* [PATCH 1/3] xen: remove tmem driver
2019-05-27 10:32 [PATCH 0/3] remove tmem and code depending on it Juergen Gross
@ 2019-05-27 10:32 ` Juergen Gross
2019-05-28 22:44 ` Boris Ostrovsky
2019-05-27 10:32 ` [PATCH 2/3] mm: remove cleancache.c Juergen Gross
2019-05-27 10:32 ` [PATCH 3/3] mm: remove tmem specifics from frontswap Juergen Gross
2 siblings, 1 reply; 8+ messages in thread
From: Juergen Gross @ 2019-05-27 10:32 UTC (permalink / raw)
To: linux-kernel, linux-doc
Cc: Juergen Gross, Jonathan Corbet, Boris Ostrovsky,
Stefano Stabellini, xen-devel
The Xen tmem (transcendent memory) driver can be removed, as the
related Xen hypervisor feature never made it past the "experimental"
state and will be removed in future Xen versions (>= 4.13).
The xen-selfballoon driver depends on tmem, so it can be removed, too.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
Documentation/admin-guide/kernel-parameters.txt | 21 -
drivers/xen/Kconfig | 23 -
drivers/xen/Makefile | 2 -
drivers/xen/tmem.c | 419 -----------------
drivers/xen/xen-balloon.c | 2 -
drivers/xen/xen-selfballoon.c | 579 ------------------------
include/xen/balloon.h | 8 -
include/xen/tmem.h | 18 -
8 files changed, 1072 deletions(-)
delete mode 100644 drivers/xen/tmem.c
delete mode 100644 drivers/xen/xen-selfballoon.c
delete mode 100644 include/xen/tmem.h
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 138f6664b2e2..2660f1a983a3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4663,27 +4663,6 @@
Force threading of all interrupt handlers except those
marked explicitly IRQF_NO_THREAD.
- tmem [KNL,XEN]
- Enable the Transcendent memory driver if built-in.
-
- tmem.cleancache=0|1 [KNL, XEN]
- Default is on (1). Disable the usage of the cleancache
- API to send anonymous pages to the hypervisor.
-
- tmem.frontswap=0|1 [KNL, XEN]
- Default is on (1). Disable the usage of the frontswap
- API to send swap pages to the hypervisor. If disabled
- the selfballooning and selfshrinking are force disabled.
-
- tmem.selfballooning=0|1 [KNL, XEN]
- Default is on (1). Disable the driving of swap pages
- to the hypervisor.
-
- tmem.selfshrinking=0|1 [KNL, XEN]
- Default is on (1). Partial swapoff that immediately
- transfers pages from Xen hypervisor back to the
- kernel based on different criteria.
-
topology= [S390]
Format: {off | on}
Specify if the kernel should make use of the cpu
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index ec6558b79e9d..79cc75096f42 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -10,21 +10,6 @@ config XEN_BALLOON
the system to expand the domain's memory allocation, or alternatively
return unneeded memory to the system.
-config XEN_SELFBALLOONING
- bool "Dynamically self-balloon kernel memory to target"
- depends on XEN && XEN_BALLOON && CLEANCACHE && SWAP && XEN_TMEM
- help
- Self-ballooning dynamically balloons available kernel memory driven
- by the current usage of anonymous memory ("committed AS") and
- controlled by various sysfs-settable parameters. Configuring
- FRONTSWAP is highly recommended; if it is not configured, self-
- ballooning is disabled by default. If FRONTSWAP is configured,
- frontswap-selfshrinking is enabled by default but can be disabled
- with the 'tmem.selfshrink=0' kernel boot parameter; and self-ballooning
- is enabled by default but can be disabled with the 'tmem.selfballooning=0'
- kernel boot parameter. Note that systems without a sufficiently
- large swap device should not enable self-ballooning.
-
config XEN_BALLOON_MEMORY_HOTPLUG
bool "Memory hotplug support for Xen balloon driver"
depends on XEN_BALLOON && MEMORY_HOTPLUG
@@ -191,14 +176,6 @@ config SWIOTLB_XEN
def_bool y
select SWIOTLB
-config XEN_TMEM
- tristate
- depends on !ARM && !ARM64
- default m if (CLEANCACHE || FRONTSWAP)
- help
- Shim to interface in-kernel Transcendent Memory hooks
- (e.g. cleancache and frontswap) to Xen tmem hypercalls.
-
config XEN_PCIDEV_BACKEND
tristate "Xen PCI-device backend driver"
depends on PCI && X86 && XEN
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index ad3844d9f876..0c4efa6fe450 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -17,14 +17,12 @@ dom0-$(CONFIG_X86) += pcpu.o
obj-$(CONFIG_XEN_DOM0) += $(dom0-y)
obj-$(CONFIG_BLOCK) += biomerge.o
obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o
-obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o
obj-$(CONFIG_XEN_DEV_EVTCHN) += xen-evtchn.o
obj-$(CONFIG_XEN_GNTDEV) += xen-gntdev.o
obj-$(CONFIG_XEN_GRANT_DEV_ALLOC) += xen-gntalloc.o
obj-$(CONFIG_XENFS) += xenfs/
obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
obj-$(CONFIG_XEN_PVHVM) += platform-pci.o
-obj-$(CONFIG_XEN_TMEM) += tmem.o
obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o
obj-$(CONFIG_XEN_MCE_LOG) += mcelog.o
obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
deleted file mode 100644
index 64d7479ad5ad..000000000000
--- a/drivers/xen/tmem.c
+++ /dev/null
@@ -1,419 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Xen implementation for transcendent memory (tmem)
- *
- * Copyright (C) 2009-2011 Oracle Corp. All rights reserved.
- * Author: Dan Magenheimer
- */
-
-#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pagemap.h>
-#include <linux/cleancache.h>
-#include <linux/frontswap.h>
-
-#include <xen/xen.h>
-#include <xen/interface/xen.h>
-#include <xen/page.h>
-#include <asm/xen/hypercall.h>
-#include <asm/xen/hypervisor.h>
-#include <xen/tmem.h>
-
-#ifndef CONFIG_XEN_TMEM_MODULE
-bool __read_mostly tmem_enabled = false;
-
-static int __init enable_tmem(char *s)
-{
- tmem_enabled = true;
- return 1;
-}
-__setup("tmem", enable_tmem);
-#endif
-
-#ifdef CONFIG_CLEANCACHE
-static bool cleancache __read_mostly = true;
-module_param(cleancache, bool, S_IRUGO);
-static bool selfballooning __read_mostly = true;
-module_param(selfballooning, bool, S_IRUGO);
-#endif /* CONFIG_CLEANCACHE */
-
-#ifdef CONFIG_FRONTSWAP
-static bool frontswap __read_mostly = true;
-module_param(frontswap, bool, S_IRUGO);
-#else /* CONFIG_FRONTSWAP */
-#define frontswap (0)
-#endif /* CONFIG_FRONTSWAP */
-
-#ifdef CONFIG_XEN_SELFBALLOONING
-static bool selfshrinking __read_mostly = true;
-module_param(selfshrinking, bool, S_IRUGO);
-#endif /* CONFIG_XEN_SELFBALLOONING */
-
-#define TMEM_CONTROL 0
-#define TMEM_NEW_POOL 1
-#define TMEM_DESTROY_POOL 2
-#define TMEM_NEW_PAGE 3
-#define TMEM_PUT_PAGE 4
-#define TMEM_GET_PAGE 5
-#define TMEM_FLUSH_PAGE 6
-#define TMEM_FLUSH_OBJECT 7
-#define TMEM_READ 8
-#define TMEM_WRITE 9
-#define TMEM_XCHG 10
-
-/* Bits for HYPERVISOR_tmem_op(TMEM_NEW_POOL) */
-#define TMEM_POOL_PERSIST 1
-#define TMEM_POOL_SHARED 2
-#define TMEM_POOL_PAGESIZE_SHIFT 4
-#define TMEM_VERSION_SHIFT 24
-
-
-struct tmem_pool_uuid {
- u64 uuid_lo;
- u64 uuid_hi;
-};
-
-struct tmem_oid {
- u64 oid[3];
-};
-
-#define TMEM_POOL_PRIVATE_UUID { 0, 0 }
-
-/* flags for tmem_ops.new_pool */
-#define TMEM_POOL_PERSIST 1
-#define TMEM_POOL_SHARED 2
-
-/* xen tmem foundation ops/hypercalls */
-
-static inline int xen_tmem_op(u32 tmem_cmd, u32 tmem_pool, struct tmem_oid oid,
- u32 index, unsigned long gmfn, u32 tmem_offset, u32 pfn_offset, u32 len)
-{
- struct tmem_op op;
- int rc = 0;
-
- op.cmd = tmem_cmd;
- op.pool_id = tmem_pool;
- op.u.gen.oid[0] = oid.oid[0];
- op.u.gen.oid[1] = oid.oid[1];
- op.u.gen.oid[2] = oid.oid[2];
- op.u.gen.index = index;
- op.u.gen.tmem_offset = tmem_offset;
- op.u.gen.pfn_offset = pfn_offset;
- op.u.gen.len = len;
- set_xen_guest_handle(op.u.gen.gmfn, (void *)gmfn);
- rc = HYPERVISOR_tmem_op(&op);
- return rc;
-}
-
-static int xen_tmem_new_pool(struct tmem_pool_uuid uuid,
- u32 flags, unsigned long pagesize)
-{
- struct tmem_op op;
- int rc = 0, pageshift;
-
- for (pageshift = 0; pagesize != 1; pageshift++)
- pagesize >>= 1;
- flags |= (pageshift - 12) << TMEM_POOL_PAGESIZE_SHIFT;
- flags |= TMEM_SPEC_VERSION << TMEM_VERSION_SHIFT;
- op.cmd = TMEM_NEW_POOL;
- op.u.new.uuid[0] = uuid.uuid_lo;
- op.u.new.uuid[1] = uuid.uuid_hi;
- op.u.new.flags = flags;
- rc = HYPERVISOR_tmem_op(&op);
- return rc;
-}
-
-/* xen generic tmem ops */
-
-static int xen_tmem_put_page(u32 pool_id, struct tmem_oid oid,
- u32 index, struct page *page)
-{
- return xen_tmem_op(TMEM_PUT_PAGE, pool_id, oid, index,
- xen_page_to_gfn(page), 0, 0, 0);
-}
-
-static int xen_tmem_get_page(u32 pool_id, struct tmem_oid oid,
- u32 index, struct page *page)
-{
- return xen_tmem_op(TMEM_GET_PAGE, pool_id, oid, index,
- xen_page_to_gfn(page), 0, 0, 0);
-}
-
-static int xen_tmem_flush_page(u32 pool_id, struct tmem_oid oid, u32 index)
-{
- return xen_tmem_op(TMEM_FLUSH_PAGE, pool_id, oid, index,
- 0, 0, 0, 0);
-}
-
-static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid)
-{
- return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0);
-}
-
-
-#ifdef CONFIG_CLEANCACHE
-static int xen_tmem_destroy_pool(u32 pool_id)
-{
- struct tmem_oid oid = { { 0 } };
-
- return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0);
-}
-
-/* cleancache ops */
-
-static void tmem_cleancache_put_page(int pool, struct cleancache_filekey key,
- pgoff_t index, struct page *page)
-{
- u32 ind = (u32) index;
- struct tmem_oid oid = *(struct tmem_oid *)&key;
-
- if (pool < 0)
- return;
- if (ind != index)
- return;
- mb(); /* ensure page is quiescent; tmem may address it with an alias */
- (void)xen_tmem_put_page((u32)pool, oid, ind, page);
-}
-
-static int tmem_cleancache_get_page(int pool, struct cleancache_filekey key,
- pgoff_t index, struct page *page)
-{
- u32 ind = (u32) index;
- struct tmem_oid oid = *(struct tmem_oid *)&key;
- int ret;
-
- /* translate return values to linux semantics */
- if (pool < 0)
- return -1;
- if (ind != index)
- return -1;
- ret = xen_tmem_get_page((u32)pool, oid, ind, page);
- if (ret == 1)
- return 0;
- else
- return -1;
-}
-
-static void tmem_cleancache_flush_page(int pool, struct cleancache_filekey key,
- pgoff_t index)
-{
- u32 ind = (u32) index;
- struct tmem_oid oid = *(struct tmem_oid *)&key;
-
- if (pool < 0)
- return;
- if (ind != index)
- return;
- (void)xen_tmem_flush_page((u32)pool, oid, ind);
-}
-
-static void tmem_cleancache_flush_inode(int pool, struct cleancache_filekey key)
-{
- struct tmem_oid oid = *(struct tmem_oid *)&key;
-
- if (pool < 0)
- return;
- (void)xen_tmem_flush_object((u32)pool, oid);
-}
-
-static void tmem_cleancache_flush_fs(int pool)
-{
- if (pool < 0)
- return;
- (void)xen_tmem_destroy_pool((u32)pool);
-}
-
-static int tmem_cleancache_init_fs(size_t pagesize)
-{
- struct tmem_pool_uuid uuid_private = TMEM_POOL_PRIVATE_UUID;
-
- return xen_tmem_new_pool(uuid_private, 0, pagesize);
-}
-
-static int tmem_cleancache_init_shared_fs(uuid_t *uuid, size_t pagesize)
-{
- struct tmem_pool_uuid shared_uuid;
-
- shared_uuid.uuid_lo = *(u64 *)&uuid->b[0];
- shared_uuid.uuid_hi = *(u64 *)&uuid->b[8];
- return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize);
-}
-
-static const struct cleancache_ops tmem_cleancache_ops = {
- .put_page = tmem_cleancache_put_page,
- .get_page = tmem_cleancache_get_page,
- .invalidate_page = tmem_cleancache_flush_page,
- .invalidate_inode = tmem_cleancache_flush_inode,
- .invalidate_fs = tmem_cleancache_flush_fs,
- .init_shared_fs = tmem_cleancache_init_shared_fs,
- .init_fs = tmem_cleancache_init_fs
-};
-#endif
-
-#ifdef CONFIG_FRONTSWAP
-/* frontswap tmem operations */
-
-/* a single tmem poolid is used for all frontswap "types" (swapfiles) */
-static int tmem_frontswap_poolid;
-
-/*
- * Swizzling increases objects per swaptype, increasing tmem concurrency
- * for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS
- */
-#define SWIZ_BITS 4
-#define SWIZ_MASK ((1 << SWIZ_BITS) - 1)
-#define _oswiz(_type, _ind) ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
-#define iswiz(_ind) (_ind >> SWIZ_BITS)
-
-static inline struct tmem_oid oswiz(unsigned type, u32 ind)
-{
- struct tmem_oid oid = { .oid = { 0 } };
- oid.oid[0] = _oswiz(type, ind);
- return oid;
-}
-
-/* returns 0 if the page was successfully put into frontswap, -1 if not */
-static int tmem_frontswap_store(unsigned type, pgoff_t offset,
- struct page *page)
-{
- u64 ind64 = (u64)offset;
- u32 ind = (u32)offset;
- int pool = tmem_frontswap_poolid;
- int ret;
-
- /* THP isn't supported */
- if (PageTransHuge(page))
- return -1;
-
- if (pool < 0)
- return -1;
- if (ind64 != ind)
- return -1;
- mb(); /* ensure page is quiescent; tmem may address it with an alias */
- ret = xen_tmem_put_page(pool, oswiz(type, ind), iswiz(ind), page);
- /* translate Xen tmem return values to linux semantics */
- if (ret == 1)
- return 0;
- else
- return -1;
-}
-
-/*
- * returns 0 if the page was successfully gotten from frontswap, -1 if
- * was not present (should never happen!)
