devices = flakey_iterate_devices,
};
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 7dd5fc8..0986baa 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -113,21 +113,21 @@ static void linear_status(struct dm_target *ti, status_type_t type,
}
}
-static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int linear_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct linear_c *lc = (struct linear_c *) ti->private;
struct dm_dev *dev = lc->dev;
- int r = 0;
+
+ *bdev = dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (lc->start ||
ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ return 1;
+ return 0;
}
static int linear_iterate_devices(struct dm_target *ti,
@@ -146,7 +146,7 @@ static struct target_type linear_target = {
.dtr = linear_dtr,
.map = linear_map,
.status = linear_status,
- .ioctl = linear_ioctl,
+ .prepare_ioctl = linear_prepare_ioctl,
.iterate_devices = linear_iterate_devices,
};
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 316cc3f..bc57ad1 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -709,20 +709,19 @@ static void log_writes_status(struct dm_target *ti, status_type_t type,
}
}
-static int log_writes_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int log_writes_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct log_writes_c *lc = ti->private;
struct dm_dev *dev = lc->dev;
- int r = 0;
+ *bdev = dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
+ return 1;
+ return 0;
}
static int log_writes_iterate_devices(struct dm_target *ti,
@@ -777,7 +776,7 @@ static struct target_type log_writes_target = {
.map = log_writes_map,
.end_io = normal_end_io,
.status = log_writes_status,
- .ioctl = log_writes_ioctl,
+ .prepare_ioctl = log_writes_prepare_ioctl,
.message = log_writes_message,
.iterate_devices = log_writes_iterate_devices,
.io_hints = log_writes_io_hints,
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index eff7bdd..97cf835 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1548,18 +1548,14 @@ out:
return r;
}
-static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
- unsigned long arg)
+static int multipath_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct multipath *m = ti->private;
struct pgpath *pgpath;
- struct block_device *bdev;
- fmode_t mode;
unsigned long flags;
int r;
- bdev = NULL;
- mode = 0;
r = 0;
spin_lock_irqsave(&m->lock, flags);
@@ -1570,26 +1566,17 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
pgpath = m->current_pgpath;
if (pgpath) {
- bdev = pgpath->path.dev->bdev;
- mode = pgpath->path.dev->mode;
+ *bdev = pgpath->path.dev->bdev;
+ *mode = pgpath->path.dev->mode;
}
if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
r = -ENOTCONN;
- else if (!bdev)
+ else if (!*bdev)
r = -EIO;
spin_unlock_irqrestore(&m->lock, flags);
- /*
- * Only pass ioctls through if the device sizes match exactly.
- */
- if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
- int err = scsi_verify_blk_ioctl(NULL, cmd);
- if (err)
- r = err;
- }
-
if (r == -ENOTCONN && !fatal_signal_pending(current)) {
spin_lock_irqsave(&m->lock, flags);
if (!m->current_pg) {
@@ -1602,7 +1589,12 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
dm_table_run_md_queue_async(m->ti->table);
}
- return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ /*
+ * Only pass ioctls through if the device sizes match exactly.
+ */
+ if (!r && ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return r;
}
static int multipath_iterate_devices(struct dm_target *ti,
@@ -1718,7 +1710,7 @@ static struct target_type multipath_target = {
.resume = multipath_resume,
.status = multipath_status,
.message = multipath_message,
- .ioctl = multipath_ioctl,
+ .prepare_ioctl = multipath_prepare_ioctl,
.iterate_devices = multipath_iterate_devices,
.busy = multipath_busy,
};
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index 50fca46..b128575 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -511,27 +511,24 @@ static void switch_status(struct dm_target *ti, status_type_t type,
*
* Passthrough all ioctls to the path for sector 0
*/
-static int switch_ioctl(struct dm_target *ti, unsigned cmd,
- unsigned long arg)
+static int switch_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct switch_ctx *sctx = ti->private;
- struct block_device *bdev;
- fmode_t mode;
unsigned path_nr;
- int r = 0;
path_nr = switch_get_path_nr(sctx, 0);
- bdev = sctx->path_list[path_nr].dmdev->bdev;
- mode = sctx->path_list[path_nr].dmdev->mode;
+ *bdev = sctx->path_list[path_nr].dmdev->bdev;
+ *mode = sctx->path_list[path_nr].dmdev->mode;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (ti->len + sctx->path_list[path_nr].start != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+ if (ti->len + sctx->path_list[path_nr].start !=
+ i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT)
+ return 1;
+ return 0;
}
static int switch_iterate_devices(struct dm_target *ti,
@@ -560,7 +557,7 @@ static struct target_type switch_target = {
.map = switch_map,
.message = switch_message,
.status = switch_status,
- .ioctl = switch_ioctl,
+ .prepare_ioctl = switch_prepare_ioctl,
.iterate_devices = switch_iterate_devices,
};
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index c137dcb..509fa05 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -635,18 +635,17 @@ static void verity_status(struct dm_target *ti, status_type_t type,
}
}
-static int verity_ioctl(struct dm_target *ti, unsigned cmd,
- unsigned long arg)
+static int verity_prepare_ioctl(struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode)
{
struct dm_verity *v = ti->private;
- int r = 0;
+
+ *bdev = v->data_dev->bdev;
if (v->data_start ||
ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- return r ? : __blkdev_driver_ioctl(v->data_dev->bdev, v->data_dev->mode,
- cmd, arg);
+ return 1;
+ return 0;
}
static int verity_iterate_devices(struct dm_target *ti,
@@ -980,7 +979,7 @@ static struct target_type verity_target = {
.dtr = verity_dtr,
.map = verity_map,
.status = verity_status,
- .ioctl = verity_ioctl,
+ .prepare_ioctl = verity_prepare_ioctl,
.iterate_devices = verity_iterate_devices,
.io_hints = verity_io_hints,
};
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6ffc01b..85dc14c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -555,18 +555,16 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
return dm_get_geometry(md, geo);
}
-static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
- unsigned int cmd, unsigned long arg)
+static int dm_get_live_table_for_ioctl(struct mapped_device *md,
+ struct dm_target **tgt, struct block_device **bdev,
+ fmode_t *mode, int *srcu_idx)
{
- struct mapped_device *md = bdev->bd_disk->private_data;
- int srcu_idx;
struct dm_table *map;
- struct dm_target *tgt;
- int r = -ENOTTY;
+ int r;
retry:
- map = dm_get_live_table(md, &srcu_idx);
-
+ r = -ENOTTY;
+ map = dm_get_live_table(md, srcu_idx);
if (!map || !dm_table_get_size(map))
goto out;
@@ -574,8 +572,9 @@ retry:
if (dm_table_get_num_targets(map) != 1)
goto out;
- tgt = dm_table_get_target(map, 0);
- if (!tgt->type->ioctl)
+ *tgt = dm_table_get_target(map, 0);
+
+ if (!(*tgt)->type->prepare_ioctl)
goto out;
if (dm_suspended_md(md)) {
@@ -583,16 +582,41 @@ retry:
goto out;
}
- r = tgt->type->ioctl(tgt, cmd, arg);
+ r = (*tgt)->type->prepare_ioctl(*tgt, bdev, mode);
+ if (r < 0)
+ goto out;
-out:
- dm_put_live_table(md, srcu_idx);
+ return r;
+out:
+ dm_put_live_table(md, *srcu_idx);
if (r == -ENOTCONN) {
msleep(10);
goto retry;
}
+ return r;
+}
+
+static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned int cmd, unsigned long arg)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ struct dm_target *tgt;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ if (r > 0) {
+ r = scsi_verify_blk_ioctl(NULL, cmd);
+ if (r)
+ goto out;
+ }
+ r = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+out:
+ dm_put_live_table(md, srcu_idx);
return r;
}
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 76d23fa..ec1c61c 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -79,8 +79,8 @@ typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
-typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
- unsigned long arg);
+typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti,
+ struct block_device **bdev, fmode_t *mode);
/*
* These iteration functions are typically used to check (and combine)
@@ -156,7 +156,7 @@ struct target_type {
dm_resume_fn resume;
dm_status_fn status;
dm_message_fn message;
- dm_ioctl_fn ioctl;
+ dm_prepare_ioctl_fn prepare_ioctl;
dm_busy_fn busy;
dm_iterate_devices_fn iterate_devices;
dm_io_hints_fn io_hints;
--
1.9.1
^ permalink raw reply related
* [PATCH 5/5] dm: add support for passing through persistent reservations
From: Christoph Hellwig @ 2015-08-26 16:56 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-scsi, linux-nvme, dm-devel, linux-api, linux-kernel
In-Reply-To: <1440608214-14497-1-git-send-email-hch@lst.de>
This adds support to pass through persistent reservation requests
similar to the existing ioctl handling, and with the same limitations,
e.g. devices may only have a single target attached.
