[PATCH 1/2] Convert target drivers to use sbitmap

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The sbitmap and the percpu_ida perform essentially the same task,
allocating tags for commands.  Since the sbitmap is more used than
the percpu_ida, convert the percpu_ida users to the sbitmap API.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/scsi/qla2xxx/qla_target.c| 16 ++-
 drivers/target/iscsi/iscsi_target_util.c | 34 +---
 drivers/target/sbp/sbp_target.c  |  8 +++---
 drivers/target/target_core_transport.c   |  5 ++--
 drivers/target/tcm_fc/tfc_cmd.c  | 11 
 drivers/usb/gadget/function/f_tcm.c  |  8 +++---
 drivers/vhost/scsi.c |  9 ---
 drivers/xen/xen-scsiback.c   |  8 +++---
 include/target/iscsi/iscsi_target_core.h |  1 +
 include/target/target_core_base.h|  5 ++--
 10 files changed, 73 insertions(+), 32 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c 
b/drivers/scsi/qla2xxx/qla_target.c
index 025dc2d3f3de..cdf671c2af61 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3719,7 +3719,8 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
return;
}
cmd->jiffies_at_free = get_jiffies_64();
-   percpu_ida_free(>se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+   sbitmap_queue_clear(>se_sess->sess_tag_pool, cmd->se_cmd.map_tag,
+   cmd->se_cmd.map_cpu);
 }
 EXPORT_SYMBOL(qlt_free_cmd);
 
@@ -4084,7 +4085,8 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
qlt_send_term_exchange(qpair, NULL, >atio, 1, 0);
 
qlt_decr_num_pend_cmds(vha);
-   percpu_ida_free(>se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+   sbitmap_queue_clear(>se_sess->sess_tag_pool, cmd->se_cmd.map_tag,
+   cmd->se_cmd.map_cpu);
spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
spin_lock_irqsave(>tgt.sess_lock, flags);
@@ -4215,9 +4217,9 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t 
*vha,
 {
struct se_session *se_sess = sess->se_sess;
struct qla_tgt_cmd *cmd;
-   int tag;
+   int tag, cpu;
 
-   tag = percpu_ida_alloc(_sess->sess_tag_pool, TASK_RUNNING);
+   tag = sbitmap_queue_get(_sess->sess_tag_pool, );
if (tag < 0)
return NULL;
 
@@ -4230,6 +4232,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t 
*vha,
qlt_incr_num_pend_cmds(vha);
cmd->vha = vha;
cmd->se_cmd.map_tag = tag;
+   cmd->se_cmd.map_cpu = cpu;
cmd->sess = sess;
cmd->loop_id = sess->loop_id;
cmd->conf_compl_supported = sess->conf_compl_supported;
@@ -5212,7 +5215,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
struct fc_port *sess;
struct se_session *se_sess;
struct qla_tgt_cmd *cmd;
-   int tag;
+   int tag, cpu;
unsigned long flags;
 
if (unlikely(tgt->tgt_stop)) {
@@ -5244,7 +5247,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 
se_sess = sess->se_sess;
 
-   tag = percpu_ida_alloc(_sess->sess_tag_pool, TASK_RUNNING);
+   tag = sbitmap_queue_get(_sess->sess_tag_pool, );
if (tag < 0)
return;
 
@@ -5275,6 +5278,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
cmd->reset_count = ha->base_qpair->chip_reset;
cmd->q_full = 1;
cmd->qpair = ha->base_qpair;
+   cmd->se_cmd.map_cpu = cpu;
 
if (qfull) {
cmd->q_full = 1;
diff --git a/drivers/target/iscsi/iscsi_target_util.c 
b/drivers/target/iscsi/iscsi_target_util.c
index 4435bf374d2d..28bcffae609f 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -17,7 +17,7 @@
  
**/
 
 #include 
-#include 
+#include 
 #include  /* ipv6_addr_equal() */
 #include 
 #include 
@@ -147,6 +147,28 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd)
spin_unlock_bh(>r2t_lock);
 }
 
+int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup)
+{
+   int tag = -1;
+   DEFINE_WAIT(wait);
+   struct sbq_wait_state *ws;
+
+   if (state == TASK_RUNNING)
+   return tag;
+
+   ws = _sess->sess_tag_pool.ws[0];
+   for (;;) {
+   prepare_to_wait_exclusive(>wait, , state);
+   if (signal_pending_state(state, current))
+   break;
+   schedule();
+   tag = sbitmap_queue_get(_sess->sess_tag_pool, cpup);
+   }
+
+   finish_wait(>wait, );
+   return tag;
+}
+
 /*
  * May be called from software interrupt (timer) context for allocating
  * iSCSI NopINs.
@@ -155,9 +177,11 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct 

[PATCH 0/2] Use sbitmap instead of percpu_ida

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a pretty rough-and-ready conversion of the target drivers
from using percpu_ida to sbitmap.  It compiles; I don't have a target
setup, so it's completely untested.  I haven't tried to do anything
particularly clever here, so it's possible that, for example, the wait
queue in iscsi_target_util could be more clever, like the block layer
uses multiple wait queues to avoid pingpongs.  Or maybe we could figure
out a way to not store the CPU that the ID was allocated on, or perhaps
the options I specified to sbitmap_queue_init() are suboptimal.

Patch 2 isn't interesting; it just deletes the implementation.  Patch 1
will be where all the action is.

Matthew Wilcox (2):
  Convert target drivers to use sbitmap
  Remove percpu_ida

 drivers/scsi/qla2xxx/qla_target.c|  16 +-
 drivers/target/iscsi/iscsi_target_util.c |  34 +-
 drivers/target/sbp/sbp_target.c  |   8 +-
 drivers/target/target_core_transport.c   |   5 +-
 drivers/target/tcm_fc/tfc_cmd.c  |  11 +-
 drivers/usb/gadget/function/f_tcm.c  |   8 +-
 drivers/vhost/scsi.c |   9 +-
 drivers/xen/xen-scsiback.c   |   8 +-
 include/linux/percpu_ida.h   |  83 -
 include/target/iscsi/iscsi_target_core.h |   1 +
 include/target/target_core_base.h|   5 +-
 lib/Makefile |   2 +-
 lib/percpu_ida.c | 391 ---
 13 files changed, 74 insertions(+), 507 deletions(-)
 delete mode 100644 include/linux/percpu_ida.h
 delete mode 100644 lib/percpu_ida.c

-- 
2.17.0

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH 2/2] Remove percpu_ida

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

With its one user gone, remove the library code.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/percpu_ida.h |  83 
 lib/Makefile   |   2 +-
 lib/percpu_ida.c   | 391 -
 3 files changed, 1 insertion(+), 475 deletions(-)
 delete mode 100644 include/linux/percpu_ida.h
 delete mode 100644 lib/percpu_ida.c

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
deleted file mode 100644
index 07d78e4653bc..
--- a/include/linux/percpu_ida.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PERCPU_IDA_H__
-#define __PERCPU_IDA_H__
-
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-
-struct percpu_ida_cpu;
-
-struct percpu_ida {
-   /*
-* number of tags available to be allocated, as passed to
-* percpu_ida_init()
-*/
-   unsignednr_tags;
-   unsignedpercpu_max_size;
-   unsignedpercpu_batch_size;
-
-   struct percpu_ida_cpu __percpu  *tag_cpu;
-
-   /*
-* Bitmap of cpus that (may) have tags on their percpu freelists:
-* steal_tags() uses this to decide when to steal tags, and which cpus
-* to try stealing from.
-*
-* It's ok for a freelist to be empty when its bit is set - steal_tags()
-* will just keep looking - but the bitmap _must_ be set whenever a
-* percpu freelist does have tags.
-*/
-   cpumask_t   cpus_have_tags;
-
-   struct {
-   spinlock_t  lock;
-   /*
-* When we go to steal tags from another cpu (see steal_tags()),
-* we want to pick a cpu at random. Cycling through them every
-* time we steal is a bit easier and more or less equivalent:
-*/
-   unsignedcpu_last_stolen;
-
-   /* For sleeping on allocation failure */
-   wait_queue_head_t   wait;
-
-   /*
-* Global freelist - it's a stack where nr_free points to the
-* top
-*/
-   unsignednr_free;
-   unsigned*freelist;
-   } cacheline_aligned_in_smp;
-};
-
-/*
- * Number of tags we move between the percpu freelist and the global freelist 
at
- * a time
- */
-#define IDA_DEFAULT_PCPU_BATCH_MOVE32U
-/* Max size of percpu freelist, */
-#define IDA_DEFAULT_PCPU_SIZE  ((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
-
-int percpu_ida_alloc(struct percpu_ida *pool, int state);
-void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
-
-void percpu_ida_destroy(struct percpu_ida *pool);
-int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
-   unsigned long max_size, unsigned long batch_size);
-static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long 
nr_tags)
-{
-   return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE,
-   IDA_DEFAULT_PCPU_BATCH_MOVE);
-}
-
-typedef int (*percpu_ida_cb)(unsigned, void *);
-int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
-   void *data);
-
-unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu);
-#endif /* __PERCPU_IDA_H__ */
diff --git a/lib/Makefile b/lib/Makefile
index ce20696d5a92..7626dece1d27 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -39,7 +39,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o 
random32.o \
 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
-percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
+percpu-refcount.o rhashtable.o reciprocal_div.o \
 once.o refcount.o usercopy.o errseq.o bucket_locks.o
 obj-$(CONFIG_STRING_SELFTEST) += test_string.o
 obj-y += string_helpers.o
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
deleted file mode 100644
index 6016f1deb1f5..
--- a/lib/percpu_ida.c
+++ /dev/null
@@ -1,391 +0,0 @@
-/*
- * Percpu IDA library
- *
- * Copyright (C) 2013 Datera, Inc. Kent Overstreet
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-#includ

Re: [PATCH] usb: mon: Change return type to vm_fault_t

[Matthew Wilcox]

On Mon, Apr 16, 2018 at 05:18:35PM +0530, Souptick Joarder wrote:
> On Mon, Apr 16, 2018 at 1:17 PM, Greg KH  wrote:
> > When a maintainer gets a patch with no context at all, the first
> > reaction is to just reject it (especially as many of these patches were
> > sent privately and did not go on any public mailing list, those all got
> > automatically dropped...)
> 
> For few drivers only maintainers name is mentioned without any mailing list
> in Maintainer file. Not sure which mailing list to add for the same.

I thought you were using scripts/get_maintainer.pl to get the maintainers;
I didn't realise you were going through MAINTAINERS manually.
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] usb: mon: Change return type to vm_fault_t

[Matthew Wilcox]

On Sun, Apr 15, 2018 at 07:49:16AM +0200, Greg KH wrote:
> On Sun, Apr 15, 2018 at 12:36:02AM +0530, Souptick Joarder wrote:
> > Use new return type vm_fault_t for fault handler
> > in struct vm_operations_struct.
> 
> Why?

commit 1c8f422059ae5da07db7406ab916203f9417e396
Author: Souptick Joarder 
Date:   Thu Apr 5 16:25:23 2018 -0700

mm: change return type to vm_fault_t

The plan for these patches is to introduce the typedef, initially just
as documentation ("These functions should return a VM_FAULT_ status").
We'll trickle the patches to individual drivers/filesystems in through
the maintainers, as far as possible.  Then we'll change the typedef to
an unsigned int and break the compilation of any unconverted
drivers/filesystems.

vmf_insert_page(), vmf_insert_mixed() and vmf_insert_pfn() are three
newly added functions.  The various drivers/filesystems where return
value of fault(), huge_fault(), page_mkwrite() and pfn_mkwrite() get
converted, will need them.  These functions will return correct
VM_FAULT_ code based on err value.

We've had bugs before where drivers returned -EFOO.  And we have this
silly inefficiency where vm_insert_xxx() return an errno which (afaict)
every driver then converts into a VM_FAULT code.  In many cases drivers
failed to return correct VM_FAULT code value despite of vm_insert_xxx()
fails.  We have indentified and clean up all those existing bugs and
silly inefficiencies in driver/filesystems by adding these three new
inline wrappers.  As mentioned above, we will trickle those patches to
individual drivers/filesystems in through maintainers after these three
wrapper functions are merged.

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: rfc: remove print_vma_addr ? (was Re: [PATCH 00/16] remove eight obsolete architectures)

[Matthew Wilcox]

On Thu, Mar 15, 2018 at 09:56:46AM -0700, Joe Perches wrote:
> I have a patchset that creates a vsprintf extension for
> print_vma_addr and removes all the uses similar to the
> print_symbol() removal.
> 
> This now avoids any possible printk interleaving.
> 
> Unfortunately, without some #ifdef in vsprintf, which
> I would like to avoid, it increases the nommu kernel
> size by ~500 bytes.
> 
> Anyone think this is acceptable?
> 
> Here's the overall patch, but I have it as a series
> ---
>  Documentation/core-api/printk-formats.rst |  9 +
>  arch/arm64/kernel/traps.c | 13 +++
>  arch/mips/mm/fault.c  | 16 -
>  arch/parisc/mm/fault.c| 15 
>  arch/riscv/kernel/traps.c | 11 +++---
>  arch/s390/mm/fault.c  |  7 ++--
>  arch/sparc/mm/fault_32.c  |  8 ++---
>  arch/sparc/mm/fault_64.c  |  8 ++---
>  arch/tile/kernel/signal.c |  9 ++---
>  arch/um/kernel/trap.c | 13 +++
>  arch/x86/kernel/signal.c  | 10 ++
>  arch/x86/kernel/traps.c   | 18 --
>  arch/x86/mm/fault.c   | 12 +++
>  include/linux/mm.h|  1 -
>  lib/vsprintf.c| 58 
> ++-
>  mm/memory.c   | 33 --
>  16 files changed, 112 insertions(+), 129 deletions(-)

This doesn't feel like a huge win since it's only called ~once per
architecture.  I'd be more excited if it made the printing of the whole
thing standardised; eg we have a print_fault() function in mm/memory.c
which takes a suitable set of arguments.
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v6] usb: core: Add "quirks" parameter for usbcore

[Matthew Wilcox]

On Tue, Mar 13, 2018 at 03:26:19PM +0800, Kai-Heng Feng wrote:
> + usbcore.quirks=
> + [USB] A list of quirks entries to supplement or
> + override the built-in usb core quirk list.  List
> + entries are separated by commas.  Each entry has
> + the form VID:PID:Flags where VID and PID are Vendor
> + and Product ID values (4-digit hex numbers) and
> + Flags is a set of characters, each corresponding
> + to a common usb core quirk flag as follows:

This doesn't really tell me that the specified quirks will be XORed with
the built-in quirks.  Maybe something like ...

[USB] A list of quirk entries to augment the
built-in usb core quirk list.  List entries are
separated by commas.  Each entry has the form
VendorID:ProductID:Flags.  The IDs are 4-digit hex
numbers and Flags is a set of letters.  Each letter
will change the built-in quirk; setting it if it is
clear and clearing it if it is set.  The letters
have the following meanings:

> + /* Each entry consists of VID:PID:flags */
> + field = strsep(, ":");
> + if (!field)
> + break;
> +
> + if (kstrtou16(field, 16, ))
> + break;
> +
> + field = strsep(, ":");
> + if (!field)
> + break;
> +
> + if (kstrtou16(field, 16, ))
> + break;

Is there a reason to not use sscanf here like hid-quirks.c does? 

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v4] usb: core: Add "quirks" parameter for usbcore

[Matthew Wilcox]

On Thu, Mar 01, 2018 at 12:01:40AM +0800, Kai Heng Feng wrote:
> > Also, you won't need to use a linked list for this; you can just allocate
> > an array of quirks.
> 
> I use linked list because the total quirks number is known after the entire
> string gets parsed.
> Do you suggest that I should just alloc a predefined number (like 16) quirk
> entries, instead of doing it dynamically?

I'd just do:

unsigned int nr = 1;
for (i = 0; i < len; i++)
if (str[i] == ',')
nr++;
kcalloc(nr, sizeof(struct), GFP_KERNEL);

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v4] usb: core: Add "quirks" parameter for usbcore

[Matthew Wilcox]

On Mon, Feb 26, 2018 at 11:04:57PM +0800, Kai-Heng Feng wrote:
> +static char quirks_param[128];
> +module_param_string(quirks, quirks_param, sizeof(quirks_param), 0644);
> +MODULE_PARM_DESC(quirks, "Add/modify USB quirks by specifying 
> quirks=vendorID:productID:quirks");
> +
> +static char quirks_param_orig[128];

> +static u32 usb_detect_dynamic_quirks(struct usb_device *udev)
> +{
> + u16 vid = le16_to_cpu(udev->descriptor.idVendor);
> + u16 pid = le16_to_cpu(udev->descriptor.idProduct);
> + struct quirk_entry *quirk;
> +
> + mutex_lock(_mutex);
> + if (strcmp(quirks_param, quirks_param_orig) != 0) {
> + strcpy(quirks_param_orig, quirks_param);

What happens if the user is writing to quirks_param at the same time
that you memcpy it?

I think you're going about this wrong by trying to use the
module_param_string machinery.  You should be using module_param_cb()
to build the quirks list when the user writes it (and then translate
back into a string when the user wants to read from it.
Also, you won't need to use a linked list for this; you can just allocate
an array of quirks.

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v3] usb: core: Add "quirks" parameter for usbcore

[Matthew Wilcox]

On Sun, Feb 25, 2018 at 08:38:33PM +0800, Kai-Heng Feng wrote:
> v2: Use in-kernel tolower() function.

... why are you using tolower at all?

You've got 13 quirks already; you may need to use upper case as well
before too long.

> + quirk = vmalloc(sizeof(struct quirk_entry));

vmalloc?  For a struct that's 24 bytes?  You know that allocates an
entire 4k page, right?

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v6 00/99] XArray version 6

[Matthew Wilcox]

On Thu, Jan 18, 2018 at 05:56:12PM +0100, David Sterba wrote:
> On Thu, Jan 18, 2018 at 08:48:43AM -0800, Matthew Wilcox wrote:
> > Thank you!  I shall attempt to debug.  Was this with a btrfs root
> > filesystem?  I'm most suspicious of those patches right now, since they've
> > received next to no testing.  I'm going to put together a smaller patchset
> > which just does the page cache conversion and nothing else in the hope
> > that we can get that merged this year.
> 
> No, the root is ext3 and there was no btrfs filesytem mounted at the
> time.

Found it; I was missing a prerequisite patch.  New (smaller) patch series
coming soon.
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v6 00/99] XArray version 6

[Matthew Wilcox]

On Thu, Jan 18, 2018 at 05:07:50PM +0100, David Sterba wrote:
> On Wed, Jan 17, 2018 at 12:20:24PM -0800, Matthew Wilcox wrote:
> > From: Matthew Wilcox <mawil...@microsoft.com>
> > 
> > This version of the XArray has no known bugs.
> 
> I've booted this patchset on 2 boxes, both had random problems during
> boot. On one I was not able to diagnose what went wrong. On the other
> one the system booted up to userspace and failed to set up networking.
> Serial console worked and the network service complained about wrong
> format of /usr/share/wicked/schema/team.xml . That's supposed to be a
> text file, though hexdump showed me lots of zeros. Trimmed output:
> 
>   00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  ||
> *
> (similar output here)
> *
> 0a10  00 00 00 00 00 00 00 00  11 03 00 00 00 00 00 00  ||
> 0a20  20 8b 7f 01 00 00 00 00  a0 84 7d 01 00 00 00 00  | .}.|
> 0a30  00 00 00 00 00 00 00 00  10 89 7f 01 00 00 00 00  ||
> 0a40  a0 84 7d 01 00 00 00 00  00 00 00 00 00 00 00 00  |..}.|
> 0a50  80 8a 7f 01 00 00 00 00  e0 cf 7d 01 00 00 00 00  |..}.|
> 0a60  00 00 00 00 00 00 00 00  60 8a 7f 01 00 00 00 00  |`...|
> 0a70  a0 84 7d 01 00 00 00 00  00 00 00 00 00 00 00 00  |..}.|
> 0a80  30 89 7f 01 00 00 00 00  a0 84 7d 01 00 00 00 00  |0.}.|
> 0a90  00 00 00 00 00 00 00 00  60 f2 7f 01 00 00 00 00  |`...|
> 0aa0  40 fd 7e 01 00 00 00 00  00 00 00 00 00 00 00 00  |@.~.|
> 0ab0  00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00  ||
> *
> 1000  3e 0a 20 20 3c 2f 6d 65  74 68 6f 64 3e 0a 3c 2f  |>.  . 1010  73 65 72 76 69 63 65 3e  0a   |service>.|
> 
> There's something at the end of the file that does look like a xml fragment.
> The file size is 4121. This looks to me like exactly the first page of the 
> file
> was not read correctly.
> 
> The xml file is supposed to be read-only during startup, so there was no write
> in flight. 'rpm -Vv' reported only this file corrupted. Booting to other
> kernels was fine, network up, and the file was ok again. So the
> corruption happened only in memory, which leads me to conclusion that
> there is an unknown bug in your patchset.

Thank you!  I shall attempt to debug.  Was this with a btrfs root
filesystem?  I'm most suspicious of those patches right now, since they've
received next to no testing.  I'm going to put together a smaller patchset
which just does the page cache conversion and nothing else in the hope
that we can get that merged this year.
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[BUG] usbfs "did not claim interface before use"

[Matthew Wilcox]

My laptop just died horribly and I'm picking through the pieces.
I'm running Debian testing, and it was kernel 4.13.0-1-amd64 #1 Debian
4.13.13-1 although now I've rebooted to 4.14.0-2-amd64 #1 SMP Debian
4.14.7-1

It seems that the original cause of the problem was usbfs going mad and
spraying this message all over my log files:

Jan 18 09:50:24 bobo kernel: [2212381.201087] usb 3-2: usbfs: process 13608 
(events) did not claim interface 0 before use
Jan 18 09:50:24 bobo kernel: [2212381.201091] usb 3-2: usbfs: process 13608 
(events) did not claim interface 0 before use
Jan 18 09:50:24 bobo kernel: [2212381.201096] usb 3-2: usbfs: process 13608 
(events) did not claim interface 0 before use
Jan 18 09:50:24 bobo kernel: [2212381.201101] usb 3-2: usbfs: process 13608 
(events) did not claim interface 0 before use

(I have 28153585 lines in kern.log and 28149224 of them contain 'usbfs').
Can this warning be ratelimited, please?

Also, it is not coding style compliant as you cannot grep for "did not
claim interface" due to the line split.

(after 280 million lines of this crap, dmcrypt failed an order-2 memory
allocation, and things went seriously downhill after that)
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 03/99] xarray: Replace exceptional entries

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Introduce xarray value entries to replace the radix tree exceptional
entry code.  This is a slight change in encoding to allow the use of an
extra bit (we can now store BITS_PER_LONG - 1 bits in a value entry).
It is also a change in emphasis; exceptional entries are intimidating
and different.  As the comment explains, you can choose to store values
or pointers in the xarray and they are both first-class citizens.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h|   4 +-
 arch/powerpc/include/asm/nohash/64/pgtable.h|   4 +-
 drivers/gpu/drm/i915/i915_gem.c |  17 ++--
 drivers/staging/lustre/lustre/mdc/mdc_request.c |   2 +-
 fs/btrfs/compression.c  |   2 +-
 fs/btrfs/inode.c|   4 +-
 fs/dax.c| 107 
 fs/proc/task_mmu.c  |   2 +-
 include/linux/fs.h  |  48 +++
 include/linux/radix-tree.h  |  36 ++--
 include/linux/swapops.h |  19 ++---
 include/linux/xarray.h  |  51 +++
 lib/idr.c   |  63 ++
 lib/radix-tree.c|  21 ++---
 mm/filemap.c|  10 +--
 mm/khugepaged.c |   2 +-
 mm/madvise.c|   2 +-
 mm/memcontrol.c |   2 +-
 mm/mincore.c|   2 +-
 mm/readahead.c  |   2 +-
 mm/shmem.c  |  10 +--
 mm/swap.c   |   2 +-
 mm/truncate.c   |  12 +--
 mm/workingset.c |  12 ++-
 tools/testing/radix-tree/idr-test.c |   6 +-
 tools/testing/radix-tree/linux/radix-tree.h |   1 +
 tools/testing/radix-tree/multiorder.c   |  47 +--
 tools/testing/radix-tree/test.c |   2 +-
 28 files changed, 256 insertions(+), 236 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h 
b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 44697817ccc6..5025c26f1acd 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -649,9 +649,7 @@ static inline bool pte_user(pte_t pte)
BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY);   \
} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)  (((x).val >> _PAGE_BIT_SWAP_TYPE) \
& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h 
b/arch/powerpc/include/asm/nohash/64/pgtable.h
index abddf5830ad5..f711773568d7 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -329,9 +329,7 @@ static inline void __ptep_set_access_flags(struct mm_struct 
*mm,
 */ \
BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
} while (0)
-/*
- * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
- */
+
 #define SWP_TYPE_BITS 5
 #define __swp_type(x)  (((x).val >> _PAGE_BIT_SWAP_TYPE) \
& ((1UL << SWP_TYPE_BITS) - 1))
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5cfba89ed586..25ce7bcf9988 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5369,7 +5369,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
count = __sg_page_count(sg);
 
while (idx + count <= n) {
-   unsigned long exception, i;
+   void *entry;
+   unsigned long i;
int ret;
 
/* If we cannot allocate and insert this entry, or the
@@ -5384,12 +5385,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
if (ret && ret != -EEXIST)
goto scan;
 
-   exception =
-   RADIX_TREE_EXCEPTIONAL_ENTRY |
-   idx << RADIX_TREE_EXCEPTIONAL_SHIFT;
+   entry = xa_mk_value(idx);
for (i = 1; i < count; i++) {
-   ret = radix_tree_insert(>radix, idx + i,
-   (void *)exception);
+   ret = radix_tree_insert(>radix, idx + i, entry);
if (ret &&

[PATCH v6 04/99] xarray: Change definition of sibling entries

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Instead of storing a pointer to the slot containing the canonical entry,
store the offset of the slot.  Produces slightly more efficient code
(~300 bytes) and simplifies the implementation.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h | 90 ++
 lib/radix-tree.c   | 66 +++-
 2 files changed, 109 insertions(+), 47 deletions(-)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 1aa4ff0c19b6..c308152fde7f 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -22,6 +22,12 @@
  * x1: Value entry
  *
  * Attempting to store internal entries in the XArray is a bug.
+ *
+ * Most internal entries are pointers to the next node in the tree.
+ * The following internal entries have a special meaning:
+ *
+ * 0-62: Sibling entries
+ * 256: Retry entry
  */
 
 #define BITS_PER_XA_VALUE  (BITS_PER_LONG - 1)
@@ -60,6 +66,39 @@ static inline bool xa_is_value(const void *entry)
return (unsigned long)entry & 1;
 }
 
+/*
+ * xa_mk_internal() - Create an internal entry.
+ * @v: Value to turn into an internal entry.
+ *
+ * Return: An XArray internal entry corresponding to this value.
+ */
+static inline void *xa_mk_internal(unsigned long v)
+{
+   return (void *)((v << 2) | 2);
+}
+
+/*
+ * xa_to_internal() - Extract the value from an internal entry.
+ * @entry: XArray entry.
+ *
+ * Return: The value which was stored in the internal entry.
+ */
+static inline unsigned long xa_to_internal(const void *entry)
+{
+   return (unsigned long)entry >> 2;
+}
+
+/*
+ * xa_is_internal() - Is the entry an internal entry?
+ * @entry: XArray entry.
+ *
+ * Return: %true if the entry is an internal entry.
+ */
+static inline bool xa_is_internal(const void *entry)
+{
+   return ((unsigned long)entry & 3) == 2;
+}
+
 #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)  spin_unlock(&(xa)->xa_lock)
@@ -72,4 +111,55 @@ static inline bool xa_is_value(const void *entry)
 #define xa_unlock_irqrestore(xa, flags) \
spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/* Everything below here is the Advanced API.  Proceed with caution. */
+
+/*
+ * The xarray is constructed out of a set of 'chunks' of pointers.  Choosing
+ * the best chunk size requires some tradeoffs.  A power of two recommends
+ * itself so that we can walk the tree based purely on shifts and masks.
+ * Generally, the larger the better; as the number of slots per level of the
+ * tree increases, the less tall the tree needs to be.  But that needs to be
+ * balanced against the memory consumption of each node.  On a 64-bit system,
+ * xa_node is currently 576 bytes, and we get 7 of them per 4kB page.  If we
+ * doubled the number of slots per node, we'd get only 3 nodes per 4kB page.
+ */
+#ifndef XA_CHUNK_SHIFT
+#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6)
+#endif
+#define XA_CHUNK_SIZE  (1UL << XA_CHUNK_SHIFT)
+#define XA_CHUNK_MASK  (XA_CHUNK_SIZE - 1)
+
+/* Private */
+static inline bool xa_is_node(const void *entry)
+{
+   return xa_is_internal(entry) && (unsigned long)entry > 4096;
+}
+
+/* Private */
+static inline void *xa_mk_sibling(unsigned int offset)
+{
+   return xa_mk_internal(offset);
+}
+
+/* Private */
+static inline unsigned long xa_to_sibling(const void *entry)
+{
+   return xa_to_internal(entry);
+}
+
+/**
+ * xa_is_sibling() - Is the entry a sibling entry?
+ * @entry: Entry retrieved from the XArray
+ *
+ * Return: %true if the entry is a sibling entry.
+ */
+static inline bool xa_is_sibling(const void *entry)
+{
+   return IS_ENABLED(CONFIG_RADIX_TREE_MULTIORDER) &&
+   xa_is_internal(entry) &&
+   (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1));
+}
+
+#define XA_RETRY_ENTRY xa_mk_internal(256)
+
 #endif /* _LINUX_XARRAY_H */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 012e4869f99b..f16f63d15edc 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -37,6 +37,7 @@
 #include 
 #include 
 #include 
+#include 
 
 
 /* Number of nodes in fully populated tree of given height */
@@ -97,24 +98,7 @@ static inline void *node_to_entry(void *ptr)
return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE);
 }
 
-#define RADIX_TREE_RETRY   node_to_entry(NULL)
-
-#ifdef CONFIG_RADIX_TREE_MULTIORDER
-/* Sibling slots point directly to another slot in the same node */
-static inline
-bool is_sibling_entry(const struct radix_tree_node *parent, void *node)
-{
-   void __rcu **ptr = node;
-   return (parent->slots <= ptr) &&
-   (ptr < parent->slots + RADIX_TREE_MAP_SIZE);
-}
-#else
-static inline
-

[PATCH v6 05/99] xarray: Add definition of struct xarray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a direct replacement for struct radix_tree_root.  Some of the
struct members have changed name; convert those, and use a #define so
that radix_tree users continue to work without change.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/radix-tree.h   | 33 --
 include/linux/xarray.h   | 59 +
 lib/Makefile |  2 +-
 lib/idr.c|  4 +-
 lib/radix-tree.c | 75 
 lib/xarray.c | 42 ++
 tools/include/linux/spinlock.h   |  1 +
 tools/testing/radix-tree/.gitignore  |  1 +
 tools/testing/radix-tree/Makefile|  8 +++-
 tools/testing/radix-tree/linux/bug.h |  1 +
 tools/testing/radix-tree/linux/kconfig.h |  1 +
 tools/testing/radix-tree/linux/xarray.h  |  2 +
 tools/testing/radix-tree/multiorder.c|  6 +--
 tools/testing/radix-tree/test.c  |  6 +--
 14 files changed, 168 insertions(+), 73 deletions(-)
 create mode 100644 lib/xarray.c
 create mode 100644 tools/testing/radix-tree/linux/kconfig.h
 create mode 100644 tools/testing/radix-tree/linux/xarray.h

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 87f35fe00e55..c8a33e9e9a3c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -30,6 +30,9 @@
 #include 
 #include 
 
+/* Keep unconverted code working */
+#define radix_tree_rootxarray
+
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
  * slot are interpreted:
@@ -59,10 +62,7 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 #define RADIX_TREE_MAX_TAGS 3
 
-#ifndef RADIX_TREE_MAP_SHIFT
-#define RADIX_TREE_MAP_SHIFT   (CONFIG_BASE_SMALL ? 4 : 6)
-#endif
-
+#define RADIX_TREE_MAP_SHIFT   XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK(RADIX_TREE_MAP_SIZE-1)
 
@@ -95,36 +95,21 @@ struct radix_tree_node {
unsigned long   tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-/* The IDR tag is stored in the low bits of the GFP flags */
+/* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR((__force gfp_t)4)
-/* The top bits of gfp_mask are used to store the root tags */
+/* The top bits of xa_flags are used to store the root tags */
 #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT)
 
-struct radix_tree_root {
-   spinlock_t  xa_lock;
-   gfp_t   gfp_mask;
-   struct radix_tree_node  __rcu *rnode;
-};
-
-#define RADIX_TREE_INIT(name, mask){   \
-   .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock),  \
-   .gfp_mask = (mask), \
-   .rnode = NULL,  \
-}
+#define RADIX_TREE_INIT(name, mask)XARRAY_INIT_FLAGS(name, mask)
 
 #define RADIX_TREE(name, mask) \
struct radix_tree_root name = RADIX_TREE_INIT(name, mask)
 
-#define INIT_RADIX_TREE(root, mask)\
-do {   \
-   spin_lock_init(&(root)->xa_lock);   \
-   (root)->gfp_mask = (mask);  \
-   (root)->rnode = NULL;   \
-} while (0)
+#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask)
 
 static inline bool radix_tree_empty(const struct radix_tree_root *root)
 {
-   return root->rnode == NULL;
+   return root->xa_head == NULL;
 }
 
 /**
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index c308152fde7f..3d2f1fafb7ec 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -10,6 +10,8 @@
  */
 
 #include 
+#include 
+#include 
 #include 
 #include 
 
@@ -99,6 +101,63 @@ static inline bool xa_is_internal(const void *entry)
return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * struct xarray - The anchor of the XArray.
+ * @xa_lock: Lock that protects the contents of the XArray.
+ *
+ * To use the xarray, define it statically or embed it in your data structure.
+ * It is a very small data structure, so it does not usually make sense to
+ * allocate it separately and keep a pointer to it in your data structure.
+ *
+ * You may use the xa_lock to protect your own data structures as well.
+ */
+/*
+ * If all of the entries in the array are NULL, @xa_head is a NULL pointer.
+ * If the only non-NULL entry in the array is at index 0, @xa_head is that
+ * entry.  If any other entry in the array is non-NULL, @xa_head points
+ * to an @xa_node.
+ */
+struct xarray {
+   spinlock_t  xa_lock;
+/* private: The rest of the data structure is not to be used dire

[PATCH v6 02/99] page cache: Use xa_lock

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Remove the address_space ->tree_lock and use the xa_lock newly added to
the radix_tree_root.  Rename the address_space ->page_tree to ->pages,
since we don't really care that it's a tree.  Take the opportunity to
rearrange the elements of address_space to pack them better on 64-bit,
and make the comments more useful.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 Documentation/cgroup-v1/memory.txt  |   2 +-
 Documentation/vm/page_migration |  14 +--
 arch/arm/include/asm/cacheflush.h   |   6 +-
 arch/nios2/include/asm/cacheflush.h |   6 +-
 arch/parisc/include/asm/cacheflush.h|   6 +-
 drivers/staging/lustre/lustre/llite/glimpse.c   |   2 +-
 drivers/staging/lustre/lustre/mdc/mdc_request.c |   8 +-
 fs/afs/write.c  |   9 +-
 fs/btrfs/compression.c  |   2 +-
 fs/btrfs/extent_io.c|  16 +--
 fs/btrfs/inode.c|   2 +-
 fs/buffer.c |  13 ++-
 fs/cifs/file.c  |   9 +-
 fs/dax.c| 123 
 fs/f2fs/data.c  |   6 +-
 fs/f2fs/dir.c   |   6 +-
 fs/f2fs/inline.c|   6 +-
 fs/f2fs/node.c  |   8 +-
 fs/fs-writeback.c   |  20 ++--
 fs/inode.c  |  11 +--
 fs/nilfs2/btnode.c  |  20 ++--
 fs/nilfs2/page.c|  22 ++---
 include/linux/backing-dev.h |  12 +--
 include/linux/fs.h  |  17 ++--
 include/linux/mm.h  |   2 +-
 include/linux/pagemap.h |   4 +-
 mm/filemap.c|  84 
 mm/huge_memory.c|  10 +-
 mm/khugepaged.c |  49 +-
 mm/memcontrol.c |   4 +-
 mm/migrate.c|  32 +++---
 mm/page-writeback.c |  42 
 mm/readahead.c  |   2 +-
 mm/rmap.c   |   4 +-
 mm/shmem.c  |  60 ++--
 mm/swap_state.c |  17 ++--
 mm/truncate.c   |  22 ++---
 mm/vmscan.c |  12 +--
 mm/workingset.c |  22 ++---
 39 files changed, 344 insertions(+), 368 deletions(-)

diff --git a/Documentation/cgroup-v1/memory.txt 
b/Documentation/cgroup-v1/memory.txt
index cefb63639070..f0ba3fc6f2d8 100644
--- a/Documentation/cgroup-v1/memory.txt
+++ b/Documentation/cgroup-v1/memory.txt
@@ -262,7 +262,7 @@ When oom event notifier is registered, event will be 
delivered.
 2.6 Locking
 
lock_page_cgroup()/unlock_page_cgroup() should not be called under
-   mapping->tree_lock.
+   the mapping's xa_lock.
 
Other lock order is following:
PG_locked.
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration
index 0478ae2ad44a..faf849596a85 100644
--- a/Documentation/vm/page_migration
+++ b/Documentation/vm/page_migration
@@ -90,7 +90,7 @@ Steps:
 
 1. Lock the page to be migrated
 
-2. Insure that writeback is complete.
+2. Ensure that writeback is complete.
 
 3. Lock the new page that we want to move to. It is locked so that accesses to
this (not yet uptodate) page immediately lock while the move is in progress.
@@ -100,8 +100,8 @@ Steps:
mapcount is not zero then we do not migrate the page. All user space
processes that attempt to access the page will now wait on the page lock.
 
-5. The radix tree lock is taken. This will cause all processes trying
-   to access the page via the mapping to block on the radix tree spinlock.
+5. The address space xa_lock is taken. This will cause all processes trying
+   to access the page via the mapping to block on the spinlock.
 
 6. The refcount of the page is examined and we back out if references remain
otherwise we know that we are the only one referencing this page.
@@ -114,12 +114,12 @@ Steps:
 
 9. The radix tree is changed to point to the new page.
 
-10. The reference count of the old page is dropped because the radix tree
+10. The reference count of the old page is dropped because the address space
 reference is gone. A reference to the new page is established because
-the new page is referenced to by the radix tree.
+the new page is referenced by the address space.
 