- */
-static int tmem_frontswap_load(unsigned type, pgoff_t offset,
- struct page *page)
-{
- u64 ind64 = (u64)offset;
- u32 ind = (u32)offset;
- int pool = tmem_frontswap_poolid;
- int ret;
-
- if (pool < 0)
- return -1;
- if (ind64 != ind)
- return -1;
- ret = xen_tmem_get_page(pool, oswiz(type, ind), iswiz(ind), page);
- /* translate Xen tmem return values to linux semantics */
- if (ret == 1)
- return 0;
- else
- return -1;
-}
-
-/* flush a single page from frontswap */
-static void tmem_frontswap_flush_page(unsigned type, pgoff_t offset)
-{
- u64 ind64 = (u64)offset;
- u32 ind = (u32)offset;
- int pool = tmem_frontswap_poolid;
-
- if (pool < 0)
- return;
- if (ind64 != ind)
- return;
- (void) xen_tmem_flush_page(pool, oswiz(type, ind), iswiz(ind));
-}
-
-/* flush all pages from the passed swaptype */
-static void tmem_frontswap_flush_area(unsigned type)
-{
- int pool = tmem_frontswap_poolid;
- int ind;
-
- if (pool < 0)
- return;
- for (ind = SWIZ_MASK; ind >= 0; ind--)
- (void)xen_tmem_flush_object(pool, oswiz(type, ind));
-}
-
-static void tmem_frontswap_init(unsigned ignored)
-{
- struct tmem_pool_uuid private = TMEM_POOL_PRIVATE_UUID;
-
- /* a single tmem poolid is used for all frontswap "types" (swapfiles) */
- if (tmem_frontswap_poolid < 0)
- tmem_frontswap_poolid =
- xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE);
-}
-
-static struct frontswap_ops tmem_frontswap_ops = {
- .store = tmem_frontswap_store,
- .load = tmem_frontswap_load,
- .invalidate_page = tmem_frontswap_flush_page,
- .invalidate_area = tmem_frontswap_flush_area,
- .init = tmem_frontswap_init
-};
-#endif
-
-static int __init xen_tmem_init(void)
-{
- if (!xen_domain())
- return 0;
-#ifdef CONFIG_FRONTSWAP
- if (tmem_enabled && frontswap) {
- char *s = "";
-
- tmem_frontswap_poolid = -1;
- frontswap_register_ops(&tmem_frontswap_ops);
- pr_info("frontswap enabled, RAM provided by Xen Transcendent Memory%s\n",
- s);
- }
-#endif
-#ifdef CONFIG_CLEANCACHE
- BUILD_BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
- if (tmem_enabled && cleancache) {
- int err;
-
- err = cleancache_register_ops(&tmem_cleancache_ops);
- if (err)
- pr_warn("xen-tmem: failed to enable cleancache: %d\n",
- err);
- else
- pr_info("cleancache enabled, RAM provided by "
- "Xen Transcendent Memory\n");
- }
-#endif
-#ifdef CONFIG_XEN_SELFBALLOONING
- /*
- * There is no point of driving pages to the swap system if they
- * aren't going anywhere in tmem universe.
- */
- if (!frontswap) {
- selfshrinking = false;
- selfballooning = false;
- }
- xen_selfballoon_init(selfballooning, selfshrinking);
-#endif
- return 0;
-}
-
-module_init(xen_tmem_init)
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Dan Magenheimer <dan.magenheimer@oracle.com>");
-MODULE_DESCRIPTION("Shim to Xen transcendent memory");
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index a67236b02452..6d12fc368210 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -129,8 +129,6 @@ void xen_balloon_init(void)
{
register_balloon(&balloon_dev);
- register_xen_selfballooning(&balloon_dev);
-
register_xenstore_notifier(&xenstore_notifier);
}
EXPORT_SYMBOL_GPL(xen_balloon_init);
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
deleted file mode 100644
index 246f6122c9ee..000000000000
--- a/drivers/xen/xen-selfballoon.c
+++ /dev/null
@@ -1,579 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/******************************************************************************
- * Xen selfballoon driver (and optional frontswap self-shrinking driver)
- *
- * Copyright (c) 2009-2011, Dan Magenheimer, Oracle Corp.
- *
- * This code complements the cleancache and frontswap patchsets to optimize
- * support for Xen Transcendent Memory ("tmem"). The policy it implements
- * is rudimentary and will likely improve over time, but it does work well
- * enough today.
- *
- * Two functionalities are implemented here which both use "control theory"
- * (feedback) to optimize memory utilization. In a virtualized environment
- * such as Xen, RAM is often a scarce resource and we would like to ensure
- * that each of a possibly large number of virtual machines is using RAM
- * efficiently, i.e. using as little as possible when under light load
- * and obtaining as much as possible when memory demands are high.
- * Since RAM needs vary highly dynamically and sometimes dramatically,
- * "hysteresis" is used, that is, memory target is determined not just
- * on current data but also on past data stored in the system.
- *
- * "Selfballooning" creates memory pressure by managing the Xen balloon
- * driver to decrease and increase available kernel memory, driven
- * largely by the target value of "Committed_AS" (see /proc/meminfo).
- * Since Committed_AS does not account for clean mapped pages (i.e. pages
- * in RAM that are identical to pages on disk), selfballooning has the
- * affect of pushing less frequently used clean pagecache pages out of
- * kernel RAM and, presumably using cleancache, into Xen tmem where
- * Xen can more efficiently optimize RAM utilization for such pages.
- *
- * When kernel memory demand unexpectedly increases faster than Xen, via
- * the selfballoon driver, is able to (or chooses to) provide usable RAM,
- * the kernel may invoke swapping. In most cases, frontswap is able
- * to absorb this swapping into Xen tmem. However, due to the fact
- * that the kernel swap subsystem assumes swapping occurs to a disk,
- * swapped pages may sit on the disk for a very long time; even if
- * the kernel knows the page will never be used again. This is because
- * the disk space costs very little and can be overwritten when
- * necessary. When such stale pages are in frontswap, however, they
- * are taking up valuable real estate. "Frontswap selfshrinking" works
- * to resolve this: When frontswap activity is otherwise stable
- * and the guest kernel is not under memory pressure, the "frontswap
- * selfshrinking" accounts for this by providing pressure to remove some
- * pages from frontswap and return them to kernel memory.
- *
- * For both "selfballooning" and "frontswap-selfshrinking", a worker
- * thread is used and sysfs tunables are provided to adjust the frequency
- * and rate of adjustments to achieve the goal, as well as to disable one
- * or both functions independently.
- *
- * While some argue that this functionality can and should be implemented
- * in userspace, it has been observed that bad things happen (e.g. OOMs).
- *
- * System configuration note: Selfballooning should not be enabled on
- * systems without a sufficiently large swap device configured; for best
- * results, it is recommended that total swap be increased by the size
- * of the guest memory. Note, that selfballooning should be disabled by default
- * if frontswap is not configured. Similarly selfballooning should be enabled
- * by default if frontswap is configured and can be disabled with the
- * "tmem.selfballooning=0" kernel boot option. Finally, when frontswap is
- * configured, frontswap-selfshrinking can be disabled with the
- * "tmem.selfshrink=0" kernel boot option.
- *
- * Selfballooning is disallowed in domain0 and force-disabled.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/memblock.h>
-#include <linux/swap.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/workqueue.h>
-#include <linux/device.h>
-#include <xen/balloon.h>
-#include <xen/tmem.h>
-#include <xen/xen.h>
-
-/* Enable/disable with sysfs. */
-static int xen_selfballooning_enabled __read_mostly;
-
-/*
- * Controls rate at which memory target (this iteration) approaches
- * ultimate goal when memory need is increasing (up-hysteresis) or
- * decreasing (down-hysteresis). Higher values of hysteresis cause
- * slower increases/decreases. The default values for the various
- * parameters were deemed reasonable by experimentation, may be
- * workload-dependent, and can all be adjusted via sysfs.
- */
-static unsigned int selfballoon_downhysteresis __read_mostly = 8;
-static unsigned int selfballoon_uphysteresis __read_mostly = 1;
-
-/* In HZ, controls frequency of worker invocation. */
-static unsigned int selfballoon_interval __read_mostly = 5;
-
-/*
- * Minimum usable RAM in MB for selfballooning target for balloon.
- * If non-zero, it is added to totalreserve_pages and self-ballooning
- * will not balloon below the sum. If zero, a piecewise linear function
- * is calculated as a minimum and added to totalreserve_pages. Note that
- * setting this value indiscriminately may cause OOMs and crashes.
- */
-static unsigned int selfballoon_min_usable_mb;
-
-/*
- * Amount of RAM in MB to add to the target number of pages.
- * Can be used to reserve some more room for caches and the like.
- */
-static unsigned int selfballoon_reserved_mb;
-
-static void selfballoon_process(struct work_struct *work);
-static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
-
-#ifdef CONFIG_FRONTSWAP
-#include <linux/frontswap.h>
-
-/* Enable/disable with sysfs. */
-static bool frontswap_selfshrinking __read_mostly;
-
-/*
- * The default values for the following parameters were deemed reasonable
- * by experimentation, may be workload-dependent, and can all be
- * adjusted via sysfs.