This is mostly intended for multipathing.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/dm.c | 123 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 85dc14c..c3eadbe 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -24,6 +24,7 @@
#include <linux/ktime.h>
#include <linux/elevator.h> /* for rq_end_sector() */
#include <linux/blk-mq.h>
+#include <linux/pr.h>
#include <trace/events/block.h>
@@ -3544,11 +3545,133 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
kfree(pools);
}
+static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
+ u32 flags)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_register)
+ r = ops->pr_register(bdev, old_key, new_key, flags);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
+ u32 flags)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_reserve)
+ r = ops->pr_reserve(bdev, key, type, flags);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_release)
+ r = ops->pr_release(bdev, key, type);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
+ enum pr_type type, bool abort)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_preempt)
+ r = ops->pr_preempt(bdev, old_key, new_key, type, abort);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static int dm_pr_clear(struct block_device *bdev, u64 key)
+{
+ struct mapped_device *md = bdev->bd_disk->private_data;
+ const struct pr_ops *ops;
+ struct dm_target *tgt;
+ fmode_t mode;
+ int srcu_idx, r;
+
+ r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+ if (r < 0)
+ return r;
+
+ ops = bdev->bd_disk->fops->pr_ops;
+ if (ops && ops->pr_clear)
+ r = ops->pr_clear(bdev, key);
+ else
+ r = -EOPNOTSUPP;
+
+ dm_put_live_table(md, srcu_idx);
+ return r;
+}
+
+static const struct pr_ops dm_pr_ops = {
+ .pr_register = dm_pr_register,
+ .pr_reserve = dm_pr_reserve,
+ .pr_release = dm_pr_release,
+ .pr_preempt = dm_pr_preempt,
+ .pr_clear = dm_pr_clear,
+};
+
static const struct block_device_operations dm_blk_dops = {
.open = dm_blk_open,
.release = dm_blk_close,
.ioctl = dm_blk_ioctl,
.getgeo = dm_blk_getgeo,
+ .pr_ops = &dm_pr_ops,
.owner = THIS_MODULE
};
--
1.9.1
^ permalink raw reply related
* Re: [PATCH 2/5] coresight-etm4x: Change the name of the ctxid_val to ctxid_pid
From: Christopher Covington @ 2015-08-26 17:57 UTC (permalink / raw)
To: Chunyan Zhang, mathieu.poirier-QSEj5FYQhm4dnm+yROfE0A,
gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r
Cc: broonie-DgEjT+Ai2ygdnm+yROfE0A,
serge.broslavsky-QSEj5FYQhm4dnm+yROfE0A,
zhang.lyra-Re5JQEeQqe8AvxtiuMwx3w,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1436258518-9339-3-git-send-email-zhang.chunyan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
On 07/07/2015 04:41 AM, Chunyan Zhang wrote:
> 'ctxid_val' array was used to store the value of ETM context ID comparator
> which actually stores the process ID to be traced, so using 'ctxid_pid' as
> its name instead make it easier to understand.
Previous discussion with some ARM folks has led me to believe there isn't a
guarantee that the Context ID Register will always have a PID. Why not allow
filtering on thread group ID, session ID, cgroup related identifiers, etc.?
> This patch also changes the ABI, it is normally not allowed, but
> fortunately it is a testing ABI and very new for now. Nevertheless,
> if you don't think it should be changed, we could always add an alias
> for userspace.
>
> Signed-off-by: Chunyan Zhang <zhang.chunyan-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> Reviewed-by: Mark Brown <broonie-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
> ---
> .../ABI/testing/sysfs-bus-coresight-devices-etm4x | 2 +-
> drivers/hwtracing/coresight/coresight-etm4x.c | 20 ++++++++++----------
> drivers/hwtracing/coresight/coresight-etm4x.h | 4 ++--
> 3 files changed, 13 insertions(+), 13 deletions(-)
>
> diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
> index 2fe2e3d..2355ed8 100644
> --- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
> +++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
> @@ -249,7 +249,7 @@ KernelVersion: 4.01
> Contact: Mathieu Poirier <mathieu.poirier-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> Description: (RW) Select which context ID comparator to work with.
>
> -What: /sys/bus/coresight/devices/<memory_map>.etm/ctxid_val
> +What: /sys/bus/coresight/devices/<memory_map>.etm/ctxid_pid
> Date: April 2015
> KernelVersion: 4.01
> Contact: Mathieu Poirier <mathieu.poirier-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
> index 1312e99..9afbda5 100644
> --- a/drivers/hwtracing/coresight/coresight-etm4x.c
> +++ b/drivers/hwtracing/coresight/coresight-etm4x.c
> @@ -155,7 +155,7 @@ static void etm4_enable_hw(void *info)
> drvdata->base + TRCACATRn(i));
> }
> for (i = 0; i < drvdata->numcidc; i++)
> - writeq_relaxed(drvdata->ctxid_val[i],
> + writeq_relaxed(drvdata->ctxid_pid[i],
> drvdata->base + TRCCIDCVRn(i));
> writel_relaxed(drvdata->ctxid_mask0, drvdata->base + TRCCIDCCTLR0);
> writel_relaxed(drvdata->ctxid_mask1, drvdata->base + TRCCIDCCTLR1);
> @@ -507,7 +507,7 @@ static ssize_t reset_store(struct device *dev,
>
> drvdata->ctxid_idx = 0x0;
> for (i = 0; i < drvdata->numcidc; i++)
> - drvdata->ctxid_val[i] = 0x0;
> + drvdata->ctxid_pid[i] = 0x0;
> drvdata->ctxid_mask0 = 0x0;
> drvdata->ctxid_mask1 = 0x0;
>
> @@ -1815,7 +1815,7 @@ static ssize_t ctxid_idx_store(struct device *dev,
> }
> static DEVICE_ATTR_RW(ctxid_idx);
>
> -static ssize_t ctxid_val_show(struct device *dev,
> +static ssize_t ctxid_pid_show(struct device *dev,
> struct device_attribute *attr,
> char *buf)
> {
> @@ -1825,12 +1825,12 @@ static ssize_t ctxid_val_show(struct device *dev,
>
> spin_lock(&drvdata->spinlock);
> idx = drvdata->ctxid_idx;
> - val = (unsigned long)drvdata->ctxid_val[idx];
> + val = (unsigned long)drvdata->ctxid_pid[idx];
> spin_unlock(&drvdata->spinlock);
> return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
> }
>
> -static ssize_t ctxid_val_store(struct device *dev,
> +static ssize_t ctxid_pid_store(struct device *dev,
> struct device_attribute *attr,
> const char *buf, size_t size)
> {
> @@ -1850,11 +1850,11 @@ static ssize_t ctxid_val_store(struct device *dev,
>
> spin_lock(&drvdata->spinlock);
> idx = drvdata->ctxid_idx;
> - drvdata->ctxid_val[idx] = (u64)val;
> + drvdata->ctxid_pid[idx] = (u64)val;
> spin_unlock(&drvdata->spinlock);
> return size;
> }
> -static DEVICE_ATTR_RW(ctxid_val);
> +static DEVICE_ATTR_RW(ctxid_pid);
>
> static ssize_t ctxid_masks_show(struct device *dev,
> struct device_attribute *attr,
> @@ -1949,7 +1949,7 @@ static ssize_t ctxid_masks_store(struct device *dev,
> */
> for (j = 0; j < 8; j++) {
> if (maskbyte & 1)
> - drvdata->ctxid_val[i] &= ~(0xFF << (j * 8));
> + drvdata->ctxid_pid[i] &= ~(0xFF << (j * 8));
> maskbyte >>= 1;
> }
> /* Select the next ctxid comparator mask value */
> @@ -2193,7 +2193,7 @@ static struct attribute *coresight_etmv4_attrs[] = {
> &dev_attr_res_idx.attr,
> &dev_attr_res_ctrl.attr,
> &dev_attr_ctxid_idx.attr,
> - &dev_attr_ctxid_val.attr,
> + &dev_attr_ctxid_pid.attr,
> &dev_attr_ctxid_masks.attr,
> &dev_attr_vmid_idx.attr,
> &dev_attr_vmid_val.attr,
> @@ -2514,7 +2514,7 @@ static void etm4_init_default_data(struct etmv4_drvdata *drvdata)
> }
>
> for (i = 0; i < drvdata->numcidc; i++)
> - drvdata->ctxid_val[i] = 0x0;
> + drvdata->ctxid_pid[i] = 0x0;
> drvdata->ctxid_mask0 = 0x0;
> drvdata->ctxid_mask1 = 0x0;
>
> diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
> index e08e983..1e8fb36 100644
> --- a/drivers/hwtracing/coresight/coresight-etm4x.h
> +++ b/drivers/hwtracing/coresight/coresight-etm4x.h
> @@ -265,7 +265,7 @@
> * @addr_type: Current status of the comparator register.
> * @ctxid_idx: Context ID index selector.
> * @ctxid_size: Size of the context ID field to consider.
> - * @ctxid_val: Value of the context ID comparator.
> + * @ctxid_pid: Value of the context ID comparator.
> * @ctxid_mask0:Context ID comparator mask for comparator 0-3.
> * @ctxid_mask1:Context ID comparator mask for comparator 4-7.