-11. The radix tree lock is dropped. With that lookups in the mapping
-become possible again. Processes

[PATCH v6 06/99] xarray: Define struct xa_node

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a direct replacement for struct radix_tree_node.  A couple of
struct members have changed name, so convert those.  Use a #define so
that radix tree users continue to work without change.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/radix-tree.h| 29 +++--
 include/linux/xarray.h| 24 ++
 lib/radix-tree.c  | 48 +--
 mm/workingset.c   | 16 ++--
 tools/testing/radix-tree/multiorder.c | 30 +++---
 5 files changed, 74 insertions(+), 73 deletions(-)

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index c8a33e9e9a3c..f64beb9ba175 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -32,6 +32,7 @@
 
 /* Keep unconverted code working */
 #define radix_tree_rootxarray
+#define radix_tree_nodexa_node
 
 /*
  * The bottom two bits of the slot determine how the remaining bits in the
@@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 
 /*** radix-tree API starts here ***/
 
-#define RADIX_TREE_MAX_TAGS 3
-
 #define RADIX_TREE_MAP_SHIFT   XA_CHUNK_SHIFT
 #define RADIX_TREE_MAP_SIZE(1UL << RADIX_TREE_MAP_SHIFT)
 #define RADIX_TREE_MAP_MASK(RADIX_TREE_MAP_SIZE-1)
 
-#define RADIX_TREE_TAG_LONGS   \
-   ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+#define RADIX_TREE_MAX_TAGSXA_MAX_TAGS
+#define RADIX_TREE_TAG_LONGS   XA_TAG_LONGS
 
 #define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
 #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
  RADIX_TREE_MAP_SHIFT))
 
-/*
- * @count is the count of every non-NULL element in the ->slots array
- * whether that is a data entry, a retry entry, a user pointer,
- * a sibling entry or a pointer to the next level of the tree.
- * @exceptional is the count of every element in ->slots which is
- * either a data entry or a sibling entry for data.
- */
-struct radix_tree_node {
-   unsigned char   shift;  /* Bits remaining in each slot */
-   unsigned char   offset; /* Slot offset in parent */
-   unsigned char   count;  /* Total entry count */
-   unsigned char   exceptional;/* Exceptional entry count */
-   struct radix_tree_node *parent; /* Used when ascending tree */
-   struct radix_tree_root *root;   /* The tree we belong to */
-   union {
-   struct list_head private_list;  /* For tree user */
-   struct rcu_head rcu_head;   /* Used when freeing node */
-   };
-   void __rcu  *slots[RADIX_TREE_MAP_SIZE];
-   unsigned long   tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
 /* The IDR tag is stored in the low bits of xa_flags */
 #define ROOT_IS_IDR((__force gfp_t)4)
 /* The top bits of xa_flags are used to store the root tags */
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 3d2f1fafb7ec..3d5f7804ef45 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -187,6 +187,30 @@ static inline void xa_init(struct xarray *xa)
 #endif
 #define XA_CHUNK_SIZE  (1UL << XA_CHUNK_SHIFT)
 #define XA_CHUNK_MASK  (XA_CHUNK_SIZE - 1)
+#define XA_MAX_TAGS3
+#define XA_TAG_LONGS   DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG)
+
+/*
+ * @count is the count of every non-NULL element in the ->slots array
+ * whether that is a value entry, a retry entry, a user pointer,
+ * a sibling entry or a pointer to the next level of the tree.
+ * @nr_values is the count of every element in ->slots which is
+ * either a value entry or a sibling entry to a value entry.
+ */
+struct xa_node {
+   unsigned char   shift;  /* Bits remaining in each slot */
+   unsigned char   offset; /* Slot offset in parent */
+   unsigned char   count;  /* Total entry count */
+   unsigned char   nr_values;  /* Value entry count */
+   struct xa_node __rcu *parent;   /* NULL at top of tree */
+   struct xarray   *array; /* The array we belong to */
+   union {
+   struct list_head private_list;  /* For tree user */
+   struct rcu_head rcu_head;   /* Used when freeing node */
+   };
+   void __rcu  *slots[XA_CHUNK_SIZE];
+   unsigned long   tags[XA_MAX_TAGS][XA_TAG_LONGS];
+};
 
 /* Private */
 static inline bool xa_is_node(const void *entry)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 126eeb06cfef..74a6ddd1d6ad 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -259,11 +259,11 @@ static void dump_node(struct radix_tree_node *node, 
unsigned long index)
 {
unsigned long i;
 
-   pr_debug("radix node: %p offset %d indices %lu-%lu p

[PATCH v6 07/99] xarray: Add documentation

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is documentation on how to use the XArray, not details about its
internal implementation.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 Documentation/core-api/index.rst  |   1 +
 Documentation/core-api/xarray.rst | 361 ++
 2 files changed, 362 insertions(+)
 create mode 100644 Documentation/core-api/xarray.rst

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index d5bbe035316d..eb16ba30aeb6 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -18,6 +18,7 @@ Core utilities
local_ops
workqueue
genericirq
+   xarray
flexible-arrays
librs
genalloc
diff --git a/Documentation/core-api/xarray.rst 
b/Documentation/core-api/xarray.rst
new file mode 100644
index ..914999c0bf3f
--- /dev/null
+++ b/Documentation/core-api/xarray.rst
@@ -0,0 +1,361 @@
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+==
+XArray
+==
+
+:Author: Matthew Wilcox
+
+Overview
+
+
+The XArray is an abstract data type which behaves like a very large array
+of pointers.  It meets many of the same needs as a hash or a conventional
+resizable array.  Unlike a hash, it allows you to sensibly go to the
+next or previous entry in a cache-efficient manner.  In contrast to
+a resizable array, there is no need for copying data or changing MMU
+mappings in order to grow the array.  It is more memory-efficient,
+parallelisable and cache friendly than a doubly-linked list.  It takes
+advantage of RCU to perform lookups without locking.
+
+The XArray implementation is efficient when the indices used are densely
+clustered; hashing the object and using the hash as the index will not
+perform well.  The XArray is optimised for small indices, but still has
+good performance with large indices.  If your index can be larger than
+``ULONG_MAX`` then the XArray is not the data type for you.  The most
+important user of the XArray is the page cache.
+
+A freshly-initialised XArray contains a ``NULL`` pointer at every index.
+Each non-``NULL`` entry in the array has three bits associated with it
+called tags.  Each tag may be set or cleared independently of the others.
+You can iterate over entries which are tagged.
+
+Normal pointers may be stored in the XArray directly.  They must be 4-byte
+aligned, which is true for any pointer returned from :c:func:`kmalloc` and
+:c:func:`alloc_page`.  It isn't true for arbitrary user-space pointers,
+nor for function pointers.  You can store pointers to statically allocated
+objects, as long as those objects have an alignment of at least 4.
+
+You can also store integers between 0 and ``LONG_MAX`` in the XArray.
+You must first convert it into an entry using :c:func:`xa_mk_value`.
+When you retrieve an entry from the XArray, you can check whether it is
+a value entry by calling :c:func:`xa_is_value`, and convert it back to
+an integer by calling :c:func:`xa_to_value`.
+
+The XArray does not support storing :c:func:`IS_ERR` pointers as some
+conflict with value entries or internal entries.
+
+An unusual feature of the XArray is the ability to create entries which
+occupy a range of indices.  Once stored to, looking up any index in
+the range will return the same entry as looking up any other index in
+the range.  Setting a tag on one index will set it on all of them.
+Storing to any index will store to all of them.  Multi-index entries can
+be explicitly split into smaller entries, or storing ``NULL`` into any
+entry will cause the XArray to forget about the range.
+
+Normal API
+==
+
+Start by initialising an XArray, either with :c:func:`DEFINE_XARRAY`
+for statically allocated XArrays or :c:func:`xa_init` for dynamically
+allocated ones.
+
+You can then set entries using :c:func:`xa_store` and get entries
+using :c:func:`xa_load`.  xa_store will overwrite any entry with the
+new entry and return the previous entry stored at that index.  You can
+use :c:func:`xa_erase` instead of calling :c:func:`xa_store` with a
+%NULL entry.  There is no difference between an entry that has never
+been stored to and one that has most recently had ``NULL`` stored to it.
+
+You can conditionally replace an entry at an index by using
+:c:func:`xa_cmpxchg`.  Like :c:func:`cmpxchg`, it will only succeed if
+the entry at that index has the 'old' value.  It also returns the entry
+which was at that index; if it returns the same entry which was passed as
+'old', then :c:func:`xa_cmpxchg` succeeded.
+
+If you want to only store a new entry to an index if the current entry
+at that index is ``NULL``, you can use :c:func:`xa_insert` which
+returns ``-EEXIST`` if the entry is not empty.
+
+Calling :c:func:`xa_reserve` ensures that there is enough memory allocated
+to store an entry at the specified index.  This is not normally needed,
+but some users have a complicated locking scheme.
+
+You can enquire whether 

[PATCH v6 10/99] xarray: Add xa_store

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

xa_store() differs from radix_tree_insert() in that it will overwrite an
existing element in the array rather than returning an error.  This is
the behaviour which most users want, and those that want more complex
behaviour generally want to use the xas family of routines anyway.

For memory allocation, xa_store() will first attempt to request memory
from the slab allocator; if memory is not immediately available, it will
drop the xa_lock and allocate memory, keeping a pointer in the xa_state.
It does not use the per-CPU cache, although those will continue to exist
until all radix tree users are converted to the xarray.

This patch also includes xa_erase() and __xa_erase() for a streamlined
way to store NULL.  Since there is no need to allocate memory in order
to store a NULL in the XArray, we do not need to trouble the user with
deciding what memory allocation flags to use.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h| 107 +
 lib/radix-tree.c  |   4 +-
 lib/xarray.c  | 642 ++
 tools/include/linux/spinlock.h|   2 +
 tools/testing/radix-tree/linux/kernel.h   |   4 +
 tools/testing/radix-tree/linux/lockdep.h  |  11 +
 tools/testing/radix-tree/linux/rcupdate.h |   1 +
 tools/testing/radix-tree/test.c   |  32 ++
 tools/testing/radix-tree/test.h   |   5 +
 tools/testing/radix-tree/xarray-test.c| 113 +-
 10 files changed, 917 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/radix-tree/linux/lockdep.h

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index ddeb49b8bfc1..139b1c1fd022 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -149,10 +149,17 @@ typedef unsigned __bitwise xa_tag_t;
 #define XA_PRESENT ((__force xa_tag_t)8U)
 #define XA_TAG_MAX XA_TAG_2
 
+enum xa_lock_type {
+   XA_LOCK_IRQ = 1,
+   XA_LOCK_BH = 2,
+};
+
 /*
  * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
  * and we remain compatible with that.
  */
+#define XA_FLAGS_LOCK_IRQ  ((__force gfp_t)XA_LOCK_IRQ)
+#define XA_FLAGS_LOCK_BH   ((__force gfp_t)XA_LOCK_BH)
 #define XA_FLAGS_TAG(tag)  ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
(__force unsigned)(tag)))
 
@@ -202,6 +209,7 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 bool xa_get_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
@@ -217,6 +225,33 @@ static inline void xa_init(struct xarray *xa)
xa_init_flags(xa, 0);
 }
 
+/**
+ * xa_erase() - Erase this entry from the XArray.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * This function is the equivalent of calling xa_store() with %NULL as
+ * the third argument.  The XArray does not need to allocate memory, so
+ * the user does not need to provide GFP flags.
+ *
+ * Return: The entry which used to be at this index.
+ */
+static inline void *xa_erase(struct xarray *xa, unsigned long index)
+{
+   return xa_store(xa, index, NULL, 0);
+}
+
+/**
+ * xa_empty() - Determine if an array has any present entries.
+ * @xa: XArray.
+ *
+ * Return: %true if the array contains only NULL pointers.
+ */
+static inline bool xa_empty(const struct xarray *xa)
+{
+   return xa->xa_head == NULL;
+}
+
 /**
  * xa_tagged() - Inquire whether any entry in this array has a tag set
  * @xa: Array
@@ -243,7 +278,11 @@ static inline bool xa_tagged(const struct xarray *xa, 
xa_tag_t tag)
 
 /*
  * Versions of the normal API which require the caller to hold the xa_lock.
+ * If the GFP flags allow it, will drop the lock in order to allocate
+ * memory, then reacquire it afterwards.
  */
+void *__xa_erase(struct xarray *, unsigned long index);
+void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void __xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void __xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
 
@@ -339,6 +378,12 @@ static inline void *xa_entry_locked(struct xarray *xa,
lockdep_is_held(>xa_lock));
 }
 
+/* Private */
+static inline void *xa_mk_node(const struct xa_node *node)
+{
+   return (void *)((unsigned long)node | 2);
+}
+
 /* Private */
 static inline struct xa_node *xa_to_node(const void *entry)
 {
@@ -519,6 +564,12 @@ static inline bool xas_valid(const struct xa_state *xas)
return !xas_invalid(xas);
 }
 
+/* True if the node represents head-of-tree, RESTART or BOUNDS */
+static inline bool xas_top(struct xa_node

[PATCH v6 09/99] xarray: Add xa_get_tag, xa_set_tag and xa_clear_tag

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

XArray tags are slightly more strongly typed than the radix tree tags,
but occupy the same bits.  This commit also adds the xas_ family of tag
operations, for cases where the caller is already holding the lock, and
xa_tagged() to ask whether any array member has a particular tag set.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h |  40 +++
 lib/xarray.c   | 229 +
 tools/include/linux/spinlock.h |   6 ++
 3 files changed, 275 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 54c694e5c33f..ddeb49b8bfc1 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -11,6 +11,7 @@
 
 #include 
 #include 
+#include 
 #include 
 #include 
 #include 
@@ -141,6 +142,20 @@ static inline int xa_err(void *entry)
return 0;
 }
 
+typedef unsigned __bitwise xa_tag_t;
+#define XA_TAG_0   ((__force xa_tag_t)0U)
+#define XA_TAG_1   ((__force xa_tag_t)1U)
+#define XA_TAG_2   ((__force xa_tag_t)2U)
+#define XA_PRESENT ((__force xa_tag_t)8U)
+#define XA_TAG_MAX XA_TAG_2
+
+/*
+ * Values for xa_flags.  The radix tree stores its GFP flags in the xa_flags,
+ * and we remain compatible with that.
+ */
+#define XA_FLAGS_TAG(tag)  ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \
+   (__force unsigned)(tag)))
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -187,6 +202,9 @@ struct xarray {
 
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
+bool xa_get_tag(struct xarray *, unsigned long index, xa_tag_t);
+void xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
+void xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -199,6 +217,18 @@ static inline void xa_init(struct xarray *xa)
xa_init_flags(xa, 0);
 }
 
+/**
+ * xa_tagged() - Inquire whether any entry in this array has a tag set
+ * @xa: Array
+ * @tag: Tag value
+ *
+ * Return: %true if any entry has this tag set.
+ */
+static inline bool xa_tagged(const struct xarray *xa, xa_tag_t tag)
+{
+   return xa->xa_flags & XA_FLAGS_TAG(tag);
+}
+
 #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)  spin_unlock(&(xa)->xa_lock)
@@ -211,6 +241,12 @@ static inline void xa_init(struct xarray *xa)
 #define xa_unlock_irqrestore(xa, flags) \
spin_unlock_irqrestore(&(xa)->xa_lock, flags)
 
+/*
+ * Versions of the normal API which require the caller to hold the xa_lock.
+ */
+void __xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
+void __xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
@@ -504,6 +540,10 @@ static inline bool xas_retry(struct xa_state *xas, const 
void *entry)
 
 void *xas_load(struct xa_state *);
 
+bool xas_get_tag(const struct xa_state *, xa_tag_t);
+void xas_set_tag(const struct xa_state *, xa_tag_t);
+void xas_clear_tag(const struct xa_state *, xa_tag_t);
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/xarray.c b/lib/xarray.c
index 83b9c25de415..59b57e6f80de 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -5,6 +5,7 @@
  * Author: Matthew Wilcox <mawil...@microsoft.com>
  */
 
+#include 
 #include 
 #include 
 
@@ -24,6 +25,55 @@
  * @entry refers to something stored in a slot in the xarray
  */
 
+static inline struct xa_node *xa_parent(struct xarray *xa,
+   const struct xa_node *node)
+{
+   return rcu_dereference_check(node->parent,
+   lockdep_is_held(>xa_lock));
+}
+
+static inline struct xa_node *xa_parent_locked(struct xarray *xa,
+   const struct xa_node *node)
+{
+   return rcu_dereference_protected(node->parent,
+   lockdep_is_held(>xa_lock));
+}
+
+static inline void xa_tag_set(struct xarray *xa, xa_tag_t tag)
+{
+   if (!(xa->xa_flags & XA_FLAGS_TAG(tag)))
+   xa->xa_flags |= XA_FLAGS_TAG(tag);
+}
+
+static inline void xa_tag_clear(struct xarray *xa, xa_tag_t tag)
+{
+   if (xa->xa_flags & XA_FLAGS_TAG(tag))
+   xa->xa_flags &= ~(XA_FLAGS_TAG(tag));
+}
+
+static inline bool node_get_tag(const struct xa_node *node, unsigned int 
offset,
+   xa_tag_t tag)
+{
+   return test_bit(offset, node->tags[(__force unsigned)tag]);
+}
+
+static inli

[PATCH v6 08/99] xarray: Add xa_load

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This first function in the XArray API brings with it a lot of support
infrastructure.  The advanced API is based around the xa_state which is
a more capable version of the radix_tree_iter.

As the test-suite demonstrates, it is possible to use the xarray and
radix tree APIs on the same data structure.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h  | 282 
 lib/radix-tree.c|  43 -
 lib/xarray.c| 190 +++
 tools/testing/radix-tree/.gitignore |   1 +
 tools/testing/radix-tree/Makefile   |   7 +-
 tools/testing/radix-tree/linux/kernel.h |   1 +
 tools/testing/radix-tree/linux/radix-tree.h |   1 -
 tools/testing/radix-tree/linux/rcupdate.h   |   1 +
 tools/testing/radix-tree/linux/xarray.h |   1 +
 tools/testing/radix-tree/xarray-test.c  |  56 ++
 10 files changed, 537 insertions(+), 46 deletions(-)
 create mode 100644 tools/testing/radix-tree/xarray-test.c

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 3d5f7804ef45..54c694e5c33f 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -12,6 +12,8 @@
 #include 
 #include 
 #include 
+#include 
+#include 
 #include 
 #include 
 
@@ -30,6 +32,10 @@
  *
  * 0-62: Sibling entries
  * 256: Retry entry
+ *
+ * Errors are also represented as internal entries, but use the negative
+ * space (-4094 to -2).  They're never stored in the slots array; only
+ * returned by the normal API.
  */
 
 #define BITS_PER_XA_VALUE  (BITS_PER_LONG - 1)
@@ -101,6 +107,40 @@ static inline bool xa_is_internal(const void *entry)
return ((unsigned long)entry & 3) == 2;
 }
 
+/**
+ * xa_is_err() - Report whether an XArray operation returned an error
+ * @entry: Result from calling an XArray function
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special value indicating an error.  This function tells you
+ * whether an error occurred; xa_err() tells you which error occurred.
+ *
+ * Return: %true if the entry indicates an error.
+ */
+static inline bool xa_is_err(const void *entry)
+{
+   return unlikely(xa_is_internal(entry));
+}
+
+/**
+ * xa_err() - Turn an XArray result into an errno.
+ * @entry: Result from calling an XArray function.
+ *
+ * If an XArray operation cannot complete an operation, it will return
+ * a special pointer value which encodes an errno.  This function extracts
+ * the errno from the pointer value, or returns 0 if the pointer does not
+ * represent an errno.
+ *
+ * Return: A negative errno or 0.
+ */
+static inline int xa_err(void *entry)
+{
+   /* xa_to_internal() would not do sign extension. */
+   if (xa_is_err(entry))
+   return (long)entry >> 2;
+   return 0;
+}
+
 /**
  * struct xarray - The anchor of the XArray.
  * @xa_lock: Lock that protects the contents of the XArray.
@@ -146,6 +186,7 @@ struct xarray {
struct xarray name = XARRAY_INIT_FLAGS(name, flags)
 
 void xa_init_flags(struct xarray *, gfp_t flags);
+void *xa_load(struct xarray *, unsigned long index);
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -212,6 +253,62 @@ struct xa_node {
unsigned long   tags[XA_MAX_TAGS][XA_TAG_LONGS];
 };
 
+#ifdef XA_DEBUG
+void xa_dump(const struct xarray *);
+void xa_dump_node(const struct xa_node *);
+#define XA_BUG_ON(xa, x) do { \
+   if (x) \
+   xa_dump(xa); \
+   BUG_ON(x); \
+   } while (0)
+#define XA_NODE_BUG_ON(node, x) do { \
+   if ((x) && (node)) \
+   xa_dump_node(node); \
+   BUG_ON(x); \
+   } while (0)
+#else
+#define XA_BUG_ON(xa, x)   do { } while (0)
+#define XA_NODE_BUG_ON(node, x)do { } while (0)
+#endif
+
+/* Private */
+static inline void *xa_head(struct xarray *xa)
+{
+   return rcu_dereference_check(xa->xa_head,
+   lockdep_is_held(>xa_lock));
+}
+
+/* Private */
+static inline void *xa_head_locked(struct xarray *xa)
+{
+   return rcu_dereference_protected(xa->xa_head,
+   lockdep_is_held(>xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry(struct xarray *xa,
+   const struct xa_node *node, unsigned int offset)
+{
+   XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+   return rcu_dereference_check(node->slots[offset],
+   lockdep_is_held(>xa_lock));
+}
+
+/* Private */
+static inline void *xa_entry_locked(struct xarray *xa,
+   const struct xa_node *node, unsigned int offset)
+{
+   XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE);
+

[PATCH v6 12/99] xarray: Add xa_for_each

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This iterator allows the user to efficiently walk a range of the array,
executing the loop body once for each entry in that range that matches
the filter.  This commit also includes xa_find() and xa_find_above()
which are helper functions for xa_for_each() but may also be useful in
their own right.

In the xas family of functions, we also have xas_for_each(), xas_find(),
xas_next_entry(), xas_for_each_tag(), xas_find_tag(), xas_next_tag()
and xas_pause().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h | 171 +
 lib/xarray.c   | 272 +
 tools/testing/radix-tree/test.c|  13 ++
 tools/testing/radix-tree/test.h|   1 +
 tools/testing/radix-tree/xarray-test.c | 122 +++
 5 files changed, 579 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index fc9ab3b13e60..fcd7ef68933a 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -215,6 +215,10 @@ void *xa_cmpxchg(struct xarray *, unsigned long index,
 bool xa_get_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
+void *xa_find(struct xarray *xa, unsigned long *index,
+   unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
+void *xa_find_after(struct xarray *xa, unsigned long *index,
+   unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
 
 /**
  * xa_init() - Initialise an empty XArray.
@@ -266,6 +270,33 @@ static inline bool xa_tagged(const struct xarray *xa, 
xa_tag_t tag)
return xa->xa_flags & XA_FLAGS_TAG(tag);
 }
 
+/**
+ * xa_for_each() - Iterate over a portion of an XArray.
+ * @xa: XArray.
+ * @entry: Entry retrieved from array.
+ * @index: Index of @entry.
+ * @max: Maximum index to retrieve from array.
+ * @filter: Selection criterion.
+ *
+ * Initialise @index to the minimum index you want to retrieve from
+ * the array.  During the iteration, @entry will have the value of the
+ * entry stored in @xa at @index.  The iteration will skip all entries in
+ * the array which do not match @filter.  You may modify @index during the
+ * iteration if you want to skip or reprocess indices.  It is safe to modify
+ * the array during the iteration.  At the end of the iteration, @entry will
+ * be set to NULL and @index will have a value less than or equal to max.
+ *
+ * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n).  You have
+ * to handle your own locking with xas_for_each(), and if you have to unlock
+ * after each iteration, it will also end up being O(n.log(n)).  xa_for_each()
+ * will spin if it hits a retry entry; if you intend to see retry entries,
+ * you should use the xas_for_each() iterator instead.  The xas_for_each()
+ * iterator will expand into more inline code than xa_for_each().
+ */
+#define xa_for_each(xa, entry, index, max, filter) \
+   for (entry = xa_find(xa, , max, filter); entry; \
+entry = xa_find_after(xa, , max, filter))
+
 /**
  * xa_insert() - Store this entry in the XArray unless another entry is
  * already present.
@@ -620,6 +651,12 @@ static inline bool xas_valid(const struct xa_state *xas)
return !xas_invalid(xas);
 }
 
+/* True if the pointer is something other than a node */
+static inline bool xas_not_node(struct xa_node *node)
+{
+   return ((unsigned long)node & 3) || !node;
+}
+
 /* True if the node represents head-of-tree, RESTART or BOUNDS */
 static inline bool xas_top(struct xa_node *node)
 {
@@ -648,13 +685,16 @@ static inline bool xas_retry(struct xa_state *xas, const 
void *entry)
 void *xas_load(struct xa_state *);
 void *xas_store(struct xa_state *, void *entry);
 void *xas_create(struct xa_state *);
+void *xas_find(struct xa_state *, unsigned long max);
 
 bool xas_get_tag(const struct xa_state *, xa_tag_t);
 void xas_set_tag(const struct xa_state *, xa_tag_t);
 void xas_clear_tag(const struct xa_state *, xa_tag_t);
+void *xas_find_tag(struct xa_state *, unsigned long max, xa_tag_t);
 void xas_init_tags(const struct xa_state *);
 
 bool xas_nomem(struct xa_state *, gfp_t);
+void xas_pause(struct xa_state *);
 
 /**
  * xas_reload() - Refetch an entry from the xarray.
@@ -727,6 +767,137 @@ static inline void xas_set_update(struct xa_state *xas, 
xa_update_node_t update)
xas->xa_update = update;
 }
 
+/* Skip over any of these entries when iterating */
+static inline bool xa_iter_skip(const void *entry)
+{
+   return unlikely(!entry ||
+   (xa_is_internal(entry) && entry < XA_RETRY_ENTRY));
+}
+
+/**
+ * xas_next_entry() - Advance iterator to next present entry.
+ * @xas: XArray operation state.
+ * @max: Highest index to return.
+ *
+ * xas_next_entry() is an inline 

[PATCH v6 11/99] xarray: Add xa_cmpxchg and xa_insert

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Like cmpxchg(), xa_cmpxchg will only store to the index if the current
entry matches the old entry.  It returns the current entry, which is
usually more useful than the errno returned by radix_tree_insert().
For the users who really only want the errno, the xa_insert() wrapper
provides a more convenient calling convention.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h | 56 
 lib/xarray.c   | 68 ++
 tools/testing/radix-tree/xarray-test.c | 10 +
 3 files changed, 134 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 139b1c1fd022..fc9ab3b13e60 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -210,6 +210,8 @@ struct xarray {
 void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
 void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
+void *xa_cmpxchg(struct xarray *, unsigned long index,
+   void *old, void *entry, gfp_t);
 bool xa_get_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
@@ -264,6 +266,32 @@ static inline bool xa_tagged(const struct xarray *xa, 
xa_tag_t tag)
return xa->xa_flags & XA_FLAGS_TAG(tag);
 }
 
+/**
+ * xa_insert() - Store this entry in the XArray unless another entry is
+ * already present.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * If you would rather see the existing entry in the array, use xa_cmpxchg().
+ * This function is for users who don't care what the entry is, only that
+ * one is present.
+ *
+ * Return: -EEXIST if another entry was present, 0 if the store succeeded,
+ * or another negative errno if a different error happened (eg -ENOMEM).
+ */
+static inline int xa_insert(struct xarray *xa, unsigned long index,
+   void *entry, gfp_t gfp)
+{
+   void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp);
+   if (!curr)
+   return 0;
+   if (xa_is_err(curr))
+   return xa_err(curr);
+   return -EEXIST;
+}
+
 #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)  spin_unlock(&(xa)->xa_lock)
@@ -283,9 +311,37 @@ static inline bool xa_tagged(const struct xarray *xa, 
xa_tag_t tag)
  */
 void *__xa_erase(struct xarray *, unsigned long index);
 void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
+void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old,
+   void *entry, gfp_t);
 void __xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void __xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
 
+/**
+ * __xa_insert() - Store this entry in the XArray unless another entry is
+ * already present.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * If you would rather see the existing entry in the array, use __xa_cmpxchg().
+ * This function is for users who don't care what the entry is, only that
+ * one is present.
+ *
+ * Return: -EEXIST if another entry was present, 0 if the store succeeded,
+ * or another negative errno if a different error happened (eg -ENOMEM).
+ */
+static inline int __xa_insert(struct xarray *xa, unsigned long index,
+   void *entry, gfp_t gfp)
+{
+   void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp);
+   if (!curr)
+   return 0;
+   if (xa_is_err(curr))
+   return xa_err(curr);
+   return -EEXIST;
+}
+
 /* Everything below here is the Advanced API.  Proceed with caution. */
 
 /*
diff --git a/lib/xarray.c b/lib/xarray.c
index 45b70e622bf1..d925a98fb9b8 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -928,6 +928,74 @@ void *__xa_store(struct xarray *xa, unsigned long index, 
void *entry, gfp_t gfp)
 }
 EXPORT_SYMBOL(__xa_store);
 
+/**
+ * xa_cmpxchg() - Conditionally replace an entry in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @old: Old value to test against.
+ * @entry: New value to place in array.
+ * @gfp: Memory allocation flags.
+ *
+ * If the entry at @index is the same as @old, replace it with @entry.
+ * If the return value is equal to @old, then the exchange was successful.
+ *
+ * Return: The old value at this index or xa_err() if an error happened.
+ */
+void *xa_cmpxchg(struct xarray *xa, unsigned long index,
+   void *old, void *entry, gfp_t gfp)
+{
+   XA_STATE(xas, xa, index);
+   void *curr;
+
+   if (WARN_ON_ONCE(xa_is_internal(entry)))
+ 

[PATCH v6 13/99] xarray: Add xa_extract

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This function combines the functionality of radix_tree_gang_lookup() and
radix_tree_gang_lookup_tagged().  It extracts entries matching the
specified filter into a normal array.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h |  2 ++
 lib/xarray.c   | 80 ++
 2 files changed, 82 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index fcd7ef68933a..d79fd48e4957 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -219,6 +219,8 @@ void *xa_find(struct xarray *xa, unsigned long *index,
unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
 void *xa_find_after(struct xarray *xa, unsigned long *index,
unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
+unsigned int xa_extract(struct xarray *, void **dst, unsigned long start,
+   unsigned long max, unsigned int n, xa_tag_t);
 
 /**
  * xa_init() - Initialise an empty XArray.
diff --git a/lib/xarray.c b/lib/xarray.c
index 3e6be0a07525..be276618f81b 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1368,6 +1368,86 @@ void *xa_find_after(struct xarray *xa, unsigned long 
*indexp,
 }
 EXPORT_SYMBOL(xa_find_after);
 
+static unsigned int xas_extract_present(struct xa_state *xas, void **dst,
+   unsigned long max, unsigned int n)
+{
+   void *entry;
+   unsigned int i = 0;
+
+   rcu_read_lock();
+   xas_for_each(xas, entry, max) {
+   if (xas_retry(xas, entry))
+   continue;
+   dst[i++] = entry;
+   if (i == n)
+   break;
+   }
+   rcu_read_unlock();
+
+   return i;
+}
+
+static unsigned int xas_extract_tag(struct xa_state *xas, void **dst,
+   unsigned long max, unsigned int n, xa_tag_t tag)
+{
+   void *entry;
+   unsigned int i = 0;
+
+   rcu_read_lock();
+   xas_for_each_tag(xas, entry, max, tag) {
+   if (xas_retry(xas, entry))
+   continue;
+   dst[i++] = entry;
+   if (i == n)
+   break;
+   }
+   rcu_read_unlock();
+
+   return i;
+}
+
+/**
+ * xa_extract() - Copy selected entries from the XArray into a normal array.
+ * @xa: The source XArray to copy from.
+ * @dst: The buffer to copy entries into.
+ * @start: The first index in the XArray eligible to be selected.
+ * @max: The last index in the XArray eligible to be selected.
+ * @n: The maximum number of entries to copy.
+ * @filter: Selection criterion.
+ *
+ * Copies up to @n entries that match @filter from the XArray.  The
+ * copied entries will have indices between @start and @max, inclusive.
+ *
+ * The @filter may be an XArray tag value, in which case entries which are
+ * tagged with that tag will be copied.  It may also be %XA_PRESENT, in
+ * which case non-NULL entries will be copied.
+ *
+ * This function uses the RCU lock to protect itself.  That means that the
+ * entries returned may not represent a snapshot of the XArray at a moment
+ * in time.  For example, if index 5 is stored to, then index 10 is stored to,
+ * calling xa_extract() may return the old contents of index 5 and the
+ * new contents of index 10.  Indices not modified while this function is
+ * running will not be skipped.
+ *
+ * If you need stronger guarantees, holding the xa_lock across calls to this
+ * function will prevent concurrent modification.
+ *
+ * Return: The number of entries copied.
+ */
+unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start,
+   unsigned long max, unsigned int n, xa_tag_t filter)
+{
+   XA_STATE(xas, xa, start);
+
+   if (!n)
+   return 0;
+
+   if ((__force unsigned int)filter < XA_MAX_TAGS)
+   return xas_extract_tag(, dst, max, n, filter);
+   return xas_extract_present(, dst, max, n);
+}
+EXPORT_SYMBOL(xa_extract);
+
 #ifdef XA_DEBUG
 void xa_dump_node(const struct xa_node *node)
 {
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 15/99] xarray: Add xas_next and xas_prev

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

These two functions move the xas index by one position, and adjust the
rest of the iterator state to match it.  This is more efficient than
calling xas_set() as it keeps the iterator at the leaves of the tree
instead of walking the iterator from the root each time.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h |  67 +
 lib/xarray.c   |  74 ++
 tools/testing/radix-tree/xarray-test.c | 259 +
 3 files changed, 400 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index d106b2fe4cec..01ce313fc00e 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -660,6 +660,12 @@ static inline bool xas_not_node(struct xa_node *node)
return ((unsigned long)node & 3) || !node;
 }
 
+/* True if the node represents RESTART or an error */
+static inline bool xas_frozen(struct xa_node *node)
+{
+   return (unsigned long)node & 2;
+}
+
 /* True if the node represents head-of-tree, RESTART or BOUNDS */
 static inline bool xas_top(struct xa_node *node)
 {
@@ -901,6 +907,67 @@ enum {
for (entry = xas_find_tag(xas, max, tag); entry; \
 entry = xas_next_tag(xas, max, tag))
 
+void *__xas_next(struct xa_state *);
+void *__xas_prev(struct xa_state *);
+
+/**
+ * xas_prev() - Move iterator to previous index.
+ * @xas: XArray operation state.
+ *
+ * If the @xas was in an error state, it will remain in an error state
+ * and this function will return %NULL.  If the @xas has never been walked,
+ * it will have the effect of calling xas_load().  Otherwise one will be
+ * subtracted from the index and the state will be walked to the correct
+ * location in the array for the next operation.
+ *
+ * If the iterator was referencing index 0, this function wraps
+ * around to %ULONG_MAX.
+ *
+ * Return: The entry at the new index.  This may be %NULL or an internal
+ * entry, although it should never be a node entry.
+ */
+static inline void *xas_prev(struct xa_state *xas)
+{
+   struct xa_node *node = xas->xa_node;
+
+   if (unlikely(xas_not_node(node) || node->shift ||
+   xas->xa_offset == 0))
+   return __xas_prev(xas);
+
+   xas->xa_index--;
+   xas->xa_offset--;
+   return xa_entry(xas->xa, node, xas->xa_offset);
+}
+
+/**
+ * xas_next() - Move state to next index.
+ * @xas: XArray operation state.
+ *
+ * If the @xas was in an error state, it will remain in an error state
+ * and this function will return %NULL.  If the @xas has never been walked,
+ * it will have the effect of calling xas_load().  Otherwise one will be
+ * added to the index and the state will be walked to the correct
+ * location in the array for the next operation.
+ *
+ * If the iterator was referencing index %ULONG_MAX, this function wraps
+ * around to 0.
+ *
+ * Return: The entry at the new index.  This may be %NULL or an internal
+ * entry, although it should never be a node entry.
+ */
+static inline void *xas_next(struct xa_state *xas)
+{
+   struct xa_node *node = xas->xa_node;
+
+   if (unlikely(xas_not_node(node) || node->shift ||
+   xas->xa_offset == XA_CHUNK_MASK))
+   return __xas_next(xas);
+
+   xas->xa_index++;
+   xas->xa_offset++;
+   return xa_entry(xas->xa, node, xas->xa_offset);
+}
+
 /* Internal functions, mostly shared between radix-tree.c, xarray.c and idr.c 
*/
 void xas_destroy(struct xa_state *);
 
diff --git a/lib/xarray.c b/lib/xarray.c
index af81d4bf9ae1..e8ece1fff9fd 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -838,6 +838,80 @@ void xas_pause(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_pause);
 
+/*
+ * __xas_prev() - Find the previous entry in the XArray.
+ * @xas: XArray operation state.
+ *
+ * Helper function for xas_prev() which handles all the complex cases
+ * out of line.
+ */
+void *__xas_prev(struct xa_state *xas)
+{
+   void *entry;
+
+   if (!xas_frozen(xas->xa_node))
+   xas->xa_index--;
+   if (xas_not_node(xas->xa_node))
+   return xas_load(xas);
+
+   if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node))
+   xas->xa_offset--;
+
+   while (xas->xa_offset == 255) {
+   xas->xa_offset = xas->xa_node->offset - 1;
+   xas->xa_node = xa_parent(xas->xa, xas->xa_node);
+   if (!xas->xa_node)
+   return set_bounds(xas);
+   }
+
+   for (;;) {
+   entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
+   if (!xa_is_node(entry))
+   return entry;
+
+   xas->xa_node = xa_to_node(entry);
+   xas_set_offset(xas);
+   }
+}
+EXPORT_SYMBOL_GPL(__xas_prev)

[PATCH v6 14/99] xarray: Add xa_destroy

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This function frees all the internal memory allocated to the xarray
and reinitialises it to be empty.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h |  1 +
 lib/xarray.c   | 26 ++
 2 files changed, 27 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index d79fd48e4957..d106b2fe4cec 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -221,6 +221,7 @@ void *xa_find_after(struct xarray *xa, unsigned long *index,
unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
 unsigned int xa_extract(struct xarray *, void **dst, unsigned long start,
unsigned long max, unsigned int n, xa_tag_t);
+void xa_destroy(struct xarray *);
 
 /**
  * xa_init() - Initialise an empty XArray.
diff --git a/lib/xarray.c b/lib/xarray.c
index be276618f81b..af81d4bf9ae1 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1448,6 +1448,32 @@ unsigned int xa_extract(struct xarray *xa, void **dst, 
unsigned long start,
 }
 EXPORT_SYMBOL(xa_extract);
 
+/**
+ * xa_destroy() - Free all internal data structures.
+ * @xa: XArray.
+ *
+ * After calling this function, the XArray is empty and has freed all memory
+ * allocated for its internal data structures.  You are responsible for
+ * freeing the objects referenced by the XArray.
+ */
+void xa_destroy(struct xarray *xa)
+{
+   XA_STATE(xas, xa, 0);
+   unsigned long flags;
+   void *entry;
+
+   xas.xa_node = NULL;
+   xas_lock_irqsave(, flags);
+   entry = xa_head_locked(xa);
+   RCU_INIT_POINTER(xa->xa_head, NULL);
+   xas_init_tags();
+   /* lockdep checks we're still holding the lock in xas_free_nodes() */
+   if (xa_is_node(entry))
+   xas_free_nodes(, xa_to_node(entry));
+   xas_unlock_irqrestore(, flags);
+}
+EXPORT_SYMBOL(xa_destroy);
+
 #ifdef XA_DEBUG
 void xa_dump_node(const struct xa_node *node)
 {
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 17/99] xarray: Add MAINTAINERS entry

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Add myself as XArray and IDR maintainer.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 MAINTAINERS | 12 
 1 file changed, 12 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 18994806e441..55ae4c0b38d5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14893,6 +14893,18 @@ T: git 
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
 S: Maintained
 F: arch/x86/entry/vdso/
 
+XARRAY
+M: Matthew Wilcox <mawil...@microsoft.com>
+M: Matthew Wilcox <wi...@infradead.org>
+L: linux-fsde...@vger.kernel.org
+S: Supported
+F: Documentation/core-api/xarray.rst
+F: lib/idr.c
+F: lib/xarray.c
+F: include/linux/idr.h
+F: include/linux/xarray.h
+F: tools/testing/radix-tree
+
 XC2028/3028 TUNER DRIVER
 M: Mauro Carvalho Chehab <mche...@s-opensource.com>
 M: Mauro Carvalho Chehab <mche...@kernel.org>
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 16/99] xarray: Add xas_create_range

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This hopefully temporary function is useful for users who have not yet
been converted to multi-index entries.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h |  2 ++
 lib/xarray.c   | 22 ++
 2 files changed, 24 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 01ce313fc00e..acb6d02ff194 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -705,6 +705,8 @@ void xas_init_tags(const struct xa_state *);
 bool xas_nomem(struct xa_state *, gfp_t);
 void xas_pause(struct xa_state *);
 
+void xas_create_range(struct xa_state *, unsigned long max);
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/xarray.c b/lib/xarray.c
index e8ece1fff9fd..c044373d6893 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -612,6 +612,28 @@ void *xas_create(struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_create);
 
+/**
+ * xas_create_range() - Ensure that stores to this range will succeed
+ * @xas: XArray operation state.
+ * @max: The highest index to create a slot for.
+ *
+ * Creates all of the slots in the range between the current position of
+ * @xas and @max.  This is for the benefit of users who have not yet been
+ * converted to multi-index entries.
+ *
+ * The implementation is naive.
+ */
+void xas_create_range(struct xa_state *xas, unsigned long max)
+{
+   XA_STATE(tmp, xas->xa, xas->xa_index);
+
+   do {
+   xas_create();
+   xas_set(, tmp.xa_index + XA_CHUNK_SIZE);
+   } while (tmp.xa_index < max);
+}
+EXPORT_SYMBOL_GPL(xas_create_range);
+
 static void store_siblings(struct xa_state *xas, void *entry, void *curr,
int *countp, int *valuesp)
 {
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 19/99] idr: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The IDR distinguishes between unallocated entries (read as NULL) and
entries where the user has chosen to store NULL.  The radix tree was
modified to consider NULL entries which had tag 0 _clear_ as being
allocated, but it added a lot of complexity.