- */
-
-/* Control rate for frontswap shrinking. Higher hysteresis is slower. */
-static unsigned int frontswap_hysteresis __read_mostly = 20;
-
-/*
- * Number of selfballoon worker invocations to wait before observing that
- * frontswap selfshrinking should commence. Note that selfshrinking does
- * not use a separate worker thread.
- */
-static unsigned int frontswap_inertia __read_mostly = 3;
-
-/* Countdown to next invocation of frontswap_shrink() */
-static unsigned long frontswap_inertia_counter;
-
-/*
- * Invoked by the selfballoon worker thread, uses current number of pages
- * in frontswap (frontswap_curr_pages()), previous status, and control
- * values (hysteresis and inertia) to determine if frontswap should be
- * shrunk and what the new frontswap size should be. Note that
- * frontswap_shrink is essentially a partial swapoff that immediately
- * transfers pages from the "swap device" (frontswap) back into kernel
- * RAM; despite the name, frontswap "shrinking" is very different from
- * the "shrinker" interface used by the kernel MM subsystem to reclaim
- * memory.
- */
-static void frontswap_selfshrink(void)
-{
- static unsigned long cur_frontswap_pages;
- unsigned long last_frontswap_pages;
- unsigned long tgt_frontswap_pages;
-
- last_frontswap_pages = cur_frontswap_pages;
- cur_frontswap_pages = frontswap_curr_pages();
- if (!cur_frontswap_pages ||
- (cur_frontswap_pages > last_frontswap_pages)) {
- frontswap_inertia_counter = frontswap_inertia;
- return;
- }
- if (frontswap_inertia_counter && --frontswap_inertia_counter)
- return;
- if (cur_frontswap_pages <= frontswap_hysteresis)
- tgt_frontswap_pages = 0;
- else
- tgt_frontswap_pages = cur_frontswap_pages -
- (cur_frontswap_pages / frontswap_hysteresis);
- frontswap_shrink(tgt_frontswap_pages);
- frontswap_inertia_counter = frontswap_inertia;
-}
-
-#endif /* CONFIG_FRONTSWAP */
-
-#define MB2PAGES(mb) ((mb) << (20 - PAGE_SHIFT))
-#define PAGES2MB(pages) ((pages) >> (20 - PAGE_SHIFT))
-
-/*
- * Use current balloon size, the goal (vm_committed_as), and hysteresis
- * parameters to set a new target balloon size
- */
-static void selfballoon_process(struct work_struct *work)
-{
- unsigned long cur_pages, goal_pages, tgt_pages, floor_pages;
- unsigned long useful_pages;
- bool reset_timer = false;
-
- if (xen_selfballooning_enabled) {
- cur_pages = totalram_pages();
- tgt_pages = cur_pages; /* default is no change */
- goal_pages = vm_memory_committed() +
- totalreserve_pages +
- MB2PAGES(selfballoon_reserved_mb);
-#ifdef CONFIG_FRONTSWAP
- /* allow space for frontswap pages to be repatriated */
- if (frontswap_selfshrinking)
- goal_pages += frontswap_curr_pages();
-#endif
- if (cur_pages > goal_pages)
- tgt_pages = cur_pages -
- ((cur_pages - goal_pages) /
- selfballoon_downhysteresis);
- else if (cur_pages < goal_pages)
- tgt_pages = cur_pages +
- ((goal_pages - cur_pages) /
- selfballoon_uphysteresis);
- /* else if cur_pages == goal_pages, no change */
- useful_pages = max_pfn - totalreserve_pages;
- if (selfballoon_min_usable_mb != 0)
- floor_pages = totalreserve_pages +
- MB2PAGES(selfballoon_min_usable_mb);
- /* piecewise linear function ending in ~3% slope */
- else if (useful_pages < MB2PAGES(16))
- floor_pages = max_pfn; /* not worth ballooning */
- else if (useful_pages < MB2PAGES(64))
- floor_pages = totalreserve_pages + MB2PAGES(16) +
- ((useful_pages - MB2PAGES(16)) >> 1);
- else if (useful_pages < MB2PAGES(512))
- floor_pages = totalreserve_pages + MB2PAGES(40) +
- ((useful_pages - MB2PAGES(40)) >> 3);
- else /* useful_pages >= MB2PAGES(512) */
- floor_pages = totalreserve_pages + MB2PAGES(99) +
- ((useful_pages - MB2PAGES(99)) >> 5);
- if (tgt_pages < floor_pages)
- tgt_pages = floor_pages;
- balloon_set_new_target(tgt_pages +
- balloon_stats.current_pages - totalram_pages());
- reset_timer = true;
- }
-#ifdef CONFIG_FRONTSWAP
- if (frontswap_selfshrinking) {
- frontswap_selfshrink();
- reset_timer = true;
- }
-#endif
- if (reset_timer)
- schedule_delayed_work(&selfballoon_worker,
- selfballoon_interval * HZ);
-}
-
-#ifdef CONFIG_SYSFS
-
-#include <linux/capability.h>
-
-#define SELFBALLOON_SHOW(name, format, args...) \
- static ssize_t show_##name(struct device *dev, \
- struct device_attribute *attr, \
- char *buf) \
- { \
- return sprintf(buf, format, ##args); \
- }
-
-SELFBALLOON_SHOW(selfballooning, "%d\n", xen_selfballooning_enabled);
-
-static ssize_t store_selfballooning(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- bool was_enabled = xen_selfballooning_enabled;
- unsigned long tmp;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- err = kstrtoul(buf, 10, &tmp);
- if (err)
- return err;
- if ((tmp != 0) && (tmp != 1))
- return -EINVAL;
-
- xen_selfballooning_enabled = !!tmp;
- if (!was_enabled && xen_selfballooning_enabled)
- schedule_delayed_work(&selfballoon_worker,
- selfballoon_interval * HZ);
-
- return count;
-}
-
-static DEVICE_ATTR(selfballooning, S_IRUGO | S_IWUSR,
- show_selfballooning, store_selfballooning);
-
-SELFBALLOON_SHOW(selfballoon_interval, "%d\n", selfballoon_interval);
-
-static ssize_t store_selfballoon_interval(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- selfballoon_interval = val;
- return count;
-}
-
-static DEVICE_ATTR(selfballoon_interval, S_IRUGO | S_IWUSR,
- show_selfballoon_interval, store_selfballoon_interval);
-
-SELFBALLOON_SHOW(selfballoon_downhys, "%d\n", selfballoon_downhysteresis);
-
-static ssize_t store_selfballoon_downhys(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- selfballoon_downhysteresis = val;
- return count;
-}
-
-static DEVICE_ATTR(selfballoon_downhysteresis, S_IRUGO | S_IWUSR,
- show_selfballoon_downhys, store_selfballoon_downhys);
-
-
-SELFBALLOON_SHOW(selfballoon_uphys, "%d\n", selfballoon_uphysteresis);
-
-static ssize_t store_selfballoon_uphys(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- selfballoon_uphysteresis = val;
- return count;
-}
-
-static DEVICE_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
- show_selfballoon_uphys, store_selfballoon_uphys);
-
-SELFBALLOON_SHOW(selfballoon_min_usable_mb, "%d\n",
- selfballoon_min_usable_mb);
-
-static ssize_t store_selfballoon_min_usable_mb(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- selfballoon_min_usable_mb = val;
- return count;
-}
-
-static DEVICE_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
- show_selfballoon_min_usable_mb,
- store_selfballoon_min_usable_mb);
-
-SELFBALLOON_SHOW(selfballoon_reserved_mb, "%d\n",
- selfballoon_reserved_mb);
-
-static ssize_t store_selfballoon_reserved_mb(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- selfballoon_reserved_mb = val;
- return count;
-}
-
-static DEVICE_ATTR(selfballoon_reserved_mb, S_IRUGO | S_IWUSR,
- show_selfballoon_reserved_mb,
- store_selfballoon_reserved_mb);
-
-
-#ifdef CONFIG_FRONTSWAP
-SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
-
-static ssize_t store_frontswap_selfshrinking(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- bool was_enabled = frontswap_selfshrinking;
- unsigned long tmp;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &tmp);
- if (err)
- return err;
- if ((tmp != 0) && (tmp != 1))
- return -EINVAL;
- frontswap_selfshrinking = !!tmp;
- if (!was_enabled && !xen_selfballooning_enabled &&
- frontswap_selfshrinking)
- schedule_delayed_work(&selfballoon_worker,
- selfballoon_interval * HZ);
-
- return count;
-}
-
-static DEVICE_ATTR(frontswap_selfshrinking, S_IRUGO | S_IWUSR,
- show_frontswap_selfshrinking, store_frontswap_selfshrinking);
-
-SELFBALLOON_SHOW(frontswap_inertia, "%d\n", frontswap_inertia);
-
-static ssize_t store_frontswap_inertia(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- frontswap_inertia = val;
- frontswap_inertia_counter = val;
- return count;
-}
-
-static DEVICE_ATTR(frontswap_inertia, S_IRUGO | S_IWUSR,
- show_frontswap_inertia, store_frontswap_inertia);
-
-SELFBALLOON_SHOW(frontswap_hysteresis, "%d\n", frontswap_hysteresis);
-
-static ssize_t store_frontswap_hysteresis(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- unsigned long val;
- int err;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- err = kstrtoul(buf, 10, &val);
- if (err)
- return err;
- if (val == 0)
- return -EINVAL;
- frontswap_hysteresis = val;
- return count;
-}
-
-static DEVICE_ATTR(frontswap_hysteresis, S_IRUGO | S_IWUSR,
- show_frontswap_hysteresis, store_frontswap_hysteresis);
-
-#endif /* CONFIG_FRONTSWAP */
-
-static struct attribute *selfballoon_attrs[] = {
- &dev_attr_selfballooning.attr,
- &dev_attr_selfballoon_interval.attr,
- &dev_attr_selfballoon_downhysteresis.attr,
- &dev_attr_selfballoon_uphysteresis.attr,
- &dev_attr_selfballoon_min_usable_mb.attr,
- &dev_attr_selfballoon_reserved_mb.attr,
-#ifdef CONFIG_FRONTSWAP
- &dev_attr_frontswap_selfshrinking.attr,
- &dev_attr_frontswap_hysteresis.attr,
- &dev_attr_frontswap_inertia.attr,
-#endif
- NULL
-};
-
-static const struct attribute_group selfballoon_group = {
- .name = "selfballoon",
- .attrs = selfballoon_attrs
-};
-#endif
-
-int register_xen_selfballooning(struct device *dev)
-{
- int error = -1;
-
-#ifdef CONFIG_SYSFS
- error = sysfs_create_group(&dev->kobj, &selfballoon_group);
-#endif
- return error;
-}
-EXPORT_SYMBOL(register_xen_selfballooning);
-
-int xen_selfballoon_init(bool use_selfballooning, bool use_frontswap_selfshrink)
-{
- bool enable = false;
- unsigned long reserve_pages;
-
- if (!xen_domain())
- return -ENODEV;
-
- if (xen_initial_domain()) {
- pr_info("Xen selfballooning driver disabled for domain0\n");
- return -ENODEV;
- }
-
- xen_selfballooning_enabled = tmem_enabled && use_selfballooning;
- if (xen_selfballooning_enabled) {
- pr_info("Initializing Xen selfballooning driver\n");
- enable = true;
- }
-#ifdef CONFIG_FRONTSWAP
- frontswap_selfshrinking = tmem_enabled && use_frontswap_selfshrink;
- if (frontswap_selfshrinking) {
- pr_info("Initializing frontswap selfshrinking driver\n");
- enable = true;
- }
-#endif
- if (!enable)
- return -ENODEV;
-
- /*
- * Give selfballoon_reserved_mb a default value(10% of total ram pages)
- * to make selfballoon not so aggressive.
- *
- * There are mainly two reasons:
- * 1) The original goal_page didn't consider some pages used by kernel
- * space, like slab pages and memory used by device drivers.
- *
- * 2) The balloon driver may not give back memory to guest OS fast
- * enough when the workload suddenly aquries a lot of physical memory.
- *
- * In both cases, the guest OS will suffer from memory pressure and
- * OOM killer may be triggered.
- * By reserving extra 10% of total ram pages, we can keep the system
- * much more reliably and response faster in some cases.