> * @vmid_idx: VM ID index selector.
> @@ -352,7 +352,7 @@ struct etmv4_drvdata {
> u8 addr_type[ETM_MAX_SINGLE_ADDR_CMP];
> u8 ctxid_idx;
> u8 ctxid_size;
> - u64 ctxid_val[ETMv4_MAX_CTXID_CMP];
> + u64 ctxid_pid[ETMv4_MAX_CTXID_CMP];
> u32 ctxid_mask0;
> u32 ctxid_mask1;
> u8 vmid_idx;
>
--
Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
^ permalink raw reply
* hello
From: Chistinam Hammock @ 2015-08-26 18:02 UTC (permalink / raw)
Bună dragă prietene,
Do you speak English
I'M Christina M Hammock. Sunt o REGATUL militare de stat / NASA.
De la stat Unite ale Americii. Sunt de susținere și îngrijire,
așteaptă cu nerăbdare pentru a obține
un prieten frumos. Am citit profilul dvs. de la facebook.com și alege
interes pe tine. Voi dori să
stabili prietenie reciprocă cu tine. Vă rugăm să continuați conversația
prin cutia mea de e-mail privat. Aici este adresa mea de e-mail
{christinamhammock2-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org} Voi mă prezint mai bine și vă va
trimite poza mea, cât mai curând am primit
e-mail-ul.
Multumesc.
Christina M Hamac.
christinamhammock2-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
^ permalink raw reply
* Re: [PATCH v2 0/3] SysFS driver for QEMU fw_cfg device
From: Christopher Covington @ 2015-08-26 18:15 UTC (permalink / raw)
To: Gabriel L. Somlo, Ard Biesheuvel
Cc: paul, Matt Fleming, Richard W.M. Jones, Leif Lindholm,
Jordan Justen, x86@kernel.org, QEMU Developers, gleb, galak,
kernelnewbies, Gerd Hoffmann, gregkh@linuxfoundation.org,
Paolo Bonzini, zajec5, linux-api, Laszlo Ersek,
linux-kernel@vger.kernel.org
In-Reply-To: <20150819204915.GA6164@GLSMBP.INI.CMU.EDU>
Hi Gabriel,
On 08/19/2015 04:49 PM, Gabriel L. Somlo wrote:
> Hi Ard,
>
> On Wed, Aug 19, 2015 at 11:42:02AM +0200, Ard Biesheuvel wrote:
>> (missed some cc's)
>>
>> On 19 August 2015 at 11:38, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
>>> From: "Gabriel L. Somlo" <somlo@cmu.edu>
>>>> Several different architectures supported by QEMU are set up with a
>>>> "firmware configuration" (fw_cfg) device, used to pass configuration
>>>> "blobs" into the guest by the host running QEMU.
>>>>
>>>> Historically, these config blobs were mostly of interest to the guest
>>>> BIOS, but since QEMU v2.4 it is possible to insert arbitrary blobs via
>>>> the command line, which makes them potentially interesting to userspace
>>>> (e.g. for passing early boot environment variables, etc.).
>>>>
>>>
>>> Does 'potentially interesting' mean you have a use case? Could you elaborate?
>
> My personal one would be something like:
>
> cat > guestinfo.txt << EOT
> KEY1="val1"
> KEY2="val2"
> ...
> EOT
>
> qemu-system-x86_64 ... -fw-cfg name="opt/guestinfo",file=./guestinfo.txt ...
>
> Then, from inside the guest:
>
> . /sys/firmware/qemu_fw_cfg/by_name/opt/guestinfo/raw
>
> do_something_with $KEY1 $KEY2
> ...
>
> But I'm thinking this is only one of the many positive things one
> could do with the ability to access random host-supplied blobs from
> guest userspace :)
I do this with kernel parameters:
host:
qemu-system-aarch64 -append="KEY1=val1 KEY2=val2"
guest:
KEY1=`sed -nr s/.*KEY1=([^ ]+).*/\1/ /proc/cmdline`
KEY2=`sed -nr s/.*KEY2=([^ ]+).*/\1/ /proc/cmdline`
do_something_with $KEY1 $KEY2
In practice it's just script=hostfile, where hostfile is available to the
guest via a 9P passthrough filesystem mount.
While quite architecture specific, I've also previously used an
"angel-cmdline" tool for similar purposes. Peter's recent semihosting patches
support such a tool for AArch64. (On AArch32 upstream QEMU disallows
semihosting from userspace.)
Before I had 9P on all the simulators I regularly ran, I used a semihosting
based "angel-load" tool.
Regards,
Christopher Covington
--
Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
^ permalink raw reply
* [PATCH v8 0/6] Allow user to request memory to be locked on page fault
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Shuah Khan, Michal Hocko, Michael Kerrisk,
Vlastimil Babka, Jonathan Corbet, Ralf Baechle, Andrea Arcangeli,
linux-alpha, linux-kernel, linux-mips, linux-parisc, linuxppc-dev,
sparclinux, linux-xtensa, linux-mm, linux-arch, linux-api
mlock() allows a user to control page out of program memory, but this
comes at the cost of faulting in the entire mapping when it is
allocated. For large mappings where the entire area is not necessary
this is not ideal. Instead of forcing all locked pages to be present
when they are allocated, this set creates a middle ground. Pages are
marked to be placed on the unevictable LRU (locked) when they are first
used, but they are not faulted in by the mlock call.
This series introduces a new mlock() system call that takes a flags
argument along with the start address and size. This flags argument
gives the caller the ability to request memory be locked in the
traditional way, or to be locked after the page is faulted in. A new
MCL flag is added to mirror the lock on fault behavior from mlock() in
mlockall().
There are two main use cases that this set covers. The first is the
security focussed mlock case. A buffer is needed that cannot be written
to swap. The maximum size is known, but on average the memory used is
significantly less than this maximum. With lock on fault, the buffer
is guaranteed to never be paged out without consuming the maximum size
every time such a buffer is created.
The second use case is focussed on performance. Portions of a large
file are needed and we want to keep the used portions in memory once
accessed. This is the case for large graphical models where the path
through the graph is not known until run time. The entire graph is
unlikely to be used in a given invocation, but once a node has been
used it needs to stay resident for further processing. Given these
constraints we have a number of options. We can potentially waste a
large amount of memory by mlocking the entire region (this can also
cause a significant stall at startup as the entire file is read in).
We can mlock every page as we access them without tracking if the page
is already resident but this introduces large overhead for each access.
The third option is mapping the entire region with PROT_NONE and using
a signal handler for SIGSEGV to mprotect(PROT_READ) and mlock() the
needed page. Doing this page at a time adds a significant performance
penalty. Batching can be used to mitigate this overhead, but in order
to safely avoid trying to mprotect pages outside of the mapping, the
boundaries of each mapping to be used in this way must be tracked and
available to the signal handler. This is precisely what the mm system
in the kernel should already be doing.
For mlock(MLOCK_ONFAULT) the user is charged against RLIMIT_MEMLOCK as
if mlock(MLOCK_LOCKED) or mmap(MAP_LOCKED) was used, so when the VMA is
created not when the pages are faulted in. For mlockall(MCL_ONFAULT)
the user is charged as if MCL_FUTURE was used. This decision was made
to keep the accounting checks out of the page fault path.
To illustrate the benefit of this set I wrote a test program that mmaps
a 5 GB file filled with random data and then makes 15,000,000 accesses
to random addresses in that mapping. The test program was run 20 times
for each setup. Results are reported for two program portions, setup
and execution. The setup phase is calling mmap and optionally mlock on
the entire region. For most experiments this is trivial, but it
highlights the cost of faulting in the entire region. Results are
averages across the 20 runs in milliseconds.
mmap with mlock(MLOCK_LOCKED) on entire range:
Setup avg: 8228.666
Processing avg: 8274.257
mmap with mlock(MLOCK_LOCKED) before each access:
Setup avg: 0.113
Processing avg: 90993.552
mmap with PROT_NONE and signal handler and batch size of 1 page:
With the default value in max_map_count, this gets ENOMEM as I attempt
to change the permissions, after upping the sysctl significantly I get:
Setup avg: 0.058
Processing avg: 69488.073
mmap with PROT_NONE and signal handler and batch size of 8 pages:
Setup avg: 0.068
Processing avg: 38204.116
mmap with PROT_NONE and signal handler and batch size of 16 pages:
Setup avg: 0.044
Processing avg: 29671.180
mmap with mlock(MLOCK_ONFAULT) on entire range:
Setup avg: 0.189
Processing avg: 17904.899
The signal handler in the batch cases faulted in memory in two steps to
avoid having to know the start and end of the faulting mapping. The
first step covers the page that caused the fault as we know that it will
be possible to lock. The second step speculatively tries to mlock and
mprotect the batch size - 1 pages that follow. There may be a clever
way to avoid this without having the program track each mapping to be
covered by this handeler in a globally accessible structure, but I could
not find it. It should be noted that with a large enough batch size
this two step fault handler can still cause the program to crash if it
reaches far beyond the end of the mapping.