Instead, the XArray has a 'zero entry', which the normal API will treat
as NULL, but is distinct from NULL when using the advanced API.  The IDR
code converts between NULL and zero entries.

The idr_for_each_entry_ul() iterator becomes an alias for xa_for_each(),
so we drop the idr_get_next_ul() function as it has no users.

The exported IDR API was a weird mix of GPL-only and general symbols;
I converted them all to GPL as there was no way to use the IDR API
without being GPL.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 Documentation/core-api/xarray.rst   |   6 +
 include/linux/idr.h | 156 ---
 include/linux/xarray.h  |  29 +++-
 lib/idr.c   | 298 ++--
 lib/radix-tree.c|  77 +-
 lib/xarray.c|  32 
 tools/testing/radix-tree/idr-test.c |  34 
 7 files changed, 419 insertions(+), 213 deletions(-)

diff --git a/Documentation/core-api/xarray.rst 
b/Documentation/core-api/xarray.rst
index 0172c7d9e6ea..1dea1c522506 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -284,6 +284,12 @@ to :c:func:`xas_retry`, and retry the operation if it 
returns ``true``.
this RCU period.  You should restart the lookup from the head of the
array.
 
+   * - Zero
+ - :c:func:`xa_is_zero`
+ - Zero entries appear as ``NULL`` through the Normal API, but occupy an
+   entry in the XArray which can be tagged or otherwise used to reserve
+   the index.
+
 Other internal entries may be added in the future.  As far as possible, they
 will be handled by :c:func:`xas_retry`.
 
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 11eea38b9629..9064ae5f0abc 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -9,35 +9,35 @@
  * tables.
  */
 
-#ifndef __IDR_H__
-#define __IDR_H__
+#ifndef _LINUX_IDR_H
+#define _LINUX_IDR_H
 
 #include 
 #include 
 #include 
-#include 
+#include 
 
 struct idr {
-   struct radix_tree_root  idr_rt;
-   unsigned intidr_next;
+   struct xarray   idr_xa;
+   unsigned intidr_next;
 };
 
-/*
- * The IDR API does not expose the tagging functionality of the radix tree
- * to users.  Use tag 0 to track whether a node has free space below it.
- */
-#define IDR_FREE   0
-
-/* Set the IDR flag and the IDR_FREE tag */
-#define IDR_RT_MARKER  (ROOT_IS_IDR | (__force gfp_t)  \
-   (1 << (ROOT_TAG_SHIFT + IDR_FREE)))
+#define IDR_INIT_FLAGS (XA_FLAGS_TRACK_FREE | XA_FLAGS_LOCK_IRQ |  \
+XA_FLAGS_TAG(XA_FREE_TAG))
 
 #define IDR_INIT(name) \
 {  \
-   .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER)  \
+   .idr_xa = XARRAY_INIT_FLAGS(name.idr_xa, IDR_INIT_FLAGS),   \
+   .idr_next = 0,  \
 }
 #define DEFINE_IDR(name)   struct idr name = IDR_INIT(name)
 
+static inline void idr_init(struct idr *idr)
+{
+   xa_init_flags(>idr_xa, IDR_INIT_FLAGS);
+   idr->idr_next = 0;
+}
+
 /**
  * idr_get_cursor - Return the current position of the cyclic allocator
  * @idr: idr handle
@@ -66,62 +66,83 @@ static inline void idr_set_cursor(struct idr *idr, unsigned 
int val)
 
 /**
  * DOC: idr sync
- * idr synchronization (stolen from radix-tree.h)
+ * idr synchronization
  *
- * idr_find() is able to be called locklessly, using RCU. The caller must
- * ensure calls to this function are made within rcu_read_lock() regions.
- * Other readers (lock-free or otherwise) and modifications may be running
- * concurrently.
+ * The IDR manages its own locking, using irqsafe spinlocks for operations
+ * which modify the IDR and RCU for operations which do not.  The user of
+ * the IDR may choose to wrap accesses to it in a lock if it needs to
+ * guarantee the IDR does not change during a read access.  The easiest way
+ * to do this is to grab the same lock the IDR uses for write accesses
+ * using one of the idr_lock() wrappers.
  *
- * It is still required that the caller manage the synchronization and
- * lifetimes of the items. So if RCU lock-free lookups are used, typically
- * this would mean that the items have their own locks, or are amenable to
- * lock-free access; and that the items are freed by RCU (or only freed after
- * having been deleted from the idr tree *and* a synchronize_rcu() grace
- * period).
+ * The caller must still manage the synch

[PATCH v6 18/99] xarray: Add ability to store errno values

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

While the radix tree offers no ability to store IS_ERR pointers,
documenting that the XArray does not led to some concern.  Here is a
sanctioned way to store errnos in the XArray.  I'm concerned that it
will confuse people who can't tell the difference between xa_is_err()
and xa_is_errno(), so I've added copious kernel-doc to help them tell
the difference.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 Documentation/core-api/xarray.rst  |  8 +--
 include/linux/xarray.h | 44 ++
 tools/testing/radix-tree/xarray-test.c |  8 ++-
 3 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/Documentation/core-api/xarray.rst 
b/Documentation/core-api/xarray.rst
index 914999c0bf3f..0172c7d9e6ea 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -42,8 +42,12 @@ When you retrieve an entry from the XArray, you can check 
whether it is
 a value entry by calling :c:func:`xa_is_value`, and convert it back to
 an integer by calling :c:func:`xa_to_value`.
 
-The XArray does not support storing :c:func:`IS_ERR` pointers as some
-conflict with value entries or internal entries.
+The XArray does not support storing :c:func:`IS_ERR` pointers because
+some conflict with value entries or internal entries.  If you need
+to store error numbers in the array, you can encode them into error
+entries with :c:func:`xa_mk_errno`, check whether a returned entry is
+an error with :c:func:`xa_is_errno` and convert it back into an errno
+with :c:func:`xa_to_errno`.
 
 An unusual feature of the XArray is the ability to create entries which
 occupy a range of indices.  Once stored to, looking up any index in
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index acb6d02ff194..ca6af6dd42c4 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -75,6 +75,50 @@ static inline bool xa_is_value(const void *entry)
return (unsigned long)entry & 1;
 }
 
+/**
+ * xa_mk_errno() - Create an XArray entry from an error number.
+ * @error: Error number to store in XArray.
+ *
+ * Return: An entry suitable for storing in the XArray.
+ */
+static inline void *xa_mk_errno(long error)
+{
+   return (void *)(error << 2);
+}
+
+/**
+ * xa_to_errno() - Get error number stored in an XArray entry.
+ * @entry: XArray entry.
+ *
+ * Calling this function on an entry which is not an xa_is_errno() will
+ * yield unpredictable results.  Do not confuse this function with xa_err();
+ * this function is for errnos which have been stored in the XArray, and
+ * that function is for errors returned from the XArray implementation.
+ *
+ * Return: The error number stored in the XArray entry.
+ */
+static inline long xa_to_errno(const void *entry)
+{
+   return (long)entry >> 2;
+}
+
+/**
+ * xa_is_errno() - Determine if an entry is an errno.
+ * @entry: XArray entry.
+ *
+ * Do not confuse this function with xa_is_err(); that function tells you
+ * whether the XArray implementation returned an error; this function
+ * tells you whether the entry you successfully stored in the XArray
+ * represented an errno.  If you have never stored an errno in the XArray,
+ * you do not have to check this.
+ *
+ * Return: True if the entry is an errno, false if it is a pointer.
+ */
+static inline bool xa_is_errno(const void *entry)
+{
+   return (((unsigned long)entry & 3) == 0) && (entry > (void *)-4096);
+}
+
 /*
  * xa_mk_internal() - Create an internal entry.
  * @v: Value to turn into an internal entry.
diff --git a/tools/testing/radix-tree/xarray-test.c 
b/tools/testing/radix-tree/xarray-test.c
index 2ad460c1febf..4d3541ac31e9 100644
--- a/tools/testing/radix-tree/xarray-test.c
+++ b/tools/testing/radix-tree/xarray-test.c
@@ -29,7 +29,13 @@ void check_xa_err(struct xarray *xa)
assert(xa_err(xa_store(xa, 1, xa_mk_value(0), GFP_KERNEL)) == 0);
assert(xa_err(xa_store(xa, 1, NULL, 0)) == 0);
 // kills the test-suite :-(
-// assert(xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) == -EINVAL);
+// assert(xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) == -EINVAL);
+
+   assert(xa_err(xa_store(xa, 0, xa_mk_errno(-ENOMEM), GFP_KERNEL)) == 0);
+   assert(xa_err(xa_load(xa, 0)) == 0);
+   assert(xa_is_errno(xa_load(xa, 0)) == true);
+   assert(xa_to_errno(xa_load(xa, 0)) == -ENOMEM);
+   xa_erase(xa, 0);
 }
 
 void check_xa_tag(struct xarray *xa)
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 00/99] XArray version 6

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This version of the XArray has no known bugs.  I have converted the
radix tree test suite entirely over to the XArray and fixed all bugs
that it has uncovered.  There are additional tests in the test suite for
the XArray, so I now claim the XArray has better test coverage than the
Radix Tree did.  Of course, that is not the same thing as fewer bugs,
but it now stands up to the tender embraces of Trinity without crashing.

You can get this version from my git tree here:
http://git.infradead.org/users/willy/linux-dax.git/shortlog/refs/heads/xarray-2018-01-09
which includes a number of other patches that are at least tangentially
related to this patch set.

Most of the work I've done recently has been converting additional users
from the radix tree to the XArray.  That's going pretty well; still 24
radix tree users left to convert.  It's been worth doing because I've
spotted several common patterns that have led to changes (the lock_type,
reserve/release) and some common patterns that I'll add support for
later (chaining multiple entries from a single index, wanting to use
64-bit indices on 32-bit machines, having an array of XArrays, various
workarounds for not having range entries yet).

As far as line count goes, for the whole git tree, we're at:
 212 files changed, 7764 insertions(+), 7002 deletions(-)
with another 1376 lines to delete from radix-tree.[ch].  That doesn't take
into account the 371 lines of xarray.rst, the 587 lines of xarray-test.c,
and the fact that almost half of lib/xarray.c and include/linux/xarray.h
is documentation.

Changes since version 5:

 - Rebased to 4.15-rc8

API changes:
 - Renamed __xa_init() to xa_init_flags().
 - Added DEFINE_XARRAY_FLAGS().
 - Renamed xa_ctx to xa_lock_type; store it in the XA_FLAGS and use separate
   locking classes for each type so that lockdep doesn't emit spurious
   warnings.  It also reduces the amount of boilerplate.
 - Combined __xa_store_bh, __xa_store_irq and __xa_store into __xa_store().
 - Ditto for __xa_cmpxchg().
 - Renamed xa_store_empty() to xa_insert().
 - Added __xa_insert().
 - Added xa_reserve() and xa_release().
 - Renamed XA_NO_TAG to XA_PRESENT.
 - Combined xa_get_entries(), xa_get_tagged() and xa_get_maybe_tag()
   into xa_extract().
 - Added 'filter' argument to xa_find(), xa_find_after() and xa_for_each()
   to match xa_extract() and provide the functionality that would
   have otherwise had to be added in the form of xa_find_tag(),
   xa_find_tag_after() and xa_for_each_tag().
 - Replaced workingset_lookup_update() with mapping_set_update().
 - Renamed page_cache_tree_delete() to page_cache_delete().

New xarray users:
 - Converted SuperH interrupt controller radix tree to XArray.
 - Converted blk-cgroup radix tree to XArray.
 - Converted blk-ioc radix tree to XArray.
 - Converted i915 handles_vma radix tree to XArray.
 - Converted s390 gmap radix trees to XArray.
 - Converted hwspinlock to XArray.
 - Converted btrfs fs_roots to XArray.
 - Converted btrfs reada_zones to XArray.
 - Converted btrfs reada_extents to XArray.
 - Converted btrfs reada_tree to XArray.
 - Converted btrfs buffer_radix to XArray.
 - Converted btrfs delayed_nodes to XArray.
 - Converted btrfs name_cache to XArray.
 - Converted f2fs pids radix tree to XArray.
 - Converted f2fs ino_root radix tree to XArray.
 - Converted f2fs extent_tree to XArray.
 - Converted f2fs gclist radix tree to XArray.
 - Converted dma-debug active cacheline radix tree to XArray.
 - Converted Xen pvcalls-back socketpass_mappings to XArray.
 - Converted net/qrtr radix tree to XArray.
 - Converted null_blk radix trees to XArray.

Documentation:
 - Added a bit more internals documentation.
 - Rewrote xa_init_flags documentation.
 - Added the __xa_ functions to the locking table.
 - Rewrote the section on using the __xa_ functions.

Internal changes:
 - Free up the bottom four bits of the xa_flags, since these are not
   valid GFP flags to pass to kmem_cache_alloc().
 - Moved the XA_FLAGS_TRACK_FREE bit to the bottom bits of the flags to leave
   space for more tags (later).
 - Fixed multiple bugs in xas_find() and xas_find_tag().
 - Fixed bug in shrinking XArray (and add a test case that exercises it).
 - Fixed bug in erasing multi-index entries.
 - Fixed a compile warning with CONFIG_RADIX_TREE_MULTIORDER=n.
 - Added an xas_update() helper.
 - Use ->array to track an xa_node's state through its lifecycle
   (allocated -> rcu_free -> actually free).
 - Made XA_BUG_ON dump the entire tree while XA_NODE_BUG_ON dumps only the
   node that appears suspect.
 - Fixed debugging printks to use %px and pr_cont/pr_info etc.
 - Renamed some internal tag functions.
 - Moved xa_track_free() from xarray.h to xarray.c.

Test suite:
 - Added new tests for xas_find() and xas_find_tag().
 - Added new tests for the update_node functionality.
 - Converted the radix tree test suite to the xarray API.

Matthew Wilcox (99):
  xarray: 

[PATCH v6 20/99] ida: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Use the xarray infrstructure like we used the radix tree infrastructure.
This lets us get rid of idr_get_free() from the radix tree code.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/idr.h|   8 +-
 include/linux/radix-tree.h |   4 -
 lib/idr.c  | 320 ++---
 lib/radix-tree.c   | 119 -
 4 files changed, 187 insertions(+), 264 deletions(-)

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 9064ae5f0abc..ad4199247301 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -232,11 +232,11 @@ struct ida_bitmap {
 DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap);
 
 struct ida {
-   struct radix_tree_root  ida_rt;
+   struct xarray   ida_xa;
 };
 
 #define IDA_INIT(name) {   \
-   .ida_rt = RADIX_TREE_INIT(name, IDR_INIT_FLAGS | GFP_NOWAIT),   \
+   .ida_xa = XARRAY_INIT_FLAGS(name.ida_xa, IDR_INIT_FLAGS)\
 }
 #define DEFINE_IDA(name)   struct ida name = IDA_INIT(name)
 
@@ -251,7 +251,7 @@ void ida_simple_remove(struct ida *ida, unsigned int id);
 
 static inline void ida_init(struct ida *ida)
 {
-   INIT_RADIX_TREE(>ida_rt, IDR_INIT_FLAGS | GFP_NOWAIT);
+   xa_init_flags(>ida_xa, IDR_INIT_FLAGS);
 }
 
 /**
@@ -268,6 +268,6 @@ static inline int ida_get_new(struct ida *ida, int *p_id)
 
 static inline bool ida_is_empty(const struct ida *ida)
 {
-   return radix_tree_empty(>ida_rt);
+   return xa_empty(>ida_xa);
 }
 #endif /* _LINUX_IDR_H */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index f64beb9ba175..4c5c36414a80 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -302,10 +302,6 @@ int radix_tree_split(struct radix_tree_root *, unsigned 
long index,
 int radix_tree_join(struct radix_tree_root *, unsigned long index,
unsigned new_order, void *);
 
-void __rcu **idr_get_free(struct radix_tree_root *root,
- struct radix_tree_iter *iter, gfp_t gfp,
- unsigned long max);
-
 enum {
RADIX_TREE_ITER_TAG_MASK = 0x0f,/* tag index in lower nybble */
RADIX_TREE_ITER_TAGGED   = 0x10,/* lookup tagged slots */
diff --git a/lib/idr.c b/lib/idr.c
index 379eaa8cb75b..7e9a8850b613 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -13,7 +13,6 @@
 #include 
 
 DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
-static DEFINE_SPINLOCK(simple_ida_lock);
 
 /* In radix-tree.c temporarily */
 extern bool idr_nomem(struct xa_state *, gfp_t);
@@ -337,26 +336,23 @@ EXPORT_SYMBOL_GPL(idr_replace);
 /*
  * Developer's notes:
  *
- * The IDA uses the functionality provided by the IDR & radix tree to store
- * bitmaps in each entry.  The XA_FREE_TAG tag means there is at least one bit
- * free, unlike the IDR where it means at least one entry is free.
- *
- * I considered telling the radix tree that each slot is an order-10 node
- * and storing the bit numbers in the radix tree, but the radix tree can't
- * allow a single multiorder entry at index 0, which would significantly
- * increase memory consumption for the IDA.  So instead we divide the index
- * by the number of bits in the leaf bitmap before doing a radix tree lookup.
- *
- * As an optimisation, if there are only a few low bits set in any given
- * leaf, instead of allocating a 128-byte bitmap, we store the bits
+ * The IDA uses the functionality provided by the IDR & XArray to store
+ * bitmaps in each entry.  The XA_FREE_TAG tag is used to mean that there
+ * is at least one bit free, unlike the IDR where it means at least one
+ * array entry is free.
+ *
+ * The XArray supports multi-index entries, so I considered teaching the
+ * XArray that each slot is an order-10 node and indexing the XArray by the
+ * ID.  The XArray has the significant optimisation of storing the first
+ * entry in the struct xarray and avoiding allocating an xa_node.
+ * Unfortunately, it can't do that for multi-order entries.
+ * So instead the XArray index is the ID divided by the number of bits in
+ * the bitmap
+ *
+ * As a further optimisation, if there are only a few low bits set in any
+ * given leaf, instead of allocating a 128-byte bitmap, we store the bits
  * directly in the entry.
  *
- * We allow the radix tree 'exceptional' count to get out of date.  Nothing
- * in the IDA nor the radix tree code checks it.  If it becomes important
- * to maintain an accurate exceptional count, switch the rcu_assign_pointer()
- * calls to radix_tree_iter_replace() which will correct the exceptional
- * count.
- *
  * The IDA always requires a lock to alloc/free.  If we add a 'test_bit'
  * equivalent, it will still need locking.  Going to RCU lookup would require
  * using RCU to free bitmaps, and that's not trivial without embedding an
@@ -366,104 +362,114 

[PATCH v6 21/99] xarray: Add xa_reserve and xa_release

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This function simply creates a slot in the XArray for users which need
to acquire multiple locks before storing their entry in the tree and
so cannot use a plain xa_store().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/xarray.h | 14 ++
 lib/xarray.c   | 51 ++
 tools/testing/radix-tree/xarray-test.c | 25 +
 3 files changed, 90 insertions(+)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 6f59f1f60205..c3f7405c5517 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -259,6 +259,7 @@ void *xa_load(struct xarray *, unsigned long index);
 void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void *xa_cmpxchg(struct xarray *, unsigned long index,
void *old, void *entry, gfp_t);
+int xa_reserve(struct xarray *, unsigned long index, gfp_t);
 bool xa_get_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_set_tag(struct xarray *, unsigned long index, xa_tag_t);
 void xa_clear_tag(struct xarray *, unsigned long index, xa_tag_t);
@@ -373,6 +374,19 @@ static inline int xa_insert(struct xarray *xa, unsigned 
long index,
return -EEXIST;
 }
 
+/**
+ * xa_release() - Release a reserved entry.
+ * @xa: XArray.
+ * @index: Index of entry.
+ *
+ * After calling xa_reserve(), you can call this function to release the
+ * reservation.  It is harmless to call this function if the entry was used.
+ */
+static inline void xa_release(struct xarray *xa, unsigned long index)
+{
+   xa_cmpxchg(xa, index, NULL, NULL, 0);
+}
+
 #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)spin_lock(&(xa)->xa_lock)
 #define xa_unlock(xa)  spin_unlock(&(xa)->xa_lock)
diff --git a/lib/xarray.c b/lib/xarray.c
index ace309cc9253..b4dec8e2d202 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1275,6 +1275,8 @@ void *xa_cmpxchg(struct xarray *xa, unsigned long index,
do {
xas_lock();
curr = xas_load();
+   if (curr == XA_ZERO_ENTRY)
+   curr = NULL;
if (curr == old)
xas_store(, entry);
xas_unlock();
@@ -1310,6 +1312,8 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index,
 
do {
curr = xas_load();
+   if (curr == XA_ZERO_ENTRY)
+   curr = NULL;
if (curr == old)
xas_store(, entry);
} while (__xas_nomem(, gfp));
@@ -1318,6 +1322,53 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long 
index,
 }
 EXPORT_SYMBOL(__xa_cmpxchg);
 
+/**
+ * xa_reserve() - Reserve this index in the XArray.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @gfp: Memory allocation flags.
+ *
+ * Ensures there is somewhere to store an entry at @index in the array.
+ * If there is already something stored at @index, this function does
+ * nothing.  If there was nothing there, the entry is marked as reserved.
+ * Loads from @index will continue to see a %NULL pointer until a
+ * subsequent store to @index.
+ *
+ * If you do not use the entry that you have reserved, call xa_release()
+ * or xa_erase() to free any unnecessary memory.
+ *
+ * Return: 0 if the reservation succeeded or -ENOMEM if it failed.
+ */
+int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp)
+{
+   XA_STATE(xas, xa, index);
+   unsigned int lock_type = xa_lock_type(xa);
+   void *curr;
+
+   do {
+   if (lock_type == XA_LOCK_IRQ)
+   xas_lock_irq();
+   else if (lock_type == XA_LOCK_BH)
+   xas_lock_bh();
+   else
+   xas_lock();
+
+   curr = xas_create();
+   if (!curr)
+   xas_store(, XA_ZERO_ENTRY);
+
+if (lock_type == XA_LOCK_IRQ)
+xas_unlock_irq();
+else if (lock_type == XA_LOCK_BH)
+xas_unlock_bh();
+else
+xas_unlock();
+   } while (xas_nomem(, gfp));
+
+   return xas_error();
+}
+EXPORT_SYMBOL(xa_reserve);
+
 /**
  * __xa_set_tag() - Set this tag on this entry while locked.
  * @xa: XArray.
diff --git a/tools/testing/radix-tree/xarray-test.c 
b/tools/testing/radix-tree/xarray-test.c
index 4d3541ac31e9..fe38b53df2ab 100644
--- a/tools/testing/radix-tree/xarray-test.c
+++ b/tools/testing/radix-tree/xarray-test.c
@@ -502,6 +502,29 @@ void check_move(struct xarray *xa)
} while (i < (1 << 16));
 }
 
+void check_reserve(struct xarray *xa)
+{
+   assert(xa_empty(xa));
+   xa_reserve(xa, 12345678, GFP_KERNEL);
+   assert(!xa_empty(xa));
+   assert(!xa_load(xa, 12345678));
+   xa_release

[PATCH v6 24/99] page cache: Add and replace pages using the XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Use the XArray APIs to add and replace pages in the page cache.  This
removes two uses of the radix tree preload API and is significantly
shorter code.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/swap.h |   8 ++-
 mm/filemap.c | 143 ++-
 2 files changed, 67 insertions(+), 84 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index c2b8128799c1..394957963c4b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, 
struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
 
-/* Do not use directly, use workingset_lookup_update */
-void workingset_update_node(struct radix_tree_node *node);
+/* Only track the nodes of mappings with shadow entries */
+void workingset_update_node(struct xa_node *node);
+#define mapping_set_update(xas, mapping) do {  \
+   if (!dax_mapping(mapping) && !shmem_mapping(mapping))   \
+   xas_set_update(xas, workingset_update_node);\
+} while (0)
 
 /* Returns workingset_update_node() if the mapping has shadow entries. */
 #define workingset_lookup_update(mapping)  \
diff --git a/mm/filemap.c b/mm/filemap.c
index f1b4480723dd..e6371b551de1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -112,35 +112,6 @@
  *   ->tasklist_lock(memory_failure, collect_procs_ao)
  */
 
-static int page_cache_tree_insert(struct address_space *mapping,
- struct page *page, void **shadowp)
-{
-   struct radix_tree_node *node;
-   void **slot;
-   int error;
-
-   error = __radix_tree_create(>pages, page->index, 0,
-   , );
-   if (error)
-   return error;
-   if (*slot) {
-   void *p;
-
-   p = radix_tree_deref_slot_protected(slot,
-   >pages.xa_lock);
-   if (!xa_is_value(p))
-   return -EEXIST;
-
-   mapping->nrexceptional--;
-   if (shadowp)
-   *shadowp = p;
-   }
-   __radix_tree_replace(>pages, node, slot, page,
-workingset_lookup_update(mapping));
-   mapping->nrpages++;
-   return 0;
-}
-
 static void page_cache_tree_delete(struct address_space *mapping,
   struct page *page, void *shadow)
 {
@@ -776,51 +747,44 @@ EXPORT_SYMBOL(file_write_and_wait_range);
  * locked.  This function does not add the new page to the LRU, the
  * caller must do that.
  *
- * The remove + add is atomic.  The only way this function can fail is
- * memory allocation failure.
+ * The remove + add is atomic.  This function cannot fail.
  */
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 {
-   int error;
+   struct address_space *mapping = old->mapping;
+   void (*freepage)(struct page *) = mapping->a_ops->freepage;
+   pgoff_t offset = old->index;
+   XA_STATE(xas, >pages, offset);
+   unsigned long flags;
 
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
 
-   error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
-   if (!error) {
-   struct address_space *mapping = old->mapping;
-   void (*freepage)(struct page *);
-   unsigned long flags;
-
-   pgoff_t offset = old->index;
-   freepage = mapping->a_ops->freepage;
-
-   get_page(new);
-   new->mapping = mapping;
-   new->index = offset;
+   get_page(new);
+   new->mapping = mapping;
+   new->index = offset;
 
-   xa_lock_irqsave(>pages, flags);
-   __delete_from_page_cache(old, NULL);
-   error = page_cache_tree_insert(mapping, new, NULL);
-   BUG_ON(error);
+   xas_lock_irqsave(, flags);
+   xas_store(, new);
 
-   /*
-* hugetlb pages do not participate in page cache accounting.
-*/
-   if (!PageHuge(new))
-   __inc_node_page_state(new, NR_FILE_PAGES);
-   if (PageSwapBacked(new))
-   __inc_node_page_state(new, NR_SHMEM);
-   xa_unlock_irqrestore(>pages, flags);
-   mem_cgroup_migrate(old, new);
-   radix_tree_preload_end();
-   if (freepage)
-   freepage(old);
-   put_page(old);
-   }
+   old->mapping = NULL;
+   /* hugetlb pages do not participate in page cache acc

[PATCH v6 23/99] page cache: Add page_cache_range_empty function

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

btrfs has its own custom function for determining whether the page cache
has any pages in a particular range.  Move this functionality to the
page cache, and call it from btrfs.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/btrfs_inode.h  |  7 -
 fs/btrfs/inode.c| 70 -
 include/linux/pagemap.h |  2 ++
 mm/filemap.c| 26 ++
 4 files changed, 34 insertions(+), 71 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 63f0ccc92a71..a48bd6e0a0bb 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -365,6 +365,11 @@ static inline void btrfs_print_data_csum_error(struct 
btrfs_inode *inode,
logical_start, csum, csum_expected, mirror_num);
 }
 
-bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
+static inline bool btrfs_page_exists_in_range(struct inode *inode,
+   loff_t start, loff_t end)
+{
+   return page_cache_range_empty(inode->i_mapping, start >> PAGE_SHIFT,
+   end >> PAGE_SHIFT);
+}
 
 #endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dbdb5bf6bca1..d7d2c556d5a2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7541,76 +7541,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 
offset, u64 *len,
return ret;
 }
 
-bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
-{
-   struct radix_tree_root *root = >i_mapping->pages;
-   bool found = false;
-   void **pagep = NULL;
-   struct page *page = NULL;
-   unsigned long start_idx;
-   unsigned long end_idx;
-
-   start_idx = start >> PAGE_SHIFT;
-
-   /*
-* end is the last byte in the last page.  end == start is legal
-*/
-   end_idx = end >> PAGE_SHIFT;
-
-   rcu_read_lock();
-
-   /* Most of the code in this while loop is lifted from
-* find_get_page.  It's been modified to begin searching from a
-* page and return just the first page found in that range.  If the
-* found idx is less than or equal to the end idx then we know that
-* a page exists.  If no pages are found or if those pages are
-* outside of the range then we're fine (yay!) */
-   while (page == NULL &&
-  radix_tree_gang_lookup_slot(root, , NULL, start_idx, 1)) {
-   page = radix_tree_deref_slot(pagep);
-   if (unlikely(!page))
-   break;
-
-   if (radix_tree_exception(page)) {
-   if (radix_tree_deref_retry(page)) {
-   page = NULL;
-   continue;
-   }
-   /*
-* Otherwise, shmem/tmpfs must be storing a swap entry
-* here so return it without attempting to raise page
-* count.
-*/
-   page = NULL;
-   break; /* TODO: Is this relevant for this use case? */
-   }
-
-   if (!page_cache_get_speculative(page)) {
-   page = NULL;
-   continue;
-   }
-
-   /*
-* Has the page moved?
-* This is part of the lockless pagecache protocol. See
-* include/linux/pagemap.h for details.
-*/
-   if (unlikely(page != *pagep)) {
-   put_page(page);
-   page = NULL;
-   }
-   }
-
-   if (page) {
-   if (page->index <= end_idx)
-   found = true;
-   put_page(page);
-   }
-
-   rcu_read_unlock();
-   return found;
-}
-
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
  struct extent_state **cached_state, int writing)
 {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0db127c3ccac..34d4fa3ad1c5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -245,6 +245,8 @@ pgoff_t page_cache_next_gap(struct address_space *mapping,
 pgoff_t index, unsigned long max_scan);
 pgoff_t page_cache_prev_gap(struct address_space *mapping,
 pgoff_t index, unsigned long max_scan);
+bool page_cache_range_empty(struct address_space *mapping,
+   pgoff_t index, pgoff_t max);
 
 #define FGP_ACCESSED   0x0001
 #define FGP_LOCK   0x0002
diff --git a/mm/filemap.c b/mm/filemap.c
index 146e8ec16ec0..f1b4480723dd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1398,6 +1398,32 @@

[PATCH v6 22/99] page cache: Convert hole search to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The page cache offers the ability to search for a miss in the previous or
next N locations.  Rather than teach the XArray about the page cache's
definition of a miss, use xas_prev() and xas_next() to search the page
array.  This should be more efficient as it does not have to start the
lookup from the top for each index.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/nfs/blocklayout/blocklayout.c |   2 +-
 include/linux/pagemap.h  |   4 +-
 mm/filemap.c | 110 ++-
 mm/readahead.c   |   4 +-
 4 files changed, 55 insertions(+), 65 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 995d707537da..7bd643538cff 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -826,7 +826,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t 
idx)
end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (end != inode->i_mapping->nrpages) {
rcu_read_lock();
-   end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
+   end = page_cache_next_gap(mapping, idx + 1, ULONG_MAX);
rcu_read_unlock();
}
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 80a6149152d4..0db127c3ccac 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -241,9 +241,9 @@ static inline gfp_t readahead_gfp_mask(struct address_space 
*x)
 
 typedef int filler_t(void *, struct page *);
 
-pgoff_t page_cache_next_hole(struct address_space *mapping,
+pgoff_t page_cache_next_gap(struct address_space *mapping,
 pgoff_t index, unsigned long max_scan);
-pgoff_t page_cache_prev_hole(struct address_space *mapping,
+pgoff_t page_cache_prev_gap(struct address_space *mapping,
 pgoff_t index, unsigned long max_scan);
 
 #define FGP_ACCESSED   0x0001
diff --git a/mm/filemap.c b/mm/filemap.c
index 309be963140c..146e8ec16ec0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1327,86 +1327,76 @@ int __lock_page_or_retry(struct page *page, struct 
mm_struct *mm,
 }
 
 /**
- * page_cache_next_hole - find the next hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
- *
- * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
- * lowest indexed hole.
- *
- * Returns: the index of the hole if found, otherwise returns an index
- * outside of the set specified (in which case 'return - index >=
- * max_scan' will be true). In rare cases of index wrap-around, 0 will
- * be returned.
- *
- * page_cache_next_hole may be called under rcu_read_lock. However,
- * like radix_tree_gang_lookup, this will not atomically search a
- * snapshot of the tree at a single point in time. For example, if a
- * hole is created at index 5, then subsequently a hole is created at
- * index 10, page_cache_next_hole covering both indexes may return 10
- * if called under rcu_read_lock.
+ * page_cache_next_gap() - Find the next gap in the page cache.
+ * @mapping: Mapping.
+ * @index: Index.
+ * @max_scan: Maximum range to search.
+ *
+ * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
+ * gap with the lowest index.
+ *
+ * This function may be called under the rcu_read_lock.  However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 5, then subsequently a gap is
+ * created at index 10, page_cache_next_gap covering both indices may
+ * return 10 if called under the rcu_read_lock.
+ *
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'return - index >= max_scan' will be true).
+ * In the rare case of index wrap-around, 0 will be returned.
  */
-pgoff_t page_cache_next_hole(struct address_space *mapping,
+pgoff_t page_cache_next_gap(struct address_space *mapping,
 pgoff_t index, unsigned long max_scan)
 {
-   unsigned long i;
+   XA_STATE(xas, >pages, index);
 
-   for (i = 0; i < max_scan; i++) {
-   struct page *page;
-
-   page = radix_tree_lookup(>pages, index);
-   if (!page || xa_is_value(page))
+   while (max_scan--) {
+   void *entry = xas_next();
+   if (!entry || xa_is_value(entry))
break;
-   index++;
-   if (index == 0)
+   if (xas.xa_index == 0)
break;
}
 
-   return index;
+   return xas.xa_index;
 }
-EXPORT_SYMBOL(page_cache_next_hole);
+EXPORT_SYMBOL(page_cache_next_gap);
 
 /**
- * page_cache_prev_hole - find the prev hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range t

[PATCH v6 27/99] page cache: Convert delete_batch to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Rename the function from page_cache_tree_delete_batch to just
page_cache_delete_batch.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/filemap.c | 28 +---
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 317a89df1945..d2a0031d61f5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -276,7 +276,7 @@ void delete_from_page_cache(struct page *page)
 EXPORT_SYMBOL(delete_from_page_cache);
 