- */
- if (!selfballoon_reserved_mb) {
- reserve_pages = totalram_pages() / 10;
- selfballoon_reserved_mb = PAGES2MB(reserve_pages);
- }
- schedule_delayed_work(&selfballoon_worker, selfballoon_interval * HZ);
-
- return 0;
-}
-EXPORT_SYMBOL(xen_selfballoon_init);
diff --git a/include/xen/balloon.h b/include/xen/balloon.h
index 4914b93a23f2..a72ef3f88b39 100644
--- a/include/xen/balloon.h
+++ b/include/xen/balloon.h
@@ -28,14 +28,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages);
void free_xenballooned_pages(int nr_pages, struct page **pages);
struct device;
-#ifdef CONFIG_XEN_SELFBALLOONING
-extern int register_xen_selfballooning(struct device *dev);
-#else
-static inline int register_xen_selfballooning(struct device *dev)
-{
- return -ENOSYS;
-}
-#endif
#ifdef CONFIG_XEN_BALLOON
void xen_balloon_init(void);
diff --git a/include/xen/tmem.h b/include/xen/tmem.h
deleted file mode 100644
index c80bafe31f14..000000000000
--- a/include/xen/tmem.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _XEN_TMEM_H
-#define _XEN_TMEM_H
-
-#include <linux/types.h>
-
-#ifdef CONFIG_XEN_TMEM_MODULE
-#define tmem_enabled true
-#else
-/* defined in drivers/xen/tmem.c */
-extern bool tmem_enabled;
-#endif
-
-#ifdef CONFIG_XEN_SELFBALLOONING
-extern int xen_selfballoon_init(bool, bool);
-#endif
-
-#endif /* _XEN_TMEM_H */
--
2.16.4
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH 1/3] xen: remove tmem driver
2019-05-27 10:32 ` [PATCH 1/3] xen: remove tmem driver Juergen Gross
@ 2019-05-28 22:44 ` Boris Ostrovsky
0 siblings, 0 replies; 8+ messages in thread
From: Boris Ostrovsky @ 2019-05-28 22:44 UTC (permalink / raw)
To: Juergen Gross, linux-kernel, linux-doc
Cc: Jonathan Corbet, Stefano Stabellini, xen-devel
> diff --git a/include/xen/balloon.h b/include/xen/balloon.h
> index 4914b93a23f2..a72ef3f88b39 100644
> --- a/include/xen/balloon.h
> +++ b/include/xen/balloon.h
> @@ -28,14 +28,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages);
> void free_xenballooned_pages(int nr_pages, struct page **pages);
>
> struct device;
This can be removed as well.
Other than that,
Acked-by: Boris Ostriovsky <boris.ostrovsky@oracle.com>
> -#ifdef CONFIG_XEN_SELFBALLOONING
> -extern int register_xen_selfballooning(struct device *dev);
> -#else
> -static inline int register_xen_selfballooning(struct device *dev)
> -{
> - return -ENOSYS;
> -}
> -#endif
>
> #ifdef CONFIG_XEN_BALLOON
> void xen_balloon_init(void);
>
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH 2/3] mm: remove cleancache.c
2019-05-27 10:32 [PATCH 0/3] remove tmem and code depending on it Juergen Gross
2019-05-27 10:32 ` [PATCH 1/3] xen: remove tmem driver Juergen Gross
@ 2019-05-27 10:32 ` Juergen Gross
2019-05-27 13:10 ` David Sterba
` (2 more replies)
2019-05-27 10:32 ` [PATCH 3/3] mm: remove tmem specifics from frontswap Juergen Gross
2 siblings, 3 replies; 8+ messages in thread
From: Juergen Gross @ 2019-05-27 10:32 UTC (permalink / raw)
To: linux-kernel, linux-doc, linux-erofs, devel, linux-fsdevel,
linux-btrfs, linux-ext4, linux-f2fs-devel, linux-mm
Cc: Juergen Gross, Jonathan Corbet, Gao Xiang, Chao Yu,
Greg Kroah-Hartman, Alexander Viro, Chris Mason, Josef Bacik,
David Sterba, Theodore Ts'o, Andreas Dilger, Jaegeuk Kim,
Mark Fasheh, Joel Becker, Joseph Qi, ocfs2-devel
With the removal of tmem and xen-selfballoon the only user of
cleancache is gone. Remove it, too.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
Documentation/vm/cleancache.rst | 296 ------------------------------------
Documentation/vm/frontswap.rst | 10 +-
Documentation/vm/index.rst | 1 -
MAINTAINERS | 7 -
drivers/staging/erofs/data.c | 6 -
drivers/staging/erofs/internal.h | 1 -
fs/block_dev.c | 5 -
fs/btrfs/extent_io.c | 9 --
fs/btrfs/super.c | 2 -
fs/ext4/readpage.c | 6 -
fs/ext4/super.c | 2 -
fs/f2fs/data.c | 3 +-
fs/mpage.c | 7 -
fs/ocfs2/super.c | 2 -
fs/super.c | 3 -
include/linux/cleancache.h | 124 ---------------
include/linux/fs.h | 5 -
mm/Kconfig | 22 ---
mm/Makefile | 1 -
mm/cleancache.c | 317 ---------------------------------------
mm/filemap.c | 11 --
mm/truncate.c | 15 +-
22 files changed, 10 insertions(+), 845 deletions(-)
delete mode 100644 Documentation/vm/cleancache.rst
delete mode 100644 include/linux/cleancache.h
delete mode 100644 mm/cleancache.c
diff --git a/Documentation/vm/cleancache.rst b/Documentation/vm/cleancache.rst
deleted file mode 100644
index 68cba9131c31..000000000000
--- a/Documentation/vm/cleancache.rst
+++ /dev/null
@@ -1,296 +0,0 @@
-.. _cleancache:
-
-==========
-Cleancache
-==========
-
-Motivation
-==========
-
-Cleancache is a new optional feature provided by the VFS layer that
-potentially dramatically increases page cache effectiveness for
-many workloads in many environments at a negligible cost.
-
-Cleancache can be thought of as a page-granularity victim cache for clean
-pages that the kernel's pageframe replacement algorithm (PFRA) would like
-to keep around, but can't since there isn't enough memory. So when the
-PFRA "evicts" a page, it first attempts to use cleancache code to
-put the data contained in that page into "transcendent memory", memory
-that is not directly accessible or addressable by the kernel and is
-of unknown and possibly time-varying size.
-
-Later, when a cleancache-enabled filesystem wishes to access a page
-in a file on disk, it first checks cleancache to see if it already
-contains it; if it does, the page of data is copied into the kernel
-and a disk access is avoided.
-
-Transcendent memory "drivers" for cleancache are currently implemented
-in Xen (using hypervisor memory) and zcache (using in-kernel compressed
-memory) and other implementations are in development.
-
-:ref:`FAQs <faq>` are included below.
-
-Implementation Overview
-=======================
-
-A cleancache "backend" that provides transcendent memory registers itself
-to the kernel's cleancache "frontend" by calling cleancache_register_ops,
-passing a pointer to a cleancache_ops structure with funcs set appropriately.
-The functions provided must conform to certain semantics as follows:
-
-Most important, cleancache is "ephemeral". Pages which are copied into
-cleancache have an indefinite lifetime which is completely unknowable
-by the kernel and so may or may not still be in cleancache at any later time.
-Thus, as its name implies, cleancache is not suitable for dirty pages.
-Cleancache has complete discretion over what pages to preserve and what
-pages to discard and when.
-
-Mounting a cleancache-enabled filesystem should call "init_fs" to obtain a
-pool id which, if positive, must be saved in the filesystem's superblock;
-a negative return value indicates failure. A "put_page" will copy a
-(presumably about-to-be-evicted) page into cleancache and associate it with
-the pool id, a file key, and a page index into the file. (The combination
-of a pool id, a file key, and an index is sometimes called a "handle".)
-A "get_page" will copy the page, if found, from cleancache into kernel memory.
-An "invalidate_page" will ensure the page no longer is present in cleancache;
-an "invalidate_inode" will invalidate all pages associated with the specified
-file; and, when a filesystem is unmounted, an "invalidate_fs" will invalidate
-all pages in all files specified by the given pool id and also surrender
-the pool id.
-
-An "init_shared_fs", like init_fs, obtains a pool id but tells cleancache
-to treat the pool as shared using a 128-bit UUID as a key. On systems
-that may run multiple kernels (such as hard partitioned or virtualized
-systems) that may share a clustered filesystem, and where cleancache
-may be shared among those kernels, calls to init_shared_fs that specify the
-same UUID will receive the same pool id, thus allowing the pages to
-be shared. Note that any security requirements must be imposed outside
-of the kernel (e.g. by "tools" that control cleancache). Or a
-cleancache implementation can simply disable shared_init by always
-returning a negative value.
-
-If a get_page is successful on a non-shared pool, the page is invalidated
-(thus making cleancache an "exclusive" cache). On a shared pool, the page
-is NOT invalidated on a successful get_page so that it remains accessible to
-other sharers. The kernel is responsible for ensuring coherency between
-cleancache (shared or not), the page cache, and the filesystem, using
-cleancache invalidate operations as required.
-
-Note that cleancache must enforce put-put-get coherency and get-get
-coherency. For the former, if two puts are made to the same handle but
-with different data, say AAA by the first put and BBB by the second, a
-subsequent get can never return the stale data (AAA). For get-get coherency,
-if a get for a given handle fails, subsequent gets for that handle will
-never succeed unless preceded by a successful put with that handle.
-
-Last, cleancache provides no SMP serialization guarantees; if two
-different Linux threads are simultaneously putting and invalidating a page
-with the same handle, the results are indeterminate. Callers must
-lock the page to ensure serial behavior.
-
-Cleancache Performance Metrics
-==============================
-
-If properly configured, monitoring of cleancache is done via debugfs in
-the `/sys/kernel/debug/cleancache` directory. The effectiveness of cleancache
-can be measured (across all filesystems) with:
-
-``succ_gets``
- number of gets that were successful
-
-``failed_gets``
- number of gets that failed
-
-``puts``
- number of puts attempted (all "succeed")
-
-``invalidates``
- number of invalidates attempted
-
-A backend implementation may provide additional metrics.
-
-.. _faq:
-
-FAQ
-===
-
-* Where's the value? (Andrew Morton)
-
-Cleancache provides a significant performance benefit to many workloads
-in many environments with negligible overhead by improving the
-effectiveness of the pagecache. Clean pagecache pages are
-saved in transcendent memory (RAM that is otherwise not directly
-addressable to the kernel); fetching those pages later avoids "refaults"
-and thus disk reads.
-
-Cleancache (and its sister code "frontswap") provide interfaces for
-this transcendent memory (aka "tmem"), which conceptually lies between
-fast kernel-directly-addressable RAM and slower DMA/asynchronous devices.
-Disallowing direct kernel or userland reads/writes to tmem
-is ideal when data is transformed to a different form and size (such
-as with compression) or secretly moved (as might be useful for write-
-balancing for some RAM-like devices). Evicted page-cache pages (and
-swap pages) are a great use for this kind of slower-than-RAM-but-much-
-faster-than-disk transcendent memory, and the cleancache (and frontswap)
-"page-object-oriented" specification provides a nice way to read and
-write -- and indirectly "name" -- the pages.
-
-In the virtual case, the whole point of virtualization is to statistically
-multiplex physical resources across the varying demands of multiple
-virtual machines. This is really hard to do with RAM and efforts to
-do it well with no kernel change have essentially failed (except in some
-well-publicized special-case workloads). Cleancache -- and frontswap --
-with a fairly small impact on the kernel, provide a huge amount
-of flexibility for more dynamic, flexible RAM multiplexing.
-Specifically, the Xen Transcendent Memory backend allows otherwise
-"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple
-virtual machines, but the pages can be compressed and deduplicated to
-optimize RAM utilization. And when guest OS's are induced to surrender
-underutilized RAM (e.g. with "self-ballooning"), page cache pages
-are the first to go, and cleancache allows those pages to be
-saved and reclaimed if overall host system memory conditions allow.
-
-And the identical interface used for cleancache can be used in
-physical systems as well. The zcache driver acts as a memory-hungry
-device that stores pages of data in a compressed state. And
-the proposed "RAMster" driver shares RAM across multiple physical
-systems.
-
-* Why does cleancache have its sticky fingers so deep inside the
- filesystems and VFS? (Andrew Morton and Christoph Hellwig)
-
-The core hooks for cleancache in VFS are in most cases a single line
-and the minimum set are placed precisely where needed to maintain
-coherency (via cleancache_invalidate operations) between cleancache,
-the page cache, and disk. All hooks compile into nothingness if
-cleancache is config'ed off and turn into a function-pointer-
-compare-to-NULL if config'ed on but no backend claims the ops
-functions, or to a compare-struct-element-to-negative if a
-backend claims the ops functions but a filesystem doesn't enable
-cleancache.
-
-Some filesystems are built entirely on top of VFS and the hooks
-in VFS are sufficient, so don't require an "init_fs" hook; the
-initial implementation of cleancache didn't provide this hook.
-But for some filesystems (such as btrfs), the VFS hooks are
-incomplete and one or more hooks in fs-specific code are required.
-And for some other filesystems, such as tmpfs, cleancache may
-be counterproductive. So it seemed prudent to require a filesystem
-to "opt in" to use cleancache, which requires adding a hook in
-each filesystem. Not all filesystems are supported by cleancache
-only because they haven't been tested. The existing set should
-be sufficient to validate the concept, the opt-in approach means
-that untested filesystems are not affected, and the hooks in the
-existing filesystems should make it very easy to add more
-filesystems in the future.
-
-The total impact of the hooks to existing fs and mm files is only
-about 40 lines added (not counting comments and blank lines).
-
-* Why not make cleancache asynchronous and batched so it can more
- easily interface with real devices with DMA instead of copying each
- individual page? (Minchan Kim)
-
-The one-page-at-a-time copy semantics simplifies the implementation
-on both the frontend and backend and also allows the backend to
-do fancy things on-the-fly like page compression and
-page deduplication. And since the data is "gone" (copied into/out
-of the pageframe) before the cleancache get/put call returns,
-a great deal of race conditions and potential coherency issues
-are avoided. While the interface seems odd for a "real device"
-or for real kernel-addressable RAM, it makes perfect sense for
-transcendent memory.
-
-* Why is non-shared cleancache "exclusive"? And where is the
- page "invalidated" after a "get"? (Minchan Kim)
-
-The main reason is to free up space in transcendent memory and
-to avoid unnecessary cleancache_invalidate calls. If you want inclusive,
-the page can be "put" immediately following the "get". If
-put-after-get for inclusive becomes common, the interface could
-be easily extended to add a "get_no_invalidate" call.
-
-The invalidate is done by the cleancache backend implementation.
-
-* What's the performance impact?
-
-Performance analysis has been presented at OLS'09 and LCA'10.
-Briefly, performance gains can be significant on most workloads,
-especially when memory pressure is high (e.g. when RAM is
-overcommitted in a virtual workload); and because the hooks are
-invoked primarily in place of or in addition to a disk read/write,
-overhead is negligible even in worst case workloads. Basically
-cleancache replaces I/O with memory-copy-CPU-overhead; on older
-single-core systems with slow memory-copy speeds, cleancache
-has little value, but in newer multicore machines, especially
-consolidated/virtualized machines, it has great value.
-
-* How do I add cleancache support for filesystem X? (Boaz Harrash)
-
-Filesystems that are well-behaved and conform to certain
-restrictions can utilize cleancache simply by making a call to
-cleancache_init_fs at mount time. Unusual, misbehaving, or
-poorly layered filesystems must either add additional hooks
-and/or undergo extensive additional testing... or should just
-not enable the optional cleancache.
-
-Some points for a filesystem to consider:
-
- - The FS should be block-device-based (e.g. a ram-based FS such
- as tmpfs should not enable cleancache)
- - To ensure coherency/correctness, the FS must ensure that all
- file removal or truncation operations either go through VFS or
- add hooks to do the equivalent cleancache "invalidate" operations
- - To ensure coherency/correctness, either inode numbers must
- be unique across the lifetime of the on-disk file OR the
- FS must provide an "encode_fh" function.
- - The FS must call the VFS superblock alloc and deactivate routines
- or add hooks to do the equivalent cleancache calls done there.
- - To maximize performance, all pages fetched from the FS should
- go through the do_mpag_readpage routine or the FS should add
- hooks to do the equivalent (cf. btrfs)
- - Currently, the FS blocksize must be the same as PAGESIZE. This
- is not an architectural restriction, but no backends currently
- support anything different.
- - A clustered FS should invoke the "shared_init_fs" cleancache
- hook to get best performance for some backends.
-
-* Why not use the KVA of the inode as the key? (Christoph Hellwig)
-
-If cleancache would use the inode virtual address instead of
-inode/filehandle, the pool id could be eliminated. But, this
-won't work because cleancache retains pagecache data pages
-persistently even when the inode has been pruned from the
-inode unused list, and only invalidates the data page if the file
-gets removed/truncated. So if cleancache used the inode kva,
-there would be potential coherency issues if/when the inode
-kva is reused for a different file. Alternately, if cleancache
-invalidated the pages when the inode kva was freed, much of the value
-of cleancache would be lost because the cache of pages in cleanache
-is potentially much larger than the kernel pagecache and is most
-useful if the pages survive inode cache removal.
-
-* Why is a global variable required?
-
-The cleancache_enabled flag is checked in all of the frequently-used
-cleancache hooks. The alternative is a function call to check a static
-variable. Since cleancache is enabled dynamically at runtime, systems
-that don't enable cleancache would suffer thousands (possibly
-tens-of-thousands) of unnecessary function calls per second. So the
-global variable allows cleancache to be enabled by default at compile
-time, but have insignificant performance impact when cleancache remains
-disabled at runtime.
-
-* Does cleanache work with KVM?
-
-The memory model of KVM is sufficiently different that a cleancache
-backend may have less value for KVM. This remains to be tested,
-especially in an overcommitted system.
-
-* Does cleancache work in userspace? It sounds useful for
- memory hungry caches like web browsers. (Jamie Lokier)
-
-No plans yet, though we agree it sounds useful, at least for
-apps that bypass the page cache (e.g. O_DIRECT).
-
-Last updated: Dan Magenheimer, April 13 2011
diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst
index 1979f430c1c5..511c921bc8d2 100644
--- a/Documentation/vm/frontswap.rst
+++ b/Documentation/vm/frontswap.rst
@@ -8,8 +8,8 @@ Frontswap provides a "transcendent memory" interface for swap pages.
In some environments, dramatic performance savings may be obtained because
swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
-(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends"
-and the only necessary changes to the core kernel for transcendent memory;
+(Note, frontswap is the "frontend"
+and the only necessary change to the core kernel for transcendent memory;
all other supporting code -- the "backends" -- is implemented as drivers.
See the LWN.net article `Transcendent memory in a nutshell`_
for a detailed overview of frontswap and related kernel parts)
@@ -87,11 +87,11 @@ This interface is ideal when data is transformed to a different form
and size (such as with compression) or secretly moved (as might be
useful for write-balancing for some RAM-like devices). Swap pages (and
evicted page-cache pages) are a great use for this kind of slower-than-RAM-
-but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and
-cleancache) interface to transcendent memory provides a nice way to read
+but-much-faster-than-disk "pseudo-RAM device" and the frontswap
+interface to transcendent memory provides a nice way to read
and write -- and indirectly "name" -- the pages.
-Frontswap -- and cleancache -- with a fairly small impact on the kernel,
+Frontswap with a fairly small impact on the kernel,
provides a huge amount of flexibility for more dynamic, flexible RAM
utilization in various system configurations:
diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst
index e8d943b21cf9..9e42be5f0c44 100644
--- a/Documentation/vm/index.rst
+++ b/Documentation/vm/index.rst
@@ -30,7 +30,6 @@ descriptions of data structures and algorithms.
active_mm
balance
- cleancache
frontswap
highmem
hmm
diff --git a/MAINTAINERS b/MAINTAINERS
index 2336dd26ece4..d33b46475629 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3928,13 +3928,6 @@ M: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
S: Maintained
F: .clang-format
-CLEANCACHE API
-M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L: linux-kernel@vger.kernel.org
-S: Maintained
-F: mm/cleancache.c
-F: include/linux/cleancache.h
-
CLK API
M: Russell King <linux@armlinux.org.uk>
L: linux-clk@vger.kernel.org
diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c
index 746685f90564..0f5f9429a01c 100644
--- a/drivers/staging/erofs/data.c
+++ b/drivers/staging/erofs/data.c
@@ -205,12 +205,6 @@ static inline struct bio *erofs_read_raw_page(struct bio *bio,
goto has_updated;
}
- if (cleancache_get_page(page) == 0) {
- err = 0;
- SetPageUptodate(page);
- goto has_updated;
- }
-
/* note that for readpage case, bio also equals to NULL */
if (bio &&
/* not continuous */
diff --git a/drivers/staging/erofs/internal.h b/drivers/staging/erofs/internal.h
index c47778b3fabd..a31b26b28985 100644
--- a/drivers/staging/erofs/internal.h
+++ b/drivers/staging/erofs/internal.h
@@ -19,7 +19,6 @@
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
-#include <linux/cleancache.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include "erofs_fs.h"
diff --git a/fs/block_dev.c b/fs/block_dev.c
index e6886c93c89d..5ddd460a927b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -29,7 +29,6 @@
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
-#include <linux/cleancache.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/uaccess.h>
@@ -96,10 +95,6 @@ void invalidate_bdev(struct block_device *bdev)
lru_add_drain_all(); /* make sure all lru add caches are flushed */
invalidate_mapping_pages(mapping, 0, -1);
}
- /* 99% of the time, we don't need to flush the cleancache on the bdev.
- * But, for the strange corners, lets be cautious
- */
- cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index db337e53aab3..07f468b4dcea 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -12,7 +12,6 @@
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/prefetch.h>
-#include <linux/cleancache.h>
#include "extent_io.h"
#include "extent_map.h"
#include "ctree.h"
@@ -3015,14 +3014,6 @@ static int __do_readpage(struct extent_io_tree *tree,
set_page_extent_mapped(page);
- if (!PageUptodate(page)) {
- if (cleancache_get_page(page) == 0) {
- BUG_ON(blocksize != PAGE_SIZE);
- unlock_extent(tree, start, end);
- goto out;
- }
- }
-
if (page->index == last_byte >> PAGE_SHIFT) {
char *userpage;
size_t zero_offset = offset_in_page(last_byte);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0645ec428b4f..707f0096b437 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -23,7 +23,6 @@
#include <linux/miscdevice.h>
#include <linux/magic.h>
#include <linux/slab.h>
-#include <linux/cleancache.h>
#include <linux/ratelimit.h>
#include <linux/crc32c.h>
#include <linux/btrfs.h>
@@ -1228,7 +1227,6 @@ static int btrfs_fill_super(struct super_block *sb,
goto fail_close;
}
- cleancache_init_fs(sb);
sb->s_flags |= SB_ACTIVE;
return 0;
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index c916017db334..5b471552e794 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -43,7 +43,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
#include "ext4.h"
@@ -225,11 +224,6 @@ int ext4_mpage_readpages(struct address_space *mapping,
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
- if (fully_mapped && blocks_per_page == 1 &&
- !PageUptodate(page) && cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
/*
* This page will go to BIO. Do we need to send this
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4079605d437a..04d083364497 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -39,7 +39,6 @@
#include <linux/log2.h>
#include <linux/crc16.h>
#include <linux/dax.h>
-#include <linux/cleancache.h>
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
@@ -2307,7 +2306,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
- cleancache_init_fs(sb);
return err;
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index eda4181d2092..935c98ef6169 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -16,7 +16,6 @@
#include <linux/bio.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
-#include <linux/cleancache.h>
#include <linux/sched/signal.h>
#include "f2fs.h"
@@ -1563,7 +1562,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
block_nr = map->m_pblk + block_in_file - map->m_lblk;
SetPageMappedToDisk(page);
- if (!PageUptodate(page) && !cleancache_get_page(page)) {
+ if (!PageUptodate(page)) {
SetPageUptodate(page);
goto confused;
}
diff --git a/fs/mpage.c b/fs/mpage.c
index 436a85260394..744b18ec3d98 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -29,7 +29,6 @@
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
-#include <linux/cleancache.h>
#include "internal.h"
/*
@@ -284,12 +283,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
SetPageMappedToDisk(page);
}
- if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
- cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
-
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8821bc7b9c72..b3f18d3b9da0 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -41,7 +41,6 @@
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/quotaops.h>
-#include <linux/cleancache.h>
#include <linux/signal.h>
#define CREATE_TRACE_POINTS
@@ -2328,7 +2327,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
mlog_errno(status);
goto bail;
}
- cleancache_init_shared_fs(sb);
osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM);
if (!osb->ocfs2_wq) {
diff --git a/fs/super.c b/fs/super.c
index 2739f57515f8..5ce5121e9e76 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -31,7 +31,6 @@
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
-#include <linux/cleancache.h>
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
@@ -257,7 +256,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
s->s_maxbytes = MAX_NON_LFS;
s->s_op = &default_op;
s->s_time_gran = 1000000000;
- s->cleancache_poolid = CLEANCACHE_NO_POOL;
s->s_shrink.seeks = DEFAULT_SEEKS;
s->s_shrink.scan_objects = super_cache_scan;
@@ -326,7 +324,6 @@ void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
- cleancache_invalidate_fs(s);
unregister_shrinker(&s->s_shrink);
fs->kill_sb(s);
diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h
deleted file mode 100644
index 5f5730c1d324..000000000000
--- a/include/linux/cleancache.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_CLEANCACHE_H
-#define _LINUX_CLEANCACHE_H
-
-#include <linux/fs.h>
-#include <linux/exportfs.h>
-#include <linux/mm.h>
-
-#define CLEANCACHE_NO_POOL -1
-#define CLEANCACHE_NO_BACKEND -2
-#define CLEANCACHE_NO_BACKEND_SHARED -3
-
-#define CLEANCACHE_KEY_MAX 6
-
-/*
- * cleancache requires every file with a page in cleancache to have a
- * unique key unless/until the file is removed/truncated. For some
- * filesystems, the inode number is unique, but for "modern" filesystems
- * an exportable filehandle is required (see exportfs.h)
- */
-struct cleancache_filekey {
- union {
- ino_t ino;
- __u32 fh[CLEANCACHE_KEY_MAX];
- u32 key[CLEANCACHE_KEY_MAX];
- } u;
-};
-
-struct cleancache_ops {
- int (*init_fs)(size_t);
- int (*init_shared_fs)(uuid_t *uuid, size_t);
- int (*get_page)(int, struct cleancache_filekey,
- pgoff_t, struct page *);
- void (*put_page)(int, struct cleancache_filekey,
- pgoff_t, struct page *);
- void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t);
- void (*invalidate_inode)(int, struct cleancache_filekey);
- void (*invalidate_fs)(int);
-};
-
-extern int cleancache_register_ops(const struct cleancache_ops *ops);
-extern void __cleancache_init_fs(struct super_block *);
-extern void __cleancache_init_shared_fs(struct super_block *);
-extern int __cleancache_get_page(struct page *);
-extern void __cleancache_put_page(struct page *);
-extern void __cleancache_invalidate_page(struct address_space *, struct page *);
-extern void __cleancache_invalidate_inode(struct address_space *);
-extern void __cleancache_invalidate_fs(struct super_block *);
-
-#ifdef CONFIG_CLEANCACHE
-#define cleancache_enabled (1)
-static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping)
-{
- return mapping->host->i_sb->cleancache_poolid >= 0;
-}
-static inline bool cleancache_fs_enabled(struct page *page)
-{
- return cleancache_fs_enabled_mapping(page->mapping);
-}
-#else
-#define cleancache_enabled (0)
-#define cleancache_fs_enabled(_page) (0)
-#define cleancache_fs_enabled_mapping(_page) (0)
-#endif
-
-/*
- * The shim layer provided by these inline functions allows the compiler
- * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE
- * is disabled, to a single global variable check if CONFIG_CLEANCACHE
- * is enabled but no cleancache "backend" has dynamically enabled it,
- * and, for the most frequent cleancache ops, to a single global variable
- * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled
- * and a cleancache backend has dynamically enabled cleancache, but the
- * filesystem referenced by that cleancache op has not enabled cleancache.
- * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially
- * no measurable performance impact.
- */
-
-static inline void cleancache_init_fs(struct super_block *sb)
-{
- if (cleancache_enabled)
- __cleancache_init_fs(sb);
-}
-
-static inline void cleancache_init_shared_fs(struct super_block *sb)
-{
- if (cleancache_enabled)
- __cleancache_init_shared_fs(sb);
-}
-
-static inline int cleancache_get_page(struct page *page)
-{
- if (cleancache_enabled && cleancache_fs_enabled(page))
- return __cleancache_get_page(page);
- return -1;
-}
-
-static inline void cleancache_put_page(struct page *page)
-{
- if (cleancache_enabled && cleancache_fs_enabled(page))
- __cleancache_put_page(page);
-}
-
-static inline void cleancache_invalidate_page(struct address_space *mapping,
- struct page *page)
-{
- /* careful... page->mapping is NULL sometimes when this is called */
- if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
- __cleancache_invalidate_page(mapping, page);
-}
-
-static inline void cleancache_invalidate_inode(struct address_space *mapping)
-{
- if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
- __cleancache_invalidate_inode(mapping);
-}
-
-static inline void cleancache_invalidate_fs(struct super_block *sb)
-{
- if (cleancache_enabled)
- __cleancache_invalidate_fs(sb);
-}
-
-#endif /* _LINUX_CLEANCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f7fdfe93e25d..a2a965bd30f2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1475,11 +1475,6 @@ struct super_block {
const struct dentry_operations *s_d_op; /* default d_op for dentries */
- /*
- * Saved pool identifier for cleancache (-1 means none)
- */
- int cleancache_poolid;
-
struct shrinker s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
diff --git a/mm/Kconfig b/mm/Kconfig
index f0c76ba47695..5166fe4af00b 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -435,28 +435,6 @@ config NEED_PER_CPU_KM
bool
default y
-config CLEANCACHE
- bool "Enable cleancache driver to cache clean pages if tmem is present"
- help
- Cleancache can be thought of as a page-granularity victim cache
- for clean pages that the kernel's pageframe replacement algorithm
- (PFRA) would like to keep around, but can't since there isn't enough
- memory. So when the PFRA "evicts" a page, it first attempts to use
- cleancache code to put the data contained in that page into
- "transcendent memory", memory that is not directly accessible or
- addressable by the kernel and is of unknown and possibly
- time-varying size. And when a cleancache-enabled
- filesystem wishes to access a page in a file on disk, it first
- checks cleancache to see if it already contains it; if it does,
- the page is copied into the kernel and a disk access is avoided.
- When a transcendent memory driver is available (such as zcache or
- Xen transcendent memory), a significant I/O reduction
- may be achieved. When none is available, all cleancache calls
- are reduced to a single pointer-compare-against-NULL resulting
- in a negligible performance hit.
-
- If unsure, say Y to enable cleancache
-
config FRONTSWAP
bool "Enable frontswap to cache swap pages if tmem is present"
depends on SWAP
diff --git a/mm/Makefile b/mm/Makefile
index ac5e5ba78874..312cc7de894c 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -85,7 +85,6 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o
obj-$(CONFIG_PAGE_OWNER) += page_owner.o
-obj-$(CONFIG_CLEANCACHE) += cleancache.o
obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
obj-$(CONFIG_ZPOOL) += zpool.o
obj-$(CONFIG_ZBUD) += zbud.o
diff --git a/mm/cleancache.c b/mm/cleancache.c
deleted file mode 100644
index 2bf12da9baa0..000000000000
--- a/mm/cleancache.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * Cleancache frontend
- *
- * This code provides the generic "frontend" layer to call a matching
- * "backend" driver implementation of cleancache. See
- * Documentation/vm/cleancache.rst for more information.
- *
- * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
- * Author: Dan Magenheimer
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/exportfs.h>
-#include <linux/mm.h>
-#include <linux/debugfs.h>
-#include <linux/cleancache.h>
-
-/*
- * cleancache_ops is set by cleancache_register_ops to contain the pointers
- * to the cleancache "backend" implementation functions.
- */
-static const struct cleancache_ops *cleancache_ops __read_mostly;
-
-/*
- * Counters available via /sys/kernel/debug/cleancache (if debugfs is
- * properly configured. These are for information only so are not protected
- * against increment races.
- */
-static u64 cleancache_succ_gets;
-static u64 cleancache_failed_gets;
-static u64 cleancache_puts;
-static u64 cleancache_invalidates;
-
-static void cleancache_register_ops_sb(struct super_block *sb, void *unused)
-{
- switch (sb->cleancache_poolid) {
- case CLEANCACHE_NO_BACKEND:
- __cleancache_init_fs(sb);
- break;
- case CLEANCACHE_NO_BACKEND_SHARED:
- __cleancache_init_shared_fs(sb);
- break;
- }
-}
-
-/*
- * Register operations for cleancache. Returns 0 on success.
- */
-int cleancache_register_ops(const struct cleancache_ops *ops)
-{
- if (cmpxchg(&cleancache_ops, NULL, ops))
- return -EBUSY;
-
- /*
- * A cleancache backend can be built as a module and hence loaded after
- * a cleancache enabled filesystem has called cleancache_init_fs. To
- * handle such a scenario, here we call ->init_fs or ->init_shared_fs
- * for each active super block. To differentiate between local and
- * shared filesystems, we temporarily initialize sb->cleancache_poolid
- * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED
- * respectively in case there is no backend registered at the time
- * cleancache_init_fs or cleancache_init_shared_fs is called.
- *
- * Since filesystems can be mounted concurrently with cleancache
- * backend registration, we have to be careful to guarantee that all
- * cleancache enabled filesystems that has been mounted by the time
- * cleancache_register_ops is called has got and all mounted later will
- * get cleancache_poolid. This is assured by the following statements
- * tied together:
- *
- * a) iterate_supers skips only those super blocks that has started
- * ->kill_sb
- *
- * b) if iterate_supers encounters a super block that has not finished
- * ->mount yet, it waits until it is finished
- *
- * c) cleancache_init_fs is called from ->mount and
- * cleancache_invalidate_fs is called from ->kill_sb
- *
- * d) we call iterate_supers after cleancache_ops has been set
- *
- * From a) it follows that if iterate_supers skips a super block, then
- * either the super block is already dead, in which case we do not need
- * to bother initializing cleancache for it, or it was mounted after we
- * initiated iterate_supers. In the latter case, it must have seen
- * cleancache_ops set according to d) and initialized cleancache from
- * ->mount by itself according to c). This proves that we call
- * ->init_fs at least once for each active super block.
- *
- * From b) and c) it follows that if iterate_supers encounters a super
- * block that has already started ->init_fs, it will wait until ->mount
- * and hence ->init_fs has finished, then check cleancache_poolid, see
- * that it has already been set and therefore do nothing. This proves
- * that we call ->init_fs no more than once for each super block.
- *
- * Combined together, the last two paragraphs prove the function
- * correctness.
- *
- * Note that various cleancache callbacks may proceed before this
- * function is called or even concurrently with it, but since
- * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop
- * until the corresponding ->init_fs has been actually called and
- * cleancache_ops has been set.
- */
- iterate_supers(cleancache_register_ops_sb, NULL);
- return 0;
-}
-EXPORT_SYMBOL(cleancache_register_ops);
-
-/* Called by a cleancache-enabled filesystem at time of mount */
-void __cleancache_init_fs(struct super_block *sb)
-{
- int pool_id = CLEANCACHE_NO_BACKEND;
-
- if (cleancache_ops) {
- pool_id = cleancache_ops->init_fs(PAGE_SIZE);
- if (pool_id < 0)
- pool_id = CLEANCACHE_NO_POOL;
- }
- sb->cleancache_poolid = pool_id;
-}
-EXPORT_SYMBOL(__cleancache_init_fs);
-
-/* Called by a cleancache-enabled clustered filesystem at time of mount */
-void __cleancache_init_shared_fs(struct super_block *sb)
-{
- int pool_id = CLEANCACHE_NO_BACKEND_SHARED;
-
- if (cleancache_ops) {
- pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE);
- if (pool_id < 0)
- pool_id = CLEANCACHE_NO_POOL;
- }
- sb->cleancache_poolid = pool_id;
-}
-EXPORT_SYMBOL(__cleancache_init_shared_fs);
-
-/*
- * If the filesystem uses exportable filehandles, use the filehandle as
- * the key, else use the inode number.
- */
-static int cleancache_get_key(struct inode *inode,
- struct cleancache_filekey *key)
-{
- int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *);
- int len = 0, maxlen = CLEANCACHE_KEY_MAX;
- struct super_block *sb = inode->i_sb;
-
- key->u.ino = inode->i_ino;
- if (sb->s_export_op != NULL) {
- fhfn = sb->s_export_op->encode_fh;
- if (fhfn) {
- len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL);
- if (len <= FILEID_ROOT || len == FILEID_INVALID)
- return -1;
- if (maxlen > CLEANCACHE_KEY_MAX)
- return -1;
- }
- }
- return 0;
-}
-
-/*
- * "Get" data from cleancache associated with the poolid/inode/index
- * that were specified when the data was put to cleanache and, if
- * successful, use it to fill the specified page with data and return 0.
- * The pageframe is unchanged and returns -1 if the get fails.
- * Page must be locked by caller.
- *
- * The function has two checks before any action is taken - whether
- * a backend is registered and whether the sb->cleancache_poolid
- * is correct.
- */
-int __cleancache_get_page(struct page *page)
-{
- int ret = -1;
- int pool_id;
- struct cleancache_filekey key = { .u.key = { 0 } };
-
- if (!cleancache_ops) {
- cleancache_failed_gets++;
- goto out;
- }
-
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- pool_id = page->mapping->host->i_sb->cleancache_poolid;
- if (pool_id < 0)
- goto out;
-
- if (cleancache_get_key(page->mapping->host, &key) < 0)
- goto out;
-
- ret = cleancache_ops->get_page(pool_id, key, page->index, page);
- if (ret == 0)
- cleancache_succ_gets++;
- else
- cleancache_failed_gets++;
-out:
- return ret;
-}
-EXPORT_SYMBOL(__cleancache_get_page);
-
-/*
- * "Put" data from a page to cleancache and associate it with the
- * (previously-obtained per-filesystem) poolid and the page's,
- * inode and page index. Page must be locked. Note that a put_page
- * always "succeeds", though a subsequent get_page may succeed or fail.
- *
- * The function has two checks before any action is taken - whether
- * a backend is registered and whether the sb->cleancache_poolid
- * is correct.
- */
-void __cleancache_put_page(struct page *page)
-{
- int pool_id;
- struct cleancache_filekey key = { .u.key = { 0 } };
-
- if (!cleancache_ops) {
- cleancache_puts++;
- return;
- }
-
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- pool_id = page->mapping->host->i_sb->cleancache_poolid;
- if (pool_id >= 0 &&
- cleancache_get_key(page->mapping->host, &key) >= 0) {
- cleancache_ops->put_page(pool_id, key, page->index, page);
- cleancache_puts++;
- }
-}
-EXPORT_SYMBOL(__cleancache_put_page);
-
-/*
- * Invalidate any data from cleancache associated with the poolid and the
- * page's inode and page index so that a subsequent "get" will fail.
- *
- * The function has two checks before any action is taken - whether
- * a backend is registered and whether the sb->cleancache_poolid
- * is correct.
- */
-void __cleancache_invalidate_page(struct address_space *mapping,
- struct page *page)
-{
- /* careful... page->mapping is NULL sometimes when this is called */
- int pool_id = mapping->host->i_sb->cleancache_poolid;
- struct cleancache_filekey key = { .u.key = { 0 } };
-
- if (!cleancache_ops)
- return;
-
- if (pool_id >= 0) {
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (cleancache_get_key(mapping->host, &key) >= 0) {
- cleancache_ops->invalidate_page(pool_id,
- key, page->index);
- cleancache_invalidates++;
- }
- }
-}
-EXPORT_SYMBOL(__cleancache_invalidate_page);
-
-/*
- * Invalidate all data from cleancache associated with the poolid and the
- * mappings's inode so that all subsequent gets to this poolid/inode
- * will fail.
- *
- * The function has two checks before any action is taken - whether
- * a backend is registered and whether the sb->cleancache_poolid
- * is correct.
- */
-void __cleancache_invalidate_inode(struct address_space *mapping)
-{
- int pool_id = mapping->host->i_sb->cleancache_poolid;
- struct cleancache_filekey key = { .u.key = { 0 } };
-
- if (!cleancache_ops)
- return;
-
- if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
- cleancache_ops->invalidate_inode(pool_id, key);
-}
-EXPORT_SYMBOL(__cleancache_invalidate_inode);
-
-/*
- * Called by any cleancache-enabled filesystem at time of unmount;
- * note that pool_id is surrendered and may be returned by a subsequent
- * cleancache_init_fs or cleancache_init_shared_fs.
- */
-void __cleancache_invalidate_fs(struct super_block *sb)
-{
- int pool_id;
-
- pool_id = sb->cleancache_poolid;
- sb->cleancache_poolid = CLEANCACHE_NO_POOL;
-
- if (cleancache_ops && pool_id >= 0)
- cleancache_ops->invalidate_fs(pool_id);
-}
-EXPORT_SYMBOL(__cleancache_invalidate_fs);
-
-static int __init init_cleancache(void)
-{
-#ifdef CONFIG_DEBUG_FS
- struct dentry *root = debugfs_create_dir("cleancache", NULL);
- if (root == NULL)
- return -ENXIO;
- debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets);
- debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets);
- debugfs_create_u64("puts", 0444, root, &cleancache_puts);
- debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates);
-#endif
- return 0;
-}
-module_init(init_cleancache)
diff --git a/mm/filemap.c b/mm/filemap.c
index df2006ba0cfa..de7c4655d752 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -35,7 +35,6 @@
#include <linux/cpuset.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
-#include <linux/cleancache.h>
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
#include <linux/delayacct.h>
@@ -157,16 +156,6 @@ static void unaccount_page_cache_page(struct address_space *mapping,
{
int nr;
- /*
- * if we're uptodate, flush out into the cleancache, otherwise
- * invalidate any existing cleancache entries. We can't leave
- * stale data around in the cleancache once our page is gone
- */
- if (PageUptodate(page) && PageMappedToDisk(page))
- cleancache_put_page(page);
- else
- cleancache_invalidate_page(mapping, page);
-
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(page_mapped(page), page);
if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) {
diff --git a/mm/truncate.c b/mm/truncate.c
index 8563339041f6..9eb4060b7a93 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -22,7 +22,6 @@
#include <linux/buffer_head.h> /* grr. try_to_release_page,
do_invalidatepage */
#include <linux/shmem_fs.h>
-#include <linux/cleancache.h>
#include <linux/rmap.h>
#include "internal.h"
@@ -301,7 +300,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
int i;
if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
- goto out;
+ return;
/* Offsets within partial pages */
partial_start = lstart & (PAGE_SIZE - 1);
@@ -382,7 +381,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
}
wait_on_page_writeback(page);
zero_user_segment(page, partial_start, top);
- cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, partial_start,
top - partial_start);
@@ -395,7 +393,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
if (page) {
wait_on_page_writeback(page);
zero_user_segment(page, 0, partial_end);
- cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, 0,
partial_end);
@@ -408,7 +405,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
* will be released, just zeroed, so we can bail out now.
*/
if (start >= end)
- goto out;
+ return;
index = start;
for ( ; ; ) {
@@ -453,9 +450,6 @@ void truncate_inode_pages_range(struct address_space *mapping,
pagevec_release(&pvec);
index++;
}
-
-out:
- cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(truncate_inode_pages_range);
@@ -681,7 +675,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
int did_range_unmap = 0;
if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
- goto out;
+ return 0;
pagevec_init(&pvec);
index = start;
@@ -751,8 +745,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
if (dax_mapping(mapping)) {
unmap_mapping_pages(mapping, start, end - start + 1, false);
}
-out:
- cleancache_invalidate_inode(mapping);
+
return ret;
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
--
2.16.4
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH 2/3] mm: remove cleancache.c
2019-05-27 10:32 ` [PATCH 2/3] mm: remove cleancache.c Juergen Gross
@ 2019-05-27 13:10 ` David Sterba
2019-05-28 0:50 ` Joseph Qi
2019-05-28 1:24 ` Chao Yu
2 siblings, 0 replies; 8+ messages in thread
From: David Sterba @ 2019-05-27 13:10 UTC (permalink / raw)
To: Juergen Gross
Cc: linux-kernel, linux-doc, linux-erofs, devel, linux-fsdevel,
linux-btrfs, linux-ext4, linux-f2fs-devel, linux-mm,
Jonathan Corbet, Gao Xiang, Chao Yu, Greg Kroah-Hartman,
Alexander Viro, Chris Mason, Josef Bacik, David Sterba,
Theodore Ts'o, Andreas Dilger, Jaegeuk Kim, Mark Fasheh,
Joel Becker, Joseph Qi, ocfs2-devel
On Mon, May 27, 2019 at 12:32:06PM +0200, Juergen Gross wrote:
> With the removal of tmem and xen-selfballoon the only user of
> cleancache is gone. Remove it, too.
>
> Signed-off-by: Juergen Gross <jgross@suse.com>
> ---
> Documentation/vm/cleancache.rst | 296 ------------------------------------
> Documentation/vm/frontswap.rst | 10 +-
> Documentation/vm/index.rst | 1 -
> MAINTAINERS | 7 -
> drivers/staging/erofs/data.c | 6 -
> drivers/staging/erofs/internal.h | 1 -
> fs/block_dev.c | 5 -
For the btrfs part:
> fs/btrfs/extent_io.c | 9 --
> fs/btrfs/super.c | 2 -
Acked-by: David Sterba <dsterba@suse.com>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH 2/3] mm: remove cleancache.c
2019-05-27 10:32 ` [PATCH 2/3] mm: remove cleancache.c Juergen Gross
2019-05-27 13:10 ` David Sterba
@ 2019-05-28 0:50 ` Joseph Qi
2019-05-28 1:24 ` Chao Yu
2 siblings, 0 replies; 8+ messages in thread
From: Joseph Qi @ 2019-05-28 0:50 UTC (permalink / raw)
To: Juergen Gross, linux-kernel, linux-doc, linux-erofs, devel,
linux-fsdevel, linux-btrfs, linux-ext4, linux-f2fs-devel,
linux-mm
Cc: Jonathan Corbet, Gao Xiang, Chao Yu, Greg Kroah-Hartman,
Alexander Viro, Chris Mason, Josef Bacik, David Sterba,
Theodore Ts'o, Andreas Dilger, Jaegeuk Kim, Mark Fasheh,
Joel Becker, ocfs2-devel
On 19/5/27 18:32, Juergen Gross wrote:
> With the removal of tmem and xen-selfballoon the only user of
> cleancache is gone. Remove it, too.
>
> Signed-off-by: Juergen Gross <jgross@suse.com>
> ---
> Documentation/vm/cleancache.rst | 296 ------------------------------------
> Documentation/vm/frontswap.rst | 10 +-
> Documentation/vm/index.rst | 1 -
> MAINTAINERS | 7 -
> drivers/staging/erofs/data.c | 6 -
> drivers/staging/erofs/internal.h | 1 -
> fs/block_dev.c | 5 -
> fs/btrfs/extent_io.c | 9 --
> fs/btrfs/super.c | 2 -
> fs/ext4/readpage.c | 6 -
> fs/ext4/super.c | 2 -
> fs/f2fs/data.c | 3 +-
> fs/mpage.c | 7 -
> fs/ocfs2/super.c | 2 -
For ocfs2 part,
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
> fs/super.c | 3 -
> include/linux/cleancache.h | 124 ---------------
> include/linux/fs.h | 5 -
> mm/Kconfig | 22 ---
> mm/Makefile | 1 -
> mm/cleancache.c | 317 ---------------------------------------
> mm/filemap.c | 11 --
> mm/truncate.c | 15 +-
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH 2/3] mm: remove cleancache.c
2019-05-27 10:32 ` [PATCH 2/3] mm: remove cleancache.c Juergen Gross
2019-05-27 13:10 ` David Sterba
2019-05-28 0:50 ` Joseph Qi
@ 2019-05-28 1:24 ` Chao Yu
2 siblings, 0 replies; 8+ messages in thread
From: Chao Yu @ 2019-05-28 1:24 UTC (permalink / raw)
To: Juergen Gross, linux-kernel, linux-doc, linux-erofs, devel,
linux-fsdevel, linux-btrfs, linux-ext4, linux-f2fs-devel,
linux-mm
Cc: Jonathan Corbet, Gao Xiang, Greg Kroah-Hartman, Alexander Viro,
Chris Mason, Josef Bacik, David Sterba, Theodore Ts'o,
Andreas Dilger, Jaegeuk Kim, Mark Fasheh, Joel Becker, Joseph Qi,
ocfs2-devel
On 2019/5/27 18:32, Juergen Gross wrote:
> With the removal of tmem and xen-selfballoon the only user of
> cleancache is gone. Remove it, too.
>
> Signed-off-by: Juergen Gross <jgross@suse.com>
> ---
> Documentation/vm/cleancache.rst | 296 ------------------------------------
> Documentation/vm/frontswap.rst | 10 +-
> Documentation/vm/index.rst | 1 -
> MAINTAINERS | 7 -
> drivers/staging/erofs/data.c | 6 -
> drivers/staging/erofs/internal.h | 1 -
> fs/block_dev.c | 5 -
> fs/btrfs/extent_io.c | 9 --
> fs/btrfs/super.c | 2 -
> fs/ext4/readpage.c | 6 -
> fs/ext4/super.c | 2 -
> fs/f2fs/data.c | 3 +-
For erofs and f2fs part,
Acked-by: Chao Yu <yuchao0@huawei.com>
Thanks,
> fs/mpage.c | 7 -
> fs/ocfs2/super.c | 2 -
> fs/super.c | 3 -
> include/linux/cleancache.h | 124 ---------------
> include/linux/fs.h | 5 -
> mm/Kconfig | 22 ---
> mm/Makefile | 1 -
> mm/cleancache.c | 317 ---------------------------------------
> mm/filemap.c | 11 --
> mm/truncate.c | 15 +-
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH 3/3] mm: remove tmem specifics from frontswap
2019-05-27 10:32 [PATCH 0/3] remove tmem and code depending on it Juergen Gross
2019-05-27 10:32 ` [PATCH 1/3] xen: remove tmem driver Juergen Gross
2019-05-27 10:32 ` [PATCH 2/3] mm: remove cleancache.c Juergen Gross
@ 2019-05-27 10:32 ` Juergen Gross
2 siblings, 0 replies; 8+ messages in thread
From: Juergen Gross @ 2019-05-27 10:32 UTC (permalink / raw)
To: linux-kernel, linux-doc, linux-mm
Cc: Juergen Gross, Jonathan Corbet, Konrad Rzeszutek Wilk
The frontswap module contains several parts which are specific to
tmem. With that no longer present those parts can be removed.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
Documentation/vm/frontswap.rst | 17 +----
include/linux/frontswap.h | 5 --
mm/Kconfig | 16 ++---
mm/frontswap.c | 156 +----------------------------------------
4 files changed, 7 insertions(+), 187 deletions(-)
diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst
index 511c921bc8d2..2c674c0c6a77 100644
--- a/Documentation/vm/frontswap.rst
+++ b/Documentation/vm/frontswap.rst
@@ -19,7 +19,7 @@ for a detailed overview of frontswap and related kernel parts)
Frontswap is so named because it can be thought of as the opposite of
a "backing" store for a swap device. The storage is assumed to be
a synchronous concurrency-safe page-oriented "pseudo-RAM device" conforming
-to the requirements of transcendent memory (such as Xen's "tmem", or
+to the requirements of transcendent memory (such as
in-kernel compressed memory, aka "zcache", or future RAM-like devices);
this pseudo-RAM device is not directly accessible or addressable by the
kernel and is of unknown and possibly time-varying size. The driver
@@ -113,21 +113,6 @@ many servers in a cluster can swap, dynamically as needed, to a single
server configured with a large amount of RAM... without pre-configuring
how much of the RAM is available for each of the clients!
-In the virtual case, the whole point of virtualization is to statistically
-multiplex physical resources across the varying demands of multiple
-virtual machines. This is really hard to do with RAM and efforts to do
-it well with no kernel changes have essentially failed (except in some
-well-publicized special-case workloads).
-Specifically, the Xen Transcendent Memory backend allows otherwise
-"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple
-virtual machines, but the pages can be compressed and deduplicated to
-optimize RAM utilization. And when guest OS's are induced to surrender
-underutilized RAM (e.g. with "selfballooning"), sudden unexpected
-memory pressure may result in swapping; frontswap allows those pages
-to be swapped to and from hypervisor RAM (if overall host system memory
-conditions allow), thus mitigating the potentially awful performance impact
-of unplanned swapping.
-
A KVM implementation is underway and has been RFC'ed to lkml. And,
using frontswap, investigation is also underway on the use of NVM as
a memory extension technology.
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 6d775984905b..052480aa3756 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -24,11 +24,6 @@ struct frontswap_ops {
};
extern void frontswap_register_ops(struct frontswap_ops *ops);
-extern void frontswap_shrink(unsigned long);
-extern unsigned long frontswap_curr_pages(void);
-extern void frontswap_writethrough(bool);
-#define FRONTSWAP_HAS_EXCLUSIVE_GETS
-extern void frontswap_tmem_exclusive_gets(bool);
extern bool __frontswap_test(struct swap_info_struct *, pgoff_t);
extern void __frontswap_init(unsigned type, unsigned long *map);
diff --git a/mm/Kconfig b/mm/Kconfig
index 5166fe4af00b..971b615ad3a6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -436,20 +436,14 @@ config NEED_PER_CPU_KM
default y
config FRONTSWAP
- bool "Enable frontswap to cache swap pages if tmem is present"
+ bool "Enable frontswap to cache swap pages if zswap is present"
depends on SWAP
help
Frontswap is so named because it can be thought of as the opposite
- of a "backing" store for a swap device. The data is stored into
- "transcendent memory", memory that is not directly accessible or
- addressable by the kernel and is of unknown and possibly
- time-varying size. When space in transcendent memory is available,
- a significant swap I/O reduction may be achieved. When none is
- available, all frontswap calls are reduced to a single pointer-
- compare-against-NULL resulting in a negligible performance hit
- and swap data is stored as normal on the matching swap device.
-
- If unsure, say Y to enable frontswap.
+ of a "backing" store for a swap device. The only user right now is
+ zswap.
+
+ If unsure, say "n".
config CMA
bool "Contiguous Memory Allocator"
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 157e5bf63504..e3370e46a0a5 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -33,23 +33,6 @@ static struct frontswap_ops *frontswap_ops __read_mostly;
#define for_each_frontswap_ops(ops) \
for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next)
-/*
- * If enabled, frontswap_store will return failure even on success. As
- * a result, the swap subsystem will always write the page to swap, in
- * effect converting frontswap into a writethrough cache. In this mode,
- * there is no direct reduction in swap writes, but a frontswap backend
- * can unilaterally "reclaim" any pages in use with no data loss, thus
- * providing increases control over maximum memory usage due to frontswap.
- */
-static bool frontswap_writethrough_enabled __read_mostly;
-
-/*
- * If enabled, the underlying tmem implementation is capable of doing
- * exclusive gets, so frontswap_load, on a successful tmem_get must
- * mark the page as no longer in frontswap AND mark it dirty.
- */
-static bool frontswap_tmem_exclusive_gets_enabled __read_mostly;
-
#ifdef CONFIG_DEBUG_FS
/*
* Counters available via /sys/kernel/debug/frontswap (if debugfs is
@@ -167,24 +150,6 @@ void frontswap_register_ops(struct frontswap_ops *ops)
}
EXPORT_SYMBOL(frontswap_register_ops);
-/*
- * Enable/disable frontswap writethrough (see above).
- */
-void frontswap_writethrough(bool enable)
-{
- frontswap_writethrough_enabled = enable;
-}
-EXPORT_SYMBOL(frontswap_writethrough);
-
-/*
- * Enable/disable frontswap exclusive gets (see above).
- */
-void frontswap_tmem_exclusive_gets(bool enable)
-{
- frontswap_tmem_exclusive_gets_enabled = enable;
-}
-EXPORT_SYMBOL(frontswap_tmem_exclusive_gets);
-
/*
* Called when a swap device is swapon'd.
*/
@@ -280,9 +245,6 @@ int __frontswap_store(struct page *page)
} else {
inc_frontswap_failed_stores();
}
- if (frontswap_writethrough_enabled)
- /* report failure so swap also writes to swap device */
- ret = -1;
return ret;
}
EXPORT_SYMBOL(__frontswap_store);
@@ -314,13 +276,8 @@ int __frontswap_load(struct page *page)
if (!ret) /* successful load */
break;
}
- if (ret == 0) {
+ if (ret == 0)
inc_frontswap_loads();
- if (frontswap_tmem_exclusive_gets_enabled) {
- SetPageDirty(page);
- __frontswap_clear(sis, offset);
- }
- }
return ret;
}
EXPORT_SYMBOL(__frontswap_load);
@@ -369,117 +326,6 @@ void __frontswap_invalidate_area(unsigned type)
}
EXPORT_SYMBOL(__frontswap_invalidate_area);
-static unsigned long __frontswap_curr_pages(void)
-{
- unsigned long totalpages = 0;
- struct swap_info_struct *si = NULL;
-
- assert_spin_locked(&swap_lock);
- plist_for_each_entry(si, &swap_active_head, list)
- totalpages += atomic_read(&si->frontswap_pages);
- return totalpages;
-}
-
-static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
- int *swapid)
-{
- int ret = -EINVAL;
- struct swap_info_struct *si = NULL;
- int si_frontswap_pages;
- unsigned long total_pages_to_unuse = total;
- unsigned long pages = 0, pages_to_unuse = 0;
-
- assert_spin_locked(&swap_lock);
- plist_for_each_entry(si, &swap_active_head, list) {
- si_frontswap_pages = atomic_read(&si->frontswap_pages);
- if (total_pages_to_unuse < si_frontswap_pages) {
- pages = pages_to_unuse = total_pages_to_unuse;
- } else {
- pages = si_frontswap_pages;
- pages_to_unuse = 0; /* unuse all */
- }
- /* ensure there is enough RAM to fetch pages from frontswap */
- if (security_vm_enough_memory_mm(current->mm, pages)) {
- ret = -ENOMEM;
- continue;
- }
- vm_unacct_memory(pages);
- *unused = pages_to_unuse;
- *swapid = si->type;
- ret = 0;
- break;
- }
-
- return ret;
-}
-
-/*
- * Used to check if it's necessory and feasible to unuse pages.
- * Return 1 when nothing to do, 0 when need to shink pages,
- * error code when there is an error.
- */
-static int __frontswap_shrink(unsigned long target_pages,
- unsigned long *pages_to_unuse,
- int *type)
-{
- unsigned long total_pages = 0, total_pages_to_unuse;
-
- assert_spin_locked(&swap_lock);
-
- total_pages = __frontswap_curr_pages();
- if (total_pages <= target_pages) {
- /* Nothing to do */
- *pages_to_unuse = 0;
- return 1;
- }
- total_pages_to_unuse = total_pages - target_pages;
- return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type);
-}
-
-/*
- * Frontswap, like a true swap device, may unnecessarily retain pages
- * under certain circumstances; "shrink" frontswap is essentially a
- * "partial swapoff" and works by calling try_to_unuse to attempt to
- * unuse enough frontswap pages to attempt to -- subject to memory
- * constraints -- reduce the number of pages in frontswap to the
- * number given in the parameter target_pages.
- */
-void frontswap_shrink(unsigned long target_pages)
-{
- unsigned long pages_to_unuse = 0;
- int uninitialized_var(type), ret;
-
- /*
- * we don't want to hold swap_lock while doing a very
- * lengthy try_to_unuse, but swap_list may change
- * so restart scan from swap_active_head each time
- */
- spin_lock(&swap_lock);
- ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
- spin_unlock(&swap_lock);
- if (ret == 0)
- try_to_unuse(type, true, pages_to_unuse);
- return;
-}
-EXPORT_SYMBOL(frontswap_shrink);
-
-/*
- * Count and return the number of frontswap pages across all
- * swap devices. This is exported so that backend drivers can
- * determine current usage without reading debugfs.
- */
-unsigned long frontswap_curr_pages(void)
-{
- unsigned long totalpages = 0;
-
- spin_lock(&swap_lock);
- totalpages = __frontswap_curr_pages();
- spin_unlock(&swap_lock);
-
- return totalpages;
-}
-EXPORT_SYMBOL(frontswap_curr_pages);
-
static int __init init_frontswap(void)
{
#ifdef CONFIG_DEBUG_FS
--
2.16.4
^ permalink raw reply related [flat|nested] 8+ messages in thread