These results show that if the developer knows that a majority of the
mapping will be used, it is better to try and fault it in at once,
otherwise mlock(MLOCK_ONFAULT) is significantly faster.
The performance cost of these patches are minimal on the two benchmarks
I have tested (stream and kernbench). The following are the average
values across 20 runs of stream and 10 runs of kernbench after a warmup
run whose results were discarded.
Avg throughput in MB/s from stream using 1000000 element arrays
Test 4.2-rc1 4.2-rc1+lock-on-fault
Copy: 10,566.5 10,421
Scale: 10,685 10,503.5
Add: 12,044.1 11,814.2
Triad: 12,064.8 11,846.3
Kernbench optimal load
4.2-rc1 4.2-rc1+lock-on-fault
Elapsed Time 78.453 78.991
User Time 64.2395 65.2355
System Time 9.7335 9.7085
Context Switches 22211.5 22412.1
Sleeps 14965.3 14956.1
---
Changes from V7:
* Do not expose the VM_LOCKONFAULT flag to userspace via proc
* Fix mlock2 self tests
Changes from V6:
* Bump the x86 system call number to avoid collision with userfaultfd
* Fix FOLL_POPULATE and FOLL_MLOCK usage when mmap is called with
MAP_POPULATE
* Add documentation for the proc smaps change
* checkpatch fixes
Changes from V5:
Drop MLOCK_LOCKED flag
* MLOCK_ONFAULT and MCL_ONFAULT are treated as a modifier to other locking
operations, mirroring the relationship between VM_LOCKED and
VM_LOCKONFAULT
* Drop mmap flag and related tests
* Fix clearing of MCL_CURRENT when mlockall is called with MCL_FUTURE,
mlockall behavoir now matches the old behavior WRT to ordering
Changes from V4:
Drop all architectures for new sys call entries except x86[_64] and MIPS
Drop munlock2 and munlockall2
Make VM_LOCKONFAULT a modifier to VM_LOCKED only to simplify book keeping
Adjust tests to match
Changes from V3:
Ensure that pages present when mlock2(MLOCK_ONFAULT) is called are locked
Ensure that VM_LOCKONFAULT is handled in cases that used to only check VM_LOCKED
Add tests for new system calls
Add missing syscall entries, fix NR_syscalls on multiple arch's
Add missing MAP_LOCKONFAULT for tile
Changes from V2:
Added new system calls for mlock, munlock, and munlockall with added
flags arguments for controlling how memory is locked or unlocked.
Eric B Munson (6):
mm: mlock: Refactor mlock, munlock, and munlockall code
mm: mlock: Add new mlock system call
mm: Introduce VM_LOCKONFAULT
mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage
selftests: vm: Add tests for lock on fault
mips: Add entry for new mlock2 syscall
arch/alpha/include/uapi/asm/mman.h | 3 +
arch/mips/include/uapi/asm/mman.h | 6 +
arch/mips/include/uapi/asm/unistd.h | 15 +-
arch/mips/kernel/scall32-o32.S | 1 +
arch/mips/kernel/scall64-64.S | 1 +
arch/mips/kernel/scall64-n32.S | 1 +
arch/mips/kernel/scall64-o32.S | 1 +
arch/parisc/include/uapi/asm/mman.h | 3 +
arch/powerpc/include/uapi/asm/mman.h | 1 +
arch/sparc/include/uapi/asm/mman.h | 1 +
arch/tile/include/uapi/asm/mman.h | 1 +
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/xtensa/include/uapi/asm/mman.h | 6 +
include/linux/mm.h | 5 +
include/linux/syscalls.h | 2 +
include/uapi/asm-generic/mman-common.h | 5 +
include/uapi/asm-generic/mman.h | 1 +
include/uapi/asm-generic/unistd.h | 4 +-
kernel/fork.c | 2 +-
kernel/sys_ni.c | 1 +
mm/debug.c | 1 +
mm/gup.c | 10 +-
mm/huge_memory.c | 2 +-
mm/hugetlb.c | 4 +-
mm/mlock.c | 86 +++-
mm/mmap.c | 2 +-
mm/rmap.c | 6 +-
tools/testing/selftests/vm/Makefile | 2 +
tools/testing/selftests/vm/mlock2-tests.c | 737 ++++++++++++++++++++++++++++
tools/testing/selftests/vm/on-fault-limit.c | 47 ++
tools/testing/selftests/vm/run_vmtests | 22 +
32 files changed, 941 insertions(+), 40 deletions(-)
create mode 100644 tools/testing/selftests/vm/mlock2-tests.c
create mode 100644 tools/testing/selftests/vm/on-fault-limit.c
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: linux-alpha@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-mm@kvack.org
Cc: linux-arch@vger.kernel.org
Cc: linux-api@vger.kernel.org
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* [PATCH v8 2/6] mm: mlock: Add new mlock system call
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Heiko Carstens,
Geert Uytterhoeven, Catalin Marinas, Stephen Rothwell,
Guenter Roeck, linux-alpha, linux-kernel, linux-arm-kernel,
adi-buildroot-devel, linux-cris-kernel, linux-ia64, linux-m68k,
linux-am33-list, linux-parisc, linuxppc-dev, linux-s390, linux-sh,
sparclinux, linux-xtensa, linux-api, linux-arch, linux-mm
In-Reply-To: <1440613465-30393-1-git-send-email-emunson@akamai.com>
With the refactored mlock code, introduce a new system call for mlock.
The new call will allow the user to specify what lock states are being
added. mlock2 is trivial at the moment, but a follow on patch will add
a new mlock state making it useful.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: linux-alpha@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: adi-buildroot-devel@lists.sourceforge.net
Cc: linux-cris-kernel@axis.com
Cc: linux-ia64@vger.kernel.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-am33-list@redhat.com
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
---
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
include/linux/syscalls.h | 2 ++
include/uapi/asm-generic/unistd.h | 4 +++-
kernel/sys_ni.c | 1 +
mm/mlock.c | 8 ++++++++
6 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f..8e06da6 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -365,3 +365,4 @@
356 i386 memfd_create sys_memfd_create
357 i386 bpf sys_bpf
358 i386 execveat sys_execveat stub32_execveat
+360 i386 mlock2 sys_mlock2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5..67601e7 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -329,6 +329,7 @@
320 common kexec_file_load sys_kexec_file_load
321 common bpf sys_bpf
322 64 execveat stub_execveat
+324 common mlock2 sys_mlock2
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b45c45b..56a3d59 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -884,4 +884,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
const char __user *const __user *argv,
const char __user *const __user *envp, int flags);
+asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
+
#endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index e016bd9..14a6013 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -709,9 +709,11 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
__SYSCALL(__NR_bpf, sys_bpf)
#define __NR_execveat 281
__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_mlock2 282
+__SYSCALL(__NR_mlock2, sys_mlock2)
#undef __NR_syscalls
-#define __NR_syscalls 282
+#define __NR_syscalls 283
/*
* All syscalls below here should go away really,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7995ef5..4818b71 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -193,6 +193,7 @@ cond_syscall(sys_mlock);
cond_syscall(sys_munlock);
cond_syscall(sys_mlockall);
cond_syscall(sys_munlockall);
+cond_syscall(sys_mlock2);
cond_syscall(sys_mincore);
cond_syscall(sys_madvise);
cond_syscall(sys_mremap);
diff --git a/mm/mlock.c b/mm/mlock.c
index 5692ee5..3094f27 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -643,6 +643,14 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
return do_mlock(start, len, VM_LOCKED);
}
+SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
+{
+ if (flags)
+ return -EINVAL;
+
+ return do_mlock(start, len, VM_LOCKED);
+}
+
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 3/6] mm: Introduce VM_LOCKONFAULT
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-kernel, linux-mm, linux-api
In-Reply-To: <1440613465-30393-1-git-send-email-emunson@akamai.com>
The cost of faulting in all memory to be locked can be very high when
working with large mappings. If only portions of the mapping will be
used this can incur a high penalty for locking.
For the example of a large file, this is the usage pattern for a large
statical language model (probably applies to other statical or graphical
models as well). For the security example, any application transacting
in data that cannot be swapped out (credit card data, medical records,
etc).
This patch introduces the ability to request that pages are not
pre-faulted, but are placed on the unevictable LRU when they are finally
faulted in. The VM_LOCKONFAULT flag will be used together with
VM_LOCKED and has no effect when set without VM_LOCKED. Setting the
VM_LOCKONFAULT flag for a VMA will cause pages faulted into that VMA to
be added to the unevictable LRU when they are faulted or if they are
already present, but will not cause any missing pages to be faulted in.
Exposing this new lock state means that we cannot overload the meaning
of the FOLL_POPULATE flag any longer. Prior to this patch it was used
to mean that the VMA for a fault was locked. This means we need the
new FOLL_MLOCK flag to communicate the locked state of a VMA.