 /*
- * page_cache_tree_delete_batch - delete several pages from page cache
+ * page_cache_delete_batch - delete several pages from page cache
  * @mapping: the mapping to which pages belong
  * @pvec: pagevec with pages to delete
  *
@@ -289,23 +289,18 @@ EXPORT_SYMBOL(delete_from_page_cache);
  *
  * The function expects xa_lock to be held.
  */
-static void
-page_cache_tree_delete_batch(struct address_space *mapping,
+static void page_cache_delete_batch(struct address_space *mapping,
 struct pagevec *pvec)
 {
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >pages, pvec->pages[0]->index);
int total_pages = 0;
int i = 0, tail_pages = 0;
struct page *page;
-   pgoff_t start;
 
-   start = pvec->pages[0]->index;
-   radix_tree_for_each_slot(slot, >pages, , start) {
+   mapping_set_update(, mapping);
+   xas_for_each(, page, ULONG_MAX) {
if (i >= pagevec_count(pvec) && !tail_pages)
break;
-   page = radix_tree_deref_slot_protected(slot,
-  >pages.xa_lock);
if (xa_is_value(page))
continue;
if (!tail_pages) {
@@ -314,8 +309,11 @@ page_cache_tree_delete_batch(struct address_space *mapping,
 * have our pages locked so they are protected from
 * being removed.
 */
-   if (page != pvec->pages[i])
+   if (page != pvec->pages[i]) {
+   VM_BUG_ON_PAGE(page->index >
+   pvec->pages[i]->index, page);
continue;
+   }
WARN_ON_ONCE(!PageLocked(page));
if (PageTransHuge(page) && !PageHuge(page))
tail_pages = HPAGE_PMD_NR - 1;
@@ -326,11 +324,11 @@ page_cache_tree_delete_batch(struct address_space 
*mapping,
 */
i++;
} else {
+   VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
+   != pvec->pages[i]->index, page);
tail_pages--;
}
-   radix_tree_clear_tags(>pages, iter.node, slot);
-   __radix_tree_replace(>pages, iter.node, slot, NULL,
-   workingset_lookup_update(mapping));
+   xas_store(, NULL);
total_pages++;
}
mapping->nrpages -= total_pages;
@@ -351,7 +349,7 @@ void delete_from_page_cache_batch(struct address_space 
*mapping,
 
unaccount_page_cache_page(mapping, pvec->pages[i]);
}
-   page_cache_tree_delete_batch(mapping, pvec);
+   page_cache_delete_batch(mapping, pvec);
xa_unlock_irqrestore(>pages, flags);
 
for (i = 0; i < pagevec_count(pvec); i++)
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 29/99] page cache: Convert filemap_range_has_page to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Instead of calling find_get_pages_range() and putting any reference,
just use xa_find() to look for a page in the right range.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/filemap.c | 9 +
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 2536fcacb5bc..cd01f353cf6a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -461,18 +461,11 @@ bool filemap_range_has_page(struct address_space *mapping,
 {
pgoff_t index = start_byte >> PAGE_SHIFT;
pgoff_t end = end_byte >> PAGE_SHIFT;
-   struct page *page;
 
if (end_byte < start_byte)
return false;
 
-   if (mapping->nrpages == 0)
-   return false;
-
-   if (!find_get_pages_range(mapping, , end, 1, ))
-   return false;
-   put_page(page);
-   return true;
+   return xa_find(>pages, , end, XA_PRESENT);
 }
 EXPORT_SYMBOL(filemap_range_has_page);
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 31/99] mm: Convert workingset to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

We construct a fake XA_STATE and use it to delete the node with xa_store()
rather than adding a special function for this unique use case.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/swap.h |  9 -
 mm/workingset.c  | 51 ++-
 2 files changed, 22 insertions(+), 38 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 394957963c4b..e519554730fa 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node);
xas_set_update(xas, workingset_update_node);\
 } while (0)
 
-/* Returns workingset_update_node() if the mapping has shadow entries. */
-#define workingset_lookup_update(mapping)  \
-({ \
-   radix_tree_update_node_t __helper = workingset_update_node; \
-   if (dax_mapping(mapping) || shmem_mapping(mapping)) \
-   __helper = NULL;\
-   __helper;   \
-})
-
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
diff --git a/mm/workingset.c b/mm/workingset.c
index 91b6e16ad4c1..f7ca6ea5d8b1 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -148,7 +148,7 @@
  * and activations is maintained (node->inactive_age).
  *
  * On eviction, a snapshot of this counter (along with some bits to
- * identify the node) is stored in the now empty page cache radix tree
+ * identify the node) is stored in the now empty page cache
  * slot of the evicted page.  This is called a shadow entry.
  *
  * On cache misses for which there are shadow entries, an eligible
@@ -162,7 +162,7 @@
 
 /*
  * Eviction timestamps need to be able to cover the full range of
- * actionable refaults. However, bits are tight in the radix tree
+ * actionable refaults. However, bits are tight in the xarray
  * entry, and after storing the identifier for the lruvec there might
  * not be enough left to represent every single actionable refault. In
  * that case, we have to sacrifice granularity for distance, and group
@@ -338,7 +338,7 @@ void workingset_activation(struct page *page)
 
 static struct list_lru shadow_nodes;
 
-void workingset_update_node(struct radix_tree_node *node)
+void workingset_update_node(struct xa_node *node)
 {
/*
 * Track non-empty nodes that contain only shadow entries;
@@ -370,7 +370,7 @@ static unsigned long count_shadow_nodes(struct shrinker 
*shrinker,
local_irq_enable();
 
/*
-* Approximate a reasonable limit for the radix tree nodes
+* Approximate a reasonable limit for the nodes
 * containing shadow entries. We don't need to keep more
 * shadow entries than possible pages on the active list,
 * since refault distances bigger than that are dismissed.
@@ -385,11 +385,11 @@ static unsigned long count_shadow_nodes(struct shrinker 
*shrinker,
 * worst-case density of 1/8th. Below that, not all eligible
 * refaults can be detected anymore.
 *
-* On 64-bit with 7 radix_tree_nodes per page and 64 slots
+* On 64-bit with 7 xa_nodes per page and 64 slots
 * each, this will reclaim shadow entries when they consume
 * ~1.8% of available memory:
 *
-* PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE
+* PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
 */
if (sc->memcg) {
cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
@@ -398,7 +398,7 @@ static unsigned long count_shadow_nodes(struct shrinker 
*shrinker,
cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) +
node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE);
}
-   max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3);
+   max_nodes = cache >> (XA_CHUNK_SHIFT - 3);
 
if (nodes <= max_nodes)
return 0;
@@ -408,11 +408,11 @@ static unsigned long count_shadow_nodes(struct shrinker 
*shrinker,
 static enum lru_status shadow_lru_isolate(struct list_head *item,
  struct list_lru_one *lru,
  spinlock_t *lru_lock,
- void *arg)
+ void *arg) __must_hold(lru_lock)
 {
+   XA_STATE(xas, NULL, 0);
struct address_space *mapping;
-   struct radix_tree_node *node;
-   unsigned int i;
+   struct xa_node *node;
int ret;
 
/*
@@ -420,7 +420,7 @@ static enum lru_status shadow_lru_isolate(struct list_head 
*item,
 * the sha

[PATCH v6 30/99] mm: Convert page-writeback to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Includes moving mapping_tagged() to fs.h as a static inline, and
changing it to return bool.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/fs.h  | 17 +--
 mm/page-writeback.c | 62 +++--
 2 files changed, 32 insertions(+), 47 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index e4345c13e237..c58bc3c619bf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -470,15 +470,18 @@ struct block_device {
struct mutexbd_fsfreeze_mutex;
 } __randomize_layout;
 
+/* XArray tags, for tagging dirty and writeback pages in the pagecache. */
+#define PAGECACHE_TAG_DIRTYXA_TAG_0
+#define PAGECACHE_TAG_WRITEBACKXA_TAG_1
+#define PAGECACHE_TAG_TOWRITE  XA_TAG_2
+
 /*
- * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
- * radix trees
+ * Returns true if any of the pages in the mapping are marked with the tag.
  */
-#define PAGECACHE_TAG_DIRTY0
-#define PAGECACHE_TAG_WRITEBACK1
-#define PAGECACHE_TAG_TOWRITE  2
-
-int mapping_tagged(struct address_space *mapping, int tag);
+static inline bool mapping_tagged(struct address_space *mapping, xa_tag_t tag)
+{
+   return xa_tagged(>pages, tag);
+}
 
 static inline void i_mmap_lock_write(struct address_space *mapping)
 {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 588ce729d199..0407436a8305 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2098,33 +2098,25 @@ void __init page_writeback_init(void)
  * dirty pages in the file (thus it is important for this function to be quick
  * so that it can tag pages faster than a dirtying process can create them).
  */
-/*
- * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce xa_lock latency.
- */
 void tag_pages_for_writeback(struct address_space *mapping,
 pgoff_t start, pgoff_t end)
 {
-#define WRITEBACK_TAG_BATCH 4096
-   unsigned long tagged = 0;
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >pages, start);
+   unsigned int tagged = 0;
+   void *page;
 
-   xa_lock_irq(>pages);
-   radix_tree_for_each_tagged(slot, >pages, , start,
-   PAGECACHE_TAG_DIRTY) {
-   if (iter.index > end)
-   break;
-   radix_tree_iter_tag_set(>pages, ,
-   PAGECACHE_TAG_TOWRITE);
-   tagged++;
-   if ((tagged % WRITEBACK_TAG_BATCH) != 0)
+   xas_lock_irq();
+   xas_for_each_tag(, page, end, PAGECACHE_TAG_DIRTY) {
+   xas_set_tag(, PAGECACHE_TAG_TOWRITE);
+   if (++tagged % XA_CHECK_SCHED)
continue;
-   slot = radix_tree_iter_resume(slot, );
-   xa_unlock_irq(>pages);
+
+   xas_pause();
+   xas_unlock_irq();
cond_resched();
-   xa_lock_irq(>pages);
+   xas_lock_irq();
}
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
 }
 EXPORT_SYMBOL(tag_pages_for_writeback);
 
@@ -2164,7 +2156,7 @@ int write_cache_pages(struct address_space *mapping,
pgoff_t done_index;
int cycled;
int range_whole = 0;
-   int tag;
+   xa_tag_t tag;
 
pagevec_init();
if (wbc->range_cyclic) {
@@ -2445,7 +2437,7 @@ void account_page_cleaned(struct page *page, struct 
address_space *mapping,
 
 /*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
- * its radix tree.
+ * the xarray.
  *
  * This is also used when a single buffer is being dirtied: we want to set the
  * page dirty in that case, but not all the buffers.  This is a "bottom-up"
@@ -2471,7 +2463,7 @@ int __set_page_dirty_nobuffers(struct page *page)
BUG_ON(page_mapping(page) != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
-   radix_tree_tag_set(>pages, page_index(page),
+   __xa_set_tag(>pages, page_index(page),
   PAGECACHE_TAG_DIRTY);
xa_unlock_irqrestore(>pages, flags);
unlock_page_memcg(page);
@@ -2634,13 +2626,13 @@ EXPORT_SYMBOL(__cancel_dirty_page);
  * Returns true if the page was previously dirty.
  *
  * This is for preparing to put the page under writeout.  We leave the page
- * tagged as dirty in the radix tree so that a concurrent write-for-sync
+ * tagged as dirty in the xarray so that a concurrent write-for-sync
  * can discover it via a PAGECACHE_TAG_DIRTY walk.  The ->writepage
  * implementation will run either set_page_writeback() or set_page_dirty(),
- * at which stage we bring the page's dirty fl

[PATCH v6 33/99] mm: Convert add_to_swap_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Combine __add_to_swap_cache and add_to_swap_cache into one function
since there is no more need to preload.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/swap_state.c | 93 ++---
 1 file changed, 29 insertions(+), 64 deletions(-)

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3f95e8fc4cb2..a57b5ad4c503 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -107,14 +107,15 @@ void show_swap_cache_info(void)
 }
 
 /*
- * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
+ * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
-int __add_to_swap_cache(struct page *page, swp_entry_t entry)
+int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
 {
-   int error, i, nr = hpage_nr_pages(page);
-   struct address_space *address_space;
+   struct address_space *address_space = swap_address_space(entry);
pgoff_t idx = swp_offset(entry);
+   XA_STATE(xas, _space->pages, idx);
+   unsigned long i, nr = 1UL << compound_order(page);
 
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapCache(page), page);
@@ -123,50 +124,30 @@ int __add_to_swap_cache(struct page *page, swp_entry_t 
entry)
page_ref_add(page, nr);
SetPageSwapCache(page);
 
-   address_space = swap_address_space(entry);
-   xa_lock_irq(_space->pages);
-   for (i = 0; i < nr; i++) {
-   set_page_private(page + i, entry.val + i);
-   error = radix_tree_insert(_space->pages,
- idx + i, page + i);
-   if (unlikely(error))
-   break;
-   }
-   if (likely(!error)) {
+   do {
+   xas_lock_irq();
+   xas_create_range(, idx + nr - 1);
+   if (xas_error())
+   goto unlock;
+   for (i = 0; i < nr; i++) {
+   VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
+   set_page_private(page + i, entry.val + i);
+   xas_store(, page + i);
+   xas_next();
+   }
address_space->nrpages += nr;
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
ADD_CACHE_INFO(add_total, nr);
-   } else {
-   /*
-* Only the context which have set SWAP_HAS_CACHE flag
-* would call add_to_swap_cache().
-* So add_to_swap_cache() doesn't returns -EEXIST.
-*/
-   VM_BUG_ON(error == -EEXIST);
-   set_page_private(page + i, 0UL);
-   while (i--) {
-   radix_tree_delete(_space->pages, idx + i);
-   set_page_private(page + i, 0UL);
-   }
-   ClearPageSwapCache(page);
-   page_ref_sub(page, nr);
-   }
-   xa_unlock_irq(_space->pages);
+unlock:
+   xas_unlock_irq();
+   } while (xas_nomem(, gfp));
 
-   return error;
-}
-
-
-int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
-{
-   int error;
+   if (!xas_error())
+   return 0;
 
-   error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page));
-   if (!error) {
-   error = __add_to_swap_cache(page, entry);
-   radix_tree_preload_end();
-   }
-   return error;
+   ClearPageSwapCache(page);
+   page_ref_sub(page, nr);
+   return xas_error();
 }
 
 /*
@@ -220,7 +201,7 @@ int add_to_swap(struct page *page)
goto fail;
 
/*
-* Radix-tree node allocations from PF_MEMALLOC contexts could
+* XArray node allocations from PF_MEMALLOC contexts could
 * completely exhaust the page allocator. __GFP_NOMEMALLOC
 * stops emergency reserves from being allocated.
 *
@@ -232,7 +213,6 @@ int add_to_swap(struct page *page)
 */
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
-   /* -ENOMEM radix-tree allocation failure */
if (err)
/*
 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
@@ -400,19 +380,11 @@ struct page *__read_swap_cache_async(swp_entry_t entry, 
gfp_t gfp_mask,
break;  /* Out of memory */
}
 
-   /*
-* call radix_tree_preload() while we can wait.
-*/
-   err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
-   if (err)
-   break;
-
/*
 * Swap entry

[PATCH v6 32/99] mm: Convert truncate to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is essentially xa_cmpxchg() with the locking handled above us,
and it doesn't have to handle replacing a NULL entry.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/truncate.c | 15 ++-
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/mm/truncate.c b/mm/truncate.c
index 69bb743dd7e5..70323c347298 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -33,15 +33,12 @@
 static inline void __clear_shadow_entry(struct address_space *mapping,
pgoff_t index, void *entry)
 {
-   struct radix_tree_node *node;
-   void **slot;
+   XA_STATE(xas, >pages, index);
 
-   if (!__radix_tree_lookup(>pages, index, , ))
+   xas_set_update(, workingset_update_node);
+   if (xas_load() != entry)
return;
-   if (*slot != entry)
-   return;
-   __radix_tree_replace(>pages, node, slot, NULL,
-workingset_update_node);
+   xas_store(, NULL);
mapping->nrexceptional--;
 }
 
@@ -746,10 +743,10 @@ int invalidate_inode_pages2_range(struct address_space 
*mapping,
index++;
}
/*
-* For DAX we invalidate page tables after invalidating radix tree.  We
+* For DAX we invalidate page tables after invalidating page cache.  We
 * could invalidate page tables while invalidating each entry however
 * that would be expensive. And doing range unmapping before doesn't
-* work as we have no cheap way to find whether radix tree entry didn't
+* work as we have no cheap way to find whether page cache entry didn't
 * get remapped later.
 */
if (dax_mapping(mapping)) {
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 34/99] mm: Convert delete_from_swap_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Both callers of __delete_from_swap_cache have the swp_entry_t already,
so pass that in to make constructing the XA_STATE easier.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/swap.h |  5 +++--
 mm/swap_state.c  | 24 ++--
 mm/vmscan.c  |  2 +-
 3 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e519554730fa..8eb99229dbc0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -408,7 +408,7 @@ extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
 extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
 extern int __add_to_swap_cache(struct page *page, swp_entry_t entry);
-extern void __delete_from_swap_cache(struct page *);
+extern void __delete_from_swap_cache(struct page *, swp_entry_t entry);
 extern void delete_from_swap_cache(struct page *);
 extern void free_page_and_swap_cache(struct page *);
 extern void free_pages_and_swap_cache(struct page **, int);
@@ -583,7 +583,8 @@ static inline int add_to_swap_cache(struct page *page, 
swp_entry_t entry,
return -1;
 }
 
-static inline void __delete_from_swap_cache(struct page *page)
+static inline void __delete_from_swap_cache(struct page *page,
+   swp_entry_t entry)
 {
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index a57b5ad4c503..219e3b4f09e6 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -154,23 +154,22 @@ int add_to_swap_cache(struct page *page, swp_entry_t 
entry, gfp_t gfp)
  * This must be called only on pages that have
  * been verified to be in the swap cache.
  */
-void __delete_from_swap_cache(struct page *page)
+void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
 {
-   struct address_space *address_space;
+   struct address_space *address_space = swap_address_space(entry);
int i, nr = hpage_nr_pages(page);
-   swp_entry_t entry;
-   pgoff_t idx;
+   pgoff_t idx = swp_offset(entry);
+   XA_STATE(xas, _space->pages, idx);
 
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
VM_BUG_ON_PAGE(PageWriteback(page), page);
 
-   entry.val = page_private(page);
-   address_space = swap_address_space(entry);
-   idx = swp_offset(entry);
for (i = 0; i < nr; i++) {
-   radix_tree_delete(_space->pages, idx + i);
+   void *entry = xas_store(, NULL);
+   VM_BUG_ON_PAGE(entry != page + i, entry);
set_page_private(page + i, 0);
+   xas_next();
}
ClearPageSwapCache(page);
address_space->nrpages -= nr;
@@ -246,14 +245,11 @@ int add_to_swap(struct page *page)
  */
 void delete_from_swap_cache(struct page *page)
 {
-   swp_entry_t entry;
-   struct address_space *address_space;
-
-   entry.val = page_private(page);
+   swp_entry_t entry = { .val = page_private(page) };
+   struct address_space *address_space = swap_address_space(entry);
 
-   address_space = swap_address_space(entry);
xa_lock_irq(_space->pages);
-   __delete_from_swap_cache(page);
+   __delete_from_swap_cache(page, entry);
xa_unlock_irq(_space->pages);
 
put_swap_page(page, entry);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2fa675a2db31..51d437a18db8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -718,7 +718,7 @@ static int __remove_mapping(struct address_space *mapping, 
struct page *page,
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page_private(page) };
mem_cgroup_swapout(page, swap);
-   __delete_from_swap_cache(page);
+   __delete_from_swap_cache(page, swap);
xa_unlock_irqrestore(>pages, flags);
put_swap_page(page, swap);
} else {
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 37/99] mm: Convert huge_memory to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Quite a straightforward conversion.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/huge_memory.c | 19 ---
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f71dd3e7d8cd..5c275295bbd3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2379,7 +2379,7 @@ static void __split_huge_page_tail(struct page *head, int 
tail,
if (PageAnon(head) && !PageSwapCache(head)) {
page_ref_inc(page_tail);
} else {
-   /* Additional pin to radix tree */
+   /* Additional pin to page cache */
page_ref_add(page_tail, 2);
}
 
@@ -2450,13 +2450,13 @@ static void __split_huge_page(struct page *page, struct 
list_head *list,
ClearPageCompound(head);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
-   /* Additional pin to radix tree of swap cache */
+   /* Additional pin to swap cache */
if (PageSwapCache(head))
page_ref_add(head, 2);
else
page_ref_inc(head);
} else {
-   /* Additional pin to radix tree */
+   /* Additional pin to page cache */
page_ref_add(head, 2);
xa_unlock(>mapping->pages);
}
@@ -2568,7 +2568,7 @@ bool can_split_huge_page(struct page *page, int 
*pextra_pins)
 {
int extra_pins;
 
-   /* Additional pins from radix tree */
+   /* Additional pins from page cache */
if (PageAnon(page))
extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
else
@@ -2664,17 +2664,14 @@ int split_huge_page_to_list(struct page *page, struct 
list_head *list)
spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
 
if (mapping) {
-   void **pslot;
+   XA_STATE(xas, >pages, page_index(head));
 
-   xa_lock(>pages);
-   pslot = radix_tree_lookup_slot(>pages,
-   page_index(head));
/*
-* Check if the head page is present in radix tree.
+* Check if the head page is present in page cache.
 * We assume all tail are present too, if head is there.
 */
-   if (radix_tree_deref_slot_protected(pslot,
-   >pages.xa_lock) != head)
+   xa_lock(>pages);
+   if (xas_load() != head)
goto fail;
}
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 36/99] mm: Convert page migration to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/migrate.c | 41 -
 1 file changed, 16 insertions(+), 25 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 75d19904dd9a..7122fec9b075 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -322,7 +322,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t 
*ptep,
page = migration_entry_to_page(entry);
 
/*
-* Once radix-tree replacement of page migration started, page_count
+* Once page cache replacement of page migration started, page_count
 * *must* be zero. And, we don't want to call wait_on_page_locked()
 * against a page without get_page().
 * So, we use get_page_unless_zero(), here. Even failed, page fault
@@ -437,10 +437,10 @@ int migrate_page_move_mapping(struct address_space 
*mapping,
struct buffer_head *head, enum migrate_mode mode,
int extra_count)
 {
+   XA_STATE(xas, >pages, page_index(page));
struct zone *oldzone, *newzone;
int dirty;
int expected_count = 1 + extra_count;
-   void **pslot;
 
/*
 * Device public or private pages have an extra refcount as they are
@@ -466,21 +466,16 @@ int migrate_page_move_mapping(struct address_space 
*mapping,
oldzone = page_zone(page);
newzone = page_zone(newpage);
 
-   xa_lock_irq(>pages);
-
-   pslot = radix_tree_lookup_slot(>pages,
-   page_index(page));
+   xas_lock_irq();
 
expected_count += 1 + page_has_private(page);
-   if (page_count(page) != expected_count ||
-   radix_tree_deref_slot_protected(pslot,
-   >pages.xa_lock) != page) {
-   xa_unlock_irq(>pages);
+   if (page_count(page) != expected_count || xas_load() != page) {
+   xas_unlock_irq();
return -EAGAIN;
}
 
if (!page_ref_freeze(page, expected_count)) {
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return -EAGAIN;
}
 
@@ -494,7 +489,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
if (mode == MIGRATE_ASYNC && head &&
!buffer_migrate_lock_buffers(head, mode)) {
page_ref_unfreeze(page, expected_count);
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return -EAGAIN;
}
 
@@ -522,7 +517,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
SetPageDirty(newpage);
}
 
-   radix_tree_replace_slot(>pages, pslot, newpage);
+   xas_store(, newpage);
 
/*
 * Drop cache reference from old page by unfreezing
@@ -531,7 +526,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 */
page_ref_unfreeze(page, expected_count - 1);
 
-   xa_unlock(>pages);
+   xas_unlock();
/* Leave irq disabled to prevent preemption while updating stats */
 
/*
@@ -571,22 +566,18 @@ EXPORT_SYMBOL(migrate_page_move_mapping);
 int migrate_huge_page_move_mapping(struct address_space *mapping,
   struct page *newpage, struct page *page)
 {
+   XA_STATE(xas, >pages, page_index(page));
int expected_count;
-   void **pslot;
-
-   xa_lock_irq(>pages);
-
-   pslot = radix_tree_lookup_slot(>pages, page_index(page));
 
+   xas_lock_irq();
expected_count = 2 + page_has_private(page);
-   if (page_count(page) != expected_count ||
-   radix_tree_deref_slot_protected(pslot, >pages.xa_lock) 
!= page) {
-   xa_unlock_irq(>pages);
+   if (page_count(page) != expected_count || xas_load() != page) {
+   xas_unlock_irq();
return -EAGAIN;
}
 
if (!page_ref_freeze(page, expected_count)) {
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return -EAGAIN;
}
 
@@ -595,11 +586,11 @@ int migrate_huge_page_move_mapping(struct address_space 
*mapping,
 
get_page(newpage);
 
-   radix_tree_replace_slot(>pages, pslot, newpage);
+   xas_store(, newpage);
 
page_ref_unfreeze(page, expected_count - 1);
 
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
 
return MIGRATEPAGE_SUCCESS;
 }
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 35/99] mm: Convert __do_page_cache_readahead to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This one is trivial.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/readahead.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index f64b31b3a84a..66bcaffd47f0 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -174,9 +174,7 @@ int __do_page_cache_readahead(struct address_space 
*mapping, struct file *filp,
if (page_offset > end_index)
break;
 
-   rcu_read_lock();
-   page = radix_tree_lookup(>pages, page_offset);
-   rcu_read_unlock();
+   page = xa_load(>pages, page_offset);
if (page && !xa_is_value(page))
continue;
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 38/99] mm: Convert collapse_shmem to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

I found another victim of the radix tree being hard to use.  Because
there was no call to radix_tree_preload(), khugepaged was allocating
radix_tree_nodes using GFP_ATOMIC.

I also converted a local_irq_save()/restore() pair to
disable()/enable().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/khugepaged.c | 158 +++-
 1 file changed, 65 insertions(+), 93 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 55ade70c33bb..9f49d0cd61c2 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1282,17 +1282,17 @@ static void retract_page_tables(struct address_space 
*mapping, pgoff_t pgoff)
  *
  * Basic scheme is simple, details are more complex:
  *  - allocate and freeze a new huge page;
- *  - scan over radix tree replacing old pages the new one
+ *  - scan page cache replacing old pages with the new one
  *+ swap in pages if necessary;
  *+ fill in gaps;
- *+ keep old pages around in case if rollback is required;
- *  - if replacing succeed:
+ *+ keep old pages around in case rollback is required;
+ *  - if replacing succeeds:
  *+ copy data over;
  *+ free old pages;
  *+ unfreeze huge page;
  *  - if replacing failed;
  *+ put all pages back and unfreeze them;
- *+ restore gaps in the radix-tree;
+ *+ restore gaps in the page cache;
  *+ free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
@@ -1300,12 +1300,11 @@ static void collapse_shmem(struct mm_struct *mm,
struct page **hpage, int node)
 {
gfp_t gfp;
-   struct page *page, *new_page, *tmp;
+   struct page *new_page;
struct mem_cgroup *memcg;
pgoff_t index, end = start + HPAGE_PMD_NR;
LIST_HEAD(pagelist);
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >pages, start);
int nr_none = 0, result = SCAN_SUCCEED;
 
VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
@@ -1330,48 +1329,48 @@ static void collapse_shmem(struct mm_struct *mm,
__SetPageLocked(new_page);
BUG_ON(!page_ref_freeze(new_page, 1));
 
-
/*
-* At this point the new_page is 'frozen' (page_count() is zero), locked
-* and not up-to-date. It's safe to insert it into radix tree, because
-* nobody would be able to map it or use it in other way until we
-* unfreeze it.
+* At this point the new_page is 'frozen' (page_count() is zero),
+* locked and not up-to-date. It's safe to insert it into the page
+* cache, because nobody would be able to map it or use it in other
+* way until we unfreeze it.
 */
 
-   index = start;
-   xa_lock_irq(>pages);
-   radix_tree_for_each_slot(slot, >pages, , start) {
-   int n = min(iter.index, end) - index;
-
-   /*
-* Handle holes in the radix tree: charge it from shmem and
-* insert relevant subpage of new_page into the radix-tree.
-*/
-   if (n && !shmem_charge(mapping->host, n)) {
-   result = SCAN_FAIL;
+   /* This will be less messy when we use multi-index entries */
+   do {
+   xas_lock_irq();
+   xas_create_range(, end - 1);
+   if (!xas_error())
break;
-   }
-   nr_none += n;
-   for (; index < min(iter.index, end); index++) {
-   radix_tree_insert(>pages, index,
-   new_page + (index % HPAGE_PMD_NR));
-   }
+   xas_unlock_irq();
+   if (!xas_nomem(, GFP_KERNEL))
+   goto out;
+   } while (1);
 
-   /* We are done. */
-   if (index >= end)
-   break;
+   for (index = start; index < end; index++) {
+   struct page *page = xas_next();
+
+   VM_BUG_ON(index != xas.xa_index);
+   if (!page) {
+   if (!shmem_charge(mapping->host, 1)) {
+   result = SCAN_FAIL;
+   break;
+   }
+   xas_store(, new_page + (index % HPAGE_PMD_NR));
+   nr_none++;
+   continue;
+   }
 
-   page = radix_tree_deref_slot_protected(slot,
-   >pages.xa_lock);
if (xa_is_value(page) || !PageUptodate(page)) {
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
/* swap in or instantiate fallocated page */
if (shmem_getpage(mapping->host, index, ,
SGP_NOHUGE)) {

[PATCH v6 39/99] mm: Convert khugepaged_scan_shmem to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Slightly shorter and easier to read code.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/khugepaged.c | 17 +
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9f49d0cd61c2..15f1b2d81a69 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1534,8 +1534,7 @@ static void khugepaged_scan_shmem(struct mm_struct *mm,
pgoff_t start, struct page **hpage)
 {
struct page *page = NULL;
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >pages, start);
int present, swap;
int node = NUMA_NO_NODE;
int result = SCAN_SUCCEED;
@@ -1544,17 +1543,11 @@ static void khugepaged_scan_shmem(struct mm_struct *mm,
swap = 0;
memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
rcu_read_lock();
-   radix_tree_for_each_slot(slot, >pages, , start) {
-   if (iter.index >= start + HPAGE_PMD_NR)
-   break;
-
-   page = radix_tree_deref_slot(slot);
-   if (radix_tree_deref_retry(page)) {
-   slot = radix_tree_iter_retry();
+   xas_for_each(, page, start + HPAGE_PMD_NR - 1) {
+   if (xas_retry(, page))
continue;
-   }
 
-   if (radix_tree_exception(page)) {
+   if (xa_is_value(page)) {
if (++swap > khugepaged_max_ptes_swap) {
result = SCAN_EXCEED_SWAP_PTE;
break;
@@ -1593,7 +1586,7 @@ static void khugepaged_scan_shmem(struct mm_struct *mm,
present++;
 
if (need_resched()) {
-   slot = radix_tree_iter_resume(slot, );
+   xas_pause();
cond_resched_rcu();
}
}
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 40/99] pagevec: Use xa_tag_t

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Removes sparse warnings.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/extent_io.c| 4 ++--
 fs/ext4/inode.c | 2 +-
 fs/f2fs/data.c  | 2 +-
 fs/gfs2/aops.c  | 2 +-
 include/linux/pagevec.h | 8 +---
 mm/swap.c   | 4 ++--
 6 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 22948f4febe7..4301cbf4e31f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3795,7 +3795,7 @@ int btree_write_cache_pages(struct address_space *mapping,
pgoff_t index;
pgoff_t end;/* Inclusive */
int scanned = 0;
-   int tag;
+   xa_tag_t tag;
 
pagevec_init();
if (wbc->range_cyclic) {
@@ -3922,7 +3922,7 @@ static int extent_write_cache_pages(struct address_space 
*mapping,
pgoff_t done_index;
int range_whole = 0;
int scanned = 0;
-   int tag;
+   xa_tag_t tag;
 
/*
 * We have to hold onto the inode so that ordered extents can do their
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 534a9130f625..4b7c10853928 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2614,7 +2614,7 @@ static int mpage_prepare_extent_to_map(struct 
mpage_da_data *mpd)
long left = mpd->wbc->nr_to_write;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
-   int tag;
+   xa_tag_t tag;
int i, err = 0;
int blkbits = mpd->inode->i_blkbits;
ext4_lblk_t lblk;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8f51ac47b77f..c8f6d9806896 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1640,7 +1640,7 @@ static int f2fs_write_cache_pages(struct address_space 
*mapping,
pgoff_t last_idx = ULONG_MAX;
int cycled;
int range_whole = 0;
-   int tag;
+   xa_tag_t tag;
 
pagevec_init();
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1daf15a1f00c..c78ecd008191 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -369,7 +369,7 @@ static int gfs2_write_cache_jdata(struct address_space 
*mapping,
pgoff_t done_index;
int cycled;
int range_whole = 0;
-   int tag;
+   xa_tag_t tag;
 
pagevec_init();
if (wbc->range_cyclic) {
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 5fb6580f7f23..5168901bf06d 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -9,6 +9,8 @@
 #ifndef _LINUX_PAGEVEC_H
 #define _LINUX_PAGEVEC_H
 
+#include 
+
 /* 14 pointers + two long's align the pagevec structure to a power of two */
 #define PAGEVEC_SIZE   14
 
@@ -40,12 +42,12 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec,
 
 unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
-   int tag);
+   xa_tag_t tag);
 unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
-   int tag, unsigned max_pages);
+   xa_tag_t tag, unsigned max_pages);
 static inline unsigned pagevec_lookup_tag(struct pagevec *pvec,
-   struct address_space *mapping, pgoff_t *index, int tag)
+   struct address_space *mapping, pgoff_t *index, xa_tag_t tag)
 {
return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag);
 }
diff --git a/mm/swap.c b/mm/swap.c
index 8d7773cb2c3f..31d79479dacf 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -991,7 +991,7 @@ EXPORT_SYMBOL(pagevec_lookup_range);
 
 unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
-   int tag)
+   xa_tag_t tag)
 {
pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
PAGEVEC_SIZE, pvec->pages);
@@ -1001,7 +1001,7 @@ EXPORT_SYMBOL(pagevec_lookup_range_tag);
 
 unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
-   int tag, unsigned max_pages)
+   xa_tag_t tag, unsigned max_pages)
 {
pvec->nr = find_get_pages_range_tag(mapping, index, end, tag,
min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 42/99] shmem: Convert shmem_confirm_swap to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

xa_load has its own RCU locking, so we can eliminate it here.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 7 +--
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index fad6c9e7402e..654f367aca90 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -348,12 +348,7 @@ static int shmem_xa_replace(struct address_space *mapping,
 static bool shmem_confirm_swap(struct address_space *mapping,
   pgoff_t index, swp_entry_t swap)
 {
-   void *item;
-
-   rcu_read_lock();
-   item = radix_tree_lookup(>pages, index);
-   rcu_read_unlock();
-   return item == swp_to_radix_entry(swap);
+   return xa_load(>pages, index) == swp_to_radix_entry(swap);
 }
 
 /*
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 41/99] shmem: Convert replace to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

shmem_radix_tree_replace() is renamed to shmem_xa_replace() and
converted to use the XArray API.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 22 --
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index c5731bb954a1..fad6c9e7402e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -321,24 +321,20 @@ void shmem_uncharge(struct inode *inode, long pages)
 }
 
 /*
- * Replace item expected in radix tree by a new item, while holding tree lock.
+ * Replace item expected in xarray by a new item, while holding xa_lock.
  */
-static int shmem_radix_tree_replace(struct address_space *mapping,
+static int shmem_xa_replace(struct address_space *mapping,
pgoff_t index, void *expected, void *replacement)
 {
-   struct radix_tree_node *node;
-   void **pslot;
+   XA_STATE(xas, >pages, index);
void *item;
 
VM_BUG_ON(!expected);
VM_BUG_ON(!replacement);
-   item = __radix_tree_lookup(>pages, index, , );
-   if (!item)
-   return -ENOENT;
+   item = xas_load();
if (item != expected)
return -ENOENT;
-   __radix_tree_replace(>pages, node, pslot,
-replacement, NULL);
+   xas_store(, replacement);
return 0;
 }
 
@@ -605,8 +601,7 @@ static int shmem_add_to_page_cache(struct page *page,
} else if (!expected) {
error = radix_tree_insert(>pages, index, page);
} else {
-   error = shmem_radix_tree_replace(mapping, index, expected,
-page);
+   error = shmem_xa_replace(mapping, index, expected, page);
}
 
if (!error) {
@@ -635,7 +630,7 @@ static void shmem_delete_from_page_cache(struct page *page, 
void *radswap)
VM_BUG_ON_PAGE(PageCompound(page), page);
 
xa_lock_irq(>pages);
-   error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
+   error = shmem_xa_replace(mapping, page->index, page, radswap);
page->mapping = NULL;
mapping->nrpages--;
__dec_node_page_state(page, NR_FILE_PAGES);
@@ -1550,8 +1545,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t 
gfp,
 * a nice clean interface for us to replace oldpage by newpage there.
 */
xa_lock_irq(_mapping->pages);
-   error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
-  newpage);
+   error = shmem_xa_replace(swap_mapping, swap_index, oldpage, newpage);
if (!error) {
__inc_node_page_state(newpage, NR_FILE_PAGES);
__dec_node_page_state(oldpage, NR_FILE_PAGES);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 43/99] shmem: Convert find_swap_entry to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a 1:1 conversion.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 23 +++
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 654f367aca90..ce285ae635ea 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1076,28 +1076,27 @@ static void shmem_evict_inode(struct inode *inode)
clear_inode(inode);
 }
 
-static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
+static unsigned long find_swap_entry(struct xarray *xa, void *item)
 {
-   struct radix_tree_iter iter;
-   void **slot;
-   unsigned long found = -1;
+   XA_STATE(xas, xa, 0);
unsigned int checked = 0;
+   void *entry;
 
rcu_read_lock();
-   radix_tree_for_each_slot(slot, root, , 0) {
-   if (*slot == item) {
-   found = iter.index;
+   xas_for_each(, entry, ULONG_MAX) {
+   if (xas_retry(, entry))
+   continue;
+   if (entry == item)
break;
-   }
checked++;
-   if ((checked % 4096) != 0)
+   if ((checked % XA_CHECK_SCHED) != 0)
continue;
-   slot = radix_tree_iter_resume(slot, );
+   xas_pause();
cond_resched_rcu();
}
-
rcu_read_unlock();
-   return found;
+
+   return xas_invalid() ? -1 : xas.xa_index;
 }
 
 /*
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 44/99] shmem: Convert shmem_tag_pins to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Simplify the locking by taking the spinlock while we walk the tree on
the assumption that many acquires and releases of the lock will be
worse than holding the lock for a (potentially) long time.

We could replicate the same locking behaviour with the xarray, but would
have to be careful that the xa_node wasn't RCU-freed under us before we
took the lock.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 39 ---
 1 file changed, 16 insertions(+), 23 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index ce285ae635ea..2f41c7ceea18 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2601,35 +2601,28 @@ static loff_t shmem_file_llseek(struct file *file, 
loff_t offset, int whence)
 
 static void shmem_tag_pins(struct address_space *mapping)
 {
-   struct radix_tree_iter iter;
-   void **slot;
-   pgoff_t start;
+   XA_STATE(xas, >pages, 0);
struct page *page;
+   unsigned int tagged = 0;
 
lru_add_drain();
-   start = 0;
-   rcu_read_lock();
 
-   radix_tree_for_each_slot(slot, >pages, , start) {
-   page = radix_tree_deref_slot(slot);
-   if (!page || radix_tree_exception(page)) {
-   if (radix_tree_deref_retry(page)) {
-   slot = radix_tree_iter_retry();
-   continue;
-   }
-   } else if (page_count(page) - page_mapcount(page) > 1) {
-   xa_lock_irq(>pages);
-   radix_tree_tag_set(>pages, iter.index,
-  SHMEM_TAG_PINNED);
-   xa_unlock_irq(>pages);
-   }
+   xas_lock_irq();
+   xas_for_each(, page, ULONG_MAX) {
+   if (xa_is_value(page))
+   continue;
+   if (page_count(page) - page_mapcount(page) > 1)
+   xas_set_tag(, SHMEM_TAG_PINNED);
 
-   if (need_resched()) {
-   slot = radix_tree_iter_resume(slot, );
-   cond_resched_rcu();
-   }
+   if (++tagged % XA_CHECK_SCHED)
+   continue;
+
+   xas_pause();
+   xas_unlock_irq();
+   cond_resched();
+   xas_lock_irq();
}
-   rcu_read_unlock();
+   xas_unlock_irq();
 }
 
 /*
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 45/99] shmem: Convert shmem_wait_for_pins to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

As with shmem_tag_pins(), hold the lock around the entire loop instead
of acquiring & dropping it for each entry we're going to untag.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 59 ---
 1 file changed, 24 insertions(+), 35 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 2f41c7ceea18..e4a2eb1336be 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2636,9 +2636,7 @@ static void shmem_tag_pins(struct address_space *mapping)
  */
 static int shmem_wait_for_pins(struct address_space *mapping)
 {
-   struct radix_tree_iter iter;
-   void **slot;
-   pgoff_t start;
+   XA_STATE(xas, >pages, 0);
struct page *page;
int error, scan;
 
@@ -2646,7 +2644,9 @@ static int shmem_wait_for_pins(struct address_space 
*mapping)
 
error = 0;
for (scan = 0; scan <= LAST_SCAN; scan++) {
-   if (!radix_tree_tagged(>pages, SHMEM_TAG_PINNED))
+   unsigned int tagged = 0;
+
+   if (!xas_tagged(, SHMEM_TAG_PINNED))
break;
 
if (!scan)
@@ -2654,45 +2654,34 @@ static int shmem_wait_for_pins(struct address_space 
*mapping)
else if (schedule_timeout_killable((HZ << scan) / 200))
scan = LAST_SCAN;
 
-   start = 0;
-   rcu_read_lock();
-   radix_tree_for_each_tagged(slot, >pages, ,
-  start, SHMEM_TAG_PINNED) {
-
-   page = radix_tree_deref_slot(slot);
-   if (radix_tree_exception(page)) {
-   if (radix_tree_deref_retry(page)) {
-   slot = radix_tree_iter_retry();
-   continue;
-   }
-
-   page = NULL;
-   }
-
-   if (page &&
-   page_count(page) - page_mapcount(page) != 1) {
-   if (scan < LAST_SCAN)
-   goto continue_resched;
-
+   xas_set(, 0);
+   xas_lock_irq();
+   xas_for_each_tag(, page, ULONG_MAX, SHMEM_TAG_PINNED) {
+   bool clear = true;
+   if (xa_is_value(page))
+   continue;
+   if (page_count(page) - page_mapcount(page) != 1) {
/*
 * On the last scan, we clean up all those tags
 * we inserted; but make a note that we still
 * found pages pinned.
 */
-   error = -EBUSY;
+   if (scan == LAST_SCAN)
+   error = -EBUSY;
+   else
+   clear = false;
}
+   if (clear)
+   xas_clear_tag(, SHMEM_TAG_PINNED);
+   if (++tagged % XA_CHECK_SCHED)
+   continue;
 
-   xa_lock_irq(>pages);
-   radix_tree_tag_clear(>pages,
-iter.index, SHMEM_TAG_PINNED);
-   xa_unlock_irq(>pages);
-continue_resched:
-   if (need_resched()) {
-   slot = radix_tree_iter_resume(slot, );
-   cond_resched_rcu();
-   }
+   xas_pause();
+   xas_unlock_irq();
+   cond_resched();
+   xas_lock_irq();
}
-   rcu_read_unlock();
+   xas_unlock_irq();
}
 
return error;
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 48/99] shmem: Convert shmem_free_swap to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a perfect use for xa_cmpxchg().  Note the use of 0 for GFP
flags; we won't be allocating memory.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 7 ++-
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index e8233cb7ab5c..5a2226e06f8c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -635,16 +635,13 @@ static void shmem_delete_from_page_cache(struct page 
*page, void *radswap)
 }
 
 /*
- * Remove swap entry from radix tree, free the swap and its page cache.
+ * Remove swap entry from page cache, free the swap and its page cache.
  */
 static int shmem_free_swap(struct address_space *mapping,
   pgoff_t index, void *radswap)
 {
-   void *old;
+   void *old = xa_cmpxchg(>pages, index, radswap, NULL, 0);
 
-   xa_lock_irq(>pages);
-   old = radix_tree_delete_item(>pages, index, radswap);
-   xa_unlock_irq(>pages);
if (old != radswap)
return -ENOENT;
free_swap_and_cache(radix_to_swp_entry(radswap));
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 47/99] shmem: Convert shmem_alloc_hugepage to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

xa_find() is a slightly easier API to use than
radix_tree_gang_lookup_slot() because it contains its own RCU locking.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 14 --
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 0f49edae05e4..e8233cb7ab5c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1413,23 +1413,17 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
 {
struct vm_area_struct pvma;
-   struct inode *inode = >vfs_inode;
-   struct address_space *mapping = inode->i_mapping;
-   pgoff_t idx, hindex;
-   void __rcu **results;
+   struct address_space *mapping = info->vfs_inode.i_mapping;
+   pgoff_t hindex;
struct page *page;
 
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
return NULL;
 
hindex = round_down(index, HPAGE_PMD_NR);
-   rcu_read_lock();
-   if (radix_tree_gang_lookup_slot(>pages, , ,
-   hindex, 1) && idx < hindex + HPAGE_PMD_NR) {
-   rcu_read_unlock();
+   if (xa_find(>pages, , hindex + HPAGE_PMD_NR - 1,
+   XA_PRESENT))
return NULL;
-   }
-   rcu_read_unlock();
 
shmem_pseudo_vma_init(, info, hindex);
page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 46/99] shmem: Convert shmem_add_to_page_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This removes the last caller of radix_tree_maybe_preload_order().
Simpler code, unless we run out of memory for new xa_nodes partway through
inserting entries into the xarray.  Hopefully we can support multi-index
entries in the page cache soon and all the awful code goes away.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 87 --
 1 file changed, 39 insertions(+), 48 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index e4a2eb1336be..0f49edae05e4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -558,9 +558,10 @@ static unsigned long shmem_unused_huge_shrink(struct 
shmem_sb_info *sbinfo,
  */
 static int shmem_add_to_page_cache(struct page *page,
   struct address_space *mapping,
-  pgoff_t index, void *expected)
+  pgoff_t index, void *expected, gfp_t gfp)
 {
-   int error, nr = hpage_nr_pages(page);
+   XA_STATE(xas, >pages, index);
+   unsigned long i, nr = 1UL << compound_order(page);
 
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
@@ -569,49 +570,47 @@ static int shmem_add_to_page_cache(struct page *page,
VM_BUG_ON(expected && PageTransHuge(page));
 
page_ref_add(page, nr);
-   page->mapping = mapping;
page->index = index;
+   page->mapping = mapping;
 
-   xa_lock_irq(>pages);
-   if (PageTransHuge(page)) {
-   void __rcu **results;
-   pgoff_t idx;
-   int i;
-
-   error = 0;
-   if (radix_tree_gang_lookup_slot(>pages,
-   , , index, 1) &&
-   idx < index + HPAGE_PMD_NR) {
-   error = -EEXIST;
+   do {
+   xas_lock_irq();
+   xas_create_range(, index + nr - 1);
+   if (xas_error())
+   goto unlock;
+   for (i = 0; i < nr; i++) {
+   void *entry = xas_load();
+   if (entry != expected)
+   xas_set_err(, -ENOENT);
+   if (xas_error())
+   goto undo;
+   xas_store(, page + i);
+   xas_next();
}
-
-   if (!error) {
-   for (i = 0; i < HPAGE_PMD_NR; i++) {
-   error = radix_tree_insert(>pages,
-   index + i, page + i);
-   VM_BUG_ON(error);
-   }
+   if (PageTransHuge(page)) {
count_vm_event(THP_FILE_ALLOC);
+   __inc_node_page_state(page, NR_SHMEM_THPS);
}
-   } else if (!expected) {
-   error = radix_tree_insert(>pages, index, page);
-   } else {
-   error = shmem_xa_replace(mapping, index, expected, page);
-   }
-
-   if (!error) {
mapping->nrpages += nr;
-   if (PageTransHuge(page))
-   __inc_node_page_state(page, NR_SHMEM_THPS);
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
-   xa_unlock_irq(>pages);
-   } else {
+   goto unlock;
+undo:
+   while (i-- > 0) {
+   xas_store(, NULL);
+   xas_prev();
+   }
+unlock:
+   xas_unlock_irq();
+   } while (xas_nomem(, gfp));
+
+   if (xas_error()) {
page->mapping = NULL;
-   xa_unlock_irq(>pages);
page_ref_sub(page, nr);
+   return xas_error();
}
-   return error;
+
+   return 0;
 }
 
 /*
@@ -1159,7 +1158,7 @@ static int shmem_unuse_inode(struct shmem_inode_info 
*info,
 */
if (!error)
error = shmem_add_to_page_cache(*pagep, mapping, index,
-   radswap);
+   radswap, gfp);
if (error != -ENOMEM) {
/*
 * Truncation and eviction use free_swap_and_cache(), which
@@ -1677,7 +1676,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t 
index,
false);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
-   swp_to_radix_entry(swap));
+   swp_to_radix_entry(swap), gfp);
/*
 * We already confirmed swap 

[PATCH v6 49/99] shmem: Convert shmem_partial_swap_usage to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Simpler code because the xarray takes care of things like the limit and
dereferencing the slot.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 18 +++---
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 5a2226e06f8c..4dbcfb436bd1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -658,29 +658,17 @@ static int shmem_free_swap(struct address_space *mapping,
 unsigned long shmem_partial_swap_usage(struct address_space *mapping,
pgoff_t start, pgoff_t end)
 {
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >pages, start);
struct page *page;
unsigned long swapped = 0;
 
rcu_read_lock();
-
-   radix_tree_for_each_slot(slot, >pages, , start) {
-   if (iter.index >= end)
-   break;
-
-   page = radix_tree_deref_slot(slot);
-
-   if (radix_tree_deref_retry(page)) {
-   slot = radix_tree_iter_retry();
-   continue;
-   }
-
+   xas_for_each(, page, end - 1) {
if (xa_is_value(page))
swapped++;
 
if (need_resched()) {
-   slot = radix_tree_iter_resume(slot, );
+   xas_pause();
cond_resched_rcu();
}
}
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 51/99] btrfs: Convert page cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/compression.c | 4 +---
 fs/btrfs/extent_io.c   | 6 ++
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index e687d06cd97c..4174b166e235 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -449,9 +449,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
if (pg_index > end_index)
break;
 
-   rcu_read_lock();
-   page = radix_tree_lookup(>pages, pg_index);
-   rcu_read_unlock();
+   page = xa_load(>pages, pg_index);
if (page && !xa_is_value(page)) {
misses++;
if (misses > 4)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4301cbf4e31f..fd5e9d887328 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5197,11 +5197,9 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 
clear_page_dirty_for_io(page);
xa_lock_irq(>mapping->pages);
-   if (!PageDirty(page)) {
-   radix_tree_tag_clear(>mapping->pages,
-   page_index(page),
+   if (!PageDirty(page))
+   __xa_clear_tag(>mapping->pages, page_index(page),
PAGECACHE_TAG_DIRTY);
-   }
xa_unlock_irq(>mapping->pages);
ClearPageError(page);
unlock_page(page);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 50/99] shmem: Comment fixups

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Remove the last mentions of radix tree from various comments.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/shmem.c | 14 +++---
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 4dbcfb436bd1..5110848885d4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -743,7 +743,7 @@ void shmem_unlock_mapping(struct address_space *mapping)
 }
 
 /*
- * Remove range of pages and swap entries from radix tree, and free them.
+ * Remove range of pages and swap entries from page cache, and free them.
  * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
  */
 static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
@@ -1118,10 +1118,10 @@ static int shmem_unuse_inode(struct shmem_inode_info 
*info,
 * We needed to drop mutex to make that restrictive page
 * allocation, but the inode might have been freed while we
 * dropped it: although a racing shmem_evict_inode() cannot
-* complete without emptying the radix_tree, our page lock
+* complete without emptying the page cache, our page lock
 * on this swapcache page is not enough to prevent that -
 * free_swap_and_cache() of our swap entry will only
-* trylock_page(), removing swap from radix_tree whatever.
+* trylock_page(), removing swap from page cache whatever.
 *
 * We must not proceed to shmem_add_to_page_cache() if the
 * inode has been freed, but of course we cannot rely on
@@ -1187,7 +1187,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
false);
if (error)
goto out;
-   /* No radix_tree_preload: swap entry keeps a place for page in tree */
+   /* No memory allocation: swap entry occupies the slot for the page */
error = -EAGAIN;
 
mutex_lock(_swaplist_mutex);
@@ -1863,7 +1863,7 @@ alloc_nohuge: page = 
shmem_alloc_and_acct_page(gfp, inode,
spin_unlock_irq(>lock);
goto repeat;
}
-   if (error == -EEXIST)   /* from above or from radix_tree_insert */
+   if (error == -EEXIST)
goto repeat;
return error;
 }
@@ -2475,7 +2475,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, 
struct iov_iter *to)
 }
 
 /*
- * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
+ * llseek SEEK_DATA or SEEK_HOLE through the page cache.
  */
 static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
pgoff_t index, pgoff_t end, int whence)
@@ -2563,7 +2563,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t 
offset, int whence)
 }
 
 /*
- * We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
+ * We need a tag: a new tag would expand every xa_node by 8 bytes,
  * so reuse a tag which we firmly believe is never set or cleared on shmem.
  */
 #define SHMEM_TAG_PINNEDPAGECACHE_TAG_TOWRITE
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 52/99] fs: Convert buffer to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Mostly comment fixes, but one use of __xa_set_tag.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/buffer.c | 14 +++---
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 1a6ae530156b..e1d18307d5c8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -592,7 +592,7 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct 
inode *inode)
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
 
 /*
- * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * Mark the page dirty, and set it dirty in the page cache, and mark the inode
  * dirty.
  *
  * If warn is true, then emit a warning if the page is not uptodate and has
@@ -609,8 +609,8 @@ void __set_page_dirty(struct page *page, struct 
address_space *mapping,
if (page->mapping) {/* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
account_page_dirtied(page, mapping);
-   radix_tree_tag_set(>pages,
-   page_index(page), PAGECACHE_TAG_DIRTY);
+   __xa_set_tag(>pages, page_index(page),
+   PAGECACHE_TAG_DIRTY);
}
xa_unlock_irqrestore(>pages, flags);
 }
@@ -1072,7 +1072,7 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * The relationship between dirty buffers and dirty pages:
  *
  * Whenever a page has any dirty buffers, the page's dirty bit is set, and
- * the page is tagged dirty in its radix tree.
+ * the page is tagged dirty in the page cache.
  *
  * At all times, the dirtiness of the buffers represents the dirtiness of
  * subsections of the page.  If the page has buffers, the page dirty bit is
@@ -1095,9 +1095,9 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * mark_buffer_dirty - mark a buffer_head as needing writeout
  * @bh: the buffer_head to mark dirty
  *
- * mark_buffer_dirty() will set the dirty bit against the buffer, then set its
- * backing page dirty, then tag the page as dirty in its address_space's radix
- * tree and then attach the address_space's inode to its superblock's dirty
+ * mark_buffer_dirty() will set the dirty bit against the buffer, then set
+ * its backing page dirty, then tag the page as dirty in the page cache
+ * and then attach the address_space's inode to its superblock's dirty
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 54/99] nilfs2: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

I'm not 100% convinced that the rewrite of nilfs_copy_back_pages is
correct, but it will at least have different bugs from the current
version.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/nilfs2/btnode.c | 37 +++-
 fs/nilfs2/page.c   | 72 +++---
 2 files changed, 56 insertions(+), 53 deletions(-)

diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 9e2a00207436..b5997e8c5441 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -177,42 +177,36 @@ int nilfs_btnode_prepare_change_key(struct address_space 
*btnc,
ctxt->newbh = NULL;
 
if (inode->i_blkbits == PAGE_SHIFT) {
-   lock_page(obh->b_page);
-   /*
-* We cannot call radix_tree_preload for the kernels older
-* than 2.6.23, because it is not exported for modules.
-*/
+   void *entry;
+   struct page *opage = obh->b_page;
+   lock_page(opage);
 retry:
-   err = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
-   if (err)
-   goto failed_unlock;
/* BUG_ON(oldkey != obh->b_page->index); */
-   if (unlikely(oldkey != obh->b_page->index))
-   NILFS_PAGE_BUG(obh->b_page,
+   if (unlikely(oldkey != opage->index))
+   NILFS_PAGE_BUG(opage,
   "invalid oldkey %lld (newkey=%lld)",
   (unsigned long long)oldkey,
   (unsigned long long)newkey);
 
-   xa_lock_irq(>pages);
-   err = radix_tree_insert(>pages, newkey, obh->b_page);
-   xa_unlock_irq(>pages);
+   entry = xa_cmpxchg(>pages, newkey, NULL, opage, GFP_NOFS);
/*
 * Note: page->index will not change to newkey until
 * nilfs_btnode_commit_change_key() will be called.
 * To protect the page in intermediate state, the page lock
 * is held.
 */
-   radix_tree_preload_end();
-   if (!err)
+   if (!entry)
return 0;
-   else if (err != -EEXIST)
+   if (xa_is_err(entry)) {
+   err = xa_err(entry);
goto failed_unlock;
+   }
 
err = invalidate_inode_pages2_range(btnc, newkey, newkey);
if (!err)
goto retry;
/* fallback to copy mode */
-   unlock_page(obh->b_page);
+   unlock_page(opage);
}
 
nbh = nilfs_btnode_create_block(btnc, newkey);
@@ -252,9 +246,8 @@ void nilfs_btnode_commit_change_key(struct address_space 
*btnc,
mark_buffer_dirty(obh);
 
xa_lock_irq(>pages);
-   radix_tree_delete(>pages, oldkey);
-   radix_tree_tag_set(>pages, newkey,
-  PAGECACHE_TAG_DIRTY);
+   __xa_erase(>pages, oldkey);
+   __xa_set_tag(>pages, newkey, PAGECACHE_TAG_DIRTY);
xa_unlock_irq(>pages);
 
opage->index = obh->b_blocknr = newkey;
@@ -283,9 +276,7 @@ void nilfs_btnode_abort_change_key(struct address_space 
*btnc,
return;
 
if (nbh == NULL) {  /* blocksize == pagesize */
-   xa_lock_irq(>pages);
-   radix_tree_delete(>pages, newkey);
-   xa_unlock_irq(>pages);
+   xa_erase(>pages, newkey);
unlock_page(ctxt->bh->b_page);
} else
brelse(nbh);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 1c6703efde9e..31d20f624971 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -304,10 +304,10 @@ int nilfs_copy_dirty_pages(struct address_space *dmap,
 void nilfs_copy_back_pages(struct address_space *dmap,
   struct address_space *smap)
 {
+   XA_STATE(xas, >pages, 0);
struct pagevec pvec;
unsigned int i, n;
pgoff_t index = 0;
-   int err;
 
pagevec_init();
 repeat:
@@ -317,43 +317,56 @@ void nilfs_copy_back_pages(struct address_space *dmap,
 
for (i = 0; i < pagevec_count(); i++) {
struct page *page = pvec.pages[i], *dpage;
-   pgoff_t offset = page->index;
+   xas_set(, page->index);
 
lock_page(page);
-   dpage = find_lock_page(dmap, offset);
+   do {
+   xas_lock_irq();
+   dpage = xas_create();
+   if (!xas_error())

[PATCH v6 53/99] fs: Convert writeback to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

A couple of short loops.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/fs-writeback.c | 25 +
 1 file changed, 9 insertions(+), 16 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e2c1ca667d9a..897a89489fe9 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -339,9 +339,9 @@ static void inode_switch_wbs_work_fn(struct work_struct 
*work)
struct address_space *mapping = inode->i_mapping;
struct bdi_writeback *old_wb = inode->i_wb;
struct bdi_writeback *new_wb = isw->new_wb;
-   struct radix_tree_iter iter;
+   XA_STATE(xas, >pages, 0);
+   struct page *page;
bool switched = false;
-   void **slot;
 
/*
 * By the time control reaches here, RCU grace period has passed
@@ -375,25 +375,18 @@ static void inode_switch_wbs_work_fn(struct work_struct 
*work)
 * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to
 * pages actually under writeback.
 */
-   radix_tree_for_each_tagged(slot, >pages, , 0,
-  PAGECACHE_TAG_DIRTY) {
-   struct page *page = radix_tree_deref_slot_protected(slot,
-   >pages.xa_lock);
-   if (likely(page) && PageDirty(page)) {
+   xas_for_each_tag(, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) {
+   if (PageDirty(page)) {
dec_wb_stat(old_wb, WB_RECLAIMABLE);
inc_wb_stat(new_wb, WB_RECLAIMABLE);
}
}
 
-   radix_tree_for_each_tagged(slot, >pages, , 0,
-  PAGECACHE_TAG_WRITEBACK) {
-   struct page *page = radix_tree_deref_slot_protected(slot,
-   >pages.xa_lock);
-   if (likely(page)) {
-   WARN_ON_ONCE(!PageWriteback(page));
-   dec_wb_stat(old_wb, WB_WRITEBACK);
-   inc_wb_stat(new_wb, WB_WRITEBACK);
-   }
+   xas_set(, 0);
+   xas_for_each_tag(, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) {
+   WARN_ON_ONCE(!PageWriteback(page));
+   dec_wb_stat(old_wb, WB_WRITEBACK);
+   inc_wb_stat(new_wb, WB_WRITEBACK);
}
 
wb_get(new_wb);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 55/99] f2fs: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a straightforward conversion.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/f2fs/data.c   |  3 +--
 fs/f2fs/dir.c|  5 +
 fs/f2fs/inline.c |  6 +-
 fs/f2fs/node.c   | 10 ++
 4 files changed, 5 insertions(+), 19 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index c8f6d9806896..1f3f192f152f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2175,8 +2175,7 @@ void f2fs_set_page_dirty_nobuffers(struct page *page)
xa_lock_irqsave(>pages, flags);
WARN_ON_ONCE(!PageUptodate(page));
account_page_dirtied(page, mapping);
-   radix_tree_tag_set(>pages,
-   page_index(page), PAGECACHE_TAG_DIRTY);
+   __xa_set_tag(>pages, page_index(page), PAGECACHE_TAG_DIRTY);
xa_unlock_irqrestore(>pages, flags);
unlock_page_memcg(page);
 
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index b5515ea6bb2f..296070016ec9 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -708,7 +708,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, 
struct page *page,
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
struct address_space *mapping = page_mapping(page);
-   unsigned long flags;
int i;
 
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
@@ -739,10 +738,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, 
struct page *page,
 
if (bit_pos == NR_DENTRY_IN_BLOCK &&
!truncate_hole(dir, page->index, page->index + 1)) {
-   xa_lock_irqsave(>pages, flags);
-   radix_tree_tag_clear(>pages, page_index(page),
+   xa_clear_tag(>pages, page_index(page),
 PAGECACHE_TAG_DIRTY);
-   xa_unlock_irqrestore(>pages, flags);
 
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 7858b8e15f33..d3c3f84beca9 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -204,7 +204,6 @@ int f2fs_write_inline_data(struct inode *inode, struct page 
*page)
void *src_addr, *dst_addr;
struct dnode_of_data dn;
struct address_space *mapping = page_mapping(page);
-   unsigned long flags;
int err;
 
set_new_dnode(, inode, NULL, NULL, 0);
@@ -226,10 +225,7 @@ int f2fs_write_inline_data(struct inode *inode, struct 
page *page)
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
 
-   xa_lock_irqsave(>pages, flags);
-   radix_tree_tag_clear(>pages, page_index(page),
-PAGECACHE_TAG_DIRTY);
-   xa_unlock_irqrestore(>pages, flags);
+   xa_clear_tag(>pages, page_index(page), PAGECACHE_TAG_DIRTY);
 
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 6b64a3009d55..0a6d5c2f996e 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -88,14 +88,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int 
type)
 static void clear_node_page_dirty(struct page *page)
 {
struct address_space *mapping = page->mapping;
-   unsigned int long flags;
 
if (PageDirty(page)) {
-   xa_lock_irqsave(>pages, flags);
-   radix_tree_tag_clear(>pages,
-   page_index(page),
+   xa_clear_tag(>pages, page_index(page),
PAGECACHE_TAG_DIRTY);
-   xa_unlock_irqrestore(>pages, flags);
 
clear_page_dirty_for_io(page);
dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
@@ -1142,9 +1138,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
return;
f2fs_bug_on(sbi, check_nid_range(sbi, nid));
 
-   rcu_read_lock();
-   apage = radix_tree_lookup(_MAPPING(sbi)->pages, nid);
-   rcu_read_unlock();
+   apage = xa_load(_MAPPING(sbi)->pages, nid);
if (apage)
return;
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 56/99] lustre: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/staging/lustre/lustre/llite/glimpse.c   | 12 +---
 drivers/staging/lustre/lustre/mdc/mdc_request.c | 16 
 2 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/staging/lustre/lustre/llite/glimpse.c 
b/drivers/staging/lustre/lustre/llite/glimpse.c
index 5f2843da911c..25232fdf5797 100644
--- a/drivers/staging/lustre/lustre/llite/glimpse.c
+++ b/drivers/staging/lustre/lustre/llite/glimpse.c
@@ -57,7 +57,7 @@ static const struct cl_lock_descr whole_file = {
 };
 
 /*
- * Check whether file has possible unwriten pages.
+ * Check whether file has possible unwritten pages.
  *
  * \retval 1file is mmap-ed or has dirty pages
  *  0otherwise
@@ -66,16 +66,14 @@ blkcnt_t dirty_cnt(struct inode *inode)
 {
blkcnt_t cnt = 0;
struct vvp_object *vob = cl_inode2vvp(inode);
-   void  *results[1];
 
-   if (inode->i_mapping)
-   cnt += radix_tree_gang_lookup_tag(>i_mapping->pages,
- results, 0, 1,
- PAGECACHE_TAG_DIRTY);
+   if (inode->i_mapping && xa_tagged(>i_mapping->pages,
+   PAGECACHE_TAG_DIRTY))
+   cnt = 1;
if (cnt == 0 && atomic_read(>vob_mmap_cnt) > 0)
cnt = 1;
 
-   return (cnt > 0) ? 1 : 0;
+   return cnt;
 }
 
 int cl_glimpse_lock(const struct lu_env *env, struct cl_io *io,
diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c 
b/drivers/staging/lustre/lustre/mdc/mdc_request.c
index 2ec79a6b17da..ea23247e9e02 100644
--- a/drivers/staging/lustre/lustre/mdc/mdc_request.c
+++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -934,17 +934,18 @@ static struct page *mdc_page_locate(struct address_space 
*mapping, __u64 *hash,
 * hash _smaller_ than one we are looking for.
 */
unsigned long offset = hash_x_index(*hash, hash64);
+   XA_STATE(xas, >pages, offset);
struct page *page;
-   int found;
 
-   xa_lock_irq(>pages);
-   found = radix_tree_gang_lookup(>pages,
-  (void **), offset, 1);
-   if (found > 0 && !xa_is_value(page)) {
+   xas_lock_irq();
+   page = xas_find(, ULONG_MAX);
+   if (xa_is_value(page))
+   page = NULL;
+   if (page) {
struct lu_dirpage *dp;
 
get_page(page);
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
/*
 * In contrast to find_lock_page() we are sure that directory
 * page cannot be truncated (while DLM lock is held) and,
@@ -992,8 +993,7 @@ static struct page *mdc_page_locate(struct address_space 
*mapping, __u64 *hash,
page = ERR_PTR(-EIO);
}
} else {
-   xa_unlock_irq(>pages);
-   page = NULL;
+   xas_unlock_irq();
}
return page;
 }
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 58/99] dax: Convert lock_slot to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 22 --
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index f3463d93a6ce..8eab0b56f7f9 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -188,12 +188,11 @@ static void dax_wake_mapping_entry_waiter(struct 
address_space *mapping,
 /*
  * Mark the given slot as locked.  Must be called with xa_lock held.
  */
-static inline void *lock_slot(struct address_space *mapping, void **slot)
+static inline void *lock_slot(struct xa_state *xas)
 {
-   unsigned long v = xa_to_value(
-   radix_tree_deref_slot_protected(slot, >pages.xa_lock));
+   unsigned long v = xa_to_value(xas_load(xas));
void *entry = xa_mk_value(v | DAX_ENTRY_LOCK);
-   radix_tree_replace_slot(>pages, slot, entry);
+   xas_store(xas, entry);
return entry;
 }
 
@@ -244,7 +243,7 @@ static void dax_unlock_mapping_entry(struct address_space 
*mapping,
 
xas_lock_irq();
entry = xas_load();
-   if (WARN_ON_ONCE(!entry || !xa_is_value(entry) || !dax_locked(entry))) {
+   if (WARN_ON_ONCE(!xa_is_value(entry) || !dax_locked(entry))) {
xas_unlock_irq();
return;
}
@@ -303,6 +302,7 @@ static void put_unlocked_mapping_entry(struct address_space 
*mapping,
 static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
unsigned long size_flag)
 {
+   XA_STATE(xas, >pages, index);
bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
void *entry, **slot;
 
@@ -341,7 +341,7 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
 * Make sure 'entry' remains valid while we drop
 * xa_lock.
 */
-   entry = lock_slot(mapping, slot);
+   entry = lock_slot();
}
 
xa_unlock_irq(>pages);
@@ -408,7 +408,7 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
xa_unlock_irq(>pages);
return entry;
}
-   entry = lock_slot(mapping, slot);
+   entry = lock_slot();
  out_unlock:
xa_unlock_irq(>pages);
return entry;
@@ -639,6 +639,7 @@ static int dax_writeback_one(struct block_device *bdev,
pgoff_t index, void *entry)
 {
struct radix_tree_root *pages = >pages;
+   XA_STATE(xas, pages, index);
void *entry2, **slot, *kaddr;
long ret = 0, id;
sector_t sector;
@@ -675,7 +676,7 @@ static int dax_writeback_one(struct block_device *bdev,
if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))
goto put_unlocked;
/* Lock the entry to serialize with page faults */
-   entry = lock_slot(mapping, slot);
+   entry = lock_slot();
/*
 * We can clear the tag now but we have to be careful so that concurrent
 * dax_writeback_one() calls for the same index cannot finish before we
@@ -1500,8 +1501,9 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf,
  pfn_t pfn)
 {
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
-   void *entry, **slot;
pgoff_t index = vmf->pgoff;
+   XA_STATE(xas, >pages, index);
+   void *entry, **slot;
int vmf_ret, error;
 
xa_lock_irq(>pages);
@@ -1517,7 +1519,7 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf,
return VM_FAULT_NOPAGE;
}
radix_tree_tag_set(>pages, index, PAGECACHE_TAG_DIRTY);
-   entry = lock_slot(mapping, slot);
+   entry = lock_slot();
xa_unlock_irq(>pages);
switch (pe_size) {
case PE_SIZE_PTE:
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 59/99] dax: More XArray conversion

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This time, we want to convert get_unlocked_mapping_entry() to use the
XArray.  That has a ripple effect, causing us to change the waitqueues
to hash on the address of the xarray rather than the address of the
mapping (functionally equivalent), and create a lot of on-the-stack
xa_state which are only used as a container for passing the xarray and
the index down to deeper function calls.

Also rename dax_wake_mapping_entry_waiter() to dax_wake_entry().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 72 +---
 1 file changed, 33 insertions(+), 39 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 8eab0b56f7f9..d3fe61b95216 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -120,7 +120,7 @@ static int dax_is_empty_entry(void *entry)
  * DAX radix tree locking
  */
 struct exceptional_entry_key {
-   struct address_space *mapping;
+   struct xarray *xa;
pgoff_t entry_start;
 };
 
@@ -129,9 +129,10 @@ struct wait_exceptional_entry_queue {
struct exceptional_entry_key key;
 };
 
-static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
-   pgoff_t index, void *entry, struct exceptional_entry_key *key)
+static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
+   void *entry, struct exceptional_entry_key *key)
 {
+   unsigned long index = xas->xa_index;
unsigned long hash;
 
/*
@@ -142,10 +143,10 @@ static wait_queue_head_t *dax_entry_waitqueue(struct 
address_space *mapping,
if (dax_is_pmd_entry(entry))
index &= ~PG_PMD_COLOUR;
 
-   key->mapping = mapping;
+   key->xa = xas->xa;
key->entry_start = index;
 
-   hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS);
+   hash = hash_long((unsigned long)xas->xa ^ index, DAX_WAIT_TABLE_BITS);
return wait_table + hash;
 }
 
@@ -156,7 +157,7 @@ static int wake_exceptional_entry_func(wait_queue_entry_t 
*wait, unsigned int mo
struct wait_exceptional_entry_queue *ewait =
container_of(wait, struct wait_exceptional_entry_queue, wait);
 
-   if (key->mapping != ewait->key.mapping ||
+   if (key->xa != ewait->key.xa ||
key->entry_start != ewait->key.entry_start)
return 0;
return autoremove_wake_function(wait, mode, sync, NULL);
@@ -167,13 +168,12 @@ static int wake_exceptional_entry_func(wait_queue_entry_t 
*wait, unsigned int mo
  * The important information it's conveying is whether the entry at
  * this index used to be a PMD entry.
  */
-static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-   pgoff_t index, void *entry, bool wake_all)
+static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all)
 {
struct exceptional_entry_key key;
wait_queue_head_t *wq;
 
-   wq = dax_entry_waitqueue(mapping, index, entry, );
+   wq = dax_entry_waitqueue(xas, entry, );
 
/*
 * Checking for locked entry and prepare_to_wait_exclusive() happens
@@ -205,10 +205,9 @@ static inline void *lock_slot(struct xa_state *xas)
  *
  * Must be called with xa_lock held.
  */
-static void *get_unlocked_mapping_entry(struct address_space *mapping,
-   pgoff_t index, void ***slotp)
+static void *get_unlocked_mapping_entry(struct xa_state *xas)
 {
-   void *entry, **slot;
+   void *entry;
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
 
@@ -216,22 +215,19 @@ static void *get_unlocked_mapping_entry(struct 
address_space *mapping,
ewait.wait.func = wake_exceptional_entry_func;
 
for (;;) {
-   entry = __radix_tree_lookup(>pages, index, NULL,
- );
-   if (!entry ||
-   WARN_ON_ONCE(!xa_is_value(entry)) || !dax_locked(entry)) {
-   if (slotp)
-   *slotp = slot;
+   entry = xas_load(xas);
+   if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
+   !dax_locked(entry))
return entry;
-   }
 
-   wq = dax_entry_waitqueue(mapping, index, entry, );
+   wq = dax_entry_waitqueue(xas, entry, );
prepare_to_wait_exclusive(wq, ,
  TASK_UNINTERRUPTIBLE);
-   xa_unlock_irq(>pages);
+   xas_pause(xas);
+   xas_unlock_irq(xas);
schedule();
finish_wait(wq, );
-   xa_lock_irq(>pages);
+   xas_lock_irq(xas);
}
 }
 
@@ -251,7 +247,7 @@ static void dax_unlock_mapping_entry(struct address_space 
*mapping,
xas_store(, entry);
/* Safe

[PATCH v6 57/99] dax: Convert dax_unlock_mapping_entry to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Replace slot_locked() with dax_locked() and inline unlock_slot() into
its only caller.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 48 
 1 file changed, 16 insertions(+), 32 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 5097a606da1a..f3463d93a6ce 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -73,6 +73,11 @@ fs_initcall(init_dax_wait_table);
 #define DAX_ZERO_PAGE  (1UL << 2)
 #define DAX_EMPTY  (1UL << 3)
 
+static bool dax_locked(void *entry)
+{
+   return xa_to_value(entry) & DAX_ENTRY_LOCK;
+}
+
 static unsigned long dax_radix_sector(void *entry)
 {
return xa_to_value(entry) >> DAX_SHIFT;
@@ -180,16 +185,6 @@ static void dax_wake_mapping_entry_waiter(struct 
address_space *mapping,
__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, );
 }
 
-/*
- * Check whether the given slot is locked.  Must be called with xa_lock held.
- */
-static inline int slot_locked(struct address_space *mapping, void **slot)
-{
-   unsigned long entry = xa_to_value(
-   radix_tree_deref_slot_protected(slot, >pages.xa_lock));
-   return entry & DAX_ENTRY_LOCK;
-}
-
 /*
  * Mark the given slot as locked.  Must be called with xa_lock held.
  */
@@ -202,18 +197,6 @@ static inline void *lock_slot(struct address_space 
*mapping, void **slot)
return entry;
 }
 
-/*
- * Mark the given slot as unlocked.  Must be called with xa_lock held.
- */
-static inline void *unlock_slot(struct address_space *mapping, void **slot)
-{
-   unsigned long v = xa_to_value(
-   radix_tree_deref_slot_protected(slot, >pages.xa_lock));
-   void *entry = xa_mk_value(v & ~DAX_ENTRY_LOCK);
-   radix_tree_replace_slot(>pages, slot, entry);
-   return entry;
-}
-
 /*
  * Lookup entry in radix tree, wait for it to become unlocked if it is
  * a DAX entry and return it. The caller must call
@@ -237,8 +220,7 @@ static void *get_unlocked_mapping_entry(struct 
address_space *mapping,
entry = __radix_tree_lookup(>pages, index, NULL,
  );
if (!entry ||
-   WARN_ON_ONCE(!xa_is_value(entry)) ||
-   !slot_locked(mapping, slot)) {
+   WARN_ON_ONCE(!xa_is_value(entry)) || !dax_locked(entry)) {
if (slotp)
*slotp = slot;
return entry;
@@ -257,17 +239,19 @@ static void *get_unlocked_mapping_entry(struct 
address_space *mapping,
 static void dax_unlock_mapping_entry(struct address_space *mapping,
 pgoff_t index)
 {
-   void *entry, **slot;
+   XA_STATE(xas, >pages, index);
+   void *entry;
 
-   xa_lock_irq(>pages);
-   entry = __radix_tree_lookup(>pages, index, NULL, );
-   if (WARN_ON_ONCE(!entry || !xa_is_value(entry) ||
-!slot_locked(mapping, slot))) {
-   xa_unlock_irq(>pages);
+   xas_lock_irq();
+   entry = xas_load();
+   if (WARN_ON_ONCE(!entry || !xa_is_value(entry) || !dax_locked(entry))) {
+   xas_unlock_irq();
return;
}
-   unlock_slot(mapping, slot);
-   xa_unlock_irq(>pages);
+   entry = xa_mk_value(xa_to_value(entry) & ~DAX_ENTRY_LOCK);
+   xas_store(, entry);
+   /* Safe to not call xas_pause here -- we don't touch the array after */
+   xas_unlock_irq();
dax_wake_mapping_entry_waiter(mapping, index, entry, false);
 }
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 61/99] dax: Convert dax_writeback_one to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Likewise easy

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 17 +++--
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 9a30224da4d6..b66b8c896ed8 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -632,8 +632,7 @@ static int dax_writeback_one(struct block_device *bdev,
struct dax_device *dax_dev, struct address_space *mapping,
pgoff_t index, void *entry)
 {
-   struct radix_tree_root *pages = >pages;
-   XA_STATE(xas, pages, index);
+   XA_STATE(xas, >pages, index);
void *entry2, *kaddr;
long ret = 0, id;
sector_t sector;
@@ -648,7 +647,7 @@ static int dax_writeback_one(struct block_device *bdev,
if (WARN_ON(!xa_is_value(entry)))
return -EIO;
 
-   xa_lock_irq(>pages);
+   xas_lock_irq();
entry2 = get_unlocked_mapping_entry();
/* Entry got punched out / reallocated? */
if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2)))
@@ -667,7 +666,7 @@ static int dax_writeback_one(struct block_device *bdev,
}
 
/* Another fsync thread may have already written back this entry */
-   if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))
+   if (!xas_get_tag(, PAGECACHE_TAG_TOWRITE))
goto put_unlocked;
/* Lock the entry to serialize with page faults */
entry = lock_slot();
@@ -678,8 +677,8 @@ static int dax_writeback_one(struct block_device *bdev,
 * at the entry only under xa_lock and once they do that they will
 * see the entry locked and wait for it to unlock.
 */
-   radix_tree_tag_clear(pages, index, PAGECACHE_TAG_TOWRITE);
-   xa_unlock_irq(>pages);
+   xas_clear_tag(, PAGECACHE_TAG_TOWRITE);
+   xas_unlock_irq();
 
/*
 * Even if dax_writeback_mapping_range() was given a wbc->range_start
@@ -717,9 +716,7 @@ static int dax_writeback_one(struct block_device *bdev,
 * the pfn mappings are writeprotected and fault waits for mapping
 * entry lock.
 */
-   xa_lock_irq(>pages);
-   radix_tree_tag_clear(pages, index, PAGECACHE_TAG_DIRTY);
-   xa_unlock_irq(>pages);
+   xa_clear_tag(>pages, index, PAGECACHE_TAG_DIRTY);
trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
  dax_unlock:
dax_read_unlock(id);
@@ -728,7 +725,7 @@ static int dax_writeback_one(struct block_device *bdev,
 
  put_unlocked:
put_unlocked_mapping_entry(, entry2);
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return ret;
 }
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 60/99] dax: Convert __dax_invalidate_mapping_entry to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Simple now that we already have an xa_state!

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 10 +-
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d3fe61b95216..9a30224da4d6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -413,24 +413,24 @@ static int __dax_invalidate_mapping_entry(struct 
address_space *mapping,
XA_STATE(xas, >pages, index);
int ret = 0;
void *entry;
-   struct radix_tree_root *pages = >pages;
 
xa_lock_irq(>pages);
entry = get_unlocked_mapping_entry();
if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
goto out;
if (!trunc &&
-   (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
-radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE)))
+   (xas_get_tag(, PAGECACHE_TAG_DIRTY) ||
+xas_get_tag(, PAGECACHE_TAG_TOWRITE)))
goto out;
-   radix_tree_delete(pages, index);
+   xas_store(, NULL);
mapping->nrexceptional--;
ret = 1;
 out:
put_unlocked_mapping_entry(, entry);
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return ret;
 }
+
 /*
  * Delete DAX entry at @index from @mapping.  Wait for it
  * to be unlocked before deleting it.
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 62/99] dax: Convert dax_insert_pfn_mkwrite to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 8 
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index b66b8c896ed8..e6b25ef112f2 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1497,21 +1497,21 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf,
void *entry;
int vmf_ret, error;
 
-   xa_lock_irq(>pages);
+   xas_lock_irq();
entry = get_unlocked_mapping_entry();
/* Did we race with someone splitting entry or so? */
if (!entry ||
(pe_size == PE_SIZE_PTE && !dax_is_pte_entry(entry)) ||
(pe_size == PE_SIZE_PMD && !dax_is_pmd_entry(entry))) {
put_unlocked_mapping_entry(, entry);
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
  VM_FAULT_NOPAGE);
return VM_FAULT_NOPAGE;
}
-   radix_tree_tag_set(>pages, index, PAGECACHE_TAG_DIRTY);
+   xas_set_tag(, PAGECACHE_TAG_DIRTY);
entry = lock_slot();
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
switch (pe_size) {
case PE_SIZE_PTE:
error = vm_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 63/99] dax: Convert dax_insert_mapping_entry to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 18 ++
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index e6b25ef112f2..494e8fb7a98f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -498,9 +498,9 @@ static void *dax_insert_mapping_entry(struct address_space 
*mapping,
  void *entry, sector_t sector,
  unsigned long flags, bool dirty)
 {
-   struct radix_tree_root *pages = >pages;
void *new_entry;
pgoff_t index = vmf->pgoff;
+   XA_STATE(xas, >pages, index);
 
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
@@ -516,7 +516,7 @@ static void *dax_insert_mapping_entry(struct address_space 
*mapping,
PAGE_SIZE, 0);
}
 
-   xa_lock_irq(>pages);
+   xas_lock_irq();
new_entry = dax_radix_locked_entry(sector, flags);
 
if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
@@ -528,21 +528,15 @@ static void *dax_insert_mapping_entry(struct 
address_space *mapping,
 * existing entry is a PMD, we will just leave the PMD in the
 * tree and dirty it if necessary.
 */
-   struct radix_tree_node *node;
-   void **slot;
-   void *ret;
-
-   ret = __radix_tree_lookup(pages, index, , );
-   WARN_ON_ONCE(ret != entry);
-   __radix_tree_replace(pages, node, slot,
-new_entry, NULL);
+   void *prev = xas_store(, new_entry);
+   WARN_ON_ONCE(prev != entry);
entry = new_entry;
}
 
if (dirty)
-   radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY);
+   xas_set_tag(, PAGECACHE_TAG_DIRTY);
 
-   xa_unlock_irq(>pages);
+   xas_unlock_irq();
return entry;
 }
 
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 65/99] dax: Fix sparse warning

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

sparse doesn't know that follow_pte_pmd() conditionally acquires the ptl,
because it's in a separate compilation unit.  Move follow_pte_pmd() to
mm.h where sparse can see it.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/mm.h | 15 ++-
 mm/memory.c| 16 +---
 2 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fe1ee4313add..9c384c486edf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1314,7 +1314,7 @@ int copy_page_range(struct mm_struct *dst, struct 
mm_struct *src,
struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
-int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 unsigned long *start, unsigned long *end,
 pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
@@ -1324,6 +1324,19 @@ int follow_phys(struct vm_area_struct *vma, unsigned 
long address,
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write);
 
+static inline int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+unsigned long *start, unsigned long *end,
+pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+{
+   int res;
+
+   /* (void) is needed to make gcc happy */
+   (void) __cond_lock(*ptlp,
+  !(res = __follow_pte_pmd(mm, address, start, end,
+   ptepp, pmdpp, ptlp)));
+   return res;
+}
+
 static inline void unmap_shared_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen)
 {
diff --git a/mm/memory.c b/mm/memory.c
index ca5674cbaff2..66184601ac03 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4201,7 +4201,7 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, 
unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
unsigned long *start, unsigned long *end,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
@@ -4278,20 +4278,6 @@ static inline int follow_pte(struct mm_struct *mm, 
unsigned long address,
return res;
 }
 
-int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
-unsigned long *start, unsigned long *end,
-pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
-{
-   int res;
-
-   /* (void) is needed to make gcc happy */
-   (void) __cond_lock(*ptlp,
-  !(res = __follow_pte_pmd(mm, address, start, end,
-   ptepp, pmdpp, ptlp)));
-   return res;
-}
-EXPORT_SYMBOL(follow_pte_pmd);
-
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 64/99] dax: Convert grab_mapping_entry to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/dax.c | 98 +---
 1 file changed, 26 insertions(+), 72 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 494e8fb7a98f..3eb0cf176d69 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -44,6 +44,7 @@
 
 /* The 'colour' (ie low bits) within a PMD of a page offset.  */
 #define PG_PMD_COLOUR  ((PMD_SIZE >> PAGE_SHIFT) - 1)
+#define PMD_ORDER  (PMD_SHIFT - PAGE_SHIFT)
 
 static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
 
@@ -89,10 +90,10 @@ static void *dax_radix_locked_entry(sector_t sector, 
unsigned long flags)
DAX_ENTRY_LOCK);
 }
 
-static unsigned int dax_radix_order(void *entry)
+static unsigned int dax_entry_order(void *entry)
 {
if (xa_to_value(entry) & DAX_PMD)
-   return PMD_SHIFT - PAGE_SHIFT;
+   return PMD_ORDER;
return 0;
 }
 
@@ -299,10 +300,11 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
 {
XA_STATE(xas, >pages, index);
bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
-   void *entry, **slot;
+   void *entry;
 
+   xas_set_order(, index, size_flag ? PMD_ORDER : 0);
 restart:
-   xa_lock_irq(>pages);
+   xas_lock_irq();
entry = get_unlocked_mapping_entry();
 
if (WARN_ON_ONCE(entry && !xa_is_value(entry))) {
@@ -326,84 +328,36 @@ static void *grab_mapping_entry(struct address_space 
*mapping, pgoff_t index,
}
}
 
-   /* No entry for given index? Make sure radix tree is big enough. */
-   if (!entry || pmd_downgrade) {
-   int err;
-
-   if (pmd_downgrade) {
-   /*
-* Make sure 'entry' remains valid while we drop
-* xa_lock.
-*/
-   entry = lock_slot();
-   }
-
-   xa_unlock_irq(>pages);
+   if (pmd_downgrade) {
+   entry = lock_slot();
/*
 * Besides huge zero pages the only other thing that gets
 * downgraded are empty entries which don't need to be
 * unmapped.
 */
-   if (pmd_downgrade && dax_is_zero_entry(entry))
+   if (dax_is_zero_entry(entry)) {
+   xas_pause();
+   xas_unlock_irq();
unmap_mapping_range(mapping,
(index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
-
-   err = radix_tree_preload(
-   mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
-   if (err) {
-   if (pmd_downgrade)
-   put_locked_mapping_entry(mapping, index);
-   return ERR_PTR(err);
+   xas_lock_irq();
}
-   xa_lock_irq(>pages);
-
-   if (!entry) {
-   /*
-* We needed to drop the pages lock while calling
-* radix_tree_preload() and we didn't have an entry to
-* lock.  See if another thread inserted an entry at
-* our index during this time.
-*/
-   entry = __radix_tree_lookup(>pages, index,
-   NULL, );
-   if (entry) {
-   radix_tree_preload_end();
-   xa_unlock_irq(>pages);
-   goto restart;
-   }
-   }
-
-   if (pmd_downgrade) {
-   radix_tree_delete(>pages, index);
-   mapping->nrexceptional--;
-   dax_wake_entry(, entry, true);
-   }
-
+   xas_store(, NULL);
+   mapping->nrexceptional--;
+   dax_wake_entry(, entry, true);
+   }
+   if (!entry || pmd_downgrade) {
entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY);
-
-   err = __radix_tree_insert(>pages, index,
-   dax_radix_order(entry), entry);
-   radix_tree_preload_end();
-   if (err) {
-   xa_unlock_irq(>pages);
-   /*
-* Our insertion of a DAX entry failed, most likely
-* because we were inserting a PMD entry and it
-* collided with a PTE sized entry at a different
-* index in the PMD range.  We haven't inserted
-

[PATCH v6 66/99] page cache: Finish XArray conversion

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

With no more radix tree API users left, we can drop the GFP flags
and use xa_init() instead of INIT_RADIX_TREE().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/inode.c | 2 +-
 include/linux/fs.h | 2 +-
 mm/swap_state.c| 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index c7b00573c10d..f5680b805336 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -348,7 +348,7 @@ EXPORT_SYMBOL(inc_nlink);
 void address_space_init_once(struct address_space *mapping)
 {
memset(mapping, 0, sizeof(*mapping));
-   INIT_RADIX_TREE(>pages, GFP_ATOMIC | __GFP_ACCOUNT);
+   xa_init_flags(>pages, XA_FLAGS_LOCK_IRQ);
init_rwsem(>i_mmap_rwsem);
INIT_LIST_HEAD(>private_list);
spin_lock_init(>private_lock);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c58bc3c619bf..b459bf4ddb62 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -410,7 +410,7 @@ int pagecache_write_end(struct file *, struct address_space 
*mapping,
  */
 struct address_space {
struct inode*host;
-   struct radix_tree_root  pages;
+   struct xarray   pages;
gfp_t   gfp_mask;
atomic_ti_mmap_writable;
struct rb_root_cached   i_mmap;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 219e3b4f09e6..25f027d0bb00 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -573,7 +573,7 @@ int init_swap_address_space(unsigned int type, unsigned 
long nr_pages)
return -ENOMEM;
for (i = 0; i < nr; i++) {
space = spaces + i;
-   INIT_RADIX_TREE(>pages, GFP_ATOMIC|__GFP_NOWARN);
+   xa_init_flags(>pages, XA_FLAGS_LOCK_IRQ);
atomic_set(>i_mmap_writable, 0);
space->a_ops = _aops;
/* swap cache doesn't use writeback related tags */
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 67/99] mm: Convert cgroup writeback to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a fairly naive conversion, leaving in place the GFP_ATOMIC
allocation.  By switching the locking around, we could use GFP_KERNEL
and probably simplify the error handling.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 include/linux/backing-dev-defs.h |  2 +-
 include/linux/backing-dev.h  |  2 +-
 mm/backing-dev.c | 22 ++
 3 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index bfe86b54f6c1..074a54aad33c 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -187,7 +187,7 @@ struct backing_dev_info {
struct bdi_writeback wb;  /* the root writeback info for this bdi */
struct list_head wb_list; /* list of all wbs */
 #ifdef CONFIG_CGROUP_WRITEBACK
-   struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
+   struct xarray cgwb_xa;  /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
 #else
struct bdi_writeback_congested *wb_congested;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 3df0d20e23f3..27e7b31bd802 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -271,7 +271,7 @@ static inline struct bdi_writeback *wb_find_current(struct 
backing_dev_info *bdi
if (!memcg_css->parent)
return >wb;
 
-   wb = radix_tree_lookup(>cgwb_tree, memcg_css->id);
+   wb = xa_load(>cgwb_xa, memcg_css->id);
 
/*
 * %current's blkcg equals the effective blkcg of its memcg.  No
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index b5f940ce0143..aa0f85df0928 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -417,8 +417,8 @@ static void wb_exit(struct bdi_writeback *wb)
 #include 
 
 /*
- * cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree,
- * blkcg->cgwb_list, and memcg->cgwb_list.  bdi->cgwb_tree is also RCU
+ * cgwb_lock protects bdi->cgwb_xa, bdi->cgwb_congested_tree,
+ * blkcg->cgwb_list, and memcg->cgwb_list.  bdi->cgwb_xa is also RCU
  * protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
@@ -539,7 +539,7 @@ static void cgwb_kill(struct bdi_writeback *wb)
 {
lockdep_assert_held(_lock);
 
-   WARN_ON(!radix_tree_delete(>bdi->cgwb_tree, wb->memcg_css->id));
+   WARN_ON(xa_erase(>bdi->cgwb_xa, wb->memcg_css->id) != wb);
list_del(>memcg_node);
list_del(>blkcg_node);
percpu_ref_kill(>refcnt);
@@ -571,7 +571,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 
/* look up again under lock and discard on blkcg mismatch */
spin_lock_irqsave(_lock, flags);
-   wb = radix_tree_lookup(>cgwb_tree, memcg_css->id);
+   wb = xa_load(>cgwb_xa, memcg_css->id);
if (wb && wb->blkcg_css != blkcg_css) {
cgwb_kill(wb);
wb = NULL;
@@ -614,8 +614,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
spin_lock_irqsave(_lock, flags);
if (test_bit(WB_registered, >wb.state) &&
blkcg_cgwb_list->next && memcg_cgwb_list->next) {
-   /* we might have raced another instance of this function */
-   ret = radix_tree_insert(>cgwb_tree, memcg_css->id, wb);
+   ret = xa_insert(>cgwb_xa, memcg_css->id, wb, GFP_ATOMIC);
if (!ret) {
list_add_tail_rcu(>bdi_node, >wb_list);
list_add(>memcg_node, memcg_cgwb_list);
@@ -682,7 +681,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info 
*bdi,
 
do {
rcu_read_lock();
-   wb = radix_tree_lookup(>cgwb_tree, memcg_css->id);
+   wb = xa_load(>cgwb_xa, memcg_css->id);
if (wb) {
struct cgroup_subsys_state *blkcg_css;
 
@@ -704,7 +703,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 {
int ret;
 
-   INIT_RADIX_TREE(>cgwb_tree, GFP_ATOMIC);
+   xa_init(>cgwb_xa);
bdi->cgwb_congested_tree = RB_ROOT;
 
ret = wb_init(>wb, bdi, 1, GFP_KERNEL);
@@ -717,15 +716,14 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 
 static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 {
-   struct radix_tree_iter iter;
-   void **slot;
+   XA_STATE(xas, >cgwb_xa, 0);
struct bdi_writeback *wb;
 
WARN_ON(test_bit(WB_registered, >wb.state));
 
spin_lock_irq(_lock);
-   radix_tree_for_each_slot(slot, >cgwb_tree, , 0)
-   cgwb_kill(*slot);
+   xas_for_each(, wb, ULONG_MAX)
+   cgwb_kill(wb);
 
while (!list_empty(>wb_list)) {
 

[PATCH v6 69/99] brd: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Convert brd_pages from a radix tree to an XArray.  Simpler and smaller
code; in particular another user of radix_tree_preload is eliminated.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/block/brd.c | 93 -
 1 file changed, 28 insertions(+), 65 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 8028a3a7e7fd..59a1af7aaa79 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -17,7 +17,7 @@
 #include 
 #include 
 #include 
-#include 
+#include 
 #include 
 #include 
 #include 
@@ -29,9 +29,9 @@
 #define PAGE_SECTORS   (1 << PAGE_SECTORS_SHIFT)
 
 /*
- * Each block ramdisk device has a radix_tree brd_pages of pages that stores
- * the pages containing the block device's contents. A brd page's ->index is
- * its offset in PAGE_SIZE units. This is similar to, but in no way connected
+ * Each block ramdisk device has an xarray brd_pages that stores the pages
+ * containing the block device's contents. A brd page's ->index is its
+ * offset in PAGE_SIZE units. This is similar to, but in no way connected
  * with, the kernel's pagecache or buffer cache (which sit above our block
  * device).
  */
@@ -41,13 +41,7 @@ struct brd_device {
struct request_queue*brd_queue;
struct gendisk  *brd_disk;
struct list_headbrd_list;
-
-   /*
-* Backing store of pages and lock to protect it. This is the contents
-* of the block device.
-*/
-   spinlock_t  brd_lock;
-   struct radix_tree_root  brd_pages;
+   struct xarray   brd_pages;
 };
 
 /*
@@ -62,17 +56,9 @@ static struct page *brd_lookup_page(struct brd_device *brd, 
sector_t sector)
 * The page lifetime is protected by the fact that we have opened the
 * device node -- brd pages will never be deleted under us, so we
 * don't need any further locking or refcounting.
-*
-* This is strictly true for the radix-tree nodes as well (ie. we
-* don't actually need the rcu_read_lock()), however that is not a
-* documented feature of the radix-tree API so it is better to be
-* safe here (we don't have total exclusion from radix tree updates
-* here, only deletes).
 */
-   rcu_read_lock();
idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
-   page = radix_tree_lookup(>brd_pages, idx);
-   rcu_read_unlock();
+   page = xa_load(>brd_pages, idx);
 
BUG_ON(page && page->index != idx);
 
@@ -87,7 +73,7 @@ static struct page *brd_lookup_page(struct brd_device *brd, 
sector_t sector)
 static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 {
pgoff_t idx;
-   struct page *page;
+   struct page *curr, *page;
gfp_t gfp_flags;
 
page = brd_lookup_page(brd, sector);
@@ -108,62 +94,40 @@ static struct page *brd_insert_page(struct brd_device 
*brd, sector_t sector)
if (!page)
return NULL;
 
-   if (radix_tree_preload(GFP_NOIO)) {
-   __free_page(page);
-   return NULL;
-   }
-
-   spin_lock(>brd_lock);
idx = sector >> PAGE_SECTORS_SHIFT;
page->index = idx;
-   if (radix_tree_insert(>brd_pages, idx, page)) {
+   curr = xa_cmpxchg(>brd_pages, idx, NULL, page, GFP_NOIO);
+   if (curr) {
__free_page(page);
-   page = radix_tree_lookup(>brd_pages, idx);
-   BUG_ON(!page);
-   BUG_ON(page->index != idx);
+   if (xa_err(curr)) {
+   page = NULL;
+   } else {
+   page = curr;
+   BUG_ON(!page);
+   BUG_ON(page->index != idx);
+   }
}
-   spin_unlock(>brd_lock);
-
-   radix_tree_preload_end();
 
return page;
 }
 
 /*
- * Free all backing store pages and radix tree. This must only be called when
+ * Free all backing store pages and xarray.  This must only be called when
  * there are no other users of the device.
  */
-#define FREE_BATCH 16
 static void brd_free_pages(struct brd_device *brd)
 {
-   unsigned long pos = 0;
-   struct page *pages[FREE_BATCH];
-   int nr_pages;
-
-   do {
-   int i;
-
-   nr_pages = radix_tree_gang_lookup(>brd_pages,
-   (void **)pages, pos, FREE_BATCH);
-
-   for (i = 0; i < nr_pages; i++) {
-   void *ret;
-
-   BUG_ON(pages[i]->index < pos);
-   pos = pages[i]->index;
-   ret = radix_tree_delete(>brd_pages, pos);
-   BUG_ON(!ret || ret != pages[i]);
-   __free_page(pages[i]);

[PATCH v6 68/99] vmalloc: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The radix tree of vmap blocks is simpler to express as an XArray.
Saves a couple of hundred bytes of text and eliminates a user of the
radix tree preload API.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 mm/vmalloc.c | 39 +--
 1 file changed, 13 insertions(+), 26 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 673942094328..b6c138633592 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -23,7 +23,7 @@
 #include 
 #include 
 #include 
-#include 
+#include 
 #include 
 #include 
 #include 
@@ -821,12 +821,11 @@ struct vmap_block {
 static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
 
 /*
- * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
+ * XArray of vmap blocks, indexed by address, to quickly find a vmap block
  * in the free path. Could get rid of this if we change the API to return a
  * "cookie" from alloc, to be passed to free. But no big deal yet.
  */
-static DEFINE_SPINLOCK(vmap_block_tree_lock);
-static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
+static DEFINE_XARRAY(vmap_block_tree);
 
 /*
  * We should probably have a fallback mechanism to allocate virtual memory
@@ -865,8 +864,8 @@ static void *new_vmap_block(unsigned int order, gfp_t 
gfp_mask)
struct vmap_block *vb;
struct vmap_area *va;
unsigned long vb_idx;
-   int node, err;
-   void *vaddr;
+   int node;
+   void *ret, *vaddr;
 
node = numa_node_id();
 
@@ -883,13 +882,6 @@ static void *new_vmap_block(unsigned int order, gfp_t 
gfp_mask)
return ERR_CAST(va);
}
 
-   err = radix_tree_preload(gfp_mask);
-   if (unlikely(err)) {
-   kfree(vb);
-   free_vmap_area(va);
-   return ERR_PTR(err);
-   }
-
vaddr = vmap_block_vaddr(va->va_start, 0);
spin_lock_init(>lock);
vb->va = va;
@@ -902,11 +894,12 @@ static void *new_vmap_block(unsigned int order, gfp_t 
gfp_mask)
INIT_LIST_HEAD(>free_list);
 
vb_idx = addr_to_vb_idx(va->va_start);
-   spin_lock(_block_tree_lock);
-   err = radix_tree_insert(_block_tree, vb_idx, vb);
-   spin_unlock(_block_tree_lock);
-   BUG_ON(err);
-   radix_tree_preload_end();
+   ret = xa_store(_block_tree, vb_idx, vb, gfp_mask);
+   if (xa_is_err(ret)) {
+   kfree(vb);
+   free_vmap_area(va);
+   return ERR_PTR(xa_err(ret));
+   }
 
vbq = _cpu_var(vmap_block_queue);
spin_lock(>lock);
@@ -923,9 +916,7 @@ static void free_vmap_block(struct vmap_block *vb)
unsigned long vb_idx;
 
vb_idx = addr_to_vb_idx(vb->va->va_start);
-   spin_lock(_block_tree_lock);
-   tmp = radix_tree_delete(_block_tree, vb_idx);
-   spin_unlock(_block_tree_lock);
+   tmp = xa_erase(_block_tree, vb_idx);
BUG_ON(tmp != vb);
 
free_vmap_area_noflush(vb->va);
@@ -1031,7 +1022,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 static void vb_free(const void *addr, unsigned long size)
 {
unsigned long offset;
-   unsigned long vb_idx;
unsigned int order;
struct vmap_block *vb;
 
@@ -1045,10 +1035,7 @@ static void vb_free(const void *addr, unsigned long size)
offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
offset >>= PAGE_SHIFT;
 
-   vb_idx = addr_to_vb_idx((unsigned long)addr);
-   rcu_read_lock();
-   vb = radix_tree_lookup(_block_tree, vb_idx);
-   rcu_read_unlock();
+   vb = xa_load(_block_tree, addr_to_vb_idx((unsigned long)addr));
BUG_ON(!vb);
 
vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 71/99] xfs: Convert pag_ici_root to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Rename pag_ici_root to pag_ici_xa and use XArray APIs instead of radix
tree APIs.  Shorter code, typechecking on tag numbers, better error
checking in xfs_reclaim_inode(), and eliminates a call to
radix_tree_preload().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/xfs/libxfs/xfs_sb.c |   2 +-
 fs/xfs/libxfs/xfs_sb.h |   2 +-
 fs/xfs/xfs_icache.c| 111 +++--
 fs/xfs/xfs_icache.h|   5 +--
 fs/xfs/xfs_inode.c |  24 ---
 fs/xfs/xfs_mount.c |   3 +-
 fs/xfs/xfs_mount.h |   3 +-
 7 files changed, 56 insertions(+), 94 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 3b0b65eb8224..8fb7c216c761 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -76,7 +76,7 @@ struct xfs_perag *
 xfs_perag_get_tag(
struct xfs_mount*mp,
xfs_agnumber_t  first,
-   int tag)
+   xa_tag_ttag)
 {
XA_STATE(xas, >m_perag_xa, first);
struct xfs_perag*pag;
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 961e6475a309..d2de90b8f39c 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -23,7 +23,7 @@
  */
 extern struct xfs_perag *xfs_perag_get(struct xfs_mount *, xfs_agnumber_t);
 extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t,
-  int tag);
+  xa_tag_t tag);
 extern voidxfs_perag_put(struct xfs_perag *pag);
 extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 65a8b91b2e70..10c76209227b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -186,7 +186,7 @@ xfs_perag_set_reclaim_tag(
 {
struct xfs_mount*mp = pag->pag_mount;
 
-   lockdep_assert_held(>pag_ici_lock);
+   lockdep_assert_held(>pag_ici_xa.xa_lock);
if (pag->pag_ici_reclaimable++)
return;
 
@@ -205,7 +205,7 @@ xfs_perag_clear_reclaim_tag(
 {
struct xfs_mount*mp = pag->pag_mount;
 
-   lockdep_assert_held(>pag_ici_lock);
+   lockdep_assert_held(>pag_ici_xa.xa_lock);
if (--pag->pag_ici_reclaimable)
return;
 
@@ -228,16 +228,16 @@ xfs_inode_set_reclaim_tag(
struct xfs_perag*pag;
 
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-   spin_lock(>pag_ici_lock);
+   xa_lock(>pag_ici_xa);
spin_lock(>i_flags_lock);
 
-   radix_tree_tag_set(>pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino),
+   __xa_set_tag(>pag_ici_xa, XFS_INO_TO_AGINO(mp, ip->i_ino),
   XFS_ICI_RECLAIM_TAG);
xfs_perag_set_reclaim_tag(pag);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
 
spin_unlock(>i_flags_lock);
-   spin_unlock(>pag_ici_lock);
+   xa_unlock(>pag_ici_xa);
xfs_perag_put(pag);
 }
 
@@ -246,7 +246,7 @@ xfs_inode_clear_reclaim_tag(
struct xfs_perag*pag,
xfs_ino_t   ino)
 {
-   radix_tree_tag_clear(>pag_ici_root,
+   __xa_clear_tag(>pag_ici_xa,
 XFS_INO_TO_AGINO(pag->pag_mount, ino),
 XFS_ICI_RECLAIM_TAG);
xfs_perag_clear_reclaim_tag(pag);
@@ -367,8 +367,8 @@ xfs_iget_cache_hit(
/*
 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
 * from stomping over us while we recycle the inode.  We can't
-* clear the radix tree reclaimable tag yet as it requires
-* pag_ici_lock to be held exclusive.
+* clear the xarray reclaimable tag yet as it requires
+* pag_ici_xa.xa_lock to be held exclusive.
 */
ip->i_flags |= XFS_IRECLAIM;
 
@@ -393,7 +393,7 @@ xfs_iget_cache_hit(
goto out_error;
}
 
-   spin_lock(>pag_ici_lock);
+   xa_lock(>pag_ici_xa);
spin_lock(>i_flags_lock);
 
/*
@@ -410,7 +410,7 @@ xfs_iget_cache_hit(
init_rwsem(>i_rwsem);
 
spin_unlock(>i_flags_lock);
-   spin_unlock(>pag_ici_lock);
+   xa_unlock(>pag_ici_xa);
} else {
/* If the VFS inode is being torn down, pause and try again. */
if (!igrab(inode)) {
@@ -471,17 +471,6 @@ xfs_iget_cache_miss(
goto out_destroy;
}
 
-   /*
-* Preload the radix tree so we can insert safely under the
-* write spinlock. Note that we cannot sleep inside the preload
-* region. Since we can be called from transaction context, don't
-* recurse into

[PATCH v6 70/99] xfs: Convert m_perag_tree to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Getting rid of the m_perag_lock lets us also get rid of the call to
radix_tree_preload().  This is a relatively naive conversion; we could
improve performance over the radix tree implementation by passing around
xa_state pointers instead of indices, possibly at the expense of extending
rcu_read_lock() periods.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/xfs/libxfs/xfs_sb.c |  9 -
 fs/xfs/xfs_icache.c| 35 +--
 fs/xfs/xfs_icache.h|  6 +++---
 fs/xfs/xfs_mount.c | 19 ---
 fs/xfs/xfs_mount.h |  3 +--
 5 files changed, 21 insertions(+), 51 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 9b5aae2bcc0b..3b0b65eb8224 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -59,7 +59,7 @@ xfs_perag_get(
int ref = 0;
 
rcu_read_lock();
-   pag = radix_tree_lookup(>m_perag_tree, agno);
+   pag = xa_load(>m_perag_xa, agno);
if (pag) {
ASSERT(atomic_read(>pag_ref) >= 0);
ref = atomic_inc_return(>pag_ref);
@@ -78,14 +78,13 @@ xfs_perag_get_tag(
xfs_agnumber_t  first,
int tag)
 {
+   XA_STATE(xas, >m_perag_xa, first);
struct xfs_perag*pag;
-   int found;
int ref;
 
rcu_read_lock();
-   found = radix_tree_gang_lookup_tag(>m_perag_tree,
-   (void **), first, 1, tag);
-   if (found <= 0) {
+   pag = xas_find_tag(, ULONG_MAX, tag);
+   if (!pag) {
rcu_read_unlock();
return NULL;
}
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 3861d61fb265..65a8b91b2e70 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -156,13 +156,10 @@ static void
 xfs_reclaim_work_queue(
struct xfs_mount*mp)
 {
-
-   rcu_read_lock();
-   if (radix_tree_tagged(>m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
+   if (xa_tagged(>m_perag_xa, XFS_ICI_RECLAIM_TAG)) {
queue_delayed_work(mp->m_reclaim_workqueue, >m_reclaim_work,
msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
}
-   rcu_read_unlock();
 }
 
 /*
@@ -194,10 +191,7 @@ xfs_perag_set_reclaim_tag(
return;
 
/* propagate the reclaim tag up into the perag radix tree */
-   spin_lock(>m_perag_lock);
-   radix_tree_tag_set(>m_perag_tree, pag->pag_agno,
-  XFS_ICI_RECLAIM_TAG);
-   spin_unlock(>m_perag_lock);
+   xa_set_tag(>m_perag_xa, pag->pag_agno, XFS_ICI_RECLAIM_TAG);
 
/* schedule periodic background inode reclaim */
xfs_reclaim_work_queue(mp);
@@ -216,10 +210,7 @@ xfs_perag_clear_reclaim_tag(
return;
 
/* clear the reclaim tag from the perag radix tree */
-   spin_lock(>m_perag_lock);
-   radix_tree_tag_clear(>m_perag_tree, pag->pag_agno,
-XFS_ICI_RECLAIM_TAG);
-   spin_unlock(>m_perag_lock);
+   xa_clear_tag(>m_perag_xa, pag->pag_agno, XFS_ICI_RECLAIM_TAG);
trace_xfs_perag_clear_reclaim(mp, pag->pag_agno, -1, _RET_IP_);
 }
 
@@ -847,12 +838,10 @@ void
 xfs_queue_eofblocks(
struct xfs_mount *mp)
 {
-   rcu_read_lock();
-   if (radix_tree_tagged(>m_perag_tree, XFS_ICI_EOFBLOCKS_TAG))
+   if (xa_tagged(>m_perag_xa, XFS_ICI_EOFBLOCKS_TAG))
queue_delayed_work(mp->m_eofblocks_workqueue,
   >m_eofblocks_work,
   msecs_to_jiffies(xfs_eofb_secs * 1000));
-   rcu_read_unlock();
 }
 
 void
@@ -874,12 +863,10 @@ void
 xfs_queue_cowblocks(
struct xfs_mount *mp)
 {
-   rcu_read_lock();
-   if (radix_tree_tagged(>m_perag_tree, XFS_ICI_COWBLOCKS_TAG))
+   if (xa_tagged(>m_perag_xa, XFS_ICI_COWBLOCKS_TAG))
queue_delayed_work(mp->m_eofblocks_workqueue,
   >m_cowblocks_work,
   msecs_to_jiffies(xfs_cowb_secs * 1000));
-   rcu_read_unlock();
 }
 
 void
@@ -1557,7 +1544,7 @@ __xfs_inode_set_blocks_tag(
void(*execute)(struct xfs_mount *mp),
void(*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno,
  int error, unsigned long caller_ip),
-   int tag)
+   xa_tag_ttag)
 {
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
@@ -1581,11 +1568,9 @@ __xfs_inode_set_blocks_tag(
   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino), tag);
if (!tagged) {
/* propagate the eofblocks tag up into the perag radix tree */
-   

[PATCH v6 74/99] usb: Convert xhci-mem to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The XArray API is a slightly better fit for xhci_insert_segment_mapping()
than the radix tree API was.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/usb/host/xhci-mem.c | 68 +++--
 drivers/usb/host/xhci.h |  6 ++--
 2 files changed, 32 insertions(+), 42 deletions(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 3a29b32a3bd0..a2e15a9abc30 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -149,70 +149,60 @@ static void xhci_link_rings(struct xhci_hcd *xhci, struct 
xhci_ring *ring,
 }
 
 /*
- * We need a radix tree for mapping physical addresses of TRBs to which stream
- * ID they belong to.  We need to do this because the host controller won't 
tell
+ * We need to map physical addresses of TRBs to the stream ID they belong to.
+ * We need to do this because the host controller won't tell
  * us which stream ring the TRB came from.  We could store the stream ID in an
  * event data TRB, but that doesn't help us for the cancellation case, since 
the
  * endpoint may stop before it reaches that event data TRB.
  *
- * The radix tree maps the upper portion of the TRB DMA address to a ring
+ * The xarray maps the upper portion of the TRB DMA address to a ring
  * segment that has the same upper portion of DMA addresses.  For example, say 
I
  * have segments of size 1KB, that are always 1KB aligned.  A segment may
  * start at 0x10c91000 and end at 0x10c913f0.  If I use the upper 10 bits, the
- * key to the stream ID is 0x43244.  I can use the DMA address of the TRB to
- * pass the radix tree a key to get the right stream ID:
+ * index of the stream ID is 0x43244.  I can use the DMA address of the TRB as
+ * the xarray index to get the right stream ID:
  *
  * 0x10c90fff >> 10 = 0x43243
  * 0x10c912c0 >> 10 = 0x43244
  * 0x10c91400 >> 10 = 0x43245
  *
  * Obviously, only those TRBs with DMA addresses that are within the segment
- * will make the radix tree return the stream ID for that ring.
+ * will make the xarray return the stream ID for that ring.
  *
- * Caveats for the radix tree:
+ * Caveats for the xarray:
  *
- * The radix tree uses an unsigned long as a key pair.  On 32-bit systems, an
+ * The xarray uses an unsigned long for the index.  On 32-bit systems, an
  * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be
  * 64-bits.  Since we only request 32-bit DMA addresses, we can use that as the
- * key on 32-bit or 64-bit systems (it would also be fine if we asked for 
64-bit
- * PCI DMA addresses on a 64-bit system).  There might be a problem on 32-bit
- * extended systems (where the DMA address can be bigger than 32-bits),
+ * index on 32-bit or 64-bit systems (it would also be fine if we asked for
+ * 64-bit PCI DMA addresses on a 64-bit system).  There might be a problem on
+ * 32-bit extended systems (where the DMA address can be bigger than 32-bits),
  * if we allow the PCI dma mask to be bigger than 32-bits.  So don't do that.
  */
-static int xhci_insert_segment_mapping(struct radix_tree_root *trb_address_map,
+
+static unsigned long trb_index(dma_addr_t dma)
+{
+   return (unsigned long)(dma >> TRB_SEGMENT_SHIFT);
+}
+
+static int xhci_insert_segment_mapping(struct xarray *trb_address_map,
struct xhci_ring *ring,
struct xhci_segment *seg,
-   gfp_t mem_flags)
+   gfp_t gfp)
 {
-   unsigned long key;
-   int ret;
-
-   key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
/* Skip any segments that were already added. */
-   if (radix_tree_lookup(trb_address_map, key))
-   return 0;
-
-   ret = radix_tree_maybe_preload(mem_flags);
-   if (ret)
-   return ret;
-   ret = radix_tree_insert(trb_address_map,
-   key, ring);
-   radix_tree_preload_end();
-   return ret;
+   return xa_err(xa_cmpxchg(trb_address_map, trb_index(seg->dma), NULL,
+   ring, gfp));
 }
 
-static void xhci_remove_segment_mapping(struct radix_tree_root 
*trb_address_map,
+static void xhci_remove_segment_mapping(struct xarray *trb_address_map,
struct xhci_segment *seg)
 {
-   unsigned long key;
-
-   key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
-   if (radix_tree_lookup(trb_address_map, key))
-   radix_tree_delete(trb_address_map, key);
+   xa_erase(trb_address_map, trb_index(seg->dma));
 }
 
 static int xhci_update_stream_segment_mapping(
-   struct radix_tree_root *trb_address_map,
+   struct xarray *trb_address_map,
struct xhci_ring *ring,
struct xhci_segment *first_seg,
struct xhci_segment *last_seg,
@@ -574,8 +564,8 @@ stru

[PATCH v6 73/99] xfs: Convert mru cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This eliminates a call to radix_tree_preload().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/xfs/xfs_mru_cache.c | 72 +++---
 1 file changed, 33 insertions(+), 39 deletions(-)

diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index f8a674d7f092..2179bede5396 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -101,10 +101,9 @@
  * an infinite loop in the code.
  */
 struct xfs_mru_cache {
-   struct radix_tree_root  store; /* Core storage data structure.  */
+   struct xarray   store; /* Core storage data structure.  */
struct list_head*lists;/* Array of lists, one per grp.  */
struct list_headreap_list; /* Elements overdue for reaping. */
-   spinlock_t  lock;  /* Lock to protect this struct.  */
unsigned intgrp_count; /* Number of discrete groups.*/
unsigned intgrp_time;  /* Time period spanned by grps.  */
unsigned intlru_grp;   /* Group containing time zero.   */
@@ -232,22 +231,21 @@ _xfs_mru_cache_list_insert(
  * data store, removing it from the reap list, calling the client's free
  * function and deleting the element from the element zone.
  *
- * We get called holding the mru->lock, which we drop and then reacquire.
- * Sparse need special help with this to tell it we know what we are doing.
+ * We get called holding the mru->store lock, which we drop and then reacquire.
+ * Sparse needs special help with this to tell it we know what we are doing.
  */
 STATIC void
 _xfs_mru_cache_clear_reap_list(
struct xfs_mru_cache*mru)
-   __releases(mru->lock) __acquires(mru->lock)
+   __releases(mru->store) __acquires(mru->store)
 {
struct xfs_mru_cache_elem *elem, *next;
struct list_headtmp;
 
INIT_LIST_HEAD();
list_for_each_entry_safe(elem, next, >reap_list, list_node) {
-
/* Remove the element from the data store. */
-   radix_tree_delete(>store, elem->key);
+   __xa_erase(>store, elem->key);
 
/*
 * remove to temp list so it can be freed without
@@ -255,14 +253,14 @@ _xfs_mru_cache_clear_reap_list(
 */
list_move(>list_node, );
}
-   spin_unlock(>lock);
+   xa_unlock(>store);
 
list_for_each_entry_safe(elem, next, , list_node) {
list_del_init(>list_node);
mru->free_func(elem);
}
 
-   spin_lock(>lock);
+   xa_lock(>store);
 }
 
 /*
@@ -284,7 +282,7 @@ _xfs_mru_cache_reap(
if (!mru || !mru->lists)
return;
 
-   spin_lock(>lock);
+   xa_lock(>store);
next = _xfs_mru_cache_migrate(mru, jiffies);
_xfs_mru_cache_clear_reap_list(mru);
 
@@ -298,7 +296,7 @@ _xfs_mru_cache_reap(
queue_delayed_work(xfs_mru_reap_wq, >work, next);
}
 
-   spin_unlock(>lock);
+   xa_unlock(>store);
 }
 
 int
@@ -358,13 +356,8 @@ xfs_mru_cache_create(
for (grp = 0; grp < mru->grp_count; grp++)
INIT_LIST_HEAD(mru->lists + grp);
 
-   /*
-* We use GFP_KERNEL radix tree preload and do inserts under a
-* spinlock so GFP_ATOMIC is appropriate for the radix tree itself.
-*/
-   INIT_RADIX_TREE(>store, GFP_ATOMIC);
+   xa_init(>store);
INIT_LIST_HEAD(>reap_list);
-   spin_lock_init(>lock);
INIT_DELAYED_WORK(>work, _xfs_mru_cache_reap);
 
mru->grp_time  = grp_time;
@@ -394,17 +387,17 @@ xfs_mru_cache_flush(
if (!mru || !mru->lists)
return;
 
-   spin_lock(>lock);
+   xa_lock(>store);
if (mru->queued) {
-   spin_unlock(>lock);
+   xa_unlock(>store);
cancel_delayed_work_sync(>work);
-   spin_lock(>lock);
+   xa_lock(>store);
}
 
_xfs_mru_cache_migrate(mru, jiffies + mru->grp_count * mru->grp_time);
_xfs_mru_cache_clear_reap_list(mru);
 
-   spin_unlock(>lock);
+   xa_unlock(>store);
 }
 
 void
@@ -431,24 +424,24 @@ xfs_mru_cache_insert(
unsigned long   key,
struct xfs_mru_cache_elem *elem)
 {
+   XA_STATE(xas, >store, key);
int error;
 
ASSERT(mru && mru->lists);
if (!mru || !mru->lists)
return -EINVAL;
 
-   if (radix_tree_preload(GFP_NOFS))
-   return -ENOMEM;
-
INIT_LIST_HEAD(>list_node);
elem->key = key;
 
-   spin_lock(>lock);
-   error = radix_tree_insert(>store, key, elem);
-   radix_tree_preload_end(

[PATCH v6 72/99] xfs: Convert xfs dquot to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a pretty straight-forward conversion.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/xfs/xfs_dquot.c | 38 +-
 fs/xfs/xfs_qm.c| 36 ++--
 fs/xfs/xfs_qm.h| 18 +-
 3 files changed, 48 insertions(+), 44 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index e2a466df5dd1..c6832db23ca8 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -44,7 +44,7 @@
  * Lock order:
  *
  * ip->i_lock
- *   qi->qi_tree_lock
+ *   qi->qi_xa_lock
  * dquot->q_qlock (xfs_dqlock() and friends)
  *   dquot->q_flush (xfs_dqflock() and friends)
  *   qi->qi_lru_lock
@@ -752,8 +752,8 @@ xfs_qm_dqget(
xfs_dquot_t **O_dqpp) /* OUT : locked incore dquot */
 {
struct xfs_quotainfo*qi = mp->m_quotainfo;
-   struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
-   struct xfs_dquot*dqp;
+   struct xarray   *xa = xfs_dquot_xa(qi, type);
+   struct xfs_dquot*dqp, *duplicate;
int error;
 
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -772,23 +772,24 @@ xfs_qm_dqget(
}
 
 restart:
-   mutex_lock(>qi_tree_lock);
-   dqp = radix_tree_lookup(tree, id);
+   mutex_lock(>qi_xa_lock);
+   dqp = xa_load(xa, id);
+found:
if (dqp) {
xfs_dqlock(dqp);
if (dqp->dq_flags & XFS_DQ_FREEING) {
xfs_dqunlock(dqp);
-   mutex_unlock(>qi_tree_lock);
+   mutex_unlock(>qi_xa_lock);
trace_xfs_dqget_freeing(dqp);
delay(1);
goto restart;
}
 
-   /* uninit / unused quota found in radix tree, keep looking  */
+   /* uninit / unused quota found, keep looking  */
if (flags & XFS_QMOPT_DQNEXT) {
if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
xfs_dqunlock(dqp);
-   mutex_unlock(>qi_tree_lock);
+   mutex_unlock(>qi_xa_lock);
error = xfs_dq_get_next_id(mp, type, );
if (error)
return error;
@@ -797,14 +798,14 @@ xfs_qm_dqget(
}
 
dqp->q_nrefs++;
-   mutex_unlock(>qi_tree_lock);
+   mutex_unlock(>qi_xa_lock);
 
trace_xfs_dqget_hit(dqp);
XFS_STATS_INC(mp, xs_qm_dqcachehits);
*O_dqpp = dqp;
return 0;
}
-   mutex_unlock(>qi_tree_lock);
+   mutex_unlock(>qi_xa_lock);
XFS_STATS_INC(mp, xs_qm_dqcachemisses);
 
/*
@@ -854,20 +855,23 @@ xfs_qm_dqget(
}
}
 
-   mutex_lock(>qi_tree_lock);
-   error = radix_tree_insert(tree, id, dqp);
-   if (unlikely(error)) {
-   WARN_ON(error != -EEXIST);
+   mutex_lock(>qi_xa_lock);
+   duplicate = xa_cmpxchg(xa, id, NULL, dqp, GFP_NOFS);
+   if (unlikely(duplicate)) {
+   if (xa_is_err(duplicate)) {
+   mutex_unlock(>qi_xa_lock);
+   return xa_err(duplicate);
+   }
 
/*
 * Duplicate found. Just throw away the new dquot and start
 * over.
 */
-   mutex_unlock(>qi_tree_lock);
trace_xfs_dqget_dup(dqp);
xfs_qm_dqdestroy(dqp);
XFS_STATS_INC(mp, xs_qm_dquot_dups);
-   goto restart;
+   dqp = duplicate;
+   goto found;
}
 
/*
@@ -877,7 +881,7 @@ xfs_qm_dqget(
dqp->q_nrefs = 1;
 
qi->qi_dquots++;
-   mutex_unlock(>qi_tree_lock);
+   mutex_unlock(>qi_xa_lock);
 
/* If we are asked to find next active id, keep looking */
if (flags & XFS_QMOPT_DQNEXT) {
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b897b11afb2c..000b207762d6 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -67,7 +67,7 @@ xfs_qm_dquot_walk(
void*data)
 {
struct xfs_quotainfo*qi = mp->m_quotainfo;
-   struct radix_tree_root  *tree = xfs_dquot_tree(qi, type);
+   struct xarray   *xa = xfs_dquot_xa(qi, type);
uint32_tnext_index;
int last_error = 0;
int skipped;
@@ -83,11 +83,11 @@ xfs_qm_dquot_walk(
int error = 0;
int i;
 
-   mutex_lock(>qi_tree_lock);
-   nr_found = radix_tree_gang_lookup(tree, (void **)batch,
-   

[PATCH v6 75/99] md: Convert raid5-cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is the first user of the radix tree I've converted which was
storing numbers rather than pointers.  I'm fairly pleased with how
well it came out.  There's less boiler-plate involved than there was
with the radix tree, so that's a win.  It does use the advanced API,
and I think that's a signal that there needs to be a separate API for
using the XArray for only integers.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/md/raid5-cache.c | 119 ---
 1 file changed, 40 insertions(+), 79 deletions(-)

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 39f31f07ffe9..2c8ad0ed9b48 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -158,9 +158,8 @@ struct r5l_log {
/* to disable write back during in degraded mode */
struct work_struct disable_writeback_work;
 
-   /* to for chunk_aligned_read in writeback mode, details below */
-   spinlock_t tree_lock;
-   struct radix_tree_root big_stripe_tree;
+   /* for chunk_aligned_read in writeback mode, details below */
+   struct xarray big_stripe;
 };
 
 /*
@@ -170,9 +169,8 @@ struct r5l_log {
  * chunk contains 64 4kB-page, so this chunk contain 64 stripes). For
  * chunk_aligned_read, these stripes are grouped into one "big_stripe".
  * For each big_stripe, we count how many stripes of this big_stripe
- * are in the write back cache. These data are tracked in a radix tree
- * (big_stripe_tree). We use radix_tree item pointer as the counter.
- * r5c_tree_index() is used to calculate keys for the radix tree.
+ * are in the write back cache. This counter is tracked in an xarray
+ * (big_stripe). r5c_index() is used to calculate the index.
  *
  * chunk_aligned_read() calls r5c_big_stripe_cached() to look up
  * big_stripe of each chunk in the tree. If this big_stripe is in the
@@ -180,9 +178,9 @@ struct r5l_log {
  * rcu_read_lock().
  *
  * It is necessary to remember whether a stripe is counted in
- * big_stripe_tree. Instead of adding new flag, we reuses existing flags:
+ * big_stripe. Instead of adding new flag, we reuses existing flags:
  * STRIPE_R5C_PARTIAL_STRIPE and STRIPE_R5C_FULL_STRIPE. If either of these
- * two flags are set, the stripe is counted in big_stripe_tree. This
+ * two flags are set, the stripe is counted in big_stripe. This
  * requires moving set_bit(STRIPE_R5C_PARTIAL_STRIPE) to
  * r5c_try_caching_write(); and moving clear_bit of
  * STRIPE_R5C_PARTIAL_STRIPE and STRIPE_R5C_FULL_STRIPE to
@@ -190,23 +188,13 @@ struct r5l_log {
  */
 
 /*
- * radix tree requests lowest 2 bits of data pointer to be 2b'00.
- * So it is necessary to left shift the counter by 2 bits before using it
- * as data pointer of the tree.
- */
-#define R5C_RADIX_COUNT_SHIFT 2
-
-/*
- * calculate key for big_stripe_tree
+ * calculate key for big_stripe
  *
  * sect: align_bi->bi_iter.bi_sector or sh->sector
  */
-static inline sector_t r5c_tree_index(struct r5conf *conf,
- sector_t sect)
+static inline sector_t r5c_index(struct r5conf *conf, sector_t sect)
 {
-   sector_t offset;
-
-   offset = sector_div(sect, conf->chunk_sectors);
+   sector_div(sect, conf->chunk_sectors);
return sect;
 }
 
@@ -2646,10 +2634,6 @@ int r5c_try_caching_write(struct r5conf *conf,
int i;
struct r5dev *dev;
int to_cache = 0;
-   void **pslot;
-   sector_t tree_index;
-   int ret;
-   uintptr_t refcount;
 
BUG_ON(!r5c_is_writeback(log));
 
@@ -2697,39 +2681,29 @@ int r5c_try_caching_write(struct r5conf *conf,
}
}
 
-   /* if the stripe is not counted in big_stripe_tree, add it now */
+   /* if the stripe is not counted in big_stripe, add it now */
if (!test_bit(STRIPE_R5C_PARTIAL_STRIPE, >state) &&
!test_bit(STRIPE_R5C_FULL_STRIPE, >state)) {
-   tree_index = r5c_tree_index(conf, sh->sector);
-   spin_lock(>tree_lock);
-   pslot = radix_tree_lookup_slot(>big_stripe_tree,
-  tree_index);
-   if (pslot) {
-   refcount = (uintptr_t)radix_tree_deref_slot_protected(
-   pslot, >tree_lock) >>
-   R5C_RADIX_COUNT_SHIFT;
-   radix_tree_replace_slot(
-   >big_stripe_tree, pslot,
-   (void *)((refcount + 1) << 
R5C_RADIX_COUNT_SHIFT));
-   } else {
-   /*
-* this radix_tree_insert can fail safely, so no
-* need to call radix_tree_preload()
-*/
-   ret = radix_tree_insert(
-   >big_stripe_tree, t

[PATCH v6 76/99] irqdomain: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

In a non-critical path, irqdomain wants to know how many entries are
stored in the xarray, so add xa_count().  This is a pretty straightforward
conversion; mostly just removing now-redundant locking.  The only thing
of note is just how much simpler irq_domain_fix_revmap() becomes.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
Acked-by: Marc Zyngier <marc.zyng...@arm.com>
---
 include/linux/irqdomain.h | 10 --
 include/linux/xarray.h|  1 +
 kernel/irq/irqdomain.c| 39 ++-
 lib/xarray.c  | 25 +
 4 files changed, 40 insertions(+), 35 deletions(-)

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 48c7e86bb556..6c69d9141709 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -33,8 +33,7 @@
 #include 
 #include 
 #include 
-#include 
-#include 
+#include 
 
 struct device_node;
 struct irq_domain;
@@ -151,7 +150,7 @@ struct irq_domain_chip_generic;
  * @revmap_direct_max_irq: The largest hwirq that can be set for controllers 
that
  * support direct mapping
  * @revmap_size: Size of the linear map table @linear_revmap[]
- * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map
+ * @revmap_array: hwirqs that don't fit in the linear map
  * @linear_revmap: Linear table of hwirq->virq reverse mappings
  */
 struct irq_domain {
@@ -177,8 +176,7 @@ struct irq_domain {
irq_hw_number_t hwirq_max;
unsigned int revmap_direct_max_irq;
unsigned int revmap_size;
-   struct radix_tree_root revmap_tree;
-   struct mutex revmap_tree_mutex;
+   struct xarray revmap_array;
unsigned int linear_revmap[];
 };
 
@@ -378,7 +376,7 @@ extern void irq_dispose_mapping(unsigned int virq);
  * This is a fast path alternative to irq_find_mapping() that can be
  * called directly by irq controller code to save a handful of
  * instructions. It is always safe to call, but won't find irqs mapped
- * using the radix tree.
+ * using the xarray.
  */
 static inline unsigned int irq_linear_revmap(struct irq_domain *domain,
 irq_hw_number_t hwirq)
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index c3f7405c5517..892288fe9595 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -269,6 +269,7 @@ void *xa_find_after(struct xarray *xa, unsigned long *index,
unsigned long max, xa_tag_t) __attribute__((nonnull(2)));
 unsigned int xa_extract(struct xarray *, void **dst, unsigned long start,
unsigned long max, unsigned int n, xa_tag_t);
+unsigned long xa_count(struct xarray *);
 void xa_destroy(struct xarray *);
 
 /**
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 62068ad46930..d6da3a8eadd2 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
 /**
  * __irq_domain_add() - Allocate a new irq_domain data structure
  * @fwnode: firmware node for the interrupt controller
- * @size: Size of linear map; 0 for radix mapping only
+ * @size: Size of linear map; 0 for xarray mapping only
  * @hwirq_max: Maximum number of interrupts supported by controller
  * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
  *  direct mapping
@@ -209,8 +209,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle 
*fwnode, int size,
of_node_get(of_node);
 
/* Fill structure */
-   INIT_RADIX_TREE(>revmap_tree, GFP_KERNEL);
-   mutex_init(>revmap_tree_mutex);
+   xa_init(>revmap_array);
domain->ops = ops;
domain->host_data = host_data;
domain->hwirq_max = hwirq_max;
@@ -241,7 +240,7 @@ void irq_domain_remove(struct irq_domain *domain)
mutex_lock(_domain_mutex);
debugfs_remove_domain_dir(domain);
 
-   WARN_ON(!radix_tree_empty(>revmap_tree));
+   WARN_ON(!xa_empty(>revmap_array));
 
list_del(>link);
 
@@ -462,9 +461,7 @@ static void irq_domain_clear_mapping(struct irq_domain 
*domain,
if (hwirq < domain->revmap_size) {
domain->linear_revmap[hwirq] = 0;
} else {
-   mutex_lock(>revmap_tree_mutex);
-   radix_tree_delete(>revmap_tree, hwirq);
-   mutex_unlock(>revmap_tree_mutex);
+   xa_erase(>revmap_array, hwirq);
}
 }
 
@@ -475,9 +472,7 @@ static void irq_domain_set_mapping(struct irq_domain 
*domain,
if (hwirq < domain->revmap_size) {
domain->linear_revmap[hwirq] = irq_data->irq;
} else {
-   mutex_lock(>revmap_tree_mutex);
-   radix_tree_insert(>revmap_tree, hwirq, irq_data);
-   mutex_unlock(>revmap_tree_mutex);
+   xa_store(>rev

[PATCH v6 77/99] fscache: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Removes another user of radix_tree_preload().

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/fscache/cookie.c |   6 +-
 fs/fscache/internal.h   |   2 +-
 fs/fscache/object.c |   2 +-
 fs/fscache/page.c   | 152 +---
 fs/fscache/stats.c  |   6 +-
 include/linux/fscache.h |   8 +--
 6 files changed, 76 insertions(+), 100 deletions(-)

diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index e9054e0c1a49..6d45134d609e 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -109,9 +109,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
cookie->netfs_data  = netfs_data;
cookie->flags   = (1 << FSCACHE_COOKIE_NO_DATA_YET);
 
-   /* radix tree insertion won't use the preallocation pool unless it's
-* told it may not wait */
-   INIT_RADIX_TREE(>stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+   xa_init(>stores);
 
switch (cookie->def->type) {
case FSCACHE_COOKIE_TYPE_INDEX:
@@ -608,7 +606,7 @@ void __fscache_relinquish_cookie(struct fscache_cookie 
*cookie, bool retire)
/* Clear pointers back to the netfs */
cookie->netfs_data  = NULL;
cookie->def = NULL;
-   BUG_ON(!radix_tree_empty(>stores));
+   BUG_ON(!xa_empty(>stores));
 
if (cookie->parent) {
ASSERTCMP(atomic_read(>parent->usage), >, 0);
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 0ff4b49a0037..468d9bd7f8c3 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -200,7 +200,7 @@ extern atomic_t fscache_n_stores_oom;
 extern atomic_t fscache_n_store_ops;
 extern atomic_t fscache_n_store_calls;
 extern atomic_t fscache_n_store_pages;
-extern atomic_t fscache_n_store_radix_deletes;
+extern atomic_t fscache_n_store_xarray_deletes;
 extern atomic_t fscache_n_store_pages_over_limit;
 
 extern atomic_t fscache_n_store_vmscan_not_storing;
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index aa0e71f02c33..ed165736a358 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -956,7 +956,7 @@ static const struct fscache_state 
*_fscache_invalidate_object(struct fscache_obj
 * retire the object instead.
 */
if (!fscache_use_cookie(object)) {
-   ASSERT(radix_tree_empty(>cookie->stores));
+   ASSERT(xa_empty(>cookie->stores));
set_bit(FSCACHE_OBJECT_RETIRED, >flags);
_leave(" [no cookie]");
return transit_to(KILL_OBJECT);
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 961029e04027..315e2745f822 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -22,13 +22,7 @@
  */
 bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page 
*page)
 {
-   void *val;
-
-   rcu_read_lock();
-   val = radix_tree_lookup(>stores, page->index);
-   rcu_read_unlock();
-
-   return val != NULL;
+   return xa_load(>stores, page->index) != NULL;
 }
 EXPORT_SYMBOL(__fscache_check_page_write);
 
@@ -64,15 +58,15 @@ bool __fscache_maybe_release_page(struct fscache_cookie 
*cookie,
  struct page *page,
  gfp_t gfp)
 {
+   XA_STATE(xas, >stores, page->index);
struct page *xpage;
-   void *val;
 
_enter("%p,%p,%x", cookie, page, gfp);
 
 try_again:
rcu_read_lock();
-   val = radix_tree_lookup(>stores, page->index);
-   if (!val) {
+   xpage = xas_load();
+   if (!xpage) {
rcu_read_unlock();
fscache_stat(_n_store_vmscan_not_storing);
__fscache_uncache_page(cookie, page);
@@ -81,31 +75,32 @@ bool __fscache_maybe_release_page(struct fscache_cookie 
*cookie,
 
/* see if the page is actually undergoing storage - if so we can't get
 * rid of it till the cache has finished with it */
-   if (radix_tree_tag_get(>stores, page->index,
-  FSCACHE_COOKIE_STORING_TAG)) {
+   if (xas_get_tag(, FSCACHE_COOKIE_STORING_TAG)) {
rcu_read_unlock();
+   xas_retry(, XA_RETRY_ENTRY);
goto page_busy;
}
 
/* the page is pending storage, so we attempt to cancel the store and
 * discard the store request so that the page can be reclaimed */
-   spin_lock(>stores_lock);
+   xas_retry(, XA_RETRY_ENTRY);
+   xas_lock();
rcu_read_unlock();
 
-   if (radix_tree_tag_get(>stores, page->index,
-  FSCACHE_COOKIE_STORING_TAG)) {
+   xpage = xas_load();
+   if (xas_get_tag(, FSCACHE_COOKIE_STORING_TAG)) {
/* the page started to undergo storage whilst we were looking,
 *

[PATCH v6 78/99] sh: intc: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The radix tree was being protected by a raw spinlock.  I believe that
was not necessary, and the new internal regular spinlock will be
adequate for this array.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/sh/intc/core.c  |  9 ++
 drivers/sh/intc/internals.h |  5 ++--
 drivers/sh/intc/virq.c  | 72 +
 3 files changed, 25 insertions(+), 61 deletions(-)

diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index 8e72bcbd3d6d..356a423d9dcb 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -30,7 +30,6 @@
 #include 
 #include 
 #include 
-#include 
 #include 
 #include 
 #include "internals.h"
@@ -78,11 +77,8 @@ static void __init intc_register_irq(struct intc_desc *desc,
struct intc_handle_int *hp;
struct irq_data *irq_data;
unsigned int data[2], primary;
-   unsigned long flags;
 
-   raw_spin_lock_irqsave(_big_lock, flags);
-   radix_tree_insert(>tree, enum_id, intc_irq_xlate_get(irq));
-   raw_spin_unlock_irqrestore(_big_lock, flags);
+   xa_store(>array, enum_id, intc_irq_xlate_get(irq), GFP_ATOMIC);
 
/*
 * Prefer single interrupt source bitmap over other combinations:
@@ -196,8 +192,7 @@ int __init register_intc_controller(struct intc_desc *desc)
INIT_LIST_HEAD(>list);
list_add_tail(>list, _list);
 
-   raw_spin_lock_init(>lock);
-   INIT_RADIX_TREE(>tree, GFP_ATOMIC);
+   xa_init(>array);
 
d->index = nr_intc_controllers;
 
diff --git a/drivers/sh/intc/internals.h b/drivers/sh/intc/internals.h
index fa73c173b56a..9b6fd07e99a6 100644
--- a/drivers/sh/intc/internals.h
+++ b/drivers/sh/intc/internals.h
@@ -5,7 +5,7 @@
 #include 
 #include 
 #include 
-#include 
+#include 
 #include 
 
 #define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \
@@ -54,8 +54,7 @@ struct intc_subgroup_entry {
 struct intc_desc_int {
struct list_head list;
struct device dev;
-   struct radix_tree_root tree;
-   raw_spinlock_t lock;
+   struct xarray array;
unsigned int index;
unsigned long *reg;
 #ifdef CONFIG_SMP
diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c
index a638c3048207..801c9c8b7556 100644
--- a/drivers/sh/intc/virq.c
+++ b/drivers/sh/intc/virq.c
@@ -12,7 +12,6 @@
 #include 
 #include 
 #include 
-#include 
 #include 
 #include 
 #include "internals.h"
@@ -27,10 +26,7 @@ struct intc_virq_list {
 #define for_each_virq(entry, head) \
for (entry = head; entry; entry = entry->next)
 
-/*
- * Tags for the radix tree
- */
-#define INTC_TAG_VIRQ_NEEDS_ALLOC  0
+#define INTC_TAG_VIRQ_NEEDS_ALLOC  XA_TAG_0
 
 void intc_irq_xlate_set(unsigned int irq, intc_enum id, struct intc_desc_int 
*d)
 {
@@ -54,23 +50,18 @@ int intc_irq_lookup(const char *chipname, intc_enum enum_id)
int irq = -1;
 
list_for_each_entry(d, _list, list) {
-   int tagged;
-
if (strcmp(d->chip.name, chipname) != 0)
continue;
 
/*
 * Catch early lookups for subgroup VIRQs that have not
-* yet been allocated an IRQ. This already includes a
-* fast-path out if the tree is untagged, so there is no
-* need to explicitly test the root tree.
+* yet been allocated an IRQ.
 */
-   tagged = radix_tree_tag_get(>tree, enum_id,
-   INTC_TAG_VIRQ_NEEDS_ALLOC);
-   if (unlikely(tagged))
+   if (unlikely(xa_get_tag(>array, enum_id,
+   INTC_TAG_VIRQ_NEEDS_ALLOC)))
break;
 
-   ptr = radix_tree_lookup(>tree, enum_id);
+   ptr = xa_load(>array, enum_id);
if (ptr) {
irq = ptr - intc_irq_xlate;
break;
@@ -148,22 +139,16 @@ static void __init intc_subgroup_init_one(struct 
intc_desc *desc,
 {
struct intc_map_entry *mapped;
unsigned int pirq;
-   unsigned long flags;
int i;
 
-   mapped = radix_tree_lookup(>tree, subgroup->parent_id);
-   if (!mapped) {
-   WARN_ON(1);
+   mapped = xa_load(>array, subgroup->parent_id);
+   if (WARN_ON(!mapped))
return;
-   }
 
pirq = mapped - intc_irq_xlate;
 
-   raw_spin_lock_irqsave(>lock, flags);
-
for (i = 0; i < ARRAY_SIZE(subgroup->enum_ids); i++) {
struct intc_subgroup_entry *entry;
-   int err;
 
if (!subgroup->enum_ids[i])
continue;
@@ -176,15 +161,14 @@ static void __init intc_subgroup_init_one(struct 
intc_desc *desc,
entry-&

[PATCH v6 79/99] blk-cgroup: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This call to radix_tree_preload is awkward.  At the point of allocation,
we're under not only a local lock, but also under the queue lock.  So we
can't back out, drop the lock and retry the allocation.  Replace this
preload call with a call to xa_reserve() which will ensure the memory is
allocated.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 block/bfq-cgroup.c |  4 ++--
 block/blk-cgroup.c | 52 ++
 block/cfq-iosched.c|  4 ++--
 include/linux/blk-cgroup.h |  5 ++---
 4 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index da1525ec4c87..0648aaa6498b 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -860,7 +860,7 @@ static int bfq_io_set_weight_legacy(struct 
cgroup_subsys_state *css,
return ret;
 
ret = 0;
-   spin_lock_irq(>lock);
+   xa_lock_irq(>blkg_array);
bfqgd->weight = (unsigned short)val;
hlist_for_each_entry(blkg, >blkg_list, blkcg_node) {
struct bfq_group *bfqg = blkg_to_bfqg(blkg);
@@ -894,7 +894,7 @@ static int bfq_io_set_weight_legacy(struct 
cgroup_subsys_state *css,
bfqg->entity.prio_changed = 1;
}
}
-   spin_unlock_irq(>lock);
+   xa_unlock_irq(>blkg_array);
 
return ret;
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4117524ca45b..37962d52f1a8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -146,12 +146,12 @@ struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct blkcg_gq *blkg;
 
/*
-* Hint didn't match.  Look up from the radix tree.  Note that the
+* Hint didn't match.  Fetch from the xarray.  Note that the
 * hint can only be updated under queue_lock as otherwise @blkg
-* could have already been removed from blkg_tree.  The caller is
+* could have already been removed from blkg_array.  The caller is
 * responsible for grabbing queue_lock if @update_hint.
 */
-   blkg = radix_tree_lookup(>blkg_tree, q->id);
+   blkg = xa_load(>blkg_array, q->id);
if (blkg && blkg->q == q) {
if (update_hint) {
lockdep_assert_held(q->queue_lock);
@@ -223,8 +223,8 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
}
 
/* insert */
-   spin_lock(>lock);
-   ret = radix_tree_insert(>blkg_tree, q->id, blkg);
+   xa_lock(>blkg_array);
+   ret = xa_err(__xa_store(>blkg_array, q->id, blkg, GFP_NOWAIT));
if (likely(!ret)) {
hlist_add_head_rcu(>blkcg_node, >blkg_list);
list_add(>q_node, >blkg_list);
@@ -237,7 +237,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
}
}
blkg->online = true;
-   spin_unlock(>lock);
+   xa_unlock(>blkg_array);
 
if (!ret)
return blkg;
@@ -314,7 +314,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
int i;
 
lockdep_assert_held(blkg->q->queue_lock);
-   lockdep_assert_held(>lock);
+   lockdep_assert_held(>blkg_array.xa_lock);
 
/* Something wrong if we are trying to remove same group twice */
WARN_ON_ONCE(list_empty(>q_node));
@@ -334,7 +334,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 
blkg->online = false;
 
-   radix_tree_delete(>blkg_tree, blkg->q->id);
+   xa_erase(>blkg_array, blkg->q->id);
list_del_init(>q_node);
hlist_del_init_rcu(>blkcg_node);
 
@@ -368,9 +368,9 @@ static void blkg_destroy_all(struct request_queue *q)
list_for_each_entry_safe(blkg, n, >blkg_list, q_node) {
struct blkcg *blkcg = blkg->blkcg;
 
-   spin_lock(>lock);
+   xa_lock(>blkg_array);
blkg_destroy(blkg);
-   spin_unlock(>lock);
+   xa_unlock(>blkg_array);
}
 
q->root_blkg = NULL;
@@ -443,7 +443,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state 
*css,
int i;
 
mutex_lock(_pol_mutex);
-   spin_lock_irq(>lock);
+   xa_lock_irq(>blkg_array);
 
/*
 * Note that stat reset is racy - it doesn't synchronize against
@@ -462,7 +462,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state 
*css,
}
}
 
-   spin_unlock_irq(>lock);
+   xa_unlock_irq(>blkg_array);
mutex_unlock(_pol_mutex);
return 0;
 }
@@ -1012,7 +1012,7 @@ static void blkcg_css_offline(struct cgroup_subsys_state 
*css)
 {
struct blkcg *blkcg = css_to_blkcg(css);
 
-   spin_lock_irq(>lock);
+   xa_lock_irq(>blkg_array);
 
while (!hlist

[PATCH v6 85/99] btrfs: Remove unused spinlock

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The reada_lock in struct btrfs_device was only initialised, and not
actually used.  That's good because there's another lock also called
reada_lock in the btrfs_fs_info that was quite heavily used.  Remove
this one.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/volumes.c | 1 -
 fs/btrfs/volumes.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a25684287501..cba286183ff9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -244,7 +244,6 @@ static struct btrfs_device *__alloc_device(void)
 
spin_lock_init(>io_lock);
 
-   spin_lock_init(>reada_lock);
atomic_set(>reada_in_flight, 0);
atomic_set(>dev_stats_ccnt, 0);
btrfs_device_data_ordered_init(dev);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ff15208344a7..335fd1590458 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -136,7 +136,6 @@ struct btrfs_device {
struct work_struct rcu_work;
 
/* readahead state */
-   spinlock_t reada_lock;
atomic_t reada_in_flight;
u64 reada_next;
struct reada_zone *reada_curr_zone;
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 84/99] btrfs: Convert fs_roots_radix to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Most of the gang lookups being done can be expressed just as efficiently
and somewhat more naturally as xa_for_each() loops.  I opted not to
change the one in btrfs_cleanup_fs_roots() as it's using SRCU which is
subtle and quick to anger.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/ctree.h |  3 +-
 fs/btrfs/disk-io.c   | 65 +++--
 fs/btrfs/tests/btrfs-tests.c |  3 +-
 fs/btrfs/transaction.c   | 87 ++--
 4 files changed, 59 insertions(+), 99 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 13c260b525a1..173d72dfaab6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -741,8 +741,7 @@ struct btrfs_fs_info {
/* the log root tree is a directory of all the other log roots */
struct btrfs_root *log_root_tree;
 
-   spinlock_t fs_roots_radix_lock;
-   struct radix_tree_root fs_roots_radix;
+   struct xarray fs_roots;
 
/* block group cache stuff */
spinlock_t block_group_cache_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a8ecccfc36de..62995a55d112 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1519,13 +1519,7 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
u64 root_id)
 {
-   struct btrfs_root *root;
-
-   spin_lock(_info->fs_roots_radix_lock);
-   root = radix_tree_lookup(_info->fs_roots_radix,
-(unsigned long)root_id);
-   spin_unlock(_info->fs_roots_radix_lock);
-   return root;
+   return xa_load(_info->fs_roots, (unsigned long)root_id);
 }
 
 int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
@@ -1533,18 +1527,13 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 {
int ret;
 
-   ret = radix_tree_preload(GFP_NOFS);
-   if (ret)
-   return ret;
-
-   spin_lock(_info->fs_roots_radix_lock);
-   ret = radix_tree_insert(_info->fs_roots_radix,
+   xa_lock(_info->fs_roots);
+   ret = __xa_insert(_info->fs_roots,
(unsigned long)root->root_key.objectid,
-   root);
+   root, GFP_NOFS);
if (ret == 0)
set_bit(BTRFS_ROOT_IN_RADIX, >state);
-   spin_unlock(_info->fs_roots_radix_lock);
-   radix_tree_preload_end();
+   xa_unlock(_info->fs_roots);
 
return ret;
 }
@@ -2079,33 +2068,25 @@ static void free_root_pointers(struct btrfs_fs_info 
*info, int chunk_root)
 
 void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 {
-   int ret;
-   struct btrfs_root *gang[8];
-   int i;
+   struct btrfs_root *root;
+   unsigned long i = 0;
 
while (!list_empty(_info->dead_roots)) {
-   gang[0] = list_entry(fs_info->dead_roots.next,
+   root = list_entry(fs_info->dead_roots.next,
 struct btrfs_root, root_list);
-   list_del([0]->root_list);
+   list_del(>root_list);
 
-   if (test_bit(BTRFS_ROOT_IN_RADIX, [0]->state)) {
-   btrfs_drop_and_free_fs_root(fs_info, gang[0]);
+   if (test_bit(BTRFS_ROOT_IN_RADIX, >state)) {
+   btrfs_drop_and_free_fs_root(fs_info, root);
} else {
-   free_extent_buffer(gang[0]->node);
-   free_extent_buffer(gang[0]->commit_root);
-   btrfs_put_fs_root(gang[0]);
+   free_extent_buffer(root->node);
+   free_extent_buffer(root->commit_root);
+   btrfs_put_fs_root(root);
}
}
 
-   while (1) {
-   ret = radix_tree_gang_lookup(_info->fs_roots_radix,
-(void **)gang, 0,
-ARRAY_SIZE(gang));
-   if (!ret)
-   break;
-   for (i = 0; i < ret; i++)
-   btrfs_drop_and_free_fs_root(fs_info, gang[i]);
-   }
+   xa_for_each(_info->fs_roots, root, i, ULONG_MAX, XA_PRESENT)
+   btrfs_drop_and_free_fs_root(fs_info, root);
 
if (test_bit(BTRFS_FS_STATE_ERROR, _info->fs_state)) {
btrfs_free_log_root_tree(NULL, fs_info);
@@ -2447,7 +2428,7 @@ int open_ctree(struct super_block *sb,
goto fail_delalloc_bytes;
}
 
-   INIT_RADIX_TREE(_info->fs_roots_radix, GFP_ATOMIC);
+   xa_init(_info->fs_roots);
INIT_RADIX_TREE(_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(_info->trans_list);
INIT_LIST_HEAD(_inf

[PATCH v6 83/99] hwspinlock: Convert to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

I had to mess with the locking a bit as I converted the code from a
mutex to the xa_lock.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 drivers/hwspinlock/hwspinlock_core.c | 151 ---
 1 file changed, 52 insertions(+), 99 deletions(-)

diff --git a/drivers/hwspinlock/hwspinlock_core.c 
b/drivers/hwspinlock/hwspinlock_core.c
index 4074441444fe..acb6e315925f 100644
--- a/drivers/hwspinlock/hwspinlock_core.c
+++ b/drivers/hwspinlock/hwspinlock_core.c
@@ -23,43 +23,32 @@
 #include 
 #include 
 #include 
-#include 
+#include 
 #include 
 #include 
-#include 
 #include 
 
 #include "hwspinlock_internal.h"
 
-/* radix tree tags */
-#define HWSPINLOCK_UNUSED  (0) /* tags an hwspinlock as unused */
+#define HWSPINLOCK_UNUSED  XA_TAG_0
 
 /*
- * A radix tree is used to maintain the available hwspinlock instances.
- * The tree associates hwspinlock pointers with their integer key id,
+ * An xarray is used to maintain the available hwspinlock instances.
+ * The array associates hwspinlock pointers with their integer key id,
  * and provides easy-to-use API which makes the hwspinlock core code simple
  * and easy to read.
  *
- * Radix trees are quick on lookups, and reasonably efficient in terms of
+ * The XArray is quick on lookups, and reasonably efficient in terms of
  * storage, especially with high density usages such as this framework
  * requires (a continuous range of integer keys, beginning with zero, is
  * used as the ID's of the hwspinlock instances).
  *
- * The radix tree API supports tagging items in the tree, which this
- * framework uses to mark unused hwspinlock instances (see the
- * HWSPINLOCK_UNUSED tag above). As a result, the process of querying the
- * tree, looking for an unused hwspinlock instance, is now reduced to a
- * single radix tree API call.
+ * The xarray API supports tagging items, which this framework uses to mark
+ * unused hwspinlock instances (see the HWSPINLOCK_UNUSED tag above). As a
+ * result, the process of querying the array, looking for an unused
+ * hwspinlock instance, is reduced to a single call.
  */
-static RADIX_TREE(hwspinlock_tree, GFP_KERNEL);
-
-/*
- * Synchronization of access to the tree is achieved using this mutex,
- * as the radix-tree API requires that users provide all synchronisation.
- * A mutex is needed because we're using non-atomic radix tree allocations.
- */
-static DEFINE_MUTEX(hwspinlock_tree_lock);
-
+static DEFINE_XARRAY(hwspinlock_xa);
 
 /**
  * __hwspin_trylock() - attempt to lock a specific hwspinlock
@@ -294,10 +283,9 @@ of_hwspin_lock_simple_xlate(const struct of_phandle_args 
*hwlock_spec)
  */
 int of_hwspin_lock_get_id(struct device_node *np, int index)
 {
+   XA_STATE(xas, _xa, 0);
struct of_phandle_args args;
struct hwspinlock *hwlock;
-   struct radix_tree_iter iter;
-   void **slot;
int id;
int ret;
 
@@ -309,22 +297,15 @@ int of_hwspin_lock_get_id(struct device_node *np, int 
index)
/* Find the hwspinlock device: we need its base_id */
ret = -EPROBE_DEFER;
rcu_read_lock();
-   radix_tree_for_each_slot(slot, _tree, , 0) {
-   hwlock = radix_tree_deref_slot(slot);
-   if (unlikely(!hwlock))
-   continue;
-   if (radix_tree_deref_retry(hwlock)) {
-   slot = radix_tree_iter_retry();
+   xas_for_each(, hwlock, ULONG_MAX) {
+   if (xas_retry(, hwlock))
continue;
-   }
 
-   if (hwlock->bank->dev->of_node == args.np) {
-   ret = 0;
+   if (hwlock->bank->dev->of_node == args.np)
break;
-   }
}
rcu_read_unlock();
-   if (ret < 0)
+   if (!hwlock)
goto out;
 
id = of_hwspin_lock_simple_xlate();
@@ -332,6 +313,7 @@ int of_hwspin_lock_get_id(struct device_node *np, int index)
ret = -EINVAL;
goto out;
}
+   ret = 0;
id += hwlock->bank->base_id;
 
 out:
@@ -342,26 +324,19 @@ EXPORT_SYMBOL_GPL(of_hwspin_lock_get_id);
 
 static int hwspin_lock_register_single(struct hwspinlock *hwlock, int id)
 {
-   struct hwspinlock *tmp;
-   int ret;
+   void *curr;
 
-   mutex_lock(_tree_lock);
-
-   ret = radix_tree_insert(_tree, id, hwlock);
-   if (ret) {
-   if (ret == -EEXIST)
+   curr = xa_cmpxchg(_xa, id, NULL, hwlock, GFP_KERNEL);
+   if (curr) {
+   if (!xa_is_err(curr))
pr_err("hwspinlock id %d already exists!\n", id);
goto out;
}
 
/* mark this hwspinlock as available */
-   tmp = radix_tree_tag_set(_tree, id, HWSPINLOCK_UNUSED);
-
-   /* self-sanity check which should never fail */

[PATCH v6 88/99] btrfs: Convert reada_tree to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Rename reada_tree to reada_array.  Use the xa_lock in reada_array to
replace reada_lock.  This has to use a nested spinlock as we take the
xa_lock of the reada_extents and reada_zones xarrays while holding
the reada_lock.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/ctree.h   |  15 +--
 fs/btrfs/disk-io.c |   3 +-
 fs/btrfs/reada.c   | 119 +
 3 files changed, 70 insertions(+), 67 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 173d72dfaab6..272d099bed7e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1052,9 +1052,8 @@ struct btrfs_fs_info {
 
struct btrfs_delayed_root *delayed_root;
 
-   /* readahead tree */
-   spinlock_t reada_lock;
-   struct radix_tree_root reada_tree;
+   /* readahead extents */
+   struct xarray reada_array;
 
/* readahead works cnt */
atomic_t reada_works_cnt;
@@ -1102,6 +1101,16 @@ struct btrfs_fs_info {
 #endif
 };
 
+static inline void reada_lock(struct btrfs_fs_info *fs_info)
+{
+   spin_lock_nested(_info->reada_array.xa_lock, SINGLE_DEPTH_NESTING);
+}
+
+static inline void reada_unlock(struct btrfs_fs_info *fs_info)
+{
+   spin_unlock(_info->reada_array.xa_lock);
+}
+
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
 {
return sb->s_fs_info;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62995a55d112..1eae29045d43 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2478,8 +2478,7 @@ int open_ctree(struct super_block *sb,
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
/* readahead state */
-   INIT_RADIX_TREE(_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
-   spin_lock_init(_info->reada_lock);
+   xa_init(_info->reada_array);
btrfs_init_ref_verify(fs_info);
 
fs_info->thread_pool_size = min_t(unsigned long,
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 8100f1565250..89ba0063903f 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -215,12 +215,11 @@ int btree_readahead_hook(struct extent_buffer *eb, int 
err)
struct reada_extent *re;
 
/* find extent */
-   spin_lock(_info->reada_lock);
-   re = radix_tree_lookup(_info->reada_tree,
-  eb->start >> PAGE_SHIFT);
+   reada_lock(fs_info);
+   re = xa_load(_info->reada_array, eb->start >> PAGE_SHIFT);
if (re)
re->refcnt++;
-   spin_unlock(_info->reada_lock);
+   reada_unlock(fs_info);
if (!re) {
ret = -1;
goto start_machine;
@@ -246,15 +245,15 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
unsigned long index = logical >> PAGE_SHIFT;
int i;
 
-   spin_lock(_info->reada_lock);
+   reada_lock(fs_info);
zone = xa_find(>reada_zones, , ULONG_MAX, XA_PRESENT);
if (zone && logical >= zone->start && logical <= zone->end) {
kref_get(>refcnt);
-   spin_unlock(_info->reada_lock);
+   reada_unlock(fs_info);
return zone;
}
 
-   spin_unlock(_info->reada_lock);
+   reada_unlock(fs_info);
 
cache = btrfs_lookup_block_group(fs_info, logical);
if (!cache)
@@ -289,7 +288,7 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
}
zone->ndevs = bbio->num_stripes;
 
-   spin_lock(_info->reada_lock);
+   reada_lock(fs_info);
curr = xa_cmpxchg(>reada_zones,
(unsigned long)(zone->end >> PAGE_SHIFT),
NULL, zone, GFP_NOWAIT | __GFP_NOWARN);
@@ -301,7 +300,7 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
else
zone = NULL;
}
-   spin_unlock(_info->reada_lock);
+   reada_unlock(fs_info);
 
return zone;
 }
@@ -323,11 +322,11 @@ static struct reada_extent *reada_find_extent(struct 
btrfs_fs_info *fs_info,
int dev_replace_is_ongoing;
int have_zone = 0;
 
-   spin_lock(_info->reada_lock);
-   re = radix_tree_lookup(_info->reada_tree, index);
+   reada_lock(fs_info);
+   re = xa_load(_info->reada_array, index);
if (re)
re->refcnt++;
-   spin_unlock(_info->reada_lock);
+   reada_unlock(fs_info);
 
if (re)
return re;
@@ -378,38 +377,32 @@ static struct reada_extent *reada_find_extent(struct 
btrfs_fs_info *fs_info,
kref_get(>refcnt);
++zone->el

[PATCH v6 87/99] btrfs: Convert reada_extents to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Straightforward conversion.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/reada.c   | 32 +---
 fs/btrfs/volumes.c |  2 +-
 fs/btrfs/volumes.h |  2 +-
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index ef8e84ff2012..8100f1565250 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -438,13 +438,14 @@ static struct reada_extent *reada_find_extent(struct 
btrfs_fs_info *fs_info,
continue;
}
prev_dev = dev;
-   ret = radix_tree_insert(>reada_extents, index, re);
+   ret = xa_insert(>reada_extents, index, re,
+   GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
if (ret) {
while (--nzones >= 0) {
dev = re->zones[nzones]->device;
BUG_ON(dev == NULL);
/* ignore whether the entry was inserted */
-   radix_tree_delete(>reada_extents, index);
+   xa_erase(>reada_extents, index);
}
radix_tree_delete(_info->reada_tree, index);
spin_unlock(_info->reada_lock);
@@ -504,7 +505,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
for (i = 0; i < re->nzones; ++i) {
struct reada_zone *zone = re->zones[i];
 
-   radix_tree_delete(>device->reada_extents, index);
+   xa_erase(>device->reada_extents, index);
}
 
spin_unlock(_info->reada_lock);
@@ -644,6 +645,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
int mirror_num = 0;
struct extent_buffer *eb = NULL;
u64 logical;
+   unsigned long index;
int ret;
int i;
 
@@ -660,19 +662,19 @@ static int reada_start_machine_dev(struct btrfs_device 
*dev)
 * a contiguous block of extents, we could also coagulate them or use
 * plugging to speed things up
 */
-   ret = radix_tree_gang_lookup(>reada_extents, (void **),
-dev->reada_next >> PAGE_SHIFT, 1);
-   if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
+   index = dev->reada_next >> PAGE_SHIFT;
+   re = xa_find(>reada_extents, , ULONG_MAX, XA_PRESENT);
+   if (!re || re->logical > dev->reada_curr_zone->end) {
ret = reada_pick_zone(dev);
if (!ret) {
spin_unlock(_info->reada_lock);
return 0;
}
-   re = NULL;
-   ret = radix_tree_gang_lookup(>reada_extents, (void **),
-   dev->reada_next >> PAGE_SHIFT, 1);
+   index = dev->reada_next >> PAGE_SHIFT;
+   re = xa_find(>reada_extents, , ULONG_MAX,
+   XA_PRESENT);
}
-   if (ret == 0) {
+   if (!re) {
spin_unlock(_info->reada_lock);
return 0;
}
@@ -828,11 +830,11 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int 
all)
cnt = 0;
index = 0;
while (all) {
-   struct reada_extent *re = NULL;
+   struct reada_extent *re;
 
-   ret = radix_tree_gang_lookup(>reada_extents,
-(void **), index, 1);
-   if (ret == 0)
+   re = xa_find(>reada_extents, , ULONG_MAX,
+   XA_PRESENT);
+   if (!re)
break;
pr_debug("  re: logical %llu size %u empty %d scheduled 
%d",
re->logical, fs_info->nodesize,
@@ -848,7 +850,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int 
all)
}
}
pr_cont("\n");
-   index = (re->logical >> PAGE_SHIFT) + 1;
+   index++;
if (++cnt > 15)
break;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8e683799b436..304c2ef4c557 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -248,7 +248,7 @@ static struct btrfs_device *__alloc_device(void)
atomic_set(>dev_stats_ccnt, 0);
btrfs_device_data_ordered_init(dev);
xa_init(>reada_zones);
-   INIT_RADIX_TREE(>re

[PATCH v6 86/99] btrfs: Convert reada_zones to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The use of the reada_lock means we have to use the xa_reserve() API.
If we can avoid using reada_lock to protect this xarray, we can drop
the use of that function.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/reada.c   | 54 +++---
 fs/btrfs/volumes.c |  2 +-
 fs/btrfs/volumes.h |  2 +-
 3 files changed, 21 insertions(+), 37 deletions(-)

diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index ab852b8e3e37..ef8e84ff2012 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -239,17 +239,16 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
 {
struct btrfs_fs_info *fs_info = dev->fs_info;
int ret;
-   struct reada_zone *zone;
+   struct reada_zone *curr, *zone;
struct btrfs_block_group_cache *cache = NULL;
u64 start;
u64 end;
+   unsigned long index = logical >> PAGE_SHIFT;
int i;
 
-   zone = NULL;
spin_lock(_info->reada_lock);
-   ret = radix_tree_gang_lookup(>reada_zones, (void **),
-logical >> PAGE_SHIFT, 1);
-   if (ret == 1 && logical >= zone->start && logical <= zone->end) {
+   zone = xa_find(>reada_zones, , ULONG_MAX, XA_PRESENT);
+   if (zone && logical >= zone->start && logical <= zone->end) {
kref_get(>refcnt);
spin_unlock(_info->reada_lock);
return zone;
@@ -269,7 +268,8 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
if (!zone)
return NULL;
 
-   ret = radix_tree_preload(GFP_KERNEL);
+   ret = xa_reserve(>reada_zones,
+(unsigned long)(end >> PAGE_SHIFT), GFP_KERNEL);
if (ret) {
kfree(zone);
return NULL;
@@ -290,21 +290,18 @@ static struct reada_zone *reada_find_zone(struct 
btrfs_device *dev, u64 logical,
zone->ndevs = bbio->num_stripes;
 
spin_lock(_info->reada_lock);
-   ret = radix_tree_insert(>reada_zones,
+   curr = xa_cmpxchg(>reada_zones,
(unsigned long)(zone->end >> PAGE_SHIFT),
-   zone);
-
-   if (ret == -EEXIST) {
+   NULL, zone, GFP_NOWAIT | __GFP_NOWARN);
+   if (curr) {
kfree(zone);
-   ret = radix_tree_gang_lookup(>reada_zones, (void **),
-logical >> PAGE_SHIFT, 1);
-   if (ret == 1 && logical >= zone->start && logical <= zone->end)
+   zone = curr;
+   if (logical >= zone->start && logical <= zone->end)
kref_get(>refcnt);
else
zone = NULL;
}
spin_unlock(_info->reada_lock);
-   radix_tree_preload_end();
 
return zone;
 }
@@ -537,9 +534,7 @@ static void reada_zone_release(struct kref *kref)
 {
struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
 
-   radix_tree_delete(>device->reada_zones,
- zone->end >> PAGE_SHIFT);
-
+   xa_erase(>device->reada_zones, zone->end >> PAGE_SHIFT);
kfree(zone);
 }
 
@@ -592,7 +587,7 @@ static void reada_peer_zones_set_lock(struct reada_zone 
*zone, int lock)
 
for (i = 0; i < zone->ndevs; ++i) {
struct reada_zone *peer;
-   peer = radix_tree_lookup(>devs[i]->reada_zones, index);
+   peer = xa_load(>devs[i]->reada_zones, index);
if (peer && peer->device != zone->device)
peer->locked = lock;
}
@@ -603,12 +598,11 @@ static void reada_peer_zones_set_lock(struct reada_zone 
*zone, int lock)
  */
 static int reada_pick_zone(struct btrfs_device *dev)
 {
-   struct reada_zone *top_zone = NULL;
+   struct reada_zone *zone, *top_zone = NULL;
struct reada_zone *top_locked_zone = NULL;
u64 top_elems = 0;
u64 top_locked_elems = 0;
unsigned long index = 0;
-   int ret;
 
if (dev->reada_curr_zone) {
reada_peer_zones_set_lock(dev->reada_curr_zone, 0);
@@ -616,14 +610,7 @@ static int reada_pick_zone(struct btrfs_device *dev)
dev->reada_curr_zone = NULL;
}
/* pick the zone with the most elements */
-   while (1) {
-   struct reada_zone *zone;
-
-   ret = radix_tree_gang_lookup(>reada_zones,
-(void **), index, 1);
-   if (ret == 0)
-   break;
-   index = (zon

[PATCH v6 89/99] btrfs: Convert buffer_radix to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Eliminate the buffer_lock as the internal xa_lock provides all the
necessary protection.  We can remove the radix_tree_preload calls, but
I can't find a good way to use the 'exists' result from xa_cmpxchg().
We could resort to the advanced API to improve this, but it's a really
unlikely case (nothing in the xarray when we first look; something there
when we try to add the newly-allocated extent buffer), so I think it's
not worth optimising for.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/ctree.h |  5 ++-
 fs/btrfs/disk-io.c   |  3 +-
 fs/btrfs/extent_io.c | 82 ++--
 fs/btrfs/tests/btrfs-tests.c | 26 +++---
 4 files changed, 40 insertions(+), 76 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 272d099bed7e..87984ce3a4c2 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1058,9 +1058,8 @@ struct btrfs_fs_info {
/* readahead works cnt */
atomic_t reada_works_cnt;
 
-   /* Extent buffer radix tree */
-   spinlock_t buffer_lock;
-   struct radix_tree_root buffer_radix;
+   /* Extent buffer array */
+   struct xarray buffer_array;
 
/* next backup root to be overwritten */
int backup_root_index;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1eae29045d43..650d1350b64d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2429,7 +2429,7 @@ int open_ctree(struct super_block *sb,
}
 
xa_init(_info->fs_roots);
-   INIT_RADIX_TREE(_info->buffer_radix, GFP_ATOMIC);
+   xa_init(_info->buffer_array);
INIT_LIST_HEAD(_info->trans_list);
INIT_LIST_HEAD(_info->dead_roots);
INIT_LIST_HEAD(_info->delayed_iputs);
@@ -2442,7 +2442,6 @@ int open_ctree(struct super_block *sb,
spin_lock_init(_info->tree_mod_seq_lock);
spin_lock_init(_info->super_lock);
spin_lock_init(_info->qgroup_op_lock);
-   spin_lock_init(_info->buffer_lock);
spin_lock_init(_info->unused_bgs_lock);
rwlock_init(_info->tree_mod_log_lock);
mutex_init(_info->unused_bg_unpin_mutex);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fd5e9d887328..2b43fa11c9e2 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4884,8 +4884,7 @@ struct extent_buffer *find_extent_buffer(struct 
btrfs_fs_info *fs_info,
struct extent_buffer *eb;
 
rcu_read_lock();
-   eb = radix_tree_lookup(_info->buffer_radix,
-  start >> PAGE_SHIFT);
+   eb = xa_load(_info->buffer_array, start >> PAGE_SHIFT);
if (eb && atomic_inc_not_zero(>refs)) {
rcu_read_unlock();
/*
@@ -4919,31 +4918,24 @@ struct extent_buffer *find_extent_buffer(struct 
btrfs_fs_info *fs_info,
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
 {
-   struct extent_buffer *eb, *exists = NULL;
-   int ret;
+   struct extent_buffer *exists, *eb = NULL;
 
-   eb = find_extent_buffer(fs_info, start);
-   if (eb)
-   return eb;
-   eb = alloc_dummy_extent_buffer(fs_info, start);
-   if (!eb)
-   return NULL;
-   eb->fs_info = fs_info;
 again:
-   ret = radix_tree_preload(GFP_NOFS);
-   if (ret)
+   exists = find_extent_buffer(fs_info, start);
+   if (exists)
goto free_eb;
-   spin_lock(_info->buffer_lock);
-   ret = radix_tree_insert(_info->buffer_radix,
-   start >> PAGE_SHIFT, eb);
-   spin_unlock(_info->buffer_lock);
-   radix_tree_preload_end();
-   if (ret == -EEXIST) {
-   exists = find_extent_buffer(fs_info, start);
-   if (exists)
+   if (!eb)
+   eb = alloc_dummy_extent_buffer(fs_info, start);
+   if (!eb)
+   return NULL;
+   exists = xa_cmpxchg(_info->buffer_array, start >> PAGE_SHIFT,
+   NULL, eb, GFP_NOFS);
+   if (unlikely(exists)) {
+   if (xa_is_err(exists)) {
+   exists = NULL;
goto free_eb;
-   else
-   goto again;
+   }
+   goto again;
}
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, >bflags);
@@ -4957,7 +4949,8 @@ struct extent_buffer *alloc_test_extent_buffer(struct 
btrfs_fs_info *fs_info,
atomic_inc(>refs);
return eb;
 free_eb:
-   btrfs_release_extent_buffer(eb);
+   if (eb)
+   btrfs_release_extent_buffer(eb);
return exists;
 }
 #endif
@@ -4969,22 +4962,24 @@ struct extent_buffer *alloc_extent_buffer(struct 
btrfs_fs_info *fs_info,
uns

[PATCH v6 90/99] btrfs: Convert delayed_nodes_tree to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Rename it to just 'delayed_nodes' and remove it from the protection of
btrfs_root->inode_lock.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/ctree.h |  8 +++---
 fs/btrfs/delayed-inode.c | 65 
 fs/btrfs/disk-io.c   |  2 +-
 fs/btrfs/inode.c |  2 +-
 4 files changed, 27 insertions(+), 50 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 87984ce3a4c2..9acfdc623d15 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1219,11 +1219,9 @@ struct btrfs_root {
/* red-black tree that keeps track of in-memory inodes */
struct rb_root inode_tree;
 
-   /*
-* radix tree that keeps track of delayed nodes of every inode,
-* protected by inode_lock
-*/
-   struct radix_tree_root delayed_nodes_tree;
+   /* track delayed nodes of every inode */
+   struct xarray delayed_nodes;
+
/*
 * right now this just gets used so that a root has its own devid
 * for stat.  It may be used for more later
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 056276101c63..156a762f3809 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -86,7 +86,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
}
 
spin_lock(>inode_lock);
-   node = radix_tree_lookup(>delayed_nodes_tree, ino);
+   node = xa_load(>delayed_nodes, ino);
 
if (node) {
if (btrfs_inode->delayed_node) {
@@ -131,10 +131,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
 static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
struct btrfs_inode *btrfs_inode)
 {
-   struct btrfs_delayed_node *node;
+   struct btrfs_delayed_node *node, *exists;
struct btrfs_root *root = btrfs_inode->root;
u64 ino = btrfs_ino(btrfs_inode);
-   int ret;
 
 again:
node = btrfs_get_delayed_node(btrfs_inode);
@@ -149,23 +148,18 @@ static struct btrfs_delayed_node 
*btrfs_get_or_create_delayed_node(
/* cached in the btrfs inode and can be accessed */
refcount_set(>refs, 2);
 
-   ret = radix_tree_preload(GFP_NOFS);
-   if (ret) {
+   xa_lock(>delayed_nodes);
+   exists = __xa_cmpxchg(>delayed_nodes, ino, NULL, node, GFP_NOFS);
+   if (unlikely(exists)) {
+   int ret = xa_err(exists);
+   xa_unlock(>delayed_nodes);
kmem_cache_free(delayed_node_cache, node);
+   if (ret == -EEXIST)
+   goto again;
return ERR_PTR(ret);
}
-
-   spin_lock(>inode_lock);
-   ret = radix_tree_insert(>delayed_nodes_tree, ino, node);
-   if (ret == -EEXIST) {
-   spin_unlock(>inode_lock);
-   kmem_cache_free(delayed_node_cache, node);
-   radix_tree_preload_end();
-   goto again;
-   }
btrfs_inode->delayed_node = node;
-   spin_unlock(>inode_lock);
-   radix_tree_preload_end();
+   xa_unlock(>delayed_nodes);
 
return node;
 }
@@ -278,15 +272,12 @@ static void __btrfs_release_delayed_node(
if (refcount_dec_and_test(_node->refs)) {
struct btrfs_root *root = delayed_node->root;
 
-   spin_lock(>inode_lock);
/*
 * Once our refcount goes to zero, nobody is allowed to bump it
 * back up.  We can delete it now.
 */
ASSERT(refcount_read(_node->refs) == 0);
-   radix_tree_delete(>delayed_nodes_tree,
- delayed_node->inode_id);
-   spin_unlock(>inode_lock);
+   xa_erase(>delayed_nodes, delayed_node->inode_id);
kmem_cache_free(delayed_node_cache, delayed_node);
}
 }
@@ -1926,31 +1917,19 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode 
*inode)
 
 void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 {
-   u64 inode_id = 0;
-   struct btrfs_delayed_node *delayed_nodes[8];
-   int i, n;
-
-   while (1) {
-   spin_lock(>inode_lock);
-   n = radix_tree_gang_lookup(>delayed_nodes_tree,
-  (void **)delayed_nodes, inode_id,
-  ARRAY_SIZE(delayed_nodes));
-   if (!n) {
-   spin_unlock(>inode_lock);
-   break;
-   }
-
-   inode_id = delayed_nodes[n - 1]->inode_id + 1;
-
-   for (i = 0; i < n; i++)
-   refcount_inc(_nodes[i]->refs);
-   spin_unlock(>inode_lock);
+   struct btrfs_delayed_node *node;
+   unsigned long inode_id = 0;
 

[PATCH v6 91/99] btrfs: Convert name_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

This is a very straightforward conversion.  The handling of collisions
in the namecache could be better handled with an hlist, but that's a
patch for another day.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/btrfs/send.c | 19 +--
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 20d3300bd268..3891a8e958fa 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -23,7 +23,7 @@
 #include 
 #include 
 #include 
-#include 
+#include 
 #include 
 #include 
 #include 
@@ -118,7 +118,7 @@ struct send_ctx {
struct list_head new_refs;
struct list_head deleted_refs;
 
-   struct radix_tree_root name_cache;
+   struct xarray name_cache;
struct list_head name_cache_list;
int name_cache_size;
 
@@ -2021,8 +2021,7 @@ static int name_cache_insert(struct send_ctx *sctx,
int ret = 0;
struct list_head *nce_head;
 
-   nce_head = radix_tree_lookup(>name_cache,
-   (unsigned long)nce->ino);
+   nce_head = xa_load(>name_cache, (unsigned long)nce->ino);
if (!nce_head) {
nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
if (!nce_head) {
@@ -2031,7 +2030,8 @@ static int name_cache_insert(struct send_ctx *sctx,
}
INIT_LIST_HEAD(nce_head);
 
-   ret = radix_tree_insert(>name_cache, nce->ino, nce_head);
+   ret = xa_insert(>name_cache, nce->ino, nce_head,
+   GFP_KERNEL);
if (ret < 0) {
kfree(nce_head);
kfree(nce);
@@ -2050,8 +2050,7 @@ static void name_cache_delete(struct send_ctx *sctx,
 {
struct list_head *nce_head;
 
-   nce_head = radix_tree_lookup(>name_cache,
-   (unsigned long)nce->ino);
+   nce_head = xa_load(>name_cache, (unsigned long)nce->ino);
if (!nce_head) {
btrfs_err(sctx->send_root->fs_info,
  "name_cache_delete lookup failed ino %llu cache size %d, leaking 
memory",
@@ -2066,7 +2065,7 @@ static void name_cache_delete(struct send_ctx *sctx,
 * We may not get to the final release of nce_head if the lookup fails
 */
if (nce_head && list_empty(nce_head)) {
-   radix_tree_delete(>name_cache, (unsigned long)nce->ino);
+   xa_erase(>name_cache, (unsigned long)nce->ino);
kfree(nce_head);
}
 }
@@ -2077,7 +2076,7 @@ static struct name_cache_entry *name_cache_search(struct 
send_ctx *sctx,
struct list_head *nce_head;
struct name_cache_entry *cur;
 
-   nce_head = radix_tree_lookup(>name_cache, (unsigned long)ino);
+   nce_head = xa_load(>name_cache, (unsigned long)ino);
if (!nce_head)
return NULL;
 
@@ -6526,7 +6525,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct 
btrfs_ioctl_send_args *arg)
 
INIT_LIST_HEAD(>new_refs);
INIT_LIST_HEAD(>deleted_refs);
-   INIT_RADIX_TREE(>name_cache, GFP_KERNEL);
+   xa_init(>name_cache);
INIT_LIST_HEAD(>name_cache_list);
 
sctx->flags = arg->flags;
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 92/99] f2fs: Convert pids radix tree to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

The XArray API works out rather well for this user.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/f2fs/super.c |  2 --
 fs/f2fs/trace.c | 60 -
 fs/f2fs/trace.h |  2 --
 3 files changed, 4 insertions(+), 60 deletions(-)

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 708155d9c2e4..d608edffe69e 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2831,8 +2831,6 @@ static int __init init_f2fs_fs(void)
 {
int err;
 
-   f2fs_build_trace_ios();
-
err = init_inodecache();
if (err)
goto fail;
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index bccbbf2616d2..f316a42c547f 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -16,8 +16,7 @@
 #include "f2fs.h"
 #include "trace.h"
 
-static RADIX_TREE(pids, GFP_ATOMIC);
-static spinlock_t pids_lock;
+static DEFINE_XARRAY(pids);
 static struct last_io_info last_io;
 
 static inline void __print_last_io(void)
@@ -57,28 +56,13 @@ void f2fs_trace_pid(struct page *page)
 {
struct inode *inode = page->mapping->host;
pid_t pid = task_pid_nr(current);
-   void *p;
 
set_page_private(page, (unsigned long)pid);
 
-   if (radix_tree_preload(GFP_NOFS))
-   return;
-
-   spin_lock(_lock);
-   p = radix_tree_lookup(, pid);
-   if (p == current)
-   goto out;
-   if (p)
-   radix_tree_delete(, pid);
-
-   f2fs_radix_tree_insert(, pid, current);
-
-   trace_printk("%3x:%3x %4x %-16s\n",
+   if (xa_store(, pid, current, GFP_NOFS) != current)
+   trace_printk("%3x:%3x %4x %-16s\n",
MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
pid, current->comm);
-out:
-   spin_unlock(_lock);
-   radix_tree_preload_end();
 }
 
 void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
@@ -120,43 +104,7 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
return;
 }
 
-void f2fs_build_trace_ios(void)
-{
-   spin_lock_init(_lock);
-}
-
-#define PIDVEC_SIZE128
-static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
-   unsigned int max_items)
-{
-   struct radix_tree_iter iter;
-   void **slot;
-   unsigned int ret = 0;
-
-   if (unlikely(!max_items))
-   return 0;
-
-   radix_tree_for_each_slot(slot, , , first_index) {
-   results[ret] = iter.index;
-   if (++ret == max_items)
-   break;
-   }
-   return ret;
-}
-
 void f2fs_destroy_trace_ios(void)
 {
-   pid_t pid[PIDVEC_SIZE];
-   pid_t next_pid = 0;
-   unsigned int found;
-
-   spin_lock(_lock);
-   while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
-   unsigned idx;
-
-   next_pid = pid[found - 1] + 1;
-   for (idx = 0; idx < found; idx++)
-   radix_tree_delete(, pid[idx]);
-   }
-   spin_unlock(_lock);
+   xa_destroy();
 }
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
index 67db24ac1e85..157e4564e48b 100644
--- a/fs/f2fs/trace.h
+++ b/fs/f2fs/trace.h
@@ -34,12 +34,10 @@ struct last_io_info {
 
 extern void f2fs_trace_pid(struct page *);
 extern void f2fs_trace_ios(struct f2fs_io_info *, int);
-extern void f2fs_build_trace_ios(void);
 extern void f2fs_destroy_trace_ios(void);
 #else
 #define f2fs_trace_pid(p)
 #define f2fs_trace_ios(i, n)
-#define f2fs_build_trace_ios()
 #define f2fs_destroy_trace_ios()
 
 #endif
-- 
2.15.1

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 94/99] f2fs: Convert extent_tree_root to XArray

[Matthew Wilcox]

From: Matthew Wilcox <mawil...@microsoft.com>

Rename it to extent_array and use the xa_lock in place of the
extent_tree_lock mutex.

Signed-off-by: Matthew Wilcox <mawil...@microsoft.com>
---
 fs/f2fs/extent_cache.c | 59 +-
 fs/f2fs/f2fs.h |  3 +--
 2 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index ff2352a0ed15..da5f3bd1808d 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -250,25 +250,25 @@ static struct extent_tree *__grab_extent_tree(struct 
inode *inode)
struct extent_tree *et;
nid_t ino = inode->i_ino;
 
-   mutex_lock(>extent_tree_lock);
-   et = radix_tree_lookup(>extent_tree_root, ino);
-   if (!et) {
-   et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
-   f2fs_radix_tree_insert(>extent_tree_root, ino, et);
-   memset(et, 0, sizeof(struct extent_tree));
-   et->ino = ino;
-   et->root = RB_ROOT;
-   et->cached_en = NULL;
-   rwlock_init(>lock);
-   INIT_LIST_HEAD(>list);
-   atomic_set(>node_cnt, 0);
-   atomic_inc(>total_ext_tree);
-   } else {
+   et = xa_load(>extent_array, ino);
+   if (et) {
atomic_dec(>total_zombie_tree);
list_del_init(>list);
+   goto out;
}
-   mutex_unlock(>extent_tree_lock);
 
+   et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS | __GFP_ZERO);
+   et->ino = ino;
+   et->root = RB_ROOT;
+   et->cached_en = NULL;
+   rwlock_init(>lock);
+   INIT_LIST_HEAD(>list);
+   atomic_set(>node_cnt, 0);
+
+   xa_store(>extent_array, ino, et, GFP_NOFS);
+   atomic_inc(>total_ext_tree);
+
+out:
/* never died until evict_inode */
F2FS_I(inode)->extent_tree = et;
 
@@ -622,7 +622,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info 
*sbi, int nr_shrink)
if (!atomic_read(>total_zombie_tree))
goto free_node;
 
-   if (!mutex_trylock(>extent_tree_lock))
+   if (!xa_trylock(>extent_array))
goto out;
 
/* 1. remove unreferenced extent tree */
@@ -634,7 +634,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info 
*sbi, int nr_shrink)
}
f2fs_bug_on(sbi, atomic_read(>node_cnt));
list_del_init(>list);
-   radix_tree_delete(>extent_tree_root, et->ino);
+   xa_erase(>extent_array, et->ino);
kmem_cache_free(extent_tree_slab, et);
atomic_dec(>total_ext_tree);
atomic_dec(>total_zombie_tree);
@@ -642,13 +642,13 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info 
*sbi, int nr_shrink)
 
if (node_cnt + tree_cnt >= nr_shrink)
goto unlock_out;
-   cond_resched();
+   cond_resched_lock(>extent_array.xa_lock);
}
-   mutex_unlock(>extent_tree_lock);
+   xa_unlock(>extent_array);
 
 free_node:
/* 2. remove LRU extent entries */
-   if (!mutex_trylock(>extent_tree_lock))
+   if (!xa_trylock(>extent_array))
goto out;
 
remained = nr_shrink - (node_cnt + tree_cnt);
@@ -678,7 +678,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info 
*sbi, int nr_shrink)
spin_unlock(>extent_lock);
 
 unlock_out:
-   mutex_unlock(>extent_tree_lock);
+   xa_unlock(>extent_array);
 out:
trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
 
@@ -725,23 +725,23 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
if (inode->i_nlink && !is_bad_inode(inode) &&
atomic_read(>node_cnt)) {
-   mutex_lock(>extent_tree_lock);
+   xa_lock(>extent_array);
list_add_tail(>list, >zombie_list);
atomic_inc(>total_zombie_tree);
-   mutex_unlock(>extent_tree_lock);
+   xa_unlock(>extent_array);
return;
}
 
/* free all extent info belong to this extent tree */
node_cnt = f2fs_destroy_extent_node(inode);
 
-   /* delete extent tree entry in radix tree */
-   mutex_lock(>extent_tree_lock);
+   /* delete extent from array */
+   xa_lock(>extent_array);
f2fs_bug_on(sbi, atomic_read(>node_cnt));
-   radix_tree_delete(>extent_tree_root, inode->i_ino);
-   kmem_cache_free(extent_tree_slab, et);
+   __xa_erase(>extent_array, inode->i_ino);
atomic_dec(>total_ext_tree);
-   mutex_unlock(>extent_tree_lock);
+   xa_unlock(>extent_array);
+   kmem_ca