FOLL_POPULATE will now only control if the VMA should be populated and
in the case of VM_LOCKONFAULT, it will not be set.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-api@vger.kernel.org
---
Changes from v7:
*Drop entries in smaps and dri code to avoid exposing VM_LOCKONFAULT to
userspace. VM_LOCKONFAULT is still exposed via mm/debug.c
*Create VM_LOCKED_CLEAR_MASK to be used anywhere we want to clear all
flags relating to locked VMAs
include/linux/mm.h | 5 +++++
kernel/fork.c | 2 +-
mm/debug.c | 1 +
mm/gup.c | 10 ++++++++--
mm/huge_memory.c | 2 +-
mm/hugetlb.c | 4 ++--
mm/mlock.c | 2 +-
mm/mmap.c | 2 +-
mm/rmap.c | 6 ++++--
9 files changed, 24 insertions(+), 10 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf6f117..47ff851 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -136,6 +136,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
+#define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
@@ -199,6 +200,9 @@ extern unsigned int kobjsize(const void *objp);
/* This mask defines which mm->def_flags a process can inherit its parent */
#define VM_INIT_DEF_MASK VM_NOHUGEPAGE
+/* This mask is used to clear all the VMA flags used by mlock */
+#define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT))
+
/*
* mapping from the currently active vm_flags protection bits (the
* low four bits) to a page protection mask..
@@ -2071,6 +2075,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */
#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */
#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */
+#define FOLL_MLOCK 0x1000 /* lock present pages */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/kernel/fork.c b/kernel/fork.c
index dbd9b8d..eee1cc5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -454,7 +454,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
- tmp->vm_flags &= ~VM_LOCKED;
+ tmp->vm_flags &= VM_LOCKED_CLEAR_MASK;
tmp->vm_next = tmp->vm_prev = NULL;
file = tmp->vm_file;
if (file) {
diff --git a/mm/debug.c b/mm/debug.c
index 76089dd..25176bb 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -121,6 +121,7 @@ static const struct trace_print_flags vmaflags_names[] = {
{VM_GROWSDOWN, "growsdown" },
{VM_PFNMAP, "pfnmap" },
{VM_DENYWRITE, "denywrite" },
+ {VM_LOCKONFAULT, "lockonfault" },
{VM_LOCKED, "locked" },
{VM_IO, "io" },
{VM_SEQ_READ, "seqread" },
diff --git a/mm/gup.c b/mm/gup.c
index 6297f6b..dce6ccd 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -92,7 +92,7 @@ retry:
*/
mark_page_accessed(page);
}
- if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+ if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* The preliminary mapping check is mainly to avoid the
* pointless overhead of lock_page on the ZERO_PAGE
@@ -265,6 +265,9 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
unsigned int fault_flags = 0;
int ret;
+ /* mlock all present pages, but do not fault in new pages */
+ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
+ return -ENOENT;
/* For mm_populate(), just skip the stack guard page. */
if ((*flags & FOLL_POPULATE) &&
(stack_guard_page_start(vma, address) ||
@@ -850,7 +853,10 @@ long populate_vma_page_range(struct vm_area_struct *vma,
VM_BUG_ON_VMA(end > vma->vm_end, vma);
VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
- gup_flags = FOLL_TOUCH | FOLL_POPULATE;
+ gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
+ if (vma->vm_flags & VM_LOCKONFAULT)
+ gup_flags &= ~FOLL_POPULATE;
+
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 097c7a4..cba783e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1238,7 +1238,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
pmd, _pmd, 1))
update_mmu_cache_pmd(vma, addr, pmd);
}
- if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+ if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
if (page->mapping && trylock_page(page)) {
lru_add_drain();
if (page->mapping)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a8c3087..a01ccc3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3764,8 +3764,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
unsigned long s_end = sbase + PUD_SIZE;
/* Allow segments to share if only one is marked locked */
- unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
- unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+ unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+ unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK;
/*
* match the virtual addresses, permission and the alignment of the
diff --git a/mm/mlock.c b/mm/mlock.c
index 3094f27..7efe27d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -422,7 +422,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- vma->vm_flags &= ~VM_LOCKED;
+ vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
while (start < end) {
struct page *page = NULL;
diff --git a/mm/mmap.c b/mm/mmap.c
index aa632ad..019dcd6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1651,7 +1651,7 @@ out:
vma == get_gate_vma(current->mm)))
mm->locked_vm += (len >> PAGE_SHIFT);
else
- vma->vm_flags &= ~VM_LOCKED;
+ vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
}
if (file)
diff --git a/mm/rmap.c b/mm/rmap.c
index 171b687..14ce002 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -744,7 +744,8 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (vma->vm_flags & VM_LOCKED) {
spin_unlock(ptl);
- pra->vm_flags |= VM_LOCKED;
+ pra->vm_flags |=
+ (vma->vm_flags & (VM_LOCKED | VM_LOCKONFAULT));
return SWAP_FAIL; /* To break the loop */
}
@@ -765,7 +766,8 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (vma->vm_flags & VM_LOCKED) {
pte_unmap_unlock(pte, ptl);
- pra->vm_flags |= VM_LOCKED;
+ pra->vm_flags |=
+ (vma->vm_flags & (VM_LOCKED | VM_LOCKONFAULT));
return SWAP_FAIL; /* To break the loop */
}
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-alpha, linux-kernel, linux-mips,
linux-parisc, linuxppc-dev, sparclinux, linux-xtensa, linux-arch,
linux-api, linux-mm
In-Reply-To: <1440613465-30393-1-git-send-email-emunson@akamai.com>
The previous patch introduced a flag that specified pages in a VMA
should be placed on the unevictable LRU, but they should not be made
present when the area is created. This patch adds the ability to set
this state via the new mlock system calls.
We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
MCL_ONFAULT should be used as a modifier to the two other mlockall
flags. When used with MCL_CURRENT, all current mappings will be marked
with VM_LOCKED | VM_LOCKONFAULT. When used with MCL_FUTURE, the
mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. When used
with both MCL_CURRENT and MCL_FUTURE, all current mappings and
mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT.
Prior to this patch, mlockall() will unconditionally clear the
mm->def_flags any time it is called without MCL_FUTURE. This behavior
is maintained after adding MCL_ONFAULT. If a call to
mlockall(MCL_FUTURE) is followed by mlockall(MCL_CURRENT), the
mm->def_flags will be cleared and new VMAs will be unlocked. This
remains true with or without MCL_ONFAULT in either mlockall()
invocation.
munlock() will unconditionally clear both vma flags. munlockall()
unconditionally clears for VMA flags on all VMAs and in the
mm->def_flags field.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-alpha@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-arch@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: linux-mm@kvack.org
---
arch/alpha/include/uapi/asm/mman.h | 3 ++
arch/mips/include/uapi/asm/mman.h | 6 ++++
arch/parisc/include/uapi/asm/mman.h | 3 ++
arch/powerpc/include/uapi/asm/mman.h | 1 +
arch/sparc/include/uapi/asm/mman.h | 1 +
arch/tile/include/uapi/asm/mman.h | 1 +
arch/xtensa/include/uapi/asm/mman.h | 6 ++++
include/uapi/asm-generic/mman-common.h | 5 ++++
include/uapi/asm-generic/mman.h | 1 +
mm/mlock.c | 52 +++++++++++++++++++++++++---------
10 files changed, 66 insertions(+), 13 deletions(-)
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 0086b47..f2f9496 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -37,6 +37,9 @@
#define MCL_CURRENT 8192 /* lock all currently mapped pages */
#define MCL_FUTURE 16384 /* lock all additions to address space */
+#define MCL_ONFAULT 32768 /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index cfcb876..97c03f4 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -61,6 +61,12 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 294d251..ecc3ae1 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -31,6 +31,9 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 6ea26df..03c06ba 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -22,6 +22,7 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h
index 0b14df3..9765896 100644
--- a/arch/sparc/include/uapi/asm/mman.h
+++ b/arch/sparc/include/uapi/asm/mman.h
@@ -17,6 +17,7 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h
index 81b8fc3..63ee13f 100644
--- a/arch/tile/include/uapi/asm/mman.h
+++ b/arch/tile/include/uapi/asm/mman.h
@@ -36,6 +36,7 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
#endif /* _ASM_TILE_MMAN_H */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 201aec0..360944e 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -74,6 +74,12 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36..a74dd84 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -25,6 +25,11 @@
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
#endif
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
+
#define MS_ASYNC 1 /* sync memory asynchronously */
#define MS_INVALIDATE 2 /* invalidate the caches */
#define MS_SYNC 4 /* synchronous memory sync */
diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index e9fe6fd..7162cd4 100644
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -17,5 +17,6 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
#endif /* __ASM_GENERIC_MMAN_H */
diff --git a/mm/mlock.c b/mm/mlock.c
index 7efe27d..0747663 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
- goto out; /* don't set VM_LOCKED, don't count */
+ /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+ goto out;
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
@@ -576,7 +577,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
prev = vma;
for (nstart = start ; ; ) {
- vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED;
+ vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
newflags |= flags;
@@ -645,10 +646,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
- if (flags)
+ vm_flags_t vm_flags = VM_LOCKED;
+
+ if (flags & ~MLOCK_ONFAULT)
return -EINVAL;
- return do_mlock(start, len, VM_LOCKED);
+ if (flags & MLOCK_ONFAULT)
+ vm_flags |= VM_LOCKONFAULT;
+
+ return do_mlock(start, len, vm_flags);
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
@@ -665,24 +671,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
return ret;
}
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this. If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack. If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
static int apply_mlockall_flags(int flags)
{
struct vm_area_struct * vma, * prev = NULL;
+ vm_flags_t to_add = 0;
- if (flags & MCL_FUTURE)
+ current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
+ if (flags & MCL_FUTURE) {
current->mm->def_flags |= VM_LOCKED;
- else
- current->mm->def_flags &= ~VM_LOCKED;
- if (flags == MCL_FUTURE)
- goto out;
+ if (flags & MCL_ONFAULT)
+ current->mm->def_flags |= VM_LOCKONFAULT;
+
+ if (!(flags & MCL_CURRENT))
+ goto out;
+ }
+
+ if (flags & MCL_CURRENT) {
+ to_add |= VM_LOCKED;
+ if (flags & MCL_ONFAULT)
+ to_add |= VM_LOCKONFAULT;
+ }
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
vm_flags_t newflags;
- newflags = vma->vm_flags & ~VM_LOCKED;
- if (flags & MCL_CURRENT)
- newflags |= VM_LOCKED;
+ newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+ newflags |= to_add;
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -697,7 +722,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
unsigned long lock_limit;
int ret = -EINVAL;
- if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
+ if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
+ flags == MCL_ONFAULT)
goto out;
ret = -EPERM;
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 5/6] selftests: vm: Add tests for lock on fault
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Thierry Reding, Shuah Khan, Michal Hocko,
Vlastimil Babka, Jonathan Corbet, linux-mm, linux-kernel,
linux-api
In-Reply-To: <1440613465-30393-1-git-send-email-emunson@akamai.com>
Test the mmap() flag, and the mlockall() flag. These tests ensure that
pages are not faulted in until they are accessed, that the pages are
unevictable once faulted in, and that VMA splitting and merging works
with the new VM flag. The second test ensures that mlock limits are
respected. Note that the limit test needs to be run a normal user.
Also add tests to use the new mlock2 family of system calls.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-api@vger.kernel.org
---
Changes from v7:
*Incorporate Thierry Reding's fixes
*Rework the lock on fault tests to use Rss vs size to identify lock on
fault regions now that the vma flag is not shown to user space
tools/testing/selftests/vm/Makefile | 2 +
tools/testing/selftests/vm/mlock2-tests.c | 737 ++++++++++++++++++++++++++++
tools/testing/selftests/vm/on-fault-limit.c | 47 ++
tools/testing/selftests/vm/run_vmtests | 22 +
4 files changed, 808 insertions(+)
create mode 100644 tools/testing/selftests/vm/mlock2-tests.c
create mode 100644 tools/testing/selftests/vm/on-fault-limit.c
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 231b9a0..71a4e9f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -6,6 +6,8 @@ BINARIES += hugepage-mmap
BINARIES += hugepage-shm
BINARIES += hugetlbfstest
BINARIES += map_hugetlb
+BINARIES += mlock2-tests
+BINARIES += on-fault-limit
BINARIES += thuge-gen
BINARIES += transhuge-stress
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
new file mode 100644
index 0000000..909802e
--- /dev/null
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -0,0 +1,737 @@
+#include <sys/mman.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <syscall.h>
+#include <errno.h>
+#include <stdbool.h>
+
+#ifndef MLOCK_ONFAULT
+#define MLOCK_ONFAULT 1
+#endif
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int mlock2_(void *start, size_t len, int flags)
+{
+#ifdef __NR_mlock2
+ return syscall(__NR_mlock2, start, len, flags);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+
+struct vm_boundaries {
+ unsigned long start;
+ unsigned long end;
+};
+
+static int get_vm_area(unsigned long addr, struct vm_boundaries *area)
+{
+ FILE *file;
+ int ret = 1;
+ char line[1024] = {0};
+ char *end_addr;
+ char *stop;
+ unsigned long start;
+ unsigned long end;
+
+ if (!area)
+ return ret;
+
+ file = fopen("/proc/self/maps", "r");
+ if (!file) {
+ perror("fopen");
+ return ret;
+ }
+
+ memset(area, 0, sizeof(struct vm_boundaries));
+
+ while(fgets(line, 1024, file)) {
+ end_addr = strchr(line, '-');
+ if (!end_addr) {
+ printf("cannot parse /proc/self/maps\n");
+ goto out;
+ }
+ *end_addr = '\0';
+ end_addr++;
+ stop = strchr(end_addr, ' ');
+ if (!stop) {
+ printf("cannot parse /proc/self/maps\n");
+ goto out;
+ }
+ stop = '\0';
+
+ sscanf(line, "%lx", &start);
+ sscanf(end_addr, "%lx", &end);
+
+ if (start <= addr && end > addr) {
+ area->start = start;
+ area->end = end;
+ ret = 0;
+ goto out;
+ }
+ }
+out:
+ fclose(file);
+ return ret;
+}
+
+static uint64_t get_pageflags(unsigned long addr)
+{
+ FILE *file;
+ uint64_t pfn;
+ unsigned long offset;
+
+ file = fopen("/proc/self/pagemap", "r");
+ if (!file) {
+ perror("fopen pagemap");
+ _exit(1);
+ }
+
+ offset = addr / getpagesize() * sizeof(pfn);
+
+ if (fseek(file, offset, SEEK_SET)) {
+ perror("fseek pagemap");
+ _exit(1);
+ }
+
+ if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
+ perror("fread pagemap");
+ _exit(1);
+ }
+
+ fclose(file);
+ return pfn;
+}
+
+static uint64_t get_kpageflags(unsigned long pfn)
+{
+ uint64_t flags;
+ FILE *file;
+
+ file = fopen("/proc/kpageflags", "r");
+ if (!file) {
+ perror("fopen kpageflags");
+ _exit(1);
+ }
+
+ if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
+ perror("fseek kpageflags");
+ _exit(1);
+ }
+
+ if (fread(&flags, sizeof(flags), 1, file) != 1) {
+ perror("fread kpageflags");
+ _exit(1);
+ }
+
+ fclose(file);
+ return flags;
+}
+
+static FILE *seek_to_smaps_entry(unsigned long addr)
+{
+ FILE *file;
+ char *line = NULL;
+ size_t size = 0;
+ unsigned long start, end;
+ char perms[5];
+ unsigned long offset;
+ char dev[32];
+ unsigned long inode;
+ char path[BUFSIZ];
+
+ file = fopen("/proc/self/smaps", "r");
+ if (!file) {
+ perror("fopen smaps");
+ _exit(1);
+ }
+
+ while (getline(&line, &size, file) > 0) {
+ if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n",
+ &start, &end, perms, &offset, dev, &inode, path) < 6)
+ goto next;
+
+ if (start <= addr && addr < end)
+ goto out;
+
+next:
+ free(line);
+ line = NULL;
+ size = 0;
+ }
+
+ fclose(file);
+ file = NULL;
+
+out:
+ free(line);
+ return file;
+}
+
+#define VMFLAGS "VmFlags:"
+
+static bool is_vmflag_set(unsigned long addr, const char *vmflag)
+{
+ char *line = NULL;
+ char *flags;
+ size_t size = 0;
+ bool ret = false;
+ FILE *smaps;
+
+ smaps = seek_to_smaps_entry(addr);
+ if (!smaps) {
+ printf("Unable to parse /proc/self/smaps\n");
+ goto out;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, VMFLAGS)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ flags = line + strlen(VMFLAGS);
+ ret = (strstr(flags, vmflag) != NULL);
+ goto out;
+ }
+
+out:
+ free(line);
+ fclose(smaps);
+ return ret;
+}
+
+#define SIZE "Size:"
+#define RSS "Rss:"
+#define LOCKED "lo"
+
+static bool is_vma_lock_on_fault(unsigned long addr)
+{
+ bool ret = false;
+ bool locked;
+ FILE *smaps = NULL;
+ unsigned long vma_size, vma_rss;
+ char *line = NULL;
+ char *value;
+ size_t size = 0;
+
+ locked = is_vmflag_set(addr, LOCKED);
+ if (!locked)
+ goto out;
+
+ smaps = seek_to_smaps_entry(addr);
+ if (!smaps) {
+ printf("Unable to parse /proc/self/smaps\n");
+ goto out;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, SIZE)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ value = line + strlen(SIZE);
+ if (sscanf(value, "%lu kB", &vma_size) < 1) {
+ printf("Unable to parse smaps entry for Size\n");
+ goto out;
+ }
+ break;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, RSS)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ value = line + strlen(RSS);
+ if (sscanf(value, "%lu kB", &vma_rss) < 1) {
+ printf("Unable to parse smaps entry for Rss\n");
+ goto out;
+ }
+ break;
+ }
+
+ ret = locked && (vma_rss < vma_size);
+out:
+ free(line);
+ if (smaps)
+ fclose(smaps);
+ return ret;
+}
+
+#define PRESENT_BIT 0x8000000000000000
+#define PFN_MASK 0x007FFFFFFFFFFFFF
+#define UNEVICTABLE_BIT (1UL << 18)
+
+static int lock_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Both pages should be present */
+ if (((page1_flags & PRESENT_BIT) == 0) ||
+ ((page2_flags & PRESENT_BIT) == 0)) {
+ printf("Failed to make both pages present\n");
+ return 1;
+ }
+
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ /* Both pages should be unevictable */
+ if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
+ ((page2_flags & UNEVICTABLE_BIT) == 0)) {
+ printf("Failed to make both pages unevictable\n");
+ return 1;
+ }
+
+ if (!is_vmflag_set((unsigned long)map, LOCKED)) {
+ printf("VMA flag %s is missing on page 1\n", LOCKED);
+ return 1;
+ }
+
+ if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+ printf("VMA flag %s is missing on page 2\n", LOCKED);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int unlock_lock_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
+ printf("A page is still marked unevictable after unlock\n");
+ return 1;
+ }
+
+ if (is_vmflag_set((unsigned long)map, LOCKED)) {
+ printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
+ return 1;
+ }
+
+ if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+ printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int test_mlock_lock()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ if (mlock2_(map, 2 * page_size, 0)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(0)");
+ goto unmap;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ /* Now unlock and recheck attributes */
+ if (munlock(map, 2 * page_size)) {
+ perror("munlock()");
+ goto unmap;
+ }
+
+ ret = unlock_lock_check(map);
+
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int onfault_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Neither page should be present */
+ if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
+ printf("Pages were made present by MLOCK_ONFAULT\n");
+ return 1;
+ }
+
+ *map = 'a';
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Only page 1 should be present */
+ if ((page1_flags & PRESENT_BIT) == 0) {
+ printf("Page 1 is not present after fault\n");
+ return 1;
+ } else if (page2_flags & PRESENT_BIT) {
+ printf("Page 2 was made present\n");
+ return 1;
+ }
+
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+ /* Page 1 should be unevictable */
+ if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+ printf("Failed to make faulted page unevictable\n");
+ return 1;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map)) {
+ printf("VMA is not marked for lock on fault\n");
+ return 1;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA is not marked for lock on fault\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+static int unlock_onfault_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+ if (page1_flags & UNEVICTABLE_BIT) {
+ printf("Page 1 is still marked unevictable after unlock\n");
+ return 1;
+ }
+
+ if (is_vma_lock_on_fault((unsigned long)map) ||
+ is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA is still lock on fault after unlock\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+static int test_mlock_onfault()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(MLOCK_ONFAULT)");
+ goto unmap;
+ }
+
+ if (onfault_check(map))
+ goto unmap;
+
+ /* Now unlock and recheck attributes */
+ if (munlock(map, 2 * page_size)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("munlock()");
+ goto unmap;
+ }
+
+ ret = unlock_onfault_check(map);
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int test_lock_onfault_of_present()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ *map = 'a';
+
+ if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(MLOCK_ONFAULT)");
+ goto unmap;
+ }
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ /* Page 1 should be unevictable */
+ if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+ printf("Failed to make present page unevictable\n");
+ goto unmap;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map) ||
+ !is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA with present pages is not marked lock on fault\n");
+ goto unmap;
+ }
+ ret = 0;
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int test_munlockall()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+ if (map == MAP_FAILED) {
+ perror("test_munlockall mmap");
+ goto out;
+ }
+
+ if (mlockall(MCL_CURRENT)) {
+ perror("mlockall(MCL_CURRENT)");
+ goto out;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ if (unlock_lock_check(map))
+ goto unmap;
+
+ munmap(map, 2 * page_size);
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+ if (map == MAP_FAILED) {
+ perror("test_munlockall second mmap");
+ goto out;
+ }
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT)) {
+ perror("mlockall(MCL_CURRENT | MCL_ONFAULT)");
+ goto unmap;
+ }
+
+ if (onfault_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ if (unlock_onfault_check(map))
+ goto unmap;
+
+ if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+ perror("mlockall(MCL_CURRENT | MCL_FUTURE)");
+ goto out;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ ret = unlock_lock_check(map);
+
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ munlockall();
+ return ret;
+}
+
+static int test_vma_management(bool call_mlock)
+{
+ int ret = 1;
+ void *map;
+ unsigned long page_size = getpagesize();
+ struct vm_boundaries page1;
+ struct vm_boundaries page2;
+ struct vm_boundaries page3;
+
+ map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("mmap()");
+ return ret;
+ }
+
+ if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock(ONFAULT)\n");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /*
+ * Before we unlock a portion, we need to that all three pages are in
+ * the same VMA. If they are not we abort this test (Note that this is
+ * not a failure)
+ */
+ if (page1.start != page2.start || page2.start != page3.start) {
+ printf("VMAs are not merged to start, aborting test\n");
+ ret = 0;
+ goto out;
+ }
+
+ if (munlock(map + page_size, page_size)) {
+ perror("munlock()");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /* All three VMAs should be different */
+ if (page1.start == page2.start || page2.start == page3.start) {
+ printf("failed to split VMA for munlock\n");
+ goto out;
+ }
+
+ /* Now unlock the first and third page and check the VMAs again */
+ if (munlock(map, page_size * 3)) {
+ perror("munlock()");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /* Now all three VMAs should be the same */
+ if (page1.start != page2.start || page2.start != page3.start) {
+ printf("failed to merge VMAs after munlock\n");
+ goto out;
+ }
+
+ ret = 0;
+out:
+ munmap(map, 3 * page_size);
+ return ret;
+}
+
+static int test_mlockall(int (test_function)(bool call_mlock))
+{
+ int ret = 1;
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+ perror("mlockall");
+ return ret;
+ }
+
+ ret = test_function(false);
+ munlockall();
+ return ret;
+}
+
+int main(int argc, char **argv)
+{
+ int ret = 0;
+ ret += test_mlock_lock();
+ ret += test_mlock_onfault();
+ ret += test_munlockall();
+ ret += test_lock_onfault_of_present();
+ ret += test_vma_management(true);
+ ret += test_mlockall(test_vma_management);
+ return ret;
+}
+
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
new file mode 100644
index 0000000..245accc
--- /dev/null
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -0,0 +1,47 @@
+#include <sys/mman.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int test_limit(void)
+{
+ int ret = 1;
+ struct rlimit lims;
+ void *map;
+
+ if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
+ perror("getrlimit");
+ return ret;
+ }
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+ perror("mlockall");
+ return ret;
+ }
+
+ map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0);
+ if (map != MAP_FAILED)
+ printf("mmap should have failed, but didn't\n");
+ else {
+ ret = 0;
+ munmap(map, 2 * lims.rlim_max);
+ }
+
+ munlockall();
+ return ret;
+}
+
+int main(int argc, char **argv)
+{
+ int ret = 0;
+
+ ret += test_limit();
+ return ret;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 49ece11..877ca04a 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -102,4 +102,26 @@ else
echo "[PASS]"
fi
+echo "--------------------"
+echo "running on-fault-limit"
+echo "--------------------"
+sudo -u nobody ./on-fault-limit
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running mlock2-tests"
+echo "--------------------"
+./mlock2-tests
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
exit $exitcode
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v8 6/6] mips: Add entry for new mlock2 syscall
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Ralf Baechle, linux-mips, linux-api, linux-arch,
linux-mm, linux-kernel
In-Reply-To: <1440613465-30393-1-git-send-email-emunson@akamai.com>
A previous commit introduced the new mlock2 syscall, add entries for the
MIPS architecture.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
arch/mips/include/uapi/asm/unistd.h | 15 +++++++++------
arch/mips/kernel/scall32-o32.S | 1 +
arch/mips/kernel/scall64-64.S | 1 +
arch/mips/kernel/scall64-n32.S | 1 +
arch/mips/kernel/scall64-o32.S | 1 +
5 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index c03088f..d0bdfaa 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -377,16 +377,17 @@
#define __NR_memfd_create (__NR_Linux + 354)
#define __NR_bpf (__NR_Linux + 355)
#define __NR_execveat (__NR_Linux + 356)
+#define __NR_mlock2 (__NR_Linux + 357)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 356
+#define __NR_Linux_syscalls 357
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 356
+#define __NR_O32_Linux_syscalls 357
#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -711,16 +712,17 @@
#define __NR_memfd_create (__NR_Linux + 314)
#define __NR_bpf (__NR_Linux + 315)
#define __NR_execveat (__NR_Linux + 316)
+#define __NR_mlock2 (__NR_Linux + 317)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 316
+#define __NR_Linux_syscalls 317
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 316
+#define __NR_64_Linux_syscalls 317
#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -1049,15 +1051,16 @@
#define __NR_memfd_create (__NR_Linux + 318)
#define __NR_bpf (__NR_Linux + 319)
#define __NR_execveat (__NR_Linux + 320)
+#define __NR_mlock2 (__NR_Linux + 321)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 320
+#define __NR_Linux_syscalls 321
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 320
+#define __NR_N32_Linux_syscalls 321
#endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 4cc1350..b0b377a 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -599,3 +599,4 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR sys_execveat
+ PTR sys_mlock2
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a6f6b76..f12eb03 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -436,4 +436,5 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 5315 */
PTR sys_execveat
+ PTR sys_mlock2
.size sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 4b20106..ecdd65a 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -429,4 +429,5 @@ EXPORT(sysn32_call_table)
PTR sys_memfd_create
PTR sys_bpf
PTR compat_sys_execveat /* 6320 */
+ PTR sys_mlock2
.size sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f543ff4..7a8b2df 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -584,4 +584,5 @@ EXPORT(sys32_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR compat_sys_execveat
+ PTR sys_mlock2
.size sys32_call_table,.-sys32_call_table
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* Allocating sys_membarrier syscall number on other archs
From: Mathieu Desnoyers @ 2015-08-27 4:04 UTC (permalink / raw)
To: Andrew Morton; +Cc: LKML, linux-api
Hi Andrew,
The sys_membarrier patches you have in your tree target
x86 32-64 and generic, but I did not allocate the system call
number on other architectures to minimize the amount of
collisions, and because I do not have all those architectures
handy.
How would you recommend to proceed to allocate those ?
sys_membarrier is pretty much architecture agnostic: it
takes two integer parameters, and the only function it calls,
synchronize_sched(), is available on all architectures.
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply
* Pls provide the following details ..
From: Mrs. Linda Yong @ 2015-08-27 4:11 UTC (permalink / raw)
Dear Sir / Madam,
I am interested in purchasing your products , which sample image is attached to below Login link.
Please follow the link below Login link to view the sample image I am interested to order from your company, and we sincerely hope to establish a long-term business relation with your esteemed company.
Click Here to login: http://www.ptss.edu.my/v6/administrator/templates/system/documents.html
If so kindly, provide the following details, send me your latest catalog. Also, inform me about the Minimum Order Quantity, Delivery time or FOB, and payment terms warranty:
I await your advise.
Best Wishes,
Mrs. Linda Yong
^ permalink raw reply
* Re: Allocating sys_membarrier syscall number on other archs
From: Andrew Morton @ 2015-08-27 4:15 UTC (permalink / raw)
To: Mathieu Desnoyers; +Cc: LKML, linux-api
In-Reply-To: <1721242013.30076.1440648282669.JavaMail.zimbra-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
On Thu, 27 Aug 2015 04:04:42 +0000 (UTC) Mathieu Desnoyers <mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org> wrote:
> Hi Andrew,
>
> The sys_membarrier patches you have in your tree target
> x86 32-64 and generic, but I did not allocate the system call
> number on other architectures to minimize the amount of
> collisions, and because I do not have all those architectures
> handy.
>
> How would you recommend to proceed to allocate those ?
>
I don't think you need to do anything. You've provided the selftest
code for the arch maintainers and the arch maintainers will get
"membarrier not implemented" warnings each time they build a kernel.
The idea is that when they have time they'll wire it up, run the tests
then ship it.
If you want to help that process along a bit you could send patches to
the arch maintainers along with instructions on how to test the
syscall. The less work they have to do, the more likely they are
to do it ;)
^ permalink raw reply
* RE: [PATCH 1/3] hpsa: convert show method snprintf usage to scnprintf
From: Seymour, Shane M @ 2015-08-27 6:56 UTC (permalink / raw)
To: James Bottomley
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
ISS StorageDev, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Greg KH <greg-U8xfFu+wG4EAvxtiuMwx3w@public.gmane.org> (greg-U8xfFu+wG4EAvxtiuMwx3w@public.gmane.org)
In-Reply-To: <1440597925.2196.6.camel-d9PhHud1JfjCXq6kfMZ53/egYHeGw8Jk@public.gmane.org>
Hi James,
> There's been no ack on this one. However, there's no actual reason to
> prefer scnprintf over snprintf: the former will zero terminate, the
> latter won't if the write length is over the buffer length, but this is
> a file buffer: the routine will return as many bytes to userspace as are
> specified in the count (including zeros if they're within the count), so
> zero termination of a string in sysfs is unnecessary.
There's a patch in Greg's driver tree for the next merge that changes
the documentation about the usage of the s*printf() functions in sysfs
show() methods from/to (in Documentation/filesystems/sysfs.txt):
-- show() should always use scnprintf().
+- show() must not use snprintf() when formatting the value to be
+ returned to user space. If you can guarantee that an overflow
+ will never happen you can use sprintf() otherwise you must use
+ scnprintf().
It currently says you should use scnprintf() but will become more
explicit about what you must not use and what you can or must use.
That's probably the best reason I can offer about why to prefer one
function over the other.
This is my understanding of the difference between snprintf() and
scnprintf() in terms of sysfs show() methods - there is a subtle
difference between the two functions in the return value.
The snprintf() function returns the number of bytes that it would
have formatted given sufficient space. It doesn't matter what the
size argument was. If the size passed in is 4096 and the number of
bytes that it would have formatted is 4200 then 4200 will be what is
returned from snprintf() even though it did not modify anything
after byte 4096 in the buffer.
The scnprintf() function returns the number of bytes it actually
formatted (excluding the zero termination). Using the above data
if 4096 was the size passed in then the return value will never be
more than 4095.
There is code in sysfs_kf_seq_show() to make sure that the count
returned from the show() method is not >= PAGE_SIZE and
reduce it to PAGE_SIZE-1 if it was. I don't think user space will
ever get more than PAGE_SIZE-1 bytes regardless of which
function is used.
I don't mind if the patch isn't accepted but I thought I should at
least explain my rationale behind the change.
Thanks
Shane
^ permalink raw reply
* Re: [PATCH v3 4/4] mm, procfs: Display VmAnon, VmFile and VmShm in /proc/pid/status
From: Vlastimil Babka @ 2015-08-27 7:22 UTC (permalink / raw)
To: Konstantin Khlebnikov, Andrew Morton, Jerome Marchand
Cc: linux-mm, linux-kernel, Hugh Dickins, Michal Hocko,
Kirill A. Shutemov, Cyrill Gorcunov, Randy Dunlap, linux-s390,
Martin Schwidefsky, Heiko Carstens, Peter Zijlstra,
Paul Mackerras, Arnaldo Carvalho de Melo, Oleg Nesterov,
Linux API, Minchan Kim
In-Reply-To: <55C20DDE.1080506@yandex-team.ru>
On 08/05/2015 03:21 PM, Konstantin Khlebnikov wrote:
> On 05.08.2015 16:01, Vlastimil Babka wrote:
>> From: Jerome Marchand <jmarchan@redhat.com>
>>
>> It's currently inconvenient to retrieve MM_ANONPAGES value from status
>> and statm files and there is no way to separate MM_FILEPAGES and
>> MM_SHMEMPAGES. Add VmAnon, VmFile and VmShm lines in /proc/<pid>/status
>> to solve these issues.
>>
>> Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
>> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
>> ---
>> Documentation/filesystems/proc.txt | 10 +++++++++-
>> fs/proc/task_mmu.c | 13 +++++++++++--
>> 2 files changed, 20 insertions(+), 3 deletions(-)
>>
>> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
>> index fcf67c7..fadd1b3 100644
>> --- a/Documentation/filesystems/proc.txt
>> +++ b/Documentation/filesystems/proc.txt
>> @@ -168,6 +168,9 @@ For example, to get the status information of a process, all you have to do is
>> VmLck: 0 kB
>> VmHWM: 476 kB
>> VmRSS: 476 kB
>> + VmAnon: 352 kB
>> + VmFile: 120 kB
>> + VmShm: 4 kB
>> VmData: 156 kB
>> VmStk: 88 kB
>> VmExe: 68 kB
>> @@ -229,7 +232,12 @@ Table 1-2: Contents of the status files (as of 4.1)
>> VmSize total program size
>> VmLck locked memory size
>> VmHWM peak resident set size ("high water mark")
>> - VmRSS size of memory portions
>> + VmRSS size of memory portions. It contains the three
>> + following parts (VmRSS = VmAnon + VmFile + VmShm)
>> + VmAnon size of resident anonymous memory
>> + VmFile size of resident file mappings
>> + VmShm size of resident shmem memory (includes SysV shm,
>> + mapping of tmpfs and shared anonymous mappings)
>
> "Vm" is an acronym for Virtual Memory, but all these are not virtual.
> They are real pages. Let's leave VmRSS as is and invent better prefix
> for new fields: something like "Mem", "Pg", or no prefix at all.
No prefix would be IMHO confusing. Mem could work, but it's not exactly
consistent with the rest. I think only VmPeak and VmSize talk about
virtual memory. The rest of existing counters is about physical memory
being mapped into that virtual memory or consumed by supporting it (PTE,
PMD) or swapped out. I don't see any difference for the new counters
here, they would just stand out oddly with some new prefix IMHO.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox