The current patches are old, update them from mainline.
Backports taken from https://github.com/yuzhaogoogle/linux/commits/mglru-5.15
Tested-by: Kazuki H <kazukih0205@gmail.com> #mt7622/Linksys E8450 UBI
Signed-off-by: Kazuki H <kazukih0205@gmail.com>
-From a8e6015d9534f39abc08e6804566af059e498a60 Mon Sep 17 00:00:00 2001
+From a4103262b01a1b8704b37c01c7c813df91b7b119 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
-Date: Wed, 4 Aug 2021 01:31:34 -0600
-Subject: [PATCH 01/10] mm: x86, arm64: add arch_has_hw_pte_young()
+Date: Sun, 18 Sep 2022 01:59:58 -0600
+Subject: [PATCH 01/29] mm: x86, arm64: add arch_has_hw_pte_young()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
-Some architectures automatically set the accessed bit in PTEs, e.g.,
-x86 and arm64 v8.2. On architectures that do not have this capability,
-clearing the accessed bit in a PTE triggers a page fault following the
-TLB miss of this PTE.
+Patch series "Multi-Gen LRU Framework", v14.
-Being aware of this capability can help make better decisions, i.e.,
-whether to limit the size of each batch of PTEs and the burst of
-batches when clearing the accessed bit.
+What's new
+==========
+1. OpenWrt, in addition to Android, Arch Linux Zen, Armbian, ChromeOS,
+ Liquorix, post-factum and XanMod, is now shipping MGLRU on 5.15.
+2. Fixed long-tailed direct reclaim latency seen on high-memory (TBs)
+ machines. The old direct reclaim backoff, which tries to enforce a
+ minimum fairness among all eligible memcgs, over-swapped by about
+ (total_mem>>DEF_PRIORITY)-nr_to_reclaim. The new backoff, which
+ pulls the plug on swapping once the target is met, trades some
+ fairness for curtailed latency:
+ https://lore.kernel.org/r/20220918080010.2920238-10-yuzhao@google.com/
+3. Fixed minior build warnings and conflicts. More comments and nits.
+TLDR
+====
+The current page reclaim is too expensive in terms of CPU usage and it
+often makes poor choices about what to evict. This patchset offers an
+alternative solution that is performant, versatile and
+straightforward.
+
+Patchset overview
+=================
+The design and implementation overview is in patch 14:
+https://lore.kernel.org/r/20220918080010.2920238-15-yuzhao@google.com/
+
+01. mm: x86, arm64: add arch_has_hw_pte_young()
+02. mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+Take advantage of hardware features when trying to clear the accessed
+bit in many PTEs.
+
+03. mm/vmscan.c: refactor shrink_node()
+04. Revert "include/linux/mm_inline.h: fold __update_lru_size() into
+ its sole caller"
+Minor refactors to improve readability for the following patches.
+
+05. mm: multi-gen LRU: groundwork
+Adds the basic data structure and the functions that insert pages to
+and remove pages from the multi-gen LRU (MGLRU) lists.
+
+06. mm: multi-gen LRU: minimal implementation
+A minimal implementation without optimizations.
+
+07. mm: multi-gen LRU: exploit locality in rmap
+Exploits spatial locality to improve efficiency when using the rmap.
+
+08. mm: multi-gen LRU: support page table walks
+Further exploits spatial locality by optionally scanning page tables.
+
+09. mm: multi-gen LRU: optimize multiple memcgs
+Optimizes the overall performance for multiple memcgs running mixed
+types of workloads.
+
+10. mm: multi-gen LRU: kill switch
+Adds a kill switch to enable or disable MGLRU at runtime.
+
+11. mm: multi-gen LRU: thrashing prevention
+12. mm: multi-gen LRU: debugfs interface
+Provide userspace with features like thrashing prevention, working set
+estimation and proactive reclaim.
+
+13. mm: multi-gen LRU: admin guide
+14. mm: multi-gen LRU: design doc
+Add an admin guide and a design doc.
+
+Benchmark results
+=================
+Independent lab results
+-----------------------
+Based on the popularity of searches [01] and the memory usage in
+Google's public cloud, the most popular open-source memory-hungry
+applications, in alphabetical order, are:
+ Apache Cassandra Memcached
+ Apache Hadoop MongoDB
+ Apache Spark PostgreSQL
+ MariaDB (MySQL) Redis
+
+An independent lab evaluated MGLRU with the most widely used benchmark
+suites for the above applications. They posted 960 data points along
+with kernel metrics and perf profiles collected over more than 500
+hours of total benchmark time. Their final reports show that, with 95%
+confidence intervals (CIs), the above applications all performed
+significantly better for at least part of their benchmark matrices.
+
+On 5.14:
+1. Apache Spark [02] took 95% CIs [9.28, 11.19]% and [12.20, 14.93]%
+ less wall time to sort three billion random integers, respectively,
+ under the medium- and the high-concurrency conditions, when
+ overcommitting memory. There were no statistically significant
+ changes in wall time for the rest of the benchmark matrix.
+2. MariaDB [03] achieved 95% CIs [5.24, 10.71]% and [20.22, 25.97]%
+ more transactions per minute (TPM), respectively, under the medium-
+ and the high-concurrency conditions, when overcommitting memory.
+ There were no statistically significant changes in TPM for the rest
+ of the benchmark matrix.
+3. Memcached [04] achieved 95% CIs [23.54, 32.25]%, [20.76, 41.61]%
+ and [21.59, 30.02]% more operations per second (OPS), respectively,
+ for sequential access, random access and Gaussian (distribution)
+ access, when THP=always; 95% CIs [13.85, 15.97]% and
+ [23.94, 29.92]% more OPS, respectively, for random access and
+ Gaussian access, when THP=never. There were no statistically
+ significant changes in OPS for the rest of the benchmark matrix.
+4. MongoDB [05] achieved 95% CIs [2.23, 3.44]%, [6.97, 9.73]% and
+ [2.16, 3.55]% more operations per second (OPS), respectively, for
+ exponential (distribution) access, random access and Zipfian
+ (distribution) access, when underutilizing memory; 95% CIs
+ [8.83, 10.03]%, [21.12, 23.14]% and [5.53, 6.46]% more OPS,
+ respectively, for exponential access, random access and Zipfian
+ access, when overcommitting memory.
+
+On 5.15:
+5. Apache Cassandra [06] achieved 95% CIs [1.06, 4.10]%, [1.94, 5.43]%
+ and [4.11, 7.50]% more operations per second (OPS), respectively,
+ for exponential (distribution) access, random access and Zipfian
+ (distribution) access, when swap was off; 95% CIs [0.50, 2.60]%,
+ [6.51, 8.77]% and [3.29, 6.75]% more OPS, respectively, for
+ exponential access, random access and Zipfian access, when swap was
+ on.
+6. Apache Hadoop [07] took 95% CIs [5.31, 9.69]% and [2.02, 7.86]%
+ less average wall time to finish twelve parallel TeraSort jobs,
+ respectively, under the medium- and the high-concurrency
+ conditions, when swap was on. There were no statistically
+ significant changes in average wall time for the rest of the
+ benchmark matrix.
+7. PostgreSQL [08] achieved 95% CI [1.75, 6.42]% more transactions per
+ minute (TPM) under the high-concurrency condition, when swap was
+ off; 95% CIs [12.82, 18.69]% and [22.70, 46.86]% more TPM,
+ respectively, under the medium- and the high-concurrency
+ conditions, when swap was on. There were no statistically
+ significant changes in TPM for the rest of the benchmark matrix.
+8. Redis [09] achieved 95% CIs [0.58, 5.94]%, [6.55, 14.58]% and
+ [11.47, 19.36]% more total operations per second (OPS),
+ respectively, for sequential access, random access and Gaussian
+ (distribution) access, when THP=always; 95% CIs [1.27, 3.54]%,
+ [10.11, 14.81]% and [8.75, 13.64]% more total OPS, respectively,
+ for sequential access, random access and Gaussian access, when
+ THP=never.
+
+Our lab results
+---------------
+To supplement the above results, we ran the following benchmark suites
+on 5.16-rc7 and found no regressions [10].
+ fs_fio_bench_hdd_mq pft
+ fs_lmbench pgsql-hammerdb
+ fs_parallelio redis
+ fs_postmark stream
+ hackbench sysbenchthread
+ kernbench tpcc_spark
+ memcached unixbench
+ multichase vm-scalability
+ mutilate will-it-scale
+ nginx
+
+[01] https://trends.google.com
+[02] https://lore.kernel.org/r/20211102002002.92051-1-bot@edi.works/
+[03] https://lore.kernel.org/r/20211009054315.47073-1-bot@edi.works/
+[04] https://lore.kernel.org/r/20211021194103.65648-1-bot@edi.works/
+[05] https://lore.kernel.org/r/20211109021346.50266-1-bot@edi.works/
+[06] https://lore.kernel.org/r/20211202062806.80365-1-bot@edi.works/
+[07] https://lore.kernel.org/r/20211209072416.33606-1-bot@edi.works/
+[08] https://lore.kernel.org/r/20211218071041.24077-1-bot@edi.works/
+[09] https://lore.kernel.org/r/20211122053248.57311-1-bot@edi.works/
+[10] https://lore.kernel.org/r/20220104202247.2903702-1-yuzhao@google.com/
+
+Read-world applications
+=======================
+Third-party testimonials
+------------------------
+Konstantin reported [11]:
+ I have Archlinux with 8G RAM + zswap + swap. While developing, I
+ have lots of apps opened such as multiple LSP-servers for different
+ langs, chats, two browsers, etc... Usually, my system gets quickly
+ to a point of SWAP-storms, where I have to kill LSP-servers,
+ restart browsers to free memory, etc, otherwise the system lags
+ heavily and is barely usable.
+
+ 1.5 day ago I migrated from 5.11.15 kernel to 5.12 + the LRU
+ patchset, and I started up by opening lots of apps to create memory
+ pressure, and worked for a day like this. Till now I had not a
+ single SWAP-storm, and mind you I got 3.4G in SWAP. I was never
+ getting to the point of 3G in SWAP before without a single
+ SWAP-storm.
+
+Vaibhav from IBM reported [12]:
+ In a synthetic MongoDB Benchmark, seeing an average of ~19%
+ throughput improvement on POWER10(Radix MMU + 64K Page Size) with
+ MGLRU patches on top of 5.16 kernel for MongoDB + YCSB across
+ three different request distributions, namely, Exponential, Uniform
+ and Zipfan.
+
+Shuang from U of Rochester reported [13]:
+ With the MGLRU, fio achieved 95% CIs [38.95, 40.26]%, [4.12, 6.64]%
+ and [9.26, 10.36]% higher throughput, respectively, for random
+ access, Zipfian (distribution) access and Gaussian (distribution)
+ access, when the average number of jobs per CPU is 1; 95% CIs
+ [42.32, 49.15]%, [9.44, 9.89]% and [20.99, 22.86]% higher
+ throughput, respectively, for random access, Zipfian access and
+ Gaussian access, when the average number of jobs per CPU is 2.
+
+Daniel from Michigan Tech reported [14]:
+ With Memcached allocating ~100GB of byte-addressable Optante,
+ performance improvement in terms of throughput (measured as queries
+ per second) was about 10% for a series of workloads.
+
+Large-scale deployments
+-----------------------
+We've rolled out MGLRU to tens of millions of ChromeOS users and
+about a million Android users. Google's fleetwide profiling [15] shows
+an overall 40% decrease in kswapd CPU usage, in addition to
+improvements in other UX metrics, e.g., an 85% decrease in the number
+of low-memory kills at the 75th percentile and an 18% decrease in
+app launch time at the 50th percentile.
+
+The downstream kernels that have been using MGLRU include:
+1. Android [16]
+2. Arch Linux Zen [17]
+3. Armbian [18]
+4. ChromeOS [19]
+5. Liquorix [20]
+6. OpenWrt [21]
+7. post-factum [22]
+8. XanMod [23]
+
+[11] https://lore.kernel.org/r/140226722f2032c86301fbd326d91baefe3d7d23.camel@yandex.ru/
+[12] https://lore.kernel.org/r/87czj3mux0.fsf@vajain21.in.ibm.com/
+[13] https://lore.kernel.org/r/20220105024423.26409-1-szhai2@cs.rochester.edu/
+[14] https://lore.kernel.org/r/CA+4-3vksGvKd18FgRinxhqHetBS1hQekJE2gwco8Ja-bJWKtFw@mail.gmail.com/
+[15] https://dl.acm.org/doi/10.1145/2749469.2750392
+[16] https://android.com
+[17] https://archlinux.org
+[18] https://armbian.com
+[19] https://chromium.org
+[20] https://liquorix.net
+[21] https://openwrt.org
+[22] https://codeberg.org/pf-kernel
+[23] https://xanmod.org
+
+Summary
+=======
+The facts are:
+1. The independent lab results and the real-world applications
+ indicate substantial improvements; there are no known regressions.
+2. Thrashing prevention, working set estimation and proactive reclaim
+ work out of the box; there are no equivalent solutions.
+3. There is a lot of new code; no smaller changes have been
+ demonstrated similar effects.
+
+Our options, accordingly, are:
+1. Given the amount of evidence, the reported improvements will likely
+ materialize for a wide range of workloads.
+2. Gauging the interest from the past discussions, the new features
+ will likely be put to use for both personal computers and data
+ centers.
+3. Based on Google's track record, the new code will likely be well
+ maintained in the long term. It'd be more difficult if not
+ impossible to achieve similar effects with other approaches.
+
+This patch (of 14):
+
+Some architectures automatically set the accessed bit in PTEs, e.g., x86
+and arm64 v8.2. On architectures that do not have this capability,
+clearing the accessed bit in a PTE usually triggers a page fault following
+the TLB miss of this PTE (to emulate the accessed bit).
+
+Being aware of this capability can help make better decisions, e.g.,
+whether to spread the work out over a period of time to reduce bursty page
+faults when trying to clear the accessed bit in many PTEs.
+
+Note that theoretically this capability can be unreliable, e.g.,
+hotplugged CPUs might be different from builtin ones. Therefore it should
+not be used in architecture-independent code that involves correctness,
+e.g., to determine whether TLB flushes are required (in combination with
+the accessed bit).
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-1-yuzhao@google.com
+Link: https://lkml.kernel.org/r/20220918080010.2920238-2-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
-Change-Id: Ib49b44fb56df3333a2ff1fcc496fb1980b976e7a
+Reviewed-by: Barry Song <baohua@kernel.org>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Acked-by: Will Deacon <will@kernel.org>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: linux-arm-kernel@lists.infradead.org
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
- arch/arm64/include/asm/cpufeature.h | 5 +++++
- arch/arm64/include/asm/pgtable.h | 13 ++++++++-----
- arch/arm64/kernel/cpufeature.c | 10 ++++++++++
- arch/arm64/tools/cpucaps | 1 +
- arch/x86/include/asm/pgtable.h | 6 +++---
- include/linux/pgtable.h | 13 +++++++++++++
- mm/memory.c | 14 +-------------
- 7 files changed, 41 insertions(+), 21 deletions(-)
-
---- a/arch/arm64/include/asm/cpufeature.h
-+++ b/arch/arm64/include/asm/cpufeature.h
-@@ -808,6 +808,11 @@ static inline bool system_supports_tlb_r
- cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
- }
-
-+static inline bool system_has_hw_af(void)
-+{
-+ return IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && cpus_have_const_cap(ARM64_HW_AF);
-+}
-+
- extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
-
- static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
+ arch/arm64/include/asm/pgtable.h | 14 ++------------
+ arch/x86/include/asm/pgtable.h | 6 +++---
+ include/linux/pgtable.h | 13 +++++++++++++
+ mm/memory.c | 14 +-------------
+ 4 files changed, 19 insertions(+), 28 deletions(-)
+
+diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
+index ed57717cd004..874827fc7bc6 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
-@@ -999,13 +999,16 @@ static inline void update_mmu_cache(stru
+@@ -999,23 +999,13 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
* page after fork() + CoW for pfn mappings. We don't always have a
* hardware-managed access flag on arm64.
*/
-static inline bool arch_faults_on_old_pte(void)
-+static inline bool arch_has_hw_pte_young(bool local)
- {
+-{
- WARN_ON(preemptible());
-+ if (local) {
-+ WARN_ON(preemptible());
-+ return cpu_has_hw_af();
-+ }
-
+-
- return !cpu_has_hw_af();
-+ return system_has_hw_af();
- }
+-}
-#define arch_faults_on_old_pte arch_faults_on_old_pte
-+#define arch_has_hw_pte_young arch_has_hw_pte_young
++#define arch_has_hw_pte_young cpu_has_hw_af
/*
* Experimentally, it's cheap to set the access flag in hardware and we
-@@ -1013,7 +1016,7 @@ static inline bool arch_faults_on_old_pt
+ * benefit from prefaulting mappings as 'old' to start with.
*/
- static inline bool arch_wants_old_prefaulted_pte(void)
- {
+-static inline bool arch_wants_old_prefaulted_pte(void)
+-{
- return !arch_faults_on_old_pte();
-+ return arch_has_hw_pte_young(true);
- }
- #define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte
+-}
+-#define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte
++#define arch_wants_old_prefaulted_pte cpu_has_hw_af
---- a/arch/arm64/kernel/cpufeature.c
-+++ b/arch/arm64/kernel/cpufeature.c
-@@ -2197,6 +2197,16 @@ static const struct arm64_cpu_capabiliti
- .matches = has_hw_dbm,
- .cpu_enable = cpu_enable_hw_dbm,
- },
-+ {
-+ .desc = "Hardware update of the Access flag",
-+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
-+ .capability = ARM64_HW_AF,
-+ .sys_reg = SYS_ID_AA64MMFR1_EL1,
-+ .sign = FTR_UNSIGNED,
-+ .field_pos = ID_AA64MMFR1_HADBS_SHIFT,
-+ .min_field_value = 1,
-+ .matches = has_cpuid_feature,
-+ },
- #endif
- {
- .desc = "CRC32 instructions",
---- a/arch/arm64/tools/cpucaps
-+++ b/arch/arm64/tools/cpucaps
-@@ -35,6 +35,7 @@ HAS_STAGE2_FWB
- HAS_SYSREG_GIC_CPUIF
- HAS_TLB_RANGE
- HAS_VIRT_HOST_EXTN
-+HW_AF
- HW_DBM
- KVM_PROTECTED_MODE
- MISMATCHED_CACHE_TYPE
+ #endif /* !__ASSEMBLY__ */
+
+diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
+index 448cd01eb3ec..3908780fc408 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
-@@ -1397,10 +1397,10 @@ static inline bool arch_has_pfn_modify_c
+@@ -1397,10 +1397,10 @@ static inline bool arch_has_pfn_modify_check(void)
return boot_cpu_has_bug(X86_BUG_L1TF);
}
-#define arch_faults_on_old_pte arch_faults_on_old_pte
-static inline bool arch_faults_on_old_pte(void)
+#define arch_has_hw_pte_young arch_has_hw_pte_young
-+static inline bool arch_has_hw_pte_young(bool local)
++static inline bool arch_has_hw_pte_young(void)
{
- return false;
+ return true;
}
#endif /* __ASSEMBLY__ */
+diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
+index d468efcf48f4..2f1188980baf 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
-@@ -259,6 +259,19 @@ static inline int pmdp_clear_flush_young
+@@ -259,6 +259,19 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif
+#ifndef arch_has_hw_pte_young
+/*
-+ * Return whether the accessed bit is supported by the local CPU or all CPUs.
++ * Return whether the accessed bit is supported on the local CPU.
+ *
-+ * Those arches which have hw access flag feature need to implement their own
-+ * helper. By default, "false" means pagefault will be hit on old pte.
++ * This stub assumes accessing through an old PTE triggers a page fault.
++ * Architectures that automatically set the access bit should overwrite it.
+ */
-+static inline bool arch_has_hw_pte_young(bool local)
++static inline bool arch_has_hw_pte_young(void)
+{
+ return false;
+}
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address,
+diff --git a/mm/memory.c b/mm/memory.c
+index a4d0f744a458..392b7326a2d2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -121,18 +121,6 @@ int randomize_va_space __read_mostly =
#ifndef arch_wants_old_prefaulted_pte
static inline bool arch_wants_old_prefaulted_pte(void)
{
-@@ -2782,7 +2770,7 @@ static inline bool cow_user_page(struct
+@@ -2782,7 +2770,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src,
* On architectures with software "accessed" bits, we would
* take a double page fault, so mark it accessed here.
*/
- if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
-+ if (!arch_has_hw_pte_young(true) && !pte_young(vmf->orig_pte)) {
++ if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) {
pte_t entry;
vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+--
+2.40.0
+
-From f8b663bbfa30af5515e222fd74df20ea4e8393a2 Mon Sep 17 00:00:00 2001
+From 493de1c4b0f2cd909169401da8c445f6c8a7e29d Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
-Date: Sat, 26 Sep 2020 21:17:18 -0600
-Subject: [PATCH 02/10] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+Date: Sun, 18 Sep 2022 01:59:59 -0600
+Subject: [PATCH 02/29] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
-Some architectures support the accessed bit on non-leaf PMD entries,
-e.g., x86_64 sets the accessed bit on a non-leaf PMD entry when using
-it as part of linear address translation [1]. As an optimization, page
-table walkers who are interested in the accessed bit can skip the PTEs
-under a non-leaf PMD entry if the accessed bit is cleared on this PMD
-entry.
+Some architectures support the accessed bit in non-leaf PMD entries, e.g.,
+x86 sets the accessed bit in a non-leaf PMD entry when using it as part of
+linear address translation [1]. Page table walkers that clear the
+accessed bit may use this capability to reduce their search space.
-Although an inline function may be preferable, this capability is
-added as a configuration option to look consistent when used with the
-existing macros.
+Note that:
+1. Although an inline function is preferable, this capability is added
+ as a configuration option for consistency with the existing macros.
+2. Due to the little interest in other varieties, this capability was
+ only tested on Intel and AMD CPUs.
+
+Thanks to the following developers for their efforts [2][3].
+ Randy Dunlap <rdunlap@infradead.org>
+ Stephen Rothwell <sfr@canb.auug.org.au>
[1]: Intel 64 and IA-32 Architectures Software Developer's Manual
Volume 3 (June 2021), section 4.8
+[2] https://lore.kernel.org/r/bfdcc7c8-922f-61a9-aa15-7e7250f04af7@infradead.org/
+[3] https://lore.kernel.org/r/20220413151513.5a0d7a7e@canb.auug.org.au/
+Link: https://lkml.kernel.org/r/20220918080010.2920238-3-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reviewed-by: Barry Song <baohua@kernel.org>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I1a17be3ae926f721f7b17ea1539e5c39e8c4f9a8
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
- arch/Kconfig | 9 +++++++++
+ arch/Kconfig | 8 ++++++++
arch/x86/Kconfig | 1 +
arch/x86/include/asm/pgtable.h | 3 ++-
arch/x86/mm/pgtable.c | 5 ++++-
include/linux/pgtable.h | 4 ++--
- 5 files changed, 18 insertions(+), 4 deletions(-)
+ 5 files changed, 17 insertions(+), 4 deletions(-)
+diff --git a/arch/Kconfig b/arch/Kconfig
+index 5987363b41c2..62d55b7ccca1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
-@@ -1295,6 +1295,15 @@ config ARCH_HAS_ELFCORE_COMPAT
+@@ -1295,6 +1295,14 @@ config ARCH_HAS_ELFCORE_COMPAT
config ARCH_HAS_PARANOID_L1D_FLUSH
bool
+config ARCH_HAS_NONLEAF_PMD_YOUNG
+ bool
-+ depends on PGTABLE_LEVELS > 2
+ help
-+ Architectures that select this are able to set the accessed bit on
-+ non-leaf PMD entries in addition to leaf PTE entries where pages are
-+ mapped. For them, page table walkers that clear the accessed bit may
-+ stop at non-leaf PMD entries if they do not see the accessed bit.
++ Architectures that select this option are capable of setting the
++ accessed bit in non-leaf PMD entries when using them as part of linear
++ address translations. Page table walkers that clear the accessed bit
++ may use this capability to reduce their search space.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
+diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
+index a08ce6360382..38e1d231d52a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -84,6 +84,7 @@ config X86
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PTE_DEVMAP if X86_64
select ARCH_HAS_PTE_SPECIAL
-+ select ARCH_HAS_NONLEAF_PMD_YOUNG if X86_64
++ select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2
select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64
select ARCH_HAS_COPY_MC if X86_64
select ARCH_HAS_SET_MEMORY
+diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
+index 3908780fc408..01a1763123ff 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
-@@ -817,7 +817,8 @@ static inline unsigned long pmd_page_vad
+@@ -817,7 +817,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
static inline int pmd_bad(pmd_t pmd)
{
}
static inline unsigned long pages_to_mb(unsigned long npg)
+diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
+index 3481b35cb4ec..a224193d84bf 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
-@@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_
+@@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
return ret;
}
int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
-@@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_
+@@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
return ret;
}
int pudp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pud_t *pudp)
{
+diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
+index 2f1188980baf..e6889556e0bf 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
-@@ -212,7 +212,7 @@ static inline int ptep_test_and_clear_yo
+@@ -212,7 +212,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
#endif
#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
-@@ -233,7 +233,7 @@ static inline int pmdp_test_and_clear_yo
+@@ -233,7 +233,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
BUILD_BUG();
return 0;
}
#endif
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+--
+2.40.0
+
-From a810f8e2f1bdd0707eaf05c8b4ba84a3ff2801bd Mon Sep 17 00:00:00 2001
+From 9e17efd11450d3d2069adaa3c58db9ac8ebd1c66 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
-Date: Sun, 27 Sep 2020 20:49:08 -0600
-Subject: [PATCH 03/10] mm/vmscan.c: refactor shrink_node()
+Date: Sun, 18 Sep 2022 02:00:00 -0600
+Subject: [PATCH 03/29] mm/vmscan.c: refactor shrink_node()
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
-This patch refactors shrink_node(). This will make the upcoming
-changes to mm/vmscan.c more readable.
+This patch refactors shrink_node() to improve readability for the upcoming
+changes to mm/vmscan.c.
+Link: https://lkml.kernel.org/r/20220918080010.2920238-4-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reviewed-by: Barry Song <baohua@kernel.org>
+Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: Iae734b5b4030205b7db6e8c841f747b6f6ae1a04
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
- mm/vmscan.c | 186 +++++++++++++++++++++++++++-------------------------
- 1 file changed, 98 insertions(+), 88 deletions(-)
+ mm/vmscan.c | 198 +++++++++++++++++++++++++++-------------------------
+ 1 file changed, 104 insertions(+), 94 deletions(-)
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 201acea81804..dc5f0381513f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
-@@ -2497,6 +2497,103 @@ enum scan_balance {
+@@ -2497,6 +2497,109 @@ enum scan_balance {
SCAN_FILE,
};
+ target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
+
+ /*
++ * Flush the memory cgroup stats, so that we read accurate per-memcg
++ * lruvec stats for heuristics.
++ */
++ mem_cgroup_flush_stats();
++
++ /*
+ * Determine the scan balance between anon and file LRUs.
+ */
+ spin_lock_irq(&target_lruvec->lru_lock);
/*
* Determine how aggressively the anon and file LRU lists should be
* scanned. The relative value of each set of LRU lists is determined
-@@ -2965,7 +3062,6 @@ static void shrink_node(pg_data_t *pgdat
+@@ -2965,109 +3068,16 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
unsigned long nr_reclaimed, nr_scanned;
struct lruvec *target_lruvec;
bool reclaimable = false;
target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
-@@ -2981,93 +3077,7 @@ again:
+ again:
+- /*
+- * Flush the memory cgroup stats, so that we read accurate per-memcg
+- * lruvec stats for heuristics.
+- */
+- mem_cgroup_flush_stats();
+-
+ memset(&sc->nr, 0, sizeof(sc->nr));
+
nr_reclaimed = sc->nr_reclaimed;
nr_scanned = sc->nr_scanned;
shrink_node_memcgs(pgdat, sc);
+--
+2.40.0
+
--- /dev/null
+From 03705be42114db7cc5bd6eb7bf7e8703c94d4880 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:01 -0600
+Subject: [PATCH 04/29] Revert "include/linux/mm_inline.h: fold
+ __update_lru_size() into its sole caller"
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+This patch undoes the following refactor: commit 289ccba18af4
+("include/linux/mm_inline.h: fold __update_lru_size() into its sole
+caller")
+
+The upcoming changes to include/linux/mm_inline.h will reuse
+__update_lru_size().
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-5-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mm_inline.h | 9 ++++++++-
+ 1 file changed, 8 insertions(+), 1 deletion(-)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 355ea1ee32bd..a822d6b690a5 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -24,7 +24,7 @@ static inline int page_is_file_lru(struct page *page)
+ return !PageSwapBacked(page);
+ }
+
+-static __always_inline void update_lru_size(struct lruvec *lruvec,
++static __always_inline void __update_lru_size(struct lruvec *lruvec,
+ enum lru_list lru, enum zone_type zid,
+ int nr_pages)
+ {
+@@ -33,6 +33,13 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
+ __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
+ __mod_zone_page_state(&pgdat->node_zones[zid],
+ NR_ZONE_LRU_BASE + lru, nr_pages);
++}
++
++static __always_inline void update_lru_size(struct lruvec *lruvec,
++ enum lru_list lru, enum zone_type zid,
++ long nr_pages)
++{
++ __update_lru_size(lruvec, lru, zid, nr_pages);
+ #ifdef CONFIG_MEMCG
+ mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
+ #endif
+--
+2.40.0
+
+++ /dev/null
-From 05f366c941ae2bb8ba21c79fafcb747a5a6b967b Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Mon, 25 Jan 2021 21:12:33 -0700
-Subject: [PATCH 04/10] mm: multigenerational lru: groundwork
-
-For each lruvec, evictable pages are divided into multiple
-generations. The youngest generation number is stored in
-lrugen->max_seq for both anon and file types as they are aged on an
-equal footing. The oldest generation numbers are stored in
-lrugen->min_seq[] separately for anon and file types as clean file
-pages can be evicted regardless of swap constraints. These three
-variables are monotonically increasing. Generation numbers are
-truncated into order_base_2(MAX_NR_GENS+1) bits in order to fit into
-page->flags. The sliding window technique is used to prevent truncated
-generation numbers from overlapping. Each truncated generation number
-is an index to
-lrugen->lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES].
-
-The framework comprises two conceptually independent components: the
-aging, which produces young generations, and the eviction, which
-consumes old generations. Both can be invoked independently from user
-space for the purpose of working set estimation and proactive reclaim.
-
-The protection of hot pages and the selection of cold pages are based
-on page access types and patterns. There are two access types: one via
-page tables and the other via file descriptors. The protection of the
-former type is by design stronger because:
- 1) The uncertainty in determining the access patterns of the former
- type is higher due to the coalesced nature of the accessed bit.
- 2) The cost of evicting the former type is higher due to the TLB
- flushes required and the likelihood of involving I/O.
- 3) The penalty of under-protecting the former type is higher because
- applications usually do not prepare themselves for major faults like
- they do for blocked I/O. For example, client applications commonly
- dedicate blocked I/O to separate threads to avoid UI janks that
- negatively affect user experience.
-
-There are also two access patterns: one with temporal locality and the
-other without. The latter pattern, e.g., random and sequential, needs
-to be explicitly excluded to avoid weakening the protection of the
-former pattern. Generally the former type follows the former pattern
-unless MADV_SEQUENTIAL is specified and the latter type follows the
-latter pattern unless outlying refaults have been observed.
-
-Upon faulting, a page is added to the youngest generation, which
-provides the strongest protection as the eviction will not consider
-this page before the aging has scanned it at least twice. The first
-scan clears the accessed bit set during the initial fault. And the
-second scan makes sure this page has not been used since the first
-scan. A page from any other generations is brought back to the
-youngest generation whenever the aging finds the accessed bit set on
-any of the PTEs mapping this page.
-
-Unmapped pages are initially added to the oldest generation and then
-conditionally protected by tiers. This is done later [PATCH 07/10].
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I71de7cd15b8dfa6f9fdd838023474693c4fee0a7
----
- fs/fuse/dev.c | 3 +-
- include/linux/cgroup.h | 15 +-
- include/linux/mm.h | 36 ++++
- include/linux/mm_inline.h | 182 ++++++++++++++++++++
- include/linux/mmzone.h | 70 ++++++++
- include/linux/page-flags-layout.h | 19 ++-
- include/linux/page-flags.h | 4 +-
- include/linux/sched.h | 3 +
- kernel/bounds.c | 3 +
- kernel/cgroup/cgroup-internal.h | 1 -
- mm/huge_memory.c | 3 +-
- mm/memcontrol.c | 1 +
- mm/memory.c | 7 +
- mm/mm_init.c | 6 +-
- mm/page_alloc.c | 1 +
- mm/swap.c | 9 +-
- mm/swapfile.c | 2 +
- mm/vmscan.c | 268 ++++++++++++++++++++++++++++++
- 18 files changed, 618 insertions(+), 15 deletions(-)
-
---- a/fs/fuse/dev.c
-+++ b/fs/fuse/dev.c
-@@ -785,7 +785,8 @@ static int fuse_check_page(struct page *
- 1 << PG_active |
- 1 << PG_workingset |
- 1 << PG_reclaim |
-- 1 << PG_waiters))) {
-+ 1 << PG_waiters |
-+ LRU_GEN_MASK | LRU_REFS_MASK))) {
- dump_page(page, "fuse: trying to steal weird page");
- return 1;
- }
---- a/include/linux/cgroup.h
-+++ b/include/linux/cgroup.h
-@@ -433,6 +433,18 @@ static inline void cgroup_put(struct cgr
- css_put(&cgrp->self);
- }
-
-+extern struct mutex cgroup_mutex;
-+
-+static inline void cgroup_lock(void)
-+{
-+ mutex_lock(&cgroup_mutex);
-+}
-+
-+static inline void cgroup_unlock(void)
-+{
-+ mutex_unlock(&cgroup_mutex);
-+}
-+
- /**
- * task_css_set_check - obtain a task's css_set with extra access conditions
- * @task: the task to obtain css_set for
-@@ -447,7 +459,6 @@ static inline void cgroup_put(struct cgr
- * as locks used during the cgroup_subsys::attach() methods.
- */
- #ifdef CONFIG_PROVE_RCU
--extern struct mutex cgroup_mutex;
- extern spinlock_t css_set_lock;
- #define task_css_set_check(task, __c) \
- rcu_dereference_check((task)->cgroups, \
-@@ -708,6 +719,8 @@ struct cgroup;
- static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; }
- static inline void css_get(struct cgroup_subsys_state *css) {}
- static inline void css_put(struct cgroup_subsys_state *css) {}
-+static inline void cgroup_lock(void) {}
-+static inline void cgroup_unlock(void) {}
- static inline int cgroup_attach_task_all(struct task_struct *from,
- struct task_struct *t) { return 0; }
- static inline int cgroupstats_build(struct cgroupstats *stats,
---- a/include/linux/mm.h
-+++ b/include/linux/mm.h
-@@ -1093,6 +1093,8 @@ vm_fault_t finish_mkwrite_fault(struct v
- #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
- #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH)
- #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
-+#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH)
-+#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH)
-
- /*
- * Define the bit shifts to access each section. For non-existent
-@@ -1807,6 +1809,40 @@ static inline void unmap_mapping_range(s
- loff_t const holebegin, loff_t const holelen, int even_cows) { }
- #endif
-
-+#ifdef CONFIG_LRU_GEN
-+static inline void task_enter_nonseq_fault(void)
-+{
-+ WARN_ON(current->in_nonseq_fault);
-+
-+ current->in_nonseq_fault = 1;
-+}
-+
-+static inline void task_exit_nonseq_fault(void)
-+{
-+ WARN_ON(!current->in_nonseq_fault);
-+
-+ current->in_nonseq_fault = 0;
-+}
-+
-+static inline bool task_in_nonseq_fault(void)
-+{
-+ return current->in_nonseq_fault;
-+}
-+#else
-+static inline void task_enter_nonseq_fault(void)
-+{
-+}
-+
-+static inline void task_exit_nonseq_fault(void)
-+{
-+}
-+
-+static inline bool task_in_nonseq_fault(void)
-+{
-+ return false;
-+}
-+#endif /* CONFIG_LRU_GEN */
-+
- static inline void unmap_shared_mapping_range(struct address_space *mapping,
- loff_t const holebegin, loff_t const holelen)
- {
---- a/include/linux/mm_inline.h
-+++ b/include/linux/mm_inline.h
-@@ -79,11 +79,187 @@ static __always_inline enum lru_list pag
- return lru;
- }
-
-+#ifdef CONFIG_LRU_GEN
-+
-+static inline bool lru_gen_enabled(void)
-+{
-+#ifdef CONFIG_LRU_GEN_ENABLED
-+ DECLARE_STATIC_KEY_TRUE(lru_gen_static_key);
-+
-+ return static_branch_likely(&lru_gen_static_key);
-+#else
-+ DECLARE_STATIC_KEY_FALSE(lru_gen_static_key);
-+
-+ return static_branch_unlikely(&lru_gen_static_key);
-+#endif
-+}
-+
-+/* Return an index within the sliding window that tracks MAX_NR_GENS generations. */
-+static inline int lru_gen_from_seq(unsigned long seq)
-+{
-+ return seq % MAX_NR_GENS;
-+}
-+
-+/* The youngest and the second youngest generations are counted as active. */
-+static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
-+{
-+ unsigned long max_seq = lruvec->evictable.max_seq;
-+
-+ VM_BUG_ON(gen >= MAX_NR_GENS);
-+
-+ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1);
-+}
-+
-+/* Update the sizes of the multigenerational lru lists. */
-+static inline void lru_gen_update_size(struct page *page, struct lruvec *lruvec,
-+ int old_gen, int new_gen)
-+{
-+ int type = page_is_file_lru(page);
-+ int zone = page_zonenum(page);
-+ int delta = thp_nr_pages(page);
-+ enum lru_list lru = type * LRU_FILE;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ lockdep_assert_held(&lruvec->lru_lock);
-+ VM_BUG_ON(old_gen != -1 && old_gen >= MAX_NR_GENS);
-+ VM_BUG_ON(new_gen != -1 && new_gen >= MAX_NR_GENS);
-+ VM_BUG_ON(old_gen == -1 && new_gen == -1);
-+
-+ if (old_gen >= 0)
-+ WRITE_ONCE(lrugen->sizes[old_gen][type][zone],
-+ lrugen->sizes[old_gen][type][zone] - delta);
-+ if (new_gen >= 0)
-+ WRITE_ONCE(lrugen->sizes[new_gen][type][zone],
-+ lrugen->sizes[new_gen][type][zone] + delta);
-+
-+ if (old_gen < 0) {
-+ if (lru_gen_is_active(lruvec, new_gen))
-+ lru += LRU_ACTIVE;
-+ update_lru_size(lruvec, lru, zone, delta);
-+ return;
-+ }
-+
-+ if (new_gen < 0) {
-+ if (lru_gen_is_active(lruvec, old_gen))
-+ lru += LRU_ACTIVE;
-+ update_lru_size(lruvec, lru, zone, -delta);
-+ return;
-+ }
-+
-+ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) {
-+ update_lru_size(lruvec, lru, zone, -delta);
-+ update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
-+ }
-+
-+ VM_BUG_ON(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
-+}
-+
-+/* Add a page to one of the multigenerational lru lists. Return true on success. */
-+static inline bool lru_gen_add_page(struct page *page, struct lruvec *lruvec, bool reclaiming)
-+{
-+ int gen;
-+ unsigned long old_flags, new_flags;
-+ int type = page_is_file_lru(page);
-+ int zone = page_zonenum(page);
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ if (PageUnevictable(page) || !lrugen->enabled[type])
-+ return false;
-+ /*
-+ * If a page shouldn't be considered for eviction, i.e., a page mapped
-+ * upon fault during which the accessed bit is set, add it to the
-+ * youngest generation.
-+ *
-+ * If a page can't be evicted immediately, i.e., an anon page not in
-+ * swap cache or a dirty page pending writeback, add it to the second
-+ * oldest generation.
-+ *
-+ * If a page could be evicted immediately, e.g., a clean page, add it to
-+ * the oldest generation.
-+ */
-+ if (PageActive(page))
-+ gen = lru_gen_from_seq(lrugen->max_seq);
-+ else if ((!type && !PageSwapCache(page)) ||
-+ (PageReclaim(page) && (PageDirty(page) || PageWriteback(page))))
-+ gen = lru_gen_from_seq(lrugen->min_seq[type] + 1);
-+ else
-+ gen = lru_gen_from_seq(lrugen->min_seq[type]);
-+
-+ do {
-+ new_flags = old_flags = READ_ONCE(page->flags);
-+ VM_BUG_ON_PAGE(new_flags & LRU_GEN_MASK, page);
-+
-+ new_flags &= ~(LRU_GEN_MASK | BIT(PG_active));
-+ new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
-+ } while (cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-+
-+ lru_gen_update_size(page, lruvec, -1, gen);
-+ /* for rotate_reclaimable_page() */
-+ if (reclaiming)
-+ list_add_tail(&page->lru, &lrugen->lists[gen][type][zone]);
-+ else
-+ list_add(&page->lru, &lrugen->lists[gen][type][zone]);
-+
-+ return true;
-+}
-+
-+/* Delete a page from one of the multigenerational lru lists. Return true on success. */
-+static inline bool lru_gen_del_page(struct page *page, struct lruvec *lruvec, bool reclaiming)
-+{
-+ int gen;
-+ unsigned long old_flags, new_flags;
-+
-+ do {
-+ new_flags = old_flags = READ_ONCE(page->flags);
-+ if (!(new_flags & LRU_GEN_MASK))
-+ return false;
-+
-+ VM_BUG_ON_PAGE(PageActive(page), page);
-+ VM_BUG_ON_PAGE(PageUnevictable(page), page);
-+
-+ gen = ((new_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
-+
-+ new_flags &= ~LRU_GEN_MASK;
-+ /* for shrink_page_list() */
-+ if (reclaiming)
-+ new_flags &= ~(BIT(PG_referenced) | BIT(PG_reclaim));
-+ else if (lru_gen_is_active(lruvec, gen))
-+ new_flags |= BIT(PG_active);
-+ } while (cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-+
-+ lru_gen_update_size(page, lruvec, gen, -1);
-+ list_del(&page->lru);
-+
-+ return true;
-+}
-+
-+#else
-+
-+static inline bool lru_gen_enabled(void)
-+{
-+ return false;
-+}
-+
-+static inline bool lru_gen_add_page(struct page *page, struct lruvec *lruvec, bool reclaiming)
-+{
-+ return false;
-+}
-+
-+static inline bool lru_gen_del_page(struct page *page, struct lruvec *lruvec, bool reclaiming)
-+{
-+ return false;
-+}
-+
-+#endif /* CONFIG_LRU_GEN */
-+
- static __always_inline void add_page_to_lru_list(struct page *page,
- struct lruvec *lruvec)
- {
- enum lru_list lru = page_lru(page);
-
-+ if (lru_gen_add_page(page, lruvec, false))
-+ return;
-+
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add(&page->lru, &lruvec->lists[lru]);
- }
-@@ -93,6 +269,9 @@ static __always_inline void add_page_to_
- {
- enum lru_list lru = page_lru(page);
-
-+ if (lru_gen_add_page(page, lruvec, true))
-+ return;
-+
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add_tail(&page->lru, &lruvec->lists[lru]);
- }
-@@ -100,6 +279,9 @@ static __always_inline void add_page_to_
- static __always_inline void del_page_from_lru_list(struct page *page,
- struct lruvec *lruvec)
- {
-+ if (lru_gen_del_page(page, lruvec, false))
-+ return;
-+
- list_del(&page->lru);
- update_lru_size(lruvec, page_lru(page), page_zonenum(page),
- -thp_nr_pages(page));
---- a/include/linux/mmzone.h
-+++ b/include/linux/mmzone.h
-@@ -294,6 +294,72 @@ enum lruvec_flags {
- */
- };
-
-+struct lruvec;
-+
-+#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
-+#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
-+
-+#ifdef CONFIG_LRU_GEN
-+
-+/*
-+ * For each lruvec, evictable pages are divided into multiple generations. The
-+ * youngest and the oldest generation numbers, AKA max_seq and min_seq, are
-+ * monotonically increasing. The sliding window technique is used to track at
-+ * least MIN_NR_GENS and at most MAX_NR_GENS generations. An offset within the
-+ * window, AKA gen, indexes an array of per-type and per-zone lists for the
-+ * corresponding generation. The counter in page->flags stores gen+1 while a
-+ * page is on one of the multigenerational lru lists. Otherwise, it stores 0.
-+ *
-+ * After a page is faulted in, the aging must check the accessed bit at least
-+ * twice before the eviction would consider it. The first check clears the
-+ * accessed bit set during the initial fault. The second check makes sure this
-+ * page hasn't been used since then.
-+ */
-+#define MIN_NR_GENS 2
-+#define MAX_NR_GENS ((unsigned int)CONFIG_NR_LRU_GENS)
-+
-+struct lrugen {
-+ /* the aging increments the max generation number */
-+ unsigned long max_seq;
-+ /* the eviction increments the min generation numbers */
-+ unsigned long min_seq[ANON_AND_FILE];
-+ /* the birth time of each generation in jiffies */
-+ unsigned long timestamps[MAX_NR_GENS];
-+ /* the multigenerational lru lists */
-+ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
-+ /* the sizes of the multigenerational lru lists in pages */
-+ unsigned long sizes[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
-+ /* whether the multigenerational lru is enabled */
-+ bool enabled[ANON_AND_FILE];
-+};
-+
-+#define MAX_BATCH_SIZE 8192
-+
-+void lru_gen_init_state(struct mem_cgroup *memcg, struct lruvec *lruvec);
-+void lru_gen_change_state(bool enable, bool main, bool swap);
-+
-+#ifdef CONFIG_MEMCG
-+void lru_gen_init_memcg(struct mem_cgroup *memcg);
-+#endif
-+
-+#else /* !CONFIG_LRU_GEN */
-+
-+static inline void lru_gen_init_state(struct mem_cgroup *memcg, struct lruvec *lruvec)
-+{
-+}
-+
-+static inline void lru_gen_change_state(bool enable, bool main, bool swap)
-+{
-+}
-+
-+#ifdef CONFIG_MEMCG
-+static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
-+{
-+}
-+#endif
-+
-+#endif /* CONFIG_LRU_GEN */
-+
- struct lruvec {
- struct list_head lists[NR_LRU_LISTS];
- /* per lruvec lru_lock for memcg */
-@@ -311,6 +377,10 @@ struct lruvec {
- unsigned long refaults[ANON_AND_FILE];
- /* Various lruvec state flags (enum lruvec_flags) */
- unsigned long flags;
-+#ifdef CONFIG_LRU_GEN
-+ /* unevictable pages are on LRU_UNEVICTABLE */
-+ struct lrugen evictable;
-+#endif
- #ifdef CONFIG_MEMCG
- struct pglist_data *pgdat;
- #endif
---- a/include/linux/page-flags-layout.h
-+++ b/include/linux/page-flags-layout.h
-@@ -26,6 +26,14 @@
-
- #define ZONES_WIDTH ZONES_SHIFT
-
-+#ifdef CONFIG_LRU_GEN
-+/* LRU_GEN_WIDTH is generated from order_base_2(CONFIG_NR_LRU_GENS + 1). */
-+#define LRU_REFS_WIDTH (CONFIG_TIERS_PER_GEN - 2)
-+#else
-+#define LRU_GEN_WIDTH 0
-+#define LRU_REFS_WIDTH 0
-+#endif /* CONFIG_LRU_GEN */
-+
- #ifdef CONFIG_SPARSEMEM
- #include <asm/sparsemem.h>
- #define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
-@@ -55,7 +63,8 @@
- #define SECTIONS_WIDTH 0
- #endif
-
--#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
-+#if ZONES_WIDTH + LRU_GEN_WIDTH + LRU_REFS_WIDTH + SECTIONS_WIDTH + NODES_SHIFT \
-+ <= BITS_PER_LONG - NR_PAGEFLAGS
- #define NODES_WIDTH NODES_SHIFT
- #elif defined(CONFIG_SPARSEMEM_VMEMMAP)
- #error "Vmemmap: No space for nodes field in page flags"
-@@ -89,8 +98,8 @@
- #define LAST_CPUPID_SHIFT 0
- #endif
-
--#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \
-- <= BITS_PER_LONG - NR_PAGEFLAGS
-+#if ZONES_WIDTH + LRU_GEN_WIDTH + LRU_REFS_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \
-+ KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
- #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
- #else
- #define LAST_CPUPID_WIDTH 0
-@@ -100,8 +109,8 @@
- #define LAST_CPUPID_NOT_IN_PAGE_FLAGS
- #endif
-
--#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \
-- > BITS_PER_LONG - NR_PAGEFLAGS
-+#if ZONES_WIDTH + LRU_GEN_WIDTH + LRU_REFS_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \
-+ KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
- #error "Not enough bits in page flags"
- #endif
-
---- a/include/linux/page-flags.h
-+++ b/include/linux/page-flags.h
-@@ -845,7 +845,7 @@ static inline void ClearPageSlabPfmemall
- 1UL << PG_private | 1UL << PG_private_2 | \
- 1UL << PG_writeback | 1UL << PG_reserved | \
- 1UL << PG_slab | 1UL << PG_active | \
-- 1UL << PG_unevictable | __PG_MLOCKED)
-+ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK)
-
- /*
- * Flags checked when a page is prepped for return by the page allocator.
-@@ -856,7 +856,7 @@ static inline void ClearPageSlabPfmemall
- * alloc-free cycle to prevent from reusing the page.
- */
- #define PAGE_FLAGS_CHECK_AT_PREP \
-- (PAGEFLAGS_MASK & ~__PG_HWPOISON)
-+ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK)
-
- #define PAGE_FLAGS_PRIVATE \
- (1UL << PG_private | 1UL << PG_private_2)
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -911,6 +911,9 @@ struct task_struct {
- #ifdef CONFIG_MEMCG
- unsigned in_user_fault:1;
- #endif
-+#ifdef CONFIG_LRU_GEN
-+ unsigned in_nonseq_fault:1;
-+#endif
- #ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
- #endif
---- a/kernel/bounds.c
-+++ b/kernel/bounds.c
-@@ -22,6 +22,9 @@ int main(void)
- DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
- #endif
- DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
-+#ifdef CONFIG_LRU_GEN
-+ DEFINE(LRU_GEN_WIDTH, order_base_2(CONFIG_NR_LRU_GENS + 1));
-+#endif
- /* End of constants */
-
- return 0;
---- a/kernel/cgroup/cgroup-internal.h
-+++ b/kernel/cgroup/cgroup-internal.h
-@@ -165,7 +165,6 @@ struct cgroup_mgctx {
- #define DEFINE_CGROUP_MGCTX(name) \
- struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
-
--extern struct mutex cgroup_mutex;
- extern spinlock_t css_set_lock;
- extern struct cgroup_subsys *cgroup_subsys[];
- extern struct list_head cgroup_roots;
---- a/mm/huge_memory.c
-+++ b/mm/huge_memory.c
-@@ -2366,7 +2366,8 @@ static void __split_huge_page_tail(struc
- #ifdef CONFIG_64BIT
- (1L << PG_arch_2) |
- #endif
-- (1L << PG_dirty)));
-+ (1L << PG_dirty) |
-+ LRU_GEN_MASK | LRU_REFS_MASK));
-
- /* ->mapping in first tail page is compound_mapcount */
- VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
---- a/mm/memcontrol.c
-+++ b/mm/memcontrol.c
-@@ -5241,6 +5241,7 @@ static struct mem_cgroup *mem_cgroup_all
- memcg->deferred_split_queue.split_queue_len = 0;
- #endif
- idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
-+ lru_gen_init_memcg(memcg);
- return memcg;
- fail:
- mem_cgroup_id_remove(memcg);
---- a/mm/memory.c
-+++ b/mm/memory.c
-@@ -4788,6 +4788,7 @@ vm_fault_t handle_mm_fault(struct vm_are
- unsigned int flags, struct pt_regs *regs)
- {
- vm_fault_t ret;
-+ bool nonseq_fault = !(vma->vm_flags & VM_SEQ_READ);
-
- __set_current_state(TASK_RUNNING);
-
-@@ -4809,11 +4810,17 @@ vm_fault_t handle_mm_fault(struct vm_are
- if (flags & FAULT_FLAG_USER)
- mem_cgroup_enter_user_fault();
-
-+ if (nonseq_fault)
-+ task_enter_nonseq_fault();
-+
- if (unlikely(is_vm_hugetlb_page(vma)))
- ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
- else
- ret = __handle_mm_fault(vma, address, flags);
-
-+ if (nonseq_fault)
-+ task_exit_nonseq_fault();
-+
- if (flags & FAULT_FLAG_USER) {
- mem_cgroup_exit_user_fault();
- /*
---- a/mm/mm_init.c
-+++ b/mm/mm_init.c
-@@ -65,14 +65,16 @@ void __init mminit_verify_pageflags_layo
-
- shift = 8 * sizeof(unsigned long);
- width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
-- - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH;
-+ - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH;
- mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
-- "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Flags %d\n",
-+ "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n",
- SECTIONS_WIDTH,
- NODES_WIDTH,
- ZONES_WIDTH,
- LAST_CPUPID_WIDTH,
- KASAN_TAG_WIDTH,
-+ LRU_GEN_WIDTH,
-+ LRU_REFS_WIDTH,
- NR_PAGEFLAGS);
- mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
- "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n",
---- a/mm/page_alloc.c
-+++ b/mm/page_alloc.c
-@@ -7459,6 +7459,7 @@ static void __meminit pgdat_init_interna
-
- pgdat_page_ext_init(pgdat);
- lruvec_init(&pgdat->__lruvec);
-+ lru_gen_init_state(NULL, &pgdat->__lruvec);
- }
-
- static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
---- a/mm/swap.c
-+++ b/mm/swap.c
-@@ -446,6 +446,11 @@ void lru_cache_add(struct page *page)
- VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
- VM_BUG_ON_PAGE(PageLRU(page), page);
-
-+ /* see the comment in lru_gen_add_page() */
-+ if (lru_gen_enabled() && !PageUnevictable(page) &&
-+ task_in_nonseq_fault() && !(current->flags & PF_MEMALLOC))
-+ SetPageActive(page);
-+
- get_page(page);
- local_lock(&lru_pvecs.lock);
- pvec = this_cpu_ptr(&lru_pvecs.lru_add);
-@@ -547,7 +552,7 @@ static void lru_deactivate_file_fn(struc
-
- static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
- {
-- if (PageActive(page) && !PageUnevictable(page)) {
-+ if (!PageUnevictable(page) && (PageActive(page) || lru_gen_enabled())) {
- int nr_pages = thp_nr_pages(page);
-
- del_page_from_lru_list(page, lruvec);
-@@ -661,7 +666,7 @@ void deactivate_file_page(struct page *p
- */
- void deactivate_page(struct page *page)
- {
-- if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
-+ if (PageLRU(page) && !PageUnevictable(page) && (PageActive(page) || lru_gen_enabled())) {
- struct pagevec *pvec;
-
- local_lock(&lru_pvecs.lock);
---- a/mm/swapfile.c
-+++ b/mm/swapfile.c
-@@ -2689,6 +2689,7 @@ SYSCALL_DEFINE1(swapoff, const char __us
- err = 0;
- atomic_inc(&proc_poll_event);
- wake_up_interruptible(&proc_poll_wait);
-+ lru_gen_change_state(false, false, true);
-
- out_dput:
- filp_close(victim, NULL);
-@@ -3350,6 +3351,7 @@ SYSCALL_DEFINE2(swapon, const char __use
- mutex_unlock(&swapon_mutex);
- atomic_inc(&proc_poll_event);
- wake_up_interruptible(&proc_poll_wait);
-+ lru_gen_change_state(true, false, true);
-
- error = 0;
- goto out;
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -50,6 +50,7 @@
- #include <linux/printk.h>
- #include <linux/dax.h>
- #include <linux/psi.h>
-+#include <linux/memory.h>
-
- #include <asm/tlbflush.h>
- #include <asm/div64.h>
-@@ -2815,6 +2816,273 @@ static bool can_age_anon_pages(struct pg
- return can_demote(pgdat->node_id, sc);
- }
-
-+#ifdef CONFIG_LRU_GEN
-+
-+/******************************************************************************
-+ * shorthand helpers
-+ ******************************************************************************/
-+
-+#define for_each_gen_type_zone(gen, type, zone) \
-+ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \
-+ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
-+ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
-+
-+static int page_lru_gen(struct page *page)
-+{
-+ unsigned long flags = READ_ONCE(page->flags);
-+
-+ return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
-+}
-+
-+static struct lruvec *get_lruvec(int nid, struct mem_cgroup *memcg)
-+{
-+ struct pglist_data *pgdat = NODE_DATA(nid);
-+
-+#ifdef CONFIG_MEMCG
-+ if (memcg) {
-+ struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
-+
-+ if (lruvec->pgdat != pgdat)
-+ lruvec->pgdat = pgdat;
-+
-+ return lruvec;
-+ }
-+#endif
-+ return pgdat ? &pgdat->__lruvec : NULL;
-+}
-+
-+static int get_nr_gens(struct lruvec *lruvec, int type)
-+{
-+ return lruvec->evictable.max_seq - lruvec->evictable.min_seq[type] + 1;
-+}
-+
-+static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
-+{
-+ return get_nr_gens(lruvec, 1) >= MIN_NR_GENS &&
-+ get_nr_gens(lruvec, 1) <= get_nr_gens(lruvec, 0) &&
-+ get_nr_gens(lruvec, 0) <= MAX_NR_GENS;
-+}
-+
-+/******************************************************************************
-+ * state change
-+ ******************************************************************************/
-+
-+#ifdef CONFIG_LRU_GEN_ENABLED
-+DEFINE_STATIC_KEY_TRUE(lru_gen_static_key);
-+#else
-+DEFINE_STATIC_KEY_FALSE(lru_gen_static_key);
-+#endif
-+
-+static int lru_gen_nr_swapfiles;
-+
-+static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
-+{
-+ int gen, type, zone;
-+ enum lru_list lru;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ for_each_evictable_lru(lru) {
-+ type = is_file_lru(lru);
-+
-+ if (lrugen->enabled[type] && !list_empty(&lruvec->lists[lru]))
-+ return false;
-+ }
-+
-+ for_each_gen_type_zone(gen, type, zone) {
-+ if (!lrugen->enabled[type] && !list_empty(&lrugen->lists[gen][type][zone]))
-+ return false;
-+
-+ /* unlikely but not a bug when reset_batch_size() is pending */
-+ VM_WARN_ON(!lrugen->enabled[type] && lrugen->sizes[gen][type][zone]);
-+ }
-+
-+ return true;
-+}
-+
-+static bool fill_lists(struct lruvec *lruvec)
-+{
-+ enum lru_list lru;
-+ int remaining = MAX_BATCH_SIZE;
-+
-+ for_each_evictable_lru(lru) {
-+ int type = is_file_lru(lru);
-+ bool active = is_active_lru(lru);
-+ struct list_head *head = &lruvec->lists[lru];
-+
-+ if (!lruvec->evictable.enabled[type])
-+ continue;
-+
-+ while (!list_empty(head)) {
-+ bool success;
-+ struct page *page = lru_to_page(head);
-+
-+ VM_BUG_ON_PAGE(PageTail(page), page);
-+ VM_BUG_ON_PAGE(PageUnevictable(page), page);
-+ VM_BUG_ON_PAGE(PageActive(page) != active, page);
-+ VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
-+ VM_BUG_ON_PAGE(page_lru_gen(page) < MAX_NR_GENS, page);
-+
-+ prefetchw_prev_lru_page(page, head, flags);
-+
-+ del_page_from_lru_list(page, lruvec);
-+ success = lru_gen_add_page(page, lruvec, false);
-+ VM_BUG_ON(!success);
-+
-+ if (!--remaining)
-+ return false;
-+ }
-+ }
-+
-+ return true;
-+}
-+
-+static bool drain_lists(struct lruvec *lruvec)
-+{
-+ int gen, type, zone;
-+ int remaining = MAX_BATCH_SIZE;
-+
-+ for_each_gen_type_zone(gen, type, zone) {
-+ struct list_head *head = &lruvec->evictable.lists[gen][type][zone];
-+
-+ if (lruvec->evictable.enabled[type])
-+ continue;
-+
-+ while (!list_empty(head)) {
-+ bool success;
-+ struct page *page = lru_to_page(head);
-+
-+ VM_BUG_ON_PAGE(PageTail(page), page);
-+ VM_BUG_ON_PAGE(PageUnevictable(page), page);
-+ VM_BUG_ON_PAGE(PageActive(page), page);
-+ VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
-+ VM_BUG_ON_PAGE(page_zonenum(page) != zone, page);
-+
-+ prefetchw_prev_lru_page(page, head, flags);
-+
-+ success = lru_gen_del_page(page, lruvec, false);
-+ VM_BUG_ON(!success);
-+ add_page_to_lru_list(page, lruvec);
-+
-+ if (!--remaining)
-+ return false;
-+ }
-+ }
-+
-+ return true;
-+}
-+
-+/*
-+ * For file page tracking, we enable/disable it according to the main switch.
-+ * For anon page tracking, we only enabled it when the main switch is on and
-+ * there is at least one swapfile; we disable it when there are no swapfiles
-+ * regardless of the value of the main switch. Otherwise, we will eventually
-+ * reach the max size of the sliding window and have to call inc_min_seq().
-+ */
-+void lru_gen_change_state(bool enable, bool main, bool swap)
-+{
-+ static DEFINE_MUTEX(state_mutex);
-+
-+ struct mem_cgroup *memcg;
-+
-+ mem_hotplug_begin();
-+ cgroup_lock();
-+ mutex_lock(&state_mutex);
-+
-+ if (swap) {
-+ if (enable)
-+ swap = !lru_gen_nr_swapfiles++;
-+ else
-+ swap = !--lru_gen_nr_swapfiles;
-+ }
-+
-+ if (main && enable != lru_gen_enabled()) {
-+ if (enable)
-+ static_branch_enable(&lru_gen_static_key);
-+ else
-+ static_branch_disable(&lru_gen_static_key);
-+ } else if (!swap || !lru_gen_enabled())
-+ goto unlock;
-+
-+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
-+ do {
-+ int nid;
-+
-+ for_each_node(nid) {
-+ struct lruvec *lruvec = get_lruvec(nid, memcg);
-+
-+ if (!lruvec)
-+ continue;
-+
-+ spin_lock_irq(&lruvec->lru_lock);
-+
-+ VM_BUG_ON(!seq_is_valid(lruvec));
-+ VM_BUG_ON(!state_is_valid(lruvec));
-+
-+ lruvec->evictable.enabled[0] = lru_gen_enabled() && lru_gen_nr_swapfiles;
-+ lruvec->evictable.enabled[1] = lru_gen_enabled();
-+
-+ while (!(enable ? fill_lists(lruvec) : drain_lists(lruvec))) {
-+ spin_unlock_irq(&lruvec->lru_lock);
-+ cond_resched();
-+ spin_lock_irq(&lruvec->lru_lock);
-+ }
-+
-+ spin_unlock_irq(&lruvec->lru_lock);
-+ }
-+
-+ cond_resched();
-+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
-+unlock:
-+ mutex_unlock(&state_mutex);
-+ cgroup_unlock();
-+ mem_hotplug_done();
-+}
-+
-+/******************************************************************************
-+ * initialization
-+ ******************************************************************************/
-+
-+void lru_gen_init_state(struct mem_cgroup *memcg, struct lruvec *lruvec)
-+{
-+ int i;
-+ int gen, type, zone;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ lrugen->max_seq = MIN_NR_GENS + 1;
-+ lrugen->enabled[0] = lru_gen_enabled() && lru_gen_nr_swapfiles;
-+ lrugen->enabled[1] = lru_gen_enabled();
-+
-+ for (i = 0; i <= MIN_NR_GENS + 1; i++)
-+ lrugen->timestamps[i] = jiffies;
-+
-+ for_each_gen_type_zone(gen, type, zone)
-+ INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
-+}
-+
-+#ifdef CONFIG_MEMCG
-+void lru_gen_init_memcg(struct mem_cgroup *memcg)
-+{
-+ int nid;
-+
-+ for_each_node(nid) {
-+ struct lruvec *lruvec = get_lruvec(nid, memcg);
-+
-+ lru_gen_init_state(memcg, lruvec);
-+ }
-+}
-+#endif
-+
-+static int __init init_lru_gen(void)
-+{
-+ BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
-+ BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
-+
-+ return 0;
-+};
-+late_initcall(init_lru_gen);
-+
-+#endif /* CONFIG_LRU_GEN */
-+
- static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
- {
- unsigned long nr[NR_LRU_LISTS];
--- /dev/null
+From a9b328add8422921a0dbbef162730800e16e8cfd Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:02 -0600
+Subject: [PATCH 05/29] mm: multi-gen LRU: groundwork
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Evictable pages are divided into multiple generations for each lruvec.
+The youngest generation number is stored in lrugen->max_seq for both
+anon and file types as they are aged on an equal footing. The oldest
+generation numbers are stored in lrugen->min_seq[] separately for anon
+and file types as clean file pages can be evicted regardless of swap
+constraints. These three variables are monotonically increasing.
+
+Generation numbers are truncated into order_base_2(MAX_NR_GENS+1) bits
+in order to fit into the gen counter in page->flags. Each truncated
+generation number is an index to lrugen->lists[]. The sliding window
+technique is used to track at least MIN_NR_GENS and at most
+MAX_NR_GENS generations. The gen counter stores a value within [1,
+MAX_NR_GENS] while a page is on one of lrugen->lists[]. Otherwise it
+stores 0.
+
+There are two conceptually independent procedures: "the aging", which
+produces young generations, and "the eviction", which consumes old
+generations. They form a closed-loop system, i.e., "the page reclaim".
+Both procedures can be invoked from userspace for the purposes of working
+set estimation and proactive reclaim. These techniques are commonly used
+to optimize job scheduling (bin packing) in data centers [1][2].
+
+To avoid confusion, the terms "hot" and "cold" will be applied to the
+multi-gen LRU, as a new convention; the terms "active" and "inactive" will
+be applied to the active/inactive LRU, as usual.
+
+The protection of hot pages and the selection of cold pages are based
+on page access channels and patterns. There are two access channels:
+one through page tables and the other through file descriptors. The
+protection of the former channel is by design stronger because:
+1. The uncertainty in determining the access patterns of the former
+ channel is higher due to the approximation of the accessed bit.
+2. The cost of evicting the former channel is higher due to the TLB
+ flushes required and the likelihood of encountering the dirty bit.
+3. The penalty of underprotecting the former channel is higher because
+ applications usually do not prepare themselves for major page
+ faults like they do for blocked I/O. E.g., GUI applications
+ commonly use dedicated I/O threads to avoid blocking rendering
+ threads.
+
+There are also two access patterns: one with temporal locality and the
+other without. For the reasons listed above, the former channel is
+assumed to follow the former pattern unless VM_SEQ_READ or VM_RAND_READ is
+present; the latter channel is assumed to follow the latter pattern unless
+outlying refaults have been observed [3][4].
+
+The next patch will address the "outlying refaults". Three macros, i.e.,
+LRU_REFS_WIDTH, LRU_REFS_PGOFF and LRU_REFS_MASK, used later are added in
+this patch to make the entire patchset less diffy.
+
+A page is added to the youngest generation on faulting. The aging needs
+to check the accessed bit at least twice before handing this page over to
+the eviction. The first check takes care of the accessed bit set on the
+initial fault; the second check makes sure this page has not been used
+since then. This protocol, AKA second chance, requires a minimum of two
+generations, hence MIN_NR_GENS.
+
+[1] https://dl.acm.org/doi/10.1145/3297858.3304053
+[2] https://dl.acm.org/doi/10.1145/3503222.3507731
+[3] https://lwn.net/Articles/495543/
+[4] https://lwn.net/Articles/815342/
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-6-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ fs/fuse/dev.c | 3 +-
+ include/linux/mm.h | 2 +
+ include/linux/mm_inline.h | 177 +++++++++++++++++++++++++++++-
+ include/linux/mmzone.h | 100 +++++++++++++++++
+ include/linux/page-flags-layout.h | 13 ++-
+ include/linux/page-flags.h | 4 +-
+ include/linux/sched.h | 4 +
+ kernel/bounds.c | 5 +
+ mm/Kconfig | 8 ++
+ mm/huge_memory.c | 3 +-
+ mm/memcontrol.c | 2 +
+ mm/memory.c | 25 +++++
+ mm/mm_init.c | 6 +-
+ mm/mmzone.c | 2 +
+ mm/swap.c | 10 +-
+ mm/vmscan.c | 75 +++++++++++++
+ 16 files changed, 425 insertions(+), 14 deletions(-)
+
+diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
+index d6b5339c56e2..4ec08f7c3e75 100644
+--- a/fs/fuse/dev.c
++++ b/fs/fuse/dev.c
+@@ -785,7 +785,8 @@ static int fuse_check_page(struct page *page)
+ 1 << PG_active |
+ 1 << PG_workingset |
+ 1 << PG_reclaim |
+- 1 << PG_waiters))) {
++ 1 << PG_waiters |
++ LRU_GEN_MASK | LRU_REFS_MASK))) {
+ dump_page(page, "fuse: trying to steal weird page");
+ return 1;
+ }
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index e4e1817bb3b8..699068f39aa0 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -1093,6 +1093,8 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
+ #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH)
+ #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH)
+ #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH)
++#define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH)
++#define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH)
+
+ /*
+ * Define the bit shifts to access each section. For non-existent
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index a822d6b690a5..65320d2b8f60 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -26,10 +26,13 @@ static inline int page_is_file_lru(struct page *page)
+
+ static __always_inline void __update_lru_size(struct lruvec *lruvec,
+ enum lru_list lru, enum zone_type zid,
+- int nr_pages)
++ long nr_pages)
+ {
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
++ lockdep_assert_held(&lruvec->lru_lock);
++ WARN_ON_ONCE(nr_pages != (int)nr_pages);
++
+ __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
+ __mod_zone_page_state(&pgdat->node_zones[zid],
+ NR_ZONE_LRU_BASE + lru, nr_pages);
+@@ -86,11 +89,177 @@ static __always_inline enum lru_list page_lru(struct page *page)
+ return lru;
+ }
+
++#ifdef CONFIG_LRU_GEN
++
++static inline bool lru_gen_enabled(void)
++{
++ return true;
++}
++
++static inline bool lru_gen_in_fault(void)
++{
++ return current->in_lru_fault;
++}
++
++static inline int lru_gen_from_seq(unsigned long seq)
++{
++ return seq % MAX_NR_GENS;
++}
++
++static inline int page_lru_gen(struct page *page)
++{
++ unsigned long flags = READ_ONCE(page->flags);
++
++ return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
++}
++
++static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
++{
++ unsigned long max_seq = lruvec->lrugen.max_seq;
++
++ VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
++
++ /* see the comment on MIN_NR_GENS */
++ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1);
++}
++
++static inline void lru_gen_update_size(struct lruvec *lruvec, struct page *page,
++ int old_gen, int new_gen)
++{
++ int type = page_is_file_lru(page);
++ int zone = page_zonenum(page);
++ int delta = thp_nr_pages(page);
++ enum lru_list lru = type * LRU_INACTIVE_FILE;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS);
++ VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS);
++ VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1);
++
++ if (old_gen >= 0)
++ WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone],
++ lrugen->nr_pages[old_gen][type][zone] - delta);
++ if (new_gen >= 0)
++ WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone],
++ lrugen->nr_pages[new_gen][type][zone] + delta);
++
++ /* addition */
++ if (old_gen < 0) {
++ if (lru_gen_is_active(lruvec, new_gen))
++ lru += LRU_ACTIVE;
++ __update_lru_size(lruvec, lru, zone, delta);
++ return;
++ }
++
++ /* deletion */
++ if (new_gen < 0) {
++ if (lru_gen_is_active(lruvec, old_gen))
++ lru += LRU_ACTIVE;
++ __update_lru_size(lruvec, lru, zone, -delta);
++ return;
++ }
++}
++
++static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
++{
++ unsigned long seq;
++ unsigned long flags;
++ int gen = page_lru_gen(page);
++ int type = page_is_file_lru(page);
++ int zone = page_zonenum(page);
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ VM_WARN_ON_ONCE_PAGE(gen != -1, page);
++
++ if (PageUnevictable(page))
++ return false;
++ /*
++ * There are three common cases for this page:
++ * 1. If it's hot, e.g., freshly faulted in or previously hot and
++ * migrated, add it to the youngest generation.
++ * 2. If it's cold but can't be evicted immediately, i.e., an anon page
++ * not in swapcache or a dirty page pending writeback, add it to the
++ * second oldest generation.
++ * 3. Everything else (clean, cold) is added to the oldest generation.
++ */
++ if (PageActive(page))
++ seq = lrugen->max_seq;
++ else if ((type == LRU_GEN_ANON && !PageSwapCache(page)) ||
++ (PageReclaim(page) &&
++ (PageDirty(page) || PageWriteback(page))))
++ seq = lrugen->min_seq[type] + 1;
++ else
++ seq = lrugen->min_seq[type];
++
++ gen = lru_gen_from_seq(seq);
++ flags = (gen + 1UL) << LRU_GEN_PGOFF;
++ /* see the comment on MIN_NR_GENS about PG_active */
++ set_mask_bits(&page->flags, LRU_GEN_MASK | BIT(PG_active), flags);
++
++ lru_gen_update_size(lruvec, page, -1, gen);
++ /* for rotate_reclaimable_page() */
++ if (reclaiming)
++ list_add_tail(&page->lru, &lrugen->lists[gen][type][zone]);
++ else
++ list_add(&page->lru, &lrugen->lists[gen][type][zone]);
++
++ return true;
++}
++
++static inline bool lru_gen_del_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
++{
++ unsigned long flags;
++ int gen = page_lru_gen(page);
++
++ if (gen < 0)
++ return false;
++
++ VM_WARN_ON_ONCE_PAGE(PageActive(page), page);
++ VM_WARN_ON_ONCE_PAGE(PageUnevictable(page), page);
++
++ /* for migrate_page_states() */
++ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0;
++ flags = set_mask_bits(&page->flags, LRU_GEN_MASK, flags);
++ gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
++
++ lru_gen_update_size(lruvec, page, gen, -1);
++ list_del(&page->lru);
++
++ return true;
++}
++
++#else /* !CONFIG_LRU_GEN */
++
++static inline bool lru_gen_enabled(void)
++{
++ return false;
++}
++
++static inline bool lru_gen_in_fault(void)
++{
++ return false;
++}
++
++static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
++{
++ return false;
++}
++
++static inline bool lru_gen_del_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
++{
++ return false;
++}
++
++#endif /* CONFIG_LRU_GEN */
++
+ static __always_inline void add_page_to_lru_list(struct page *page,
+ struct lruvec *lruvec)
+ {
+ enum lru_list lru = page_lru(page);
+
++ if (lru_gen_add_page(lruvec, page, false))
++ return;
++
+ update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
+ list_add(&page->lru, &lruvec->lists[lru]);
+ }
+@@ -100,6 +269,9 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page,
+ {
+ enum lru_list lru = page_lru(page);
+
++ if (lru_gen_add_page(lruvec, page, true))
++ return;
++
+ update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
+ list_add_tail(&page->lru, &lruvec->lists[lru]);
+ }
+@@ -107,6 +279,9 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page,
+ static __always_inline void del_page_from_lru_list(struct page *page,
+ struct lruvec *lruvec)
+ {
++ if (lru_gen_del_page(lruvec, page, false))
++ return;
++
+ list_del(&page->lru);
+ update_lru_size(lruvec, page_lru(page), page_zonenum(page),
+ -thp_nr_pages(page));
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 6ba100216530..0c39f72184d0 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -294,6 +294,102 @@ enum lruvec_flags {
+ */
+ };
+
++#endif /* !__GENERATING_BOUNDS_H */
++
++/*
++ * Evictable pages are divided into multiple generations. The youngest and the
++ * oldest generation numbers, max_seq and min_seq, are monotonically increasing.
++ * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
++ * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
++ * corresponding generation. The gen counter in page->flags stores gen+1 while
++ * a page is on one of lrugen->lists[]. Otherwise it stores 0.
++ *
++ * A page is added to the youngest generation on faulting. The aging needs to
++ * check the accessed bit at least twice before handing this page over to the
++ * eviction. The first check takes care of the accessed bit set on the initial
++ * fault; the second check makes sure this page hasn't been used since then.
++ * This process, AKA second chance, requires a minimum of two generations,
++ * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive
++ * LRU, e.g., /proc/vmstat, these two generations are considered active; the
++ * rest of generations, if they exist, are considered inactive. See
++ * lru_gen_is_active().
++ *
++ * PG_active is always cleared while a page is on one of lrugen->lists[] so that
++ * the aging needs not to worry about it. And it's set again when a page
++ * considered active is isolated for non-reclaiming purposes, e.g., migration.
++ * See lru_gen_add_page() and lru_gen_del_page().
++ *
++ * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the
++ * number of categories of the active/inactive LRU when keeping track of
++ * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits
++ * in page->flags.
++ */
++#define MIN_NR_GENS 2U
++#define MAX_NR_GENS 4U
++
++#ifndef __GENERATING_BOUNDS_H
++
++struct lruvec;
++
++#define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
++#define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
++
++#ifdef CONFIG_LRU_GEN
++
++enum {
++ LRU_GEN_ANON,
++ LRU_GEN_FILE,
++};
++
++/*
++ * The youngest generation number is stored in max_seq for both anon and file
++ * types as they are aged on an equal footing. The oldest generation numbers are
++ * stored in min_seq[] separately for anon and file types as clean file pages
++ * can be evicted regardless of swap constraints.
++ *
++ * Normally anon and file min_seq are in sync. But if swapping is constrained,
++ * e.g., out of swap space, file min_seq is allowed to advance and leave anon
++ * min_seq behind.
++ *
++ * The number of pages in each generation is eventually consistent and therefore
++ * can be transiently negative.
++ */
++struct lru_gen_struct {
++ /* the aging increments the youngest generation number */
++ unsigned long max_seq;
++ /* the eviction increments the oldest generation numbers */
++ unsigned long min_seq[ANON_AND_FILE];
++ /* the multi-gen LRU lists, lazily sorted on eviction */
++ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
++ /* the multi-gen LRU sizes, eventually consistent */
++ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
++};
++
++void lru_gen_init_lruvec(struct lruvec *lruvec);
++
++#ifdef CONFIG_MEMCG
++void lru_gen_init_memcg(struct mem_cgroup *memcg);
++void lru_gen_exit_memcg(struct mem_cgroup *memcg);
++#endif
++
++#else /* !CONFIG_LRU_GEN */
++
++static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
++{
++}
++
++#ifdef CONFIG_MEMCG
++static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
++{
++}
++
++static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg)
++{
++}
++#endif
++
++#endif /* CONFIG_LRU_GEN */
++
+ struct lruvec {
+ struct list_head lists[NR_LRU_LISTS];
+ /* per lruvec lru_lock for memcg */
+@@ -311,6 +407,10 @@ struct lruvec {
+ unsigned long refaults[ANON_AND_FILE];
+ /* Various lruvec state flags (enum lruvec_flags) */
+ unsigned long flags;
++#ifdef CONFIG_LRU_GEN
++ /* evictable pages divided into generations */
++ struct lru_gen_struct lrugen;
++#endif
+ #ifdef CONFIG_MEMCG
+ struct pglist_data *pgdat;
+ #endif
+diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
+index ef1e3e736e14..240905407a18 100644
+--- a/include/linux/page-flags-layout.h
++++ b/include/linux/page-flags-layout.h
+@@ -55,7 +55,8 @@
+ #define SECTIONS_WIDTH 0
+ #endif
+
+-#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
++#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_SHIFT \
++ <= BITS_PER_LONG - NR_PAGEFLAGS
+ #define NODES_WIDTH NODES_SHIFT
+ #elif defined(CONFIG_SPARSEMEM_VMEMMAP)
+ #error "Vmemmap: No space for nodes field in page flags"
+@@ -89,8 +90,8 @@
+ #define LAST_CPUPID_SHIFT 0
+ #endif
+
+-#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT \
+- <= BITS_PER_LONG - NR_PAGEFLAGS
++#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \
++ KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+ #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
+ #else
+ #define LAST_CPUPID_WIDTH 0
+@@ -100,10 +101,12 @@
+ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS
+ #endif
+
+-#if ZONES_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH \
+- > BITS_PER_LONG - NR_PAGEFLAGS
++#if ZONES_WIDTH + LRU_GEN_WIDTH + SECTIONS_WIDTH + NODES_WIDTH + \
++ KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
+ #error "Not enough bits in page flags"
+ #endif
+
++#define LRU_REFS_WIDTH 0
++
+ #endif
+ #endif /* _LINUX_PAGE_FLAGS_LAYOUT */
+diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
+index fbfd3fad48f2..a7d7ff4c621d 100644
+--- a/include/linux/page-flags.h
++++ b/include/linux/page-flags.h
+@@ -845,7 +845,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
+ 1UL << PG_private | 1UL << PG_private_2 | \
+ 1UL << PG_writeback | 1UL << PG_reserved | \
+ 1UL << PG_slab | 1UL << PG_active | \
+- 1UL << PG_unevictable | __PG_MLOCKED)
++ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK)
+
+ /*
+ * Flags checked when a page is prepped for return by the page allocator.
+@@ -856,7 +856,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
+ * alloc-free cycle to prevent from reusing the page.
+ */
+ #define PAGE_FLAGS_CHECK_AT_PREP \
+- (PAGEFLAGS_MASK & ~__PG_HWPOISON)
++ ((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK)
+
+ #define PAGE_FLAGS_PRIVATE \
+ (1UL << PG_private | 1UL << PG_private_2)
+diff --git a/include/linux/sched.h b/include/linux/sched.h
+index e418935f8db6..545f6b1ccd50 100644
+--- a/include/linux/sched.h
++++ b/include/linux/sched.h
+@@ -911,6 +911,10 @@ struct task_struct {
+ #ifdef CONFIG_MEMCG
+ unsigned in_user_fault:1;
+ #endif
++#ifdef CONFIG_LRU_GEN
++ /* whether the LRU algorithm may apply to this access */
++ unsigned in_lru_fault:1;
++#endif
+ #ifdef CONFIG_COMPAT_BRK
+ unsigned brk_randomized:1;
+ #endif
+diff --git a/kernel/bounds.c b/kernel/bounds.c
+index 9795d75b09b2..5ee60777d8e4 100644
+--- a/kernel/bounds.c
++++ b/kernel/bounds.c
+@@ -22,6 +22,11 @@ int main(void)
+ DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+ #endif
+ DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
++#ifdef CONFIG_LRU_GEN
++ DEFINE(LRU_GEN_WIDTH, order_base_2(MAX_NR_GENS + 1));
++#else
++ DEFINE(LRU_GEN_WIDTH, 0);
++#endif
+ /* End of constants */
+
+ return 0;
+diff --git a/mm/Kconfig b/mm/Kconfig
+index c048dea7e342..0eeb27397884 100644
+--- a/mm/Kconfig
++++ b/mm/Kconfig
+@@ -897,6 +897,14 @@ config IO_MAPPING
+ config SECRETMEM
+ def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
++config LRU_GEN
++ bool "Multi-Gen LRU"
++ depends on MMU
++ # make sure page->flags has enough spare bits
++ depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
++ help
++ A high performance LRU implementation to overcommit memory.
++
+ source "mm/damon/Kconfig"
+
+ endmenu
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 98ff57c8eda6..f260ef82f03a 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -2366,7 +2366,8 @@ static void __split_huge_page_tail(struct page *head, int tail,
+ #ifdef CONFIG_64BIT
+ (1L << PG_arch_2) |
+ #endif
+- (1L << PG_dirty)));
++ (1L << PG_dirty) |
++ LRU_GEN_MASK | LRU_REFS_MASK));
+
+ /* ->mapping in first tail page is compound_mapcount */
+ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index b68b2fe639fd..8b634dc72e7f 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -5178,6 +5178,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
+
+ static void mem_cgroup_free(struct mem_cgroup *memcg)
+ {
++ lru_gen_exit_memcg(memcg);
+ memcg_wb_domain_exit(memcg);
+ __mem_cgroup_free(memcg);
+ }
+@@ -5241,6 +5242,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
+ memcg->deferred_split_queue.split_queue_len = 0;
+ #endif
+ idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
++ lru_gen_init_memcg(memcg);
+ return memcg;
+ fail:
+ mem_cgroup_id_remove(memcg);
+diff --git a/mm/memory.c b/mm/memory.c
+index 392b7326a2d2..7d5be951de9e 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -4778,6 +4778,27 @@ static inline void mm_account_fault(struct pt_regs *regs,
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+ }
+
++#ifdef CONFIG_LRU_GEN
++static void lru_gen_enter_fault(struct vm_area_struct *vma)
++{
++ /* the LRU algorithm doesn't apply to sequential or random reads */
++ current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ));
++}
++
++static void lru_gen_exit_fault(void)
++{
++ current->in_lru_fault = false;
++}
++#else
++static void lru_gen_enter_fault(struct vm_area_struct *vma)
++{
++}
++
++static void lru_gen_exit_fault(void)
++{
++}
++#endif /* CONFIG_LRU_GEN */
++
+ /*
+ * By the time we get here, we already hold the mm semaphore
+ *
+@@ -4809,11 +4830,15 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
+ if (flags & FAULT_FLAG_USER)
+ mem_cgroup_enter_user_fault();
+
++ lru_gen_enter_fault(vma);
++
+ if (unlikely(is_vm_hugetlb_page(vma)))
+ ret = hugetlb_fault(vma->vm_mm, vma, address, flags);
+ else
+ ret = __handle_mm_fault(vma, address, flags);
+
++ lru_gen_exit_fault();
++
+ if (flags & FAULT_FLAG_USER) {
+ mem_cgroup_exit_user_fault();
+ /*
+diff --git a/mm/mm_init.c b/mm/mm_init.c
+index 9ddaf0e1b0ab..0d7b2bd2454a 100644
+--- a/mm/mm_init.c
++++ b/mm/mm_init.c
+@@ -65,14 +65,16 @@ void __init mminit_verify_pageflags_layout(void)
+
+ shift = 8 * sizeof(unsigned long);
+ width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
+- - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH;
++ - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH;
+ mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
+- "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Flags %d\n",
++ "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n",
+ SECTIONS_WIDTH,
+ NODES_WIDTH,
+ ZONES_WIDTH,
+ LAST_CPUPID_WIDTH,
+ KASAN_TAG_WIDTH,
++ LRU_GEN_WIDTH,
++ LRU_REFS_WIDTH,
+ NR_PAGEFLAGS);
+ mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
+ "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n",
+diff --git a/mm/mmzone.c b/mm/mmzone.c
+index eb89d6e018e2..2ec0d7793424 100644
+--- a/mm/mmzone.c
++++ b/mm/mmzone.c
+@@ -81,6 +81,8 @@ void lruvec_init(struct lruvec *lruvec)
+
+ for_each_lru(lru)
+ INIT_LIST_HEAD(&lruvec->lists[lru]);
++
++ lru_gen_init_lruvec(lruvec);
+ }
+
+ #if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
+diff --git a/mm/swap.c b/mm/swap.c
+index af3cad4e5378..0bdc96661fb6 100644
+--- a/mm/swap.c
++++ b/mm/swap.c
+@@ -446,6 +446,11 @@ void lru_cache_add(struct page *page)
+ VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
+ VM_BUG_ON_PAGE(PageLRU(page), page);
+
++ /* see the comment in lru_gen_add_page() */
++ if (lru_gen_enabled() && !PageUnevictable(page) &&
++ lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
++ SetPageActive(page);
++
+ get_page(page);
+ local_lock(&lru_pvecs.lock);
+ pvec = this_cpu_ptr(&lru_pvecs.lru_add);
+@@ -547,7 +552,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
+
+ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
+ {
+- if (PageActive(page) && !PageUnevictable(page)) {
++ if (!PageUnevictable(page) && (PageActive(page) || lru_gen_enabled())) {
+ int nr_pages = thp_nr_pages(page);
+
+ del_page_from_lru_list(page, lruvec);
+@@ -661,7 +666,8 @@ void deactivate_file_page(struct page *page)
+ */
+ void deactivate_page(struct page *page)
+ {
+- if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
++ if (PageLRU(page) && !PageUnevictable(page) &&
++ (PageActive(page) || lru_gen_enabled())) {
+ struct pagevec *pvec;
+
+ local_lock(&lru_pvecs.lock);
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index dc5f0381513f..41826fe17eb3 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -2821,6 +2821,81 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
+ return can_demote(pgdat->node_id, sc);
+ }
+
++#ifdef CONFIG_LRU_GEN
++
++/******************************************************************************
++ * shorthand helpers
++ ******************************************************************************/
++
++#define for_each_gen_type_zone(gen, type, zone) \
++ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \
++ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
++ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
++
++static struct lruvec __maybe_unused *get_lruvec(struct mem_cgroup *memcg, int nid)
++{
++ struct pglist_data *pgdat = NODE_DATA(nid);
++
++#ifdef CONFIG_MEMCG
++ if (memcg) {
++ struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec;
++
++ /* for hotadd_new_pgdat() */
++ if (!lruvec->pgdat)
++ lruvec->pgdat = pgdat;
++
++ return lruvec;
++ }
++#endif
++ VM_WARN_ON_ONCE(!mem_cgroup_disabled());
++
++ return pgdat ? &pgdat->__lruvec : NULL;
++}
++
++/******************************************************************************
++ * initialization
++ ******************************************************************************/
++
++void lru_gen_init_lruvec(struct lruvec *lruvec)
++{
++ int gen, type, zone;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ lrugen->max_seq = MIN_NR_GENS + 1;
++
++ for_each_gen_type_zone(gen, type, zone)
++ INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
++}
++
++#ifdef CONFIG_MEMCG
++void lru_gen_init_memcg(struct mem_cgroup *memcg)
++{
++}
++
++void lru_gen_exit_memcg(struct mem_cgroup *memcg)
++{
++ int nid;
++
++ for_each_node(nid) {
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0,
++ sizeof(lruvec->lrugen.nr_pages)));
++ }
++}
++#endif
++
++static int __init init_lru_gen(void)
++{
++ BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
++ BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
++
++ return 0;
++};
++late_initcall(init_lru_gen);
++
++#endif /* CONFIG_LRU_GEN */
++
+ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ unsigned long nr[NR_LRU_LISTS];
+--
+2.40.0
+
+++ /dev/null
-From 534bcc4a0bb5b24600891ce793f0295a142e9dae Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Mon, 5 Apr 2021 04:17:41 -0600
-Subject: [PATCH 05/10] mm: multigenerational lru: mm_struct list
-
-To scan PTEs for accessed pages, a mm_struct list is maintained for
-each memcg. When multiple threads traverse the same memcg->mm_list,
-each of them gets a unique mm_struct and therefore they can run
-walk_page_range() concurrently to reach page tables of all processes
-of this memcg.
-
-This infrastructure also provides the following optimizations:
- 1) it allows walkers to skip processes that have been sleeping since
- the last walk by tracking the usage of mm_struct between context
- switches.
- 2) it allows walkers to add interesting items they find during a
- walk to a Bloom filter so that they can skip uninteresting items
- during the next walk by testing whether an item is in this Bloom
- filter.
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I25d9eda8c6bdc7c3653b9f210a159d6c247c81e8
----
- fs/exec.c | 2 +
- include/linux/memcontrol.h | 4 +
- include/linux/mm_inline.h | 6 +
- include/linux/mm_types.h | 75 +++++++++
- include/linux/mmzone.h | 63 +++++++
- kernel/exit.c | 1 +
- kernel/fork.c | 9 +
- kernel/sched/core.c | 1 +
- mm/memcontrol.c | 25 +++
- mm/vmscan.c | 331 +++++++++++++++++++++++++++++++++++++
- 10 files changed, 517 insertions(+)
-
---- a/fs/exec.c
-+++ b/fs/exec.c
-@@ -1013,6 +1013,7 @@ static int exec_mmap(struct mm_struct *m
- active_mm = tsk->active_mm;
- tsk->active_mm = mm;
- tsk->mm = mm;
-+ lru_gen_add_mm(mm);
- /*
- * This prevents preemption while active_mm is being loaded and
- * it and mm are being updated, which could cause problems for
-@@ -1023,6 +1024,7 @@ static int exec_mmap(struct mm_struct *m
- if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
- local_irq_enable();
- activate_mm(active_mm, mm);
-+ lru_gen_activate_mm(mm);
- if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
- local_irq_enable();
- tsk->mm->vmacache_seqnum = 0;
---- a/include/linux/memcontrol.h
-+++ b/include/linux/memcontrol.h
-@@ -348,6 +348,10 @@ struct mem_cgroup {
- struct deferred_split deferred_split_queue;
- #endif
-
-+#ifdef CONFIG_LRU_GEN
-+ struct lru_gen_mm_list mm_list;
-+#endif
-+
- struct mem_cgroup_per_node *nodeinfo[];
- };
-
---- a/include/linux/mm_inline.h
-+++ b/include/linux/mm_inline.h
-@@ -100,6 +100,12 @@ static inline int lru_gen_from_seq(unsig
- return seq % MAX_NR_GENS;
- }
-
-+/* Return a proper index regardless whether we keep stats for historical generations. */
-+static inline int lru_hist_from_seq(unsigned long seq)
-+{
-+ return seq % NR_HIST_GENS;
-+}
-+
- /* The youngest and the second youngest generations are counted as active. */
- static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
- {
---- a/include/linux/mm_types.h
-+++ b/include/linux/mm_types.h
-@@ -3,6 +3,7 @@
- #define _LINUX_MM_TYPES_H
-
- #include <linux/mm_types_task.h>
-+#include <linux/sched.h>
-
- #include <linux/auxvec.h>
- #include <linux/list.h>
-@@ -15,6 +16,8 @@
- #include <linux/page-flags-layout.h>
- #include <linux/workqueue.h>
- #include <linux/seqlock.h>
-+#include <linux/nodemask.h>
-+#include <linux/mmdebug.h>
-
- #include <asm/mmu.h>
-
-@@ -580,6 +583,18 @@ struct mm_struct {
- #ifdef CONFIG_IOMMU_SUPPORT
- u32 pasid;
- #endif
-+#ifdef CONFIG_LRU_GEN
-+ struct {
-+ /* the node of a global or per-memcg mm_struct list */
-+ struct list_head list;
-+#ifdef CONFIG_MEMCG
-+ /* points to the memcg of the owner task above */
-+ struct mem_cgroup *memcg;
-+#endif
-+ /* whether this mm_struct has been used since the last walk */
-+ nodemask_t nodes;
-+ } lrugen;
-+#endif /* CONFIG_LRU_GEN */
- } __randomize_layout;
-
- /*
-@@ -606,6 +621,66 @@ static inline cpumask_t *mm_cpumask(stru
- return (struct cpumask *)&mm->cpu_bitmap;
- }
-
-+#ifdef CONFIG_LRU_GEN
-+
-+struct lru_gen_mm_list {
-+ /* a global or per-memcg mm_struct list */
-+ struct list_head fifo;
-+ /* protects the list above */
-+ spinlock_t lock;
-+};
-+
-+void lru_gen_add_mm(struct mm_struct *mm);
-+void lru_gen_del_mm(struct mm_struct *mm);
-+#ifdef CONFIG_MEMCG
-+void lru_gen_migrate_mm(struct mm_struct *mm);
-+#endif
-+
-+static inline void lru_gen_init_mm(struct mm_struct *mm)
-+{
-+ INIT_LIST_HEAD(&mm->lrugen.list);
-+#ifdef CONFIG_MEMCG
-+ mm->lrugen.memcg = NULL;
-+#endif
-+ nodes_clear(mm->lrugen.nodes);
-+}
-+
-+/* Track the usage of each mm_struct so that we can skip inactive ones. */
-+static inline void lru_gen_activate_mm(struct mm_struct *mm)
-+{
-+ /* unlikely but not a bug when racing with lru_gen_migrate_mm() */
-+ VM_WARN_ON(list_empty(&mm->lrugen.list));
-+
-+ if (!(current->flags & PF_KTHREAD) && !nodes_full(mm->lrugen.nodes))
-+ nodes_setall(mm->lrugen.nodes);
-+}
-+
-+#else /* !CONFIG_LRU_GEN */
-+
-+static inline void lru_gen_add_mm(struct mm_struct *mm)
-+{
-+}
-+
-+static inline void lru_gen_del_mm(struct mm_struct *mm)
-+{
-+}
-+
-+#ifdef CONFIG_MEMCG
-+static inline void lru_gen_migrate_mm(struct mm_struct *mm)
-+{
-+}
-+#endif
-+
-+static inline void lru_gen_init_mm(struct mm_struct *mm)
-+{
-+}
-+
-+static inline void lru_gen_activate_mm(struct mm_struct *mm)
-+{
-+}
-+
-+#endif /* CONFIG_LRU_GEN */
-+
- struct mmu_gather;
- extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
- extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
---- a/include/linux/mmzone.h
-+++ b/include/linux/mmzone.h
-@@ -318,6 +318,13 @@ struct lruvec;
- #define MIN_NR_GENS 2
- #define MAX_NR_GENS ((unsigned int)CONFIG_NR_LRU_GENS)
-
-+/* Whether to keep stats for historical generations. */
-+#ifdef CONFIG_LRU_GEN_STATS
-+#define NR_HIST_GENS ((unsigned int)CONFIG_NR_LRU_GENS)
-+#else
-+#define NR_HIST_GENS 1U
-+#endif
-+
- struct lrugen {
- /* the aging increments the max generation number */
- unsigned long max_seq;
-@@ -333,13 +340,63 @@ struct lrugen {
- bool enabled[ANON_AND_FILE];
- };
-
-+enum {
-+ MM_LEAF_TOTAL, /* total leaf entries */
-+ MM_LEAF_OLD, /* old leaf entries */
-+ MM_LEAF_YOUNG, /* young leaf entries */
-+ MM_NONLEAF_TOTAL, /* total non-leaf entries */
-+ MM_NONLEAF_PREV, /* previously worthy non-leaf entries */
-+ MM_NONLEAF_CUR, /* currently worthy non-leaf entries */
-+ NR_MM_STATS
-+};
-+
-+/* mnemonic codes for the stats above */
-+#define MM_STAT_CODES "toydpc"
-+
-+/* double buffering bloom filters */
-+#define NR_BLOOM_FILTERS 2
-+
-+struct lru_gen_mm_walk {
-+ /* set to max_seq after each round of walk */
-+ unsigned long seq;
-+ /* the next mm_struct on the list to walk */
-+ struct list_head *head;
-+ /* the first mm_struct never walked before */
-+ struct list_head *tail;
-+ /* to wait for the last walker to finish */
-+ struct wait_queue_head wait;
-+ /* bloom filters flip after each round of walk */
-+ unsigned long *filters[NR_BLOOM_FILTERS];
-+ /* page table stats for debugging */
-+ unsigned long stats[NR_HIST_GENS][NR_MM_STATS];
-+ /* the number of concurrent walkers */
-+ int nr_walkers;
-+};
-+
-+#define MIN_BATCH_SIZE 64
- #define MAX_BATCH_SIZE 8192
-
-+struct mm_walk_args {
-+ struct mem_cgroup *memcg;
-+ unsigned long max_seq;
-+ unsigned long start_pfn;
-+ unsigned long end_pfn;
-+ unsigned long next_addr;
-+ unsigned long bitmap[BITS_TO_LONGS(MIN_BATCH_SIZE)];
-+ int node_id;
-+ int swappiness;
-+ int batch_size;
-+ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
-+ int mm_stats[NR_MM_STATS];
-+ bool use_filter;
-+};
-+
- void lru_gen_init_state(struct mem_cgroup *memcg, struct lruvec *lruvec);
- void lru_gen_change_state(bool enable, bool main, bool swap);
-
- #ifdef CONFIG_MEMCG
- void lru_gen_init_memcg(struct mem_cgroup *memcg);
-+void lru_gen_free_memcg(struct mem_cgroup *memcg);
- #endif
-
- #else /* !CONFIG_LRU_GEN */
-@@ -356,6 +413,10 @@ static inline void lru_gen_change_state(
- static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
- {
- }
-+
-+static inline void lru_gen_free_memcg(struct mem_cgroup *memcg)
-+{
-+}
- #endif
-
- #endif /* CONFIG_LRU_GEN */
-@@ -380,6 +441,8 @@ struct lruvec {
- #ifdef CONFIG_LRU_GEN
- /* unevictable pages are on LRU_UNEVICTABLE */
- struct lrugen evictable;
-+ /* state for mm list and page table walks */
-+ struct lru_gen_mm_walk mm_walk;
- #endif
- #ifdef CONFIG_MEMCG
- struct pglist_data *pgdat;
---- a/kernel/exit.c
-+++ b/kernel/exit.c
-@@ -469,6 +469,7 @@ assign_new_owner:
- goto retry;
- }
- WRITE_ONCE(mm->owner, c);
-+ lru_gen_migrate_mm(mm);
- task_unlock(c);
- put_task_struct(c);
- }
---- a/kernel/fork.c
-+++ b/kernel/fork.c
-@@ -1083,6 +1083,7 @@ static struct mm_struct *mm_init(struct
- goto fail_nocontext;
-
- mm->user_ns = get_user_ns(user_ns);
-+ lru_gen_init_mm(mm);
- return mm;
-
- fail_nocontext:
-@@ -1125,6 +1126,7 @@ static inline void __mmput(struct mm_str
- }
- if (mm->binfmt)
- module_put(mm->binfmt->module);
-+ lru_gen_del_mm(mm);
- mmdrop(mm);
- }
-
-@@ -2622,6 +2624,13 @@ pid_t kernel_clone(struct kernel_clone_a
- get_task_struct(p);
- }
-
-+ if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
-+ /* lock the task to synchronize with memcg migration */
-+ task_lock(p);
-+ lru_gen_add_mm(p->mm);
-+ task_unlock(p);
-+ }
-+
- wake_up_new_task(p);
-
- /* forking complete and child started to run, tell ptracer */
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -5007,6 +5007,7 @@ context_switch(struct rq *rq, struct tas
- * finish_task_switch()'s mmdrop().
- */
- switch_mm_irqs_off(prev->active_mm, next->mm, next);
-+ lru_gen_activate_mm(next->mm);
-
- if (!prev->mm) { // from kernel
- /* will mmdrop() in finish_task_switch(). */
---- a/mm/memcontrol.c
-+++ b/mm/memcontrol.c
-@@ -5178,6 +5178,7 @@ static void __mem_cgroup_free(struct mem
-
- static void mem_cgroup_free(struct mem_cgroup *memcg)
- {
-+ lru_gen_free_memcg(memcg);
- memcg_wb_domain_exit(memcg);
- __mem_cgroup_free(memcg);
- }
-@@ -6210,6 +6211,29 @@ static void mem_cgroup_move_task(void)
- }
- #endif
-
-+#ifdef CONFIG_LRU_GEN
-+static void mem_cgroup_attach(struct cgroup_taskset *tset)
-+{
-+ struct cgroup_subsys_state *css;
-+ struct task_struct *task = NULL;
-+
-+ cgroup_taskset_for_each_leader(task, css, tset)
-+ break;
-+
-+ if (!task)
-+ return;
-+
-+ task_lock(task);
-+ if (task->mm && task->mm->owner == task)
-+ lru_gen_migrate_mm(task->mm);
-+ task_unlock(task);
-+}
-+#else
-+static void mem_cgroup_attach(struct cgroup_taskset *tset)
-+{
-+}
-+#endif /* CONFIG_LRU_GEN */
-+
- static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
- {
- if (value == PAGE_COUNTER_MAX)
-@@ -6553,6 +6577,7 @@ struct cgroup_subsys memory_cgrp_subsys
- .css_reset = mem_cgroup_css_reset,
- .css_rstat_flush = mem_cgroup_css_rstat_flush,
- .can_attach = mem_cgroup_can_attach,
-+ .attach = mem_cgroup_attach,
- .cancel_attach = mem_cgroup_cancel_attach,
- .post_attach = mem_cgroup_move_task,
- .dfl_cftypes = memory_files,
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -2864,6 +2864,306 @@ static bool __maybe_unused seq_is_valid(
- }
-
- /******************************************************************************
-+ * mm_struct list
-+ ******************************************************************************/
-+
-+static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
-+{
-+ static struct lru_gen_mm_list mm_list = {
-+ .fifo = LIST_HEAD_INIT(mm_list.fifo),
-+ .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock),
-+ };
-+
-+#ifdef CONFIG_MEMCG
-+ if (memcg)
-+ return &memcg->mm_list;
-+#endif
-+ return &mm_list;
-+}
-+
-+void lru_gen_add_mm(struct mm_struct *mm)
-+{
-+ int nid;
-+ struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
-+ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-+
-+ VM_BUG_ON_MM(!list_empty(&mm->lrugen.list), mm);
-+#ifdef CONFIG_MEMCG
-+ VM_BUG_ON_MM(mm->lrugen.memcg, mm);
-+ mm->lrugen.memcg = memcg;
-+#endif
-+ spin_lock(&mm_list->lock);
-+
-+ list_add_tail(&mm->lrugen.list, &mm_list->fifo);
-+
-+ for_each_node(nid) {
-+ struct lruvec *lruvec = get_lruvec(nid, memcg);
-+
-+ if (!lruvec)
-+ continue;
-+
-+ if (lruvec->mm_walk.tail == &mm_list->fifo)
-+ lruvec->mm_walk.tail = lruvec->mm_walk.tail->prev;
-+ }
-+
-+ spin_unlock(&mm_list->lock);
-+}
-+
-+void lru_gen_del_mm(struct mm_struct *mm)
-+{
-+ int nid;
-+ struct lru_gen_mm_list *mm_list;
-+ struct mem_cgroup *memcg = NULL;
-+
-+ if (list_empty(&mm->lrugen.list))
-+ return;
-+
-+#ifdef CONFIG_MEMCG
-+ memcg = mm->lrugen.memcg;
-+#endif
-+ mm_list = get_mm_list(memcg);
-+
-+ spin_lock(&mm_list->lock);
-+
-+ for_each_node(nid) {
-+ struct lruvec *lruvec = get_lruvec(nid, memcg);
-+
-+ if (!lruvec)
-+ continue;
-+
-+ if (lruvec->mm_walk.tail == &mm->lrugen.list)
-+ lruvec->mm_walk.tail = lruvec->mm_walk.tail->next;
-+
-+ if (lruvec->mm_walk.head != &mm->lrugen.list)
-+ continue;
-+
-+ lruvec->mm_walk.head = lruvec->mm_walk.head->next;
-+ if (lruvec->mm_walk.head == &mm_list->fifo)
-+ WRITE_ONCE(lruvec->mm_walk.seq, lruvec->mm_walk.seq + 1);
-+ }
-+
-+ list_del_init(&mm->lrugen.list);
-+
-+ spin_unlock(&mm_list->lock);
-+
-+#ifdef CONFIG_MEMCG
-+ mem_cgroup_put(mm->lrugen.memcg);
-+ mm->lrugen.memcg = NULL;
-+#endif
-+}
-+
-+#ifdef CONFIG_MEMCG
-+void lru_gen_migrate_mm(struct mm_struct *mm)
-+{
-+ struct mem_cgroup *memcg;
-+
-+ lockdep_assert_held(&mm->owner->alloc_lock);
-+
-+ if (mem_cgroup_disabled())
-+ return;
-+
-+ rcu_read_lock();
-+ memcg = mem_cgroup_from_task(mm->owner);
-+ rcu_read_unlock();
-+ if (memcg == mm->lrugen.memcg)
-+ return;
-+
-+ VM_BUG_ON_MM(!mm->lrugen.memcg, mm);
-+ VM_BUG_ON_MM(list_empty(&mm->lrugen.list), mm);
-+
-+ lru_gen_del_mm(mm);
-+ lru_gen_add_mm(mm);
-+}
-+#endif
-+
-+#define BLOOM_FILTER_SHIFT 15
-+
-+static inline int filter_gen_from_seq(unsigned long seq)
-+{
-+ return seq % NR_BLOOM_FILTERS;
-+}
-+
-+static void get_item_key(void *item, int *key)
-+{
-+ u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2);
-+
-+ BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32));
-+
-+ key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1);
-+ key[1] = hash >> BLOOM_FILTER_SHIFT;
-+}
-+
-+static void clear_bloom_filter(struct lruvec *lruvec, unsigned long seq)
-+{
-+ unsigned long *filter;
-+ int gen = filter_gen_from_seq(seq);
-+
-+ lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
-+
-+ filter = lruvec->mm_walk.filters[gen];
-+ if (filter) {
-+ bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
-+ return;
-+ }
-+
-+ filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), GFP_ATOMIC);
-+ WRITE_ONCE(lruvec->mm_walk.filters[gen], filter);
-+}
-+
-+static void set_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
-+{
-+ int key[2];
-+ unsigned long *filter;
-+ int gen = filter_gen_from_seq(seq);
-+
-+ filter = READ_ONCE(lruvec->mm_walk.filters[gen]);
-+ if (!filter)
-+ return;
-+
-+ get_item_key(item, key);
-+
-+ if (!test_bit(key[0], filter))
-+ set_bit(key[0], filter);
-+ if (!test_bit(key[1], filter))
-+ set_bit(key[1], filter);
-+}
-+
-+static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
-+{
-+ int key[2];
-+ unsigned long *filter;
-+ int gen = filter_gen_from_seq(seq);
-+
-+ filter = READ_ONCE(lruvec->mm_walk.filters[gen]);
-+ if (!filter)
-+ return false;
-+
-+ get_item_key(item, key);
-+
-+ return test_bit(key[0], filter) && test_bit(key[1], filter);
-+}
-+
-+static void reset_mm_stats(struct lruvec *lruvec, bool last, struct mm_walk_args *args)
-+{
-+ int i;
-+ int hist = lru_hist_from_seq(args->max_seq);
-+
-+ lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
-+
-+ for (i = 0; i < NR_MM_STATS; i++) {
-+ WRITE_ONCE(lruvec->mm_walk.stats[hist][i],
-+ lruvec->mm_walk.stats[hist][i] + args->mm_stats[i]);
-+ args->mm_stats[i] = 0;
-+ }
-+
-+ if (!last || NR_HIST_GENS == 1)
-+ return;
-+
-+ hist = lru_hist_from_seq(args->max_seq + 1);
-+ for (i = 0; i < NR_MM_STATS; i++)
-+ WRITE_ONCE(lruvec->mm_walk.stats[hist][i], 0);
-+}
-+
-+static bool should_skip_mm(struct mm_struct *mm, struct mm_walk_args *args)
-+{
-+ int type;
-+ unsigned long size = 0;
-+
-+ if (cpumask_empty(mm_cpumask(mm)) && !node_isset(args->node_id, mm->lrugen.nodes))
-+ return true;
-+
-+ if (mm_is_oom_victim(mm))
-+ return true;
-+
-+ for (type = !args->swappiness; type < ANON_AND_FILE; type++) {
-+ size += type ? get_mm_counter(mm, MM_FILEPAGES) :
-+ get_mm_counter(mm, MM_ANONPAGES) +
-+ get_mm_counter(mm, MM_SHMEMPAGES);
-+ }
-+
-+ if (size < MIN_BATCH_SIZE)
-+ return true;
-+
-+ if (!mmget_not_zero(mm))
-+ return true;
-+
-+ node_clear(args->node_id, mm->lrugen.nodes);
-+
-+ return false;
-+}
-+
-+/* To support multiple walkers that concurrently walk an mm_struct list. */
-+static bool get_next_mm(struct lruvec *lruvec, struct mm_walk_args *args,
-+ struct mm_struct **iter)
-+{
-+ bool first = false;
-+ bool last = true;
-+ struct mm_struct *mm = NULL;
-+ struct lru_gen_mm_walk *mm_walk = &lruvec->mm_walk;
-+ struct lru_gen_mm_list *mm_list = get_mm_list(args->memcg);
-+
-+ if (*iter)
-+ mmput_async(*iter);
-+ else if (args->max_seq <= READ_ONCE(mm_walk->seq))
-+ return false;
-+
-+ spin_lock(&mm_list->lock);
-+
-+ VM_BUG_ON(args->max_seq > mm_walk->seq + 1);
-+ VM_BUG_ON(*iter && args->max_seq < mm_walk->seq);
-+ VM_BUG_ON(*iter && !mm_walk->nr_walkers);
-+
-+ if (args->max_seq <= mm_walk->seq) {
-+ if (!*iter)
-+ last = false;
-+ goto done;
-+ }
-+
-+ if (mm_walk->head == &mm_list->fifo) {
-+ VM_BUG_ON(mm_walk->nr_walkers);
-+ mm_walk->head = mm_walk->head->next;
-+ first = true;
-+ }
-+
-+ while (!mm && mm_walk->head != &mm_list->fifo) {
-+ mm = list_entry(mm_walk->head, struct mm_struct, lrugen.list);
-+
-+ mm_walk->head = mm_walk->head->next;
-+
-+ if (mm_walk->tail == &mm->lrugen.list) {
-+ mm_walk->tail = mm_walk->tail->next;
-+ args->use_filter = false;
-+ }
-+
-+ if (should_skip_mm(mm, args))
-+ mm = NULL;
-+ }
-+
-+ if (mm_walk->head == &mm_list->fifo)
-+ WRITE_ONCE(mm_walk->seq, mm_walk->seq + 1);
-+done:
-+ if (*iter && !mm)
-+ mm_walk->nr_walkers--;
-+ if (!*iter && mm)
-+ mm_walk->nr_walkers++;
-+
-+ if (mm_walk->nr_walkers)
-+ last = false;
-+
-+ if (mm && first)
-+ clear_bloom_filter(lruvec, args->max_seq + 1);
-+
-+ if (*iter || last)
-+ reset_mm_stats(lruvec, last, args);
-+
-+ spin_unlock(&mm_list->lock);
-+
-+ *iter = mm;
-+
-+ return last;
-+}
-+
-+/******************************************************************************
- * state change
- ******************************************************************************/
-
-@@ -3047,6 +3347,7 @@ void lru_gen_init_state(struct mem_cgrou
- int i;
- int gen, type, zone;
- struct lrugen *lrugen = &lruvec->evictable;
-+ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-
- lrugen->max_seq = MIN_NR_GENS + 1;
- lrugen->enabled[0] = lru_gen_enabled() && lru_gen_nr_swapfiles;
-@@ -3057,6 +3358,17 @@ void lru_gen_init_state(struct mem_cgrou
-
- for_each_gen_type_zone(gen, type, zone)
- INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
-+
-+ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && !memcg)
-+ spin_lock(&mm_list->lock);
-+
-+ lruvec->mm_walk.seq = MIN_NR_GENS;
-+ lruvec->mm_walk.head = &mm_list->fifo;
-+ lruvec->mm_walk.tail = &mm_list->fifo;
-+ init_waitqueue_head(&lruvec->mm_walk.wait);
-+
-+ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && !memcg)
-+ spin_unlock(&mm_list->lock);
- }
-
- #ifdef CONFIG_MEMCG
-@@ -3064,18 +3376,37 @@ void lru_gen_init_memcg(struct mem_cgrou
- {
- int nid;
-
-+ INIT_LIST_HEAD(&memcg->mm_list.fifo);
-+ spin_lock_init(&memcg->mm_list.lock);
-+
- for_each_node(nid) {
- struct lruvec *lruvec = get_lruvec(nid, memcg);
-
- lru_gen_init_state(memcg, lruvec);
- }
- }
-+
-+void lru_gen_free_memcg(struct mem_cgroup *memcg)
-+{
-+ int nid;
-+
-+ for_each_node(nid) {
-+ int i;
-+ struct lruvec *lruvec = get_lruvec(nid, memcg);
-+
-+ for (i = 0; i < NR_BLOOM_FILTERS; i++) {
-+ bitmap_free(lruvec->mm_walk.filters[i]);
-+ lruvec->mm_walk.filters[i] = NULL;
-+ }
-+ }
-+}
- #endif
-
- static int __init init_lru_gen(void)
- {
- BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
- BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
-+ BUILD_BUG_ON(sizeof(MM_STAT_CODES) != NR_MM_STATS + 1);
-
- return 0;
- };
--- /dev/null
+From b564b9471cd60ef1ee3961a224898ce4a9620d84 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:03 -0600
+Subject: [PATCH 06/29] mm: multi-gen LRU: minimal implementation
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+To avoid confusion, the terms "promotion" and "demotion" will be applied
+to the multi-gen LRU, as a new convention; the terms "activation" and
+"deactivation" will be applied to the active/inactive LRU, as usual.
+
+The aging produces young generations. Given an lruvec, it increments
+max_seq when max_seq-min_seq+1 approaches MIN_NR_GENS. The aging promotes
+hot pages to the youngest generation when it finds them accessed through
+page tables; the demotion of cold pages happens consequently when it
+increments max_seq. Promotion in the aging path does not involve any LRU
+list operations, only the updates of the gen counter and
+lrugen->nr_pages[]; demotion, unless as the result of the increment of
+max_seq, requires LRU list operations, e.g., lru_deactivate_fn(). The
+aging has the complexity O(nr_hot_pages), since it is only interested in
+hot pages.
+
+The eviction consumes old generations. Given an lruvec, it increments
+min_seq when lrugen->lists[] indexed by min_seq%MAX_NR_GENS becomes empty.
+A feedback loop modeled after the PID controller monitors refaults over
+anon and file types and decides which type to evict when both types are
+available from the same generation.
+
+The protection of pages accessed multiple times through file descriptors
+takes place in the eviction path. Each generation is divided into
+multiple tiers. A page accessed N times through file descriptors is in
+tier order_base_2(N). Tiers do not have dedicated lrugen->lists[], only
+bits in page->flags. The aforementioned feedback loop also monitors
+refaults over all tiers and decides when to protect pages in which tiers
+(N>1), using the first tier (N=0,1) as a baseline. The first tier
+contains single-use unmapped clean pages, which are most likely the best
+choices. In contrast to promotion in the aging path, the protection of a
+page in the eviction path is achieved by moving this page to the next
+generation, i.e., min_seq+1, if the feedback loop decides so. This
+approach has the following advantages:
+
+1. It removes the cost of activation in the buffered access path by
+ inferring whether pages accessed multiple times through file
+ descriptors are statistically hot and thus worth protecting in the
+ eviction path.
+2. It takes pages accessed through page tables into account and avoids
+ overprotecting pages accessed multiple times through file
+ descriptors. (Pages accessed through page tables are in the first
+ tier, since N=0.)
+3. More tiers provide better protection for pages accessed more than
+ twice through file descriptors, when under heavy buffered I/O
+ workloads.
+
+Server benchmark results:
+ Single workload:
+ fio (buffered I/O): +[30, 32]%
+ IOPS BW
+ 5.19-rc1: 2673k 10.2GiB/s
+ patch1-6: 3491k 13.3GiB/s
+
+ Single workload:
+ memcached (anon): -[4, 6]%
+ Ops/sec KB/sec
+ 5.19-rc1: 1161501.04 45177.25
+ patch1-6: 1106168.46 43025.04
+
+ Configurations:
+ CPU: two Xeon 6154
+ Mem: total 256G
+
+ Node 1 was only used as a ram disk to reduce the variance in the
+ results.
+
+ patch drivers/block/brd.c <<EOF
+ 99,100c99,100
+ < gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM;
+ < page = alloc_page(gfp_flags);
+ ---
+ > gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM | __GFP_THISNODE;
+ > page = alloc_pages_node(1, gfp_flags, 0);
+ EOF
+
+ cat >>/etc/systemd/system.conf <<EOF
+ CPUAffinity=numa
+ NUMAPolicy=bind
+ NUMAMask=0
+ EOF
+
+ cat >>/etc/memcached.conf <<EOF
+ -m 184320
+ -s /var/run/memcached/memcached.sock
+ -a 0766
+ -t 36
+ -B binary
+ EOF
+
+ cat fio.sh
+ modprobe brd rd_nr=1 rd_size=113246208
+ swapoff -a
+ mkfs.ext4 /dev/ram0
+ mount -t ext4 /dev/ram0 /mnt
+
+ mkdir /sys/fs/cgroup/user.slice/test
+ echo 38654705664 >/sys/fs/cgroup/user.slice/test/memory.max
+ echo $$ >/sys/fs/cgroup/user.slice/test/cgroup.procs
+ fio -name=mglru --numjobs=72 --directory=/mnt --size=1408m \
+ --buffered=1 --ioengine=io_uring --iodepth=128 \
+ --iodepth_batch_submit=32 --iodepth_batch_complete=32 \
+ --rw=randread --random_distribution=random --norandommap \
+ --time_based --ramp_time=10m --runtime=5m --group_reporting
+
+ cat memcached.sh
+ modprobe brd rd_nr=1 rd_size=113246208
+ swapoff -a
+ mkswap /dev/ram0
+ swapon /dev/ram0
+
+ memtier_benchmark -S /var/run/memcached/memcached.sock \
+ -P memcache_binary -n allkeys --key-minimum=1 \
+ --key-maximum=65000000 --key-pattern=P:P -c 1 -t 36 \
+ --ratio 1:0 --pipeline 8 -d 2000
+
+ memtier_benchmark -S /var/run/memcached/memcached.sock \
+ -P memcache_binary -n allkeys --key-minimum=1 \
+ --key-maximum=65000000 --key-pattern=R:R -c 1 -t 36 \
+ --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed
+
+Client benchmark results:
+ kswapd profiles:
+ 5.19-rc1
+ 40.33% page_vma_mapped_walk (overhead)
+ 21.80% lzo1x_1_do_compress (real work)
+ 7.53% do_raw_spin_lock
+ 3.95% _raw_spin_unlock_irq
+ 2.52% vma_interval_tree_iter_next
+ 2.37% page_referenced_one
+ 2.28% vma_interval_tree_subtree_search
+ 1.97% anon_vma_interval_tree_iter_first
+ 1.60% ptep_clear_flush
+ 1.06% __zram_bvec_write
+
+ patch1-6
+ 39.03% lzo1x_1_do_compress (real work)
+ 18.47% page_vma_mapped_walk (overhead)
+ 6.74% _raw_spin_unlock_irq
+ 3.97% do_raw_spin_lock
+ 2.49% ptep_clear_flush
+ 2.48% anon_vma_interval_tree_iter_first
+ 1.92% page_referenced_one
+ 1.88% __zram_bvec_write
+ 1.48% memmove
+ 1.31% vma_interval_tree_iter_next
+
+ Configurations:
+ CPU: single Snapdragon 7c
+ Mem: total 4G
+
+ ChromeOS MemoryPressure [1]
+
+[1] https://chromium.googlesource.com/chromiumos/platform/tast-tests/
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-7-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mm_inline.h | 36 ++
+ include/linux/mmzone.h | 41 ++
+ include/linux/page-flags-layout.h | 5 +-
+ kernel/bounds.c | 2 +
+ mm/Kconfig | 11 +
+ mm/swap.c | 39 ++
+ mm/vmscan.c | 792 +++++++++++++++++++++++++++++-
+ mm/workingset.c | 110 ++++-
+ 8 files changed, 1025 insertions(+), 11 deletions(-)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 65320d2b8f60..58aabb1ba020 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -106,6 +106,33 @@ static inline int lru_gen_from_seq(unsigned long seq)
+ return seq % MAX_NR_GENS;
+ }
+
++static inline int lru_hist_from_seq(unsigned long seq)
++{
++ return seq % NR_HIST_GENS;
++}
++
++static inline int lru_tier_from_refs(int refs)
++{
++ VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));
++
++ /* see the comment in page_lru_refs() */
++ return order_base_2(refs + 1);
++}
++
++static inline int page_lru_refs(struct page *page)
++{
++ unsigned long flags = READ_ONCE(page->flags);
++ bool workingset = flags & BIT(PG_workingset);
++
++ /*
++ * Return the number of accesses beyond PG_referenced, i.e., N-1 if the
++ * total number of accesses is N>1, since N=0,1 both map to the first
++ * tier. lru_tier_from_refs() will account for this off-by-one. Also see
++ * the comment on MAX_NR_TIERS.
++ */
++ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
++}
++
+ static inline int page_lru_gen(struct page *page)
+ {
+ unsigned long flags = READ_ONCE(page->flags);
+@@ -158,6 +185,15 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct page *page,
+ __update_lru_size(lruvec, lru, zone, -delta);
+ return;
+ }
++
++ /* promotion */
++ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) {
++ __update_lru_size(lruvec, lru, zone, -delta);
++ __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
++ }
++
++ /* demotion requires isolation, e.g., lru_deactivate_fn() */
++ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
+ }
+
+ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 0c39f72184d0..fce8945c507c 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -327,6 +327,28 @@ enum lruvec_flags {
+ #define MIN_NR_GENS 2U
+ #define MAX_NR_GENS 4U
+
++/*
++ * Each generation is divided into multiple tiers. A page accessed N times
++ * through file descriptors is in tier order_base_2(N). A page in the first tier
++ * (N=0,1) is marked by PG_referenced unless it was faulted in through page
++ * tables or read ahead. A page in any other tier (N>1) is marked by
++ * PG_referenced and PG_workingset. This implies a minimum of two tiers is
++ * supported without using additional bits in page->flags.
++ *
++ * In contrast to moving across generations which requires the LRU lock, moving
++ * across tiers only involves atomic operations on page->flags and therefore
++ * has a negligible cost in the buffered access path. In the eviction path,
++ * comparisons of refaulted/(evicted+protected) from the first tier and the
++ * rest infer whether pages accessed multiple times through file descriptors
++ * are statistically hot and thus worth protecting.
++ *
++ * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
++ * number of categories of the active/inactive LRU when keeping track of
++ * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
++ * page->flags.
++ */
++#define MAX_NR_TIERS 4U
++
+ #ifndef __GENERATING_BOUNDS_H
+
+ struct lruvec;
+@@ -341,6 +363,16 @@ enum {
+ LRU_GEN_FILE,
+ };
+
++#define MIN_LRU_BATCH BITS_PER_LONG
++#define MAX_LRU_BATCH (MIN_LRU_BATCH * 64)
++
++/* whether to keep historical stats from evicted generations */
++#ifdef CONFIG_LRU_GEN_STATS
++#define NR_HIST_GENS MAX_NR_GENS
++#else
++#define NR_HIST_GENS 1U
++#endif
++
+ /*
+ * The youngest generation number is stored in max_seq for both anon and file
+ * types as they are aged on an equal footing. The oldest generation numbers are
+@@ -363,6 +395,15 @@ struct lru_gen_struct {
+ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+ /* the multi-gen LRU sizes, eventually consistent */
+ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
++ /* the exponential moving average of refaulted */
++ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
++ /* the exponential moving average of evicted+protected */
++ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
++ /* the first tier doesn't need protection, hence the minus one */
++ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
++ /* can be modified without holding the LRU lock */
++ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
++ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+ };
+
+ void lru_gen_init_lruvec(struct lruvec *lruvec);
+diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
+index 240905407a18..7d79818dc065 100644
+--- a/include/linux/page-flags-layout.h
++++ b/include/linux/page-flags-layout.h
+@@ -106,7 +106,10 @@
+ #error "Not enough bits in page flags"
+ #endif
+
+-#define LRU_REFS_WIDTH 0
++/* see the comment on MAX_NR_TIERS */
++#define LRU_REFS_WIDTH min(__LRU_REFS_WIDTH, BITS_PER_LONG - NR_PAGEFLAGS - \
++ ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \
++ NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH)
+
+ #endif
+ #endif /* _LINUX_PAGE_FLAGS_LAYOUT */
+diff --git a/kernel/bounds.c b/kernel/bounds.c
+index 5ee60777d8e4..b529182e8b04 100644
+--- a/kernel/bounds.c
++++ b/kernel/bounds.c
+@@ -24,8 +24,10 @@ int main(void)
+ DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
+ #ifdef CONFIG_LRU_GEN
+ DEFINE(LRU_GEN_WIDTH, order_base_2(MAX_NR_GENS + 1));
++ DEFINE(__LRU_REFS_WIDTH, MAX_NR_TIERS - 2);
+ #else
+ DEFINE(LRU_GEN_WIDTH, 0);
++ DEFINE(__LRU_REFS_WIDTH, 0);
+ #endif
+ /* End of constants */
+
+diff --git a/mm/Kconfig b/mm/Kconfig
+index 0eeb27397884..62433f3cd7ae 100644
+--- a/mm/Kconfig
++++ b/mm/Kconfig
+@@ -897,6 +897,7 @@ config IO_MAPPING
+ config SECRETMEM
+ def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
+
++# multi-gen LRU {
+ config LRU_GEN
+ bool "Multi-Gen LRU"
+ depends on MMU
+@@ -905,6 +906,16 @@ config LRU_GEN
+ help
+ A high performance LRU implementation to overcommit memory.
+
++config LRU_GEN_STATS
++ bool "Full stats for debugging"
++ depends on LRU_GEN
++ help
++ Do not enable this option unless you plan to look at historical stats
++ from evicted generations for debugging purpose.
++
++ This option has a per-memcg and per-node memory overhead.
++# }
++
+ source "mm/damon/Kconfig"
+
+ endmenu
+diff --git a/mm/swap.c b/mm/swap.c
+index 0bdc96661fb6..5d227577b609 100644
+--- a/mm/swap.c
++++ b/mm/swap.c
+@@ -389,6 +389,40 @@ static void __lru_cache_activate_page(struct page *page)
+ local_unlock(&lru_pvecs.lock);
+ }
+
++#ifdef CONFIG_LRU_GEN
++static void page_inc_refs(struct page *page)
++{
++ unsigned long new_flags, old_flags = READ_ONCE(page->flags);
++
++ if (PageUnevictable(page))
++ return;
++
++ if (!PageReferenced(page)) {
++ SetPageReferenced(page);
++ return;
++ }
++
++ if (!PageWorkingset(page)) {
++ SetPageWorkingset(page);
++ return;
++ }
++
++ /* see the comment on MAX_NR_TIERS */
++ do {
++ new_flags = old_flags & LRU_REFS_MASK;
++ if (new_flags == LRU_REFS_MASK)
++ break;
++
++ new_flags += BIT(LRU_REFS_PGOFF);
++ new_flags |= old_flags & ~LRU_REFS_MASK;
++ } while (!try_cmpxchg(&page->flags, &old_flags, new_flags));
++}
++#else
++static void page_inc_refs(struct page *page)
++{
++}
++#endif /* CONFIG_LRU_GEN */
++
+ /*
+ * Mark a page as having seen activity.
+ *
+@@ -403,6 +437,11 @@ void mark_page_accessed(struct page *page)
+ {
+ page = compound_head(page);
+
++ if (lru_gen_enabled()) {
++ page_inc_refs(page);
++ return;
++ }
++
+ if (!PageReferenced(page)) {
+ SetPageReferenced(page);
+ } else if (PageUnevictable(page)) {
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 41826fe17eb3..932abd24c1b3 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -1142,9 +1142,11 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
+
+ if (PageSwapCache(page)) {
+ swp_entry_t swap = { .val = page_private(page) };
+- mem_cgroup_swapout(page, swap);
++
++ /* get a shadow entry before mem_cgroup_swapout() clears page_memcg() */
+ if (reclaimed && !mapping_exiting(mapping))
+ shadow = workingset_eviction(page, target_memcg);
++ mem_cgroup_swapout(page, swap);
+ __delete_from_swap_cache(page, swap, shadow);
+ xa_unlock_irq(&mapping->i_pages);
+ put_swap_page(page, swap);
+@@ -2502,6 +2504,9 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
+ unsigned long file;
+ struct lruvec *target_lruvec;
+
++ if (lru_gen_enabled())
++ return;
++
+ target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
+
+ /*
+@@ -2827,6 +2832,17 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
+ * shorthand helpers
+ ******************************************************************************/
+
++#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset))
++
++#define DEFINE_MAX_SEQ(lruvec) \
++ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq)
++
++#define DEFINE_MIN_SEQ(lruvec) \
++ unsigned long min_seq[ANON_AND_FILE] = { \
++ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \
++ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \
++ }
++
+ #define for_each_gen_type_zone(gen, type, zone) \
+ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \
+ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
+@@ -2852,6 +2868,745 @@ static struct lruvec __maybe_unused *get_lruvec(struct mem_cgroup *memcg, int ni
+ return pgdat ? &pgdat->__lruvec : NULL;
+ }
+
++static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
++{
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
++
++ if (!can_demote(pgdat->node_id, sc) &&
++ mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
++ return 0;
++
++ return mem_cgroup_swappiness(memcg);
++}
++
++static int get_nr_gens(struct lruvec *lruvec, int type)
++{
++ return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1;
++}
++
++static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
++{
++ /* see the comment on lru_gen_struct */
++ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
++ get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
++ get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
++}
++
++/******************************************************************************
++ * refault feedback loop
++ ******************************************************************************/
++
++/*
++ * A feedback loop based on Proportional-Integral-Derivative (PID) controller.
++ *
++ * The P term is refaulted/(evicted+protected) from a tier in the generation
++ * currently being evicted; the I term is the exponential moving average of the
++ * P term over the generations previously evicted, using the smoothing factor
++ * 1/2; the D term isn't supported.
++ *
++ * The setpoint (SP) is always the first tier of one type; the process variable
++ * (PV) is either any tier of the other type or any other tier of the same
++ * type.
++ *
++ * The error is the difference between the SP and the PV; the correction is to
++ * turn off protection when SP>PV or turn on protection when SP<PV.
++ *
++ * For future optimizations:
++ * 1. The D term may discount the other two terms over time so that long-lived
++ * generations can resist stale information.
++ */
++struct ctrl_pos {
++ unsigned long refaulted;
++ unsigned long total;
++ int gain;
++};
++
++static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
++ struct ctrl_pos *pos)
++{
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
++
++ pos->refaulted = lrugen->avg_refaulted[type][tier] +
++ atomic_long_read(&lrugen->refaulted[hist][type][tier]);
++ pos->total = lrugen->avg_total[type][tier] +
++ atomic_long_read(&lrugen->evicted[hist][type][tier]);
++ if (tier)
++ pos->total += lrugen->protected[hist][type][tier - 1];
++ pos->gain = gain;
++}
++
++static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
++{
++ int hist, tier;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1;
++ unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1;
++
++ lockdep_assert_held(&lruvec->lru_lock);
++
++ if (!carryover && !clear)
++ return;
++
++ hist = lru_hist_from_seq(seq);
++
++ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
++ if (carryover) {
++ unsigned long sum;
++
++ sum = lrugen->avg_refaulted[type][tier] +
++ atomic_long_read(&lrugen->refaulted[hist][type][tier]);
++ WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);
++
++ sum = lrugen->avg_total[type][tier] +
++ atomic_long_read(&lrugen->evicted[hist][type][tier]);
++ if (tier)
++ sum += lrugen->protected[hist][type][tier - 1];
++ WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
++ }
++
++ if (clear) {
++ atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
++ atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
++ if (tier)
++ WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
++ }
++ }
++}
++
++static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
++{
++ /*
++ * Return true if the PV has a limited number of refaults or a lower
++ * refaulted/total than the SP.
++ */
++ return pv->refaulted < MIN_LRU_BATCH ||
++ pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <=
++ (sp->refaulted + 1) * pv->total * pv->gain;
++}
++
++/******************************************************************************
++ * the aging
++ ******************************************************************************/
++
++/* protect pages accessed multiple times through file descriptors */
++static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaiming)
++{
++ int type = page_is_file_lru(page);
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
++ unsigned long new_flags, old_flags = READ_ONCE(page->flags);
++
++ VM_WARN_ON_ONCE_PAGE(!(old_flags & LRU_GEN_MASK), page);
++
++ do {
++ new_gen = (old_gen + 1) % MAX_NR_GENS;
++
++ new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
++ new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
++ /* for end_page_writeback() */
++ if (reclaiming)
++ new_flags |= BIT(PG_reclaim);
++ } while (!try_cmpxchg(&page->flags, &old_flags, new_flags));
++
++ lru_gen_update_size(lruvec, page, old_gen, new_gen);
++
++ return new_gen;
++}
++
++static void inc_min_seq(struct lruvec *lruvec, int type)
++{
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ reset_ctrl_pos(lruvec, type, true);
++ WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
++}
++
++static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
++{
++ int gen, type, zone;
++ bool success = false;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ DEFINE_MIN_SEQ(lruvec);
++
++ VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
++
++ /* find the oldest populated generation */
++ for (type = !can_swap; type < ANON_AND_FILE; type++) {
++ while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) {
++ gen = lru_gen_from_seq(min_seq[type]);
++
++ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
++ if (!list_empty(&lrugen->lists[gen][type][zone]))
++ goto next;
++ }
++
++ min_seq[type]++;
++ }
++next:
++ ;
++ }
++
++ /* see the comment on lru_gen_struct */
++ if (can_swap) {
++ min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
++ min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
++ }
++
++ for (type = !can_swap; type < ANON_AND_FILE; type++) {
++ if (min_seq[type] == lrugen->min_seq[type])
++ continue;
++
++ reset_ctrl_pos(lruvec, type, true);
++ WRITE_ONCE(lrugen->min_seq[type], min_seq[type]);
++ success = true;
++ }
++
++ return success;
++}
++
++static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_swap)
++{
++ int prev, next;
++ int type, zone;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ spin_lock_irq(&lruvec->lru_lock);
++
++ VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
++
++ if (max_seq != lrugen->max_seq)
++ goto unlock;
++
++ for (type = ANON_AND_FILE - 1; type >= 0; type--) {
++ if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
++ continue;
++
++ VM_WARN_ON_ONCE(type == LRU_GEN_FILE || can_swap);
++
++ inc_min_seq(lruvec, type);
++ }
++
++ /*
++ * Update the active/inactive LRU sizes for compatibility. Both sides of
++ * the current max_seq need to be covered, since max_seq+1 can overlap
++ * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do
++ * overlap, cold/hot inversion happens.
++ */
++ prev = lru_gen_from_seq(lrugen->max_seq - 1);
++ next = lru_gen_from_seq(lrugen->max_seq + 1);
++
++ for (type = 0; type < ANON_AND_FILE; type++) {
++ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
++ enum lru_list lru = type * LRU_INACTIVE_FILE;
++ long delta = lrugen->nr_pages[prev][type][zone] -
++ lrugen->nr_pages[next][type][zone];
++
++ if (!delta)
++ continue;
++
++ __update_lru_size(lruvec, lru, zone, delta);
++ __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta);
++ }
++ }
++
++ for (type = 0; type < ANON_AND_FILE; type++)
++ reset_ctrl_pos(lruvec, type, false);
++
++ /* make sure preceding modifications appear */
++ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
++unlock:
++ spin_unlock_irq(&lruvec->lru_lock);
++}
++
++static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq,
++ struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
++{
++ int gen, type, zone;
++ unsigned long old = 0;
++ unsigned long young = 0;
++ unsigned long total = 0;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++
++ for (type = !can_swap; type < ANON_AND_FILE; type++) {
++ unsigned long seq;
++
++ for (seq = min_seq[type]; seq <= max_seq; seq++) {
++ unsigned long size = 0;
++
++ gen = lru_gen_from_seq(seq);
++
++ for (zone = 0; zone < MAX_NR_ZONES; zone++)
++ size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
++
++ total += size;
++ if (seq == max_seq)
++ young += size;
++ else if (seq + MIN_NR_GENS == max_seq)
++ old += size;
++ }
++ }
++
++ /* try to scrape all its memory if this memcg was deleted */
++ *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
++
++ /*
++ * The aging tries to be lazy to reduce the overhead, while the eviction
++ * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
++ * ideal number of generations is MIN_NR_GENS+1.
++ */
++ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq)
++ return true;
++ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
++ return false;
++
++ /*
++ * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
++ * of the total number of pages for each generation. A reasonable range
++ * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
++ * aging cares about the upper bound of hot pages, while the eviction
++ * cares about the lower bound of cold pages.
++ */
++ if (young * MIN_NR_GENS > total)
++ return true;
++ if (old * (MIN_NR_GENS + 2) < total)
++ return true;
++
++ return false;
++}
++
++static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++{
++ bool need_aging;
++ unsigned long nr_to_scan;
++ int swappiness = get_swappiness(lruvec, sc);
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MAX_SEQ(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
++
++ mem_cgroup_calculate_protection(NULL, memcg);
++
++ if (mem_cgroup_below_min(memcg))
++ return;
++
++ need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
++ if (need_aging)
++ inc_max_seq(lruvec, max_seq, swappiness);
++}
++
++static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ struct mem_cgroup *memcg;
++
++ VM_WARN_ON_ONCE(!current_is_kswapd());
++
++ memcg = mem_cgroup_iter(NULL, NULL, NULL);
++ do {
++ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
++
++ age_lruvec(lruvec, sc);
++
++ cond_resched();
++ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
++}
++
++/******************************************************************************
++ * the eviction
++ ******************************************************************************/
++
++static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
++{
++ bool success;
++ int gen = page_lru_gen(page);
++ int type = page_is_file_lru(page);
++ int zone = page_zonenum(page);
++ int delta = thp_nr_pages(page);
++ int refs = page_lru_refs(page);
++ int tier = lru_tier_from_refs(refs);
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ VM_WARN_ON_ONCE_PAGE(gen >= MAX_NR_GENS, page);
++
++ /* unevictable */
++ if (!page_evictable(page)) {
++ success = lru_gen_del_page(lruvec, page, true);
++ VM_WARN_ON_ONCE_PAGE(!success, page);
++ SetPageUnevictable(page);
++ add_page_to_lru_list(page, lruvec);
++ __count_vm_events(UNEVICTABLE_PGCULLED, delta);
++ return true;
++ }
++
++ /* dirty lazyfree */
++ if (type == LRU_GEN_FILE && PageAnon(page) && PageDirty(page)) {
++ success = lru_gen_del_page(lruvec, page, true);
++ VM_WARN_ON_ONCE_PAGE(!success, page);
++ SetPageSwapBacked(page);
++ add_page_to_lru_list_tail(page, lruvec);
++ return true;
++ }
++
++ /* protected */
++ if (tier > tier_idx) {
++ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
++
++ gen = page_inc_gen(lruvec, page, false);
++ list_move_tail(&page->lru, &lrugen->lists[gen][type][zone]);
++
++ WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
++ lrugen->protected[hist][type][tier - 1] + delta);
++ __mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
++ return true;
++ }
++
++ /* waiting for writeback */
++ if (PageLocked(page) || PageWriteback(page) ||
++ (type == LRU_GEN_FILE && PageDirty(page))) {
++ gen = page_inc_gen(lruvec, page, true);
++ list_move(&page->lru, &lrugen->lists[gen][type][zone]);
++ return true;
++ }
++
++ return false;
++}
++
++static bool isolate_page(struct lruvec *lruvec, struct page *page, struct scan_control *sc)
++{
++ bool success;
++
++ /* unmapping inhibited */
++ if (!sc->may_unmap && page_mapped(page))
++ return false;
++
++ /* swapping inhibited */
++ if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
++ (PageDirty(page) ||
++ (PageAnon(page) && !PageSwapCache(page))))
++ return false;
++
++ /* raced with release_pages() */
++ if (!get_page_unless_zero(page))
++ return false;
++
++ /* raced with another isolation */
++ if (!TestClearPageLRU(page)) {
++ put_page(page);
++ return false;
++ }
++
++ /* see the comment on MAX_NR_TIERS */
++ if (!PageReferenced(page))
++ set_mask_bits(&page->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
++
++ /* for shrink_page_list() */
++ ClearPageReclaim(page);
++ ClearPageReferenced(page);
++
++ success = lru_gen_del_page(lruvec, page, true);
++ VM_WARN_ON_ONCE_PAGE(!success, page);
++
++ return true;
++}
++
++static int scan_pages(struct lruvec *lruvec, struct scan_control *sc,
++ int type, int tier, struct list_head *list)
++{
++ int gen, zone;
++ enum vm_event_item item;
++ int sorted = 0;
++ int scanned = 0;
++ int isolated = 0;
++ int remaining = MAX_LRU_BATCH;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++
++ VM_WARN_ON_ONCE(!list_empty(list));
++
++ if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
++ return 0;
++
++ gen = lru_gen_from_seq(lrugen->min_seq[type]);
++
++ for (zone = sc->reclaim_idx; zone >= 0; zone--) {
++ LIST_HEAD(moved);
++ int skipped = 0;
++ struct list_head *head = &lrugen->lists[gen][type][zone];
++
++ while (!list_empty(head)) {
++ struct page *page = lru_to_page(head);
++ int delta = thp_nr_pages(page);
++
++ VM_WARN_ON_ONCE_PAGE(PageUnevictable(page), page);
++ VM_WARN_ON_ONCE_PAGE(PageActive(page), page);
++ VM_WARN_ON_ONCE_PAGE(page_is_file_lru(page) != type, page);
++ VM_WARN_ON_ONCE_PAGE(page_zonenum(page) != zone, page);
++
++ scanned += delta;
++
++ if (sort_page(lruvec, page, tier))
++ sorted += delta;
++ else if (isolate_page(lruvec, page, sc)) {
++ list_add(&page->lru, list);
++ isolated += delta;
++ } else {
++ list_move(&page->lru, &moved);
++ skipped += delta;
++ }
++
++ if (!--remaining || max(isolated, skipped) >= MIN_LRU_BATCH)
++ break;
++ }
++
++ if (skipped) {
++ list_splice(&moved, head);
++ __count_zid_vm_events(PGSCAN_SKIP, zone, skipped);
++ }
++
++ if (!remaining || isolated >= MIN_LRU_BATCH)
++ break;
++ }
++
++ item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
++ if (!cgroup_reclaim(sc)) {
++ __count_vm_events(item, isolated);
++ __count_vm_events(PGREFILL, sorted);
++ }
++ __count_memcg_events(memcg, item, isolated);
++ __count_memcg_events(memcg, PGREFILL, sorted);
++ __count_vm_events(PGSCAN_ANON + type, isolated);
++
++ /*
++ * There might not be eligible pages due to reclaim_idx, may_unmap and
++ * may_writepage. Check the remaining to prevent livelock if it's not
++ * making progress.
++ */
++ return isolated || !remaining ? scanned : 0;
++}
++
++static int get_tier_idx(struct lruvec *lruvec, int type)
++{
++ int tier;
++ struct ctrl_pos sp, pv;
++
++ /*
++ * To leave a margin for fluctuations, use a larger gain factor (1:2).
++ * This value is chosen because any other tier would have at least twice
++ * as many refaults as the first tier.
++ */
++ read_ctrl_pos(lruvec, type, 0, 1, &sp);
++ for (tier = 1; tier < MAX_NR_TIERS; tier++) {
++ read_ctrl_pos(lruvec, type, tier, 2, &pv);
++ if (!positive_ctrl_err(&sp, &pv))
++ break;
++ }
++
++ return tier - 1;
++}
++
++static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
++{
++ int type, tier;
++ struct ctrl_pos sp, pv;
++ int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness };
++
++ /*
++ * Compare the first tier of anon with that of file to determine which
++ * type to scan. Also need to compare other tiers of the selected type
++ * with the first tier of the other type to determine the last tier (of
++ * the selected type) to evict.
++ */
++ read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp);
++ read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv);
++ type = positive_ctrl_err(&sp, &pv);
++
++ read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
++ for (tier = 1; tier < MAX_NR_TIERS; tier++) {
++ read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
++ if (!positive_ctrl_err(&sp, &pv))
++ break;
++ }
++
++ *tier_idx = tier - 1;
++
++ return type;
++}
++
++static int isolate_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
++ int *type_scanned, struct list_head *list)
++{
++ int i;
++ int type;
++ int scanned;
++ int tier = -1;
++ DEFINE_MIN_SEQ(lruvec);
++
++ /*
++ * Try to make the obvious choice first. When anon and file are both
++ * available from the same generation, interpret swappiness 1 as file
++ * first and 200 as anon first.
++ */
++ if (!swappiness)
++ type = LRU_GEN_FILE;
++ else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE])
++ type = LRU_GEN_ANON;
++ else if (swappiness == 1)
++ type = LRU_GEN_FILE;
++ else if (swappiness == 200)
++ type = LRU_GEN_ANON;
++ else
++ type = get_type_to_scan(lruvec, swappiness, &tier);
++
++ for (i = !swappiness; i < ANON_AND_FILE; i++) {
++ if (tier < 0)
++ tier = get_tier_idx(lruvec, type);
++
++ scanned = scan_pages(lruvec, sc, type, tier, list);
++ if (scanned)
++ break;
++
++ type = !type;
++ tier = -1;
++ }
++
++ *type_scanned = type;
++
++ return scanned;
++}
++
++static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
++{
++ int type;
++ int scanned;
++ int reclaimed;
++ LIST_HEAD(list);
++ struct page *page;
++ enum vm_event_item item;
++ struct reclaim_stat stat;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
++
++ spin_lock_irq(&lruvec->lru_lock);
++
++ scanned = isolate_pages(lruvec, sc, swappiness, &type, &list);
++
++ scanned += try_to_inc_min_seq(lruvec, swappiness);
++
++ if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
++ scanned = 0;
++
++ spin_unlock_irq(&lruvec->lru_lock);
++
++ if (list_empty(&list))
++ return scanned;
++
++ reclaimed = shrink_page_list(&list, pgdat, sc, &stat, false);
++
++ list_for_each_entry(page, &list, lru) {
++ /* restore LRU_REFS_FLAGS cleared by isolate_page() */
++ if (PageWorkingset(page))
++ SetPageReferenced(page);
++
++ /* don't add rejected pages to the oldest generation */
++ if (PageReclaim(page) &&
++ (PageDirty(page) || PageWriteback(page)))
++ ClearPageActive(page);
++ else
++ SetPageActive(page);
++ }
++
++ spin_lock_irq(&lruvec->lru_lock);
++
++ move_pages_to_lru(lruvec, &list);
++
++ item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
++ if (!cgroup_reclaim(sc))
++ __count_vm_events(item, reclaimed);
++ __count_memcg_events(memcg, item, reclaimed);
++ __count_vm_events(PGSTEAL_ANON + type, reclaimed);
++
++ spin_unlock_irq(&lruvec->lru_lock);
++
++ mem_cgroup_uncharge_list(&list);
++ free_unref_page_list(&list);
++
++ sc->nr_reclaimed += reclaimed;
++
++ return scanned;
++}
++
++static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
++ bool can_swap)
++{
++ bool need_aging;
++ unsigned long nr_to_scan;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MAX_SEQ(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ if (mem_cgroup_below_min(memcg) ||
++ (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
++ return 0;
++
++ need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
++ if (!need_aging)
++ return nr_to_scan;
++
++ /* skip the aging path at the default priority */
++ if (sc->priority == DEF_PRIORITY)
++ goto done;
++
++ /* leave the work to lru_gen_age_node() */
++ if (current_is_kswapd())
++ return 0;
++
++ inc_max_seq(lruvec, max_seq, can_swap);
++done:
++ return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
++}
++
++static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++{
++ struct blk_plug plug;
++ unsigned long scanned = 0;
++
++ lru_add_drain();
++
++ blk_start_plug(&plug);
++
++ while (true) {
++ int delta;
++ int swappiness;
++ unsigned long nr_to_scan;
++
++ if (sc->may_swap)
++ swappiness = get_swappiness(lruvec, sc);
++ else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc))
++ swappiness = 1;
++ else
++ swappiness = 0;
++
++ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
++ if (!nr_to_scan)
++ break;
++
++ delta = evict_pages(lruvec, sc, swappiness);
++ if (!delta)
++ break;
++
++ scanned += delta;
++ if (scanned >= nr_to_scan)
++ break;
++
++ cond_resched();
++ }
++
++ blk_finish_plug(&plug);
++}
++
+ /******************************************************************************
+ * initialization
+ ******************************************************************************/
+@@ -2894,6 +3649,16 @@ static int __init init_lru_gen(void)
+ };
+ late_initcall(init_lru_gen);
+
++#else /* !CONFIG_LRU_GEN */
++
++static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
++{
++}
++
++static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++{
++}
++
+ #endif /* CONFIG_LRU_GEN */
+
+ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+@@ -2907,6 +3672,11 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ bool proportional_reclaim;
+ struct blk_plug plug;
+
++ if (lru_gen_enabled()) {
++ lru_gen_shrink_lruvec(lruvec, sc);
++ return;
++ }
++
+ get_scan_count(lruvec, sc, nr);
+
+ /* Record the original scan target for proportional adjustments later */
+@@ -3372,6 +4142,9 @@ static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
+ struct lruvec *target_lruvec;
+ unsigned long refaults;
+
++ if (lru_gen_enabled())
++ return;
++
+ target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
+ target_lruvec->refaults[0] = refaults;
+@@ -3736,12 +4509,16 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+ }
+ #endif
+
+-static void age_active_anon(struct pglist_data *pgdat,
+- struct scan_control *sc)
++static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ {
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
++ if (lru_gen_enabled()) {
++ lru_gen_age_node(pgdat, sc);
++ return;
++ }
++
+ if (!can_age_anon_pages(pgdat, sc))
+ return;
+
+@@ -4058,12 +4835,11 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
+ sc.may_swap = !nr_boost_reclaim;
+
+ /*
+- * Do some background aging of the anon list, to give
+- * pages a chance to be referenced before reclaiming. All
+- * pages are rotated regardless of classzone as this is
+- * about consistent aging.
++ * Do some background aging, to give pages a chance to be
++ * referenced before reclaiming. All pages are rotated
++ * regardless of classzone as this is about consistent aging.
+ */
+- age_active_anon(pgdat, &sc);
++ kswapd_age_node(pgdat, &sc);
+
+ /*
+ * If we're getting trouble reclaiming, start doing writepage
+diff --git a/mm/workingset.c b/mm/workingset.c
+index 880d882f3325..aeba62cebf8c 100644
+--- a/mm/workingset.c
++++ b/mm/workingset.c
+@@ -187,7 +187,6 @@ static unsigned int bucket_order __read_mostly;
+ static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
+ bool workingset)
+ {
+- eviction >>= bucket_order;
+ eviction &= EVICTION_MASK;
+ eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
+ eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
+@@ -212,10 +211,107 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
+
+ *memcgidp = memcgid;
+ *pgdat = NODE_DATA(nid);
+- *evictionp = entry << bucket_order;
++ *evictionp = entry;
+ *workingsetp = workingset;
+ }
+
++#ifdef CONFIG_LRU_GEN
++
++static void *lru_gen_eviction(struct page *page)
++{
++ int hist;
++ unsigned long token;
++ unsigned long min_seq;
++ struct lruvec *lruvec;
++ struct lru_gen_struct *lrugen;
++ int type = page_is_file_lru(page);
++ int delta = thp_nr_pages(page);
++ int refs = page_lru_refs(page);
++ int tier = lru_tier_from_refs(refs);
++ struct mem_cgroup *memcg = page_memcg(page);
++ struct pglist_data *pgdat = page_pgdat(page);
++
++ BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);
++
++ lruvec = mem_cgroup_lruvec(memcg, pgdat);
++ lrugen = &lruvec->lrugen;
++ min_seq = READ_ONCE(lrugen->min_seq[type]);
++ token = (min_seq << LRU_REFS_WIDTH) | max(refs - 1, 0);
++
++ hist = lru_hist_from_seq(min_seq);
++ atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);
++
++ return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
++}
++
++static void lru_gen_refault(struct page *page, void *shadow)
++{
++ int hist, tier, refs;
++ int memcg_id;
++ bool workingset;
++ unsigned long token;
++ unsigned long min_seq;
++ struct lruvec *lruvec;
++ struct lru_gen_struct *lrugen;
++ struct mem_cgroup *memcg;
++ struct pglist_data *pgdat;
++ int type = page_is_file_lru(page);
++ int delta = thp_nr_pages(page);
++
++ unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);
++
++ if (pgdat != page_pgdat(page))
++ return;
++
++ rcu_read_lock();
++
++ memcg = page_memcg_rcu(page);
++ if (memcg_id != mem_cgroup_id(memcg))
++ goto unlock;
++
++ lruvec = mem_cgroup_lruvec(memcg, pgdat);
++ lrugen = &lruvec->lrugen;
++
++ min_seq = READ_ONCE(lrugen->min_seq[type]);
++ if ((token >> LRU_REFS_WIDTH) != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)))
++ goto unlock;
++
++ hist = lru_hist_from_seq(min_seq);
++ /* see the comment in page_lru_refs() */
++ refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset;
++ tier = lru_tier_from_refs(refs);
++
++ atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
++ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);
++
++ /*
++ * Count the following two cases as stalls:
++ * 1. For pages accessed through page tables, hotter pages pushed out
++ * hot pages which refaulted immediately.
++ * 2. For pages accessed multiple times through file descriptors,
++ * numbers of accesses might have been out of the range.
++ */
++ if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
++ SetPageWorkingset(page);
++ mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
++ }
++unlock:
++ rcu_read_unlock();
++}
++
++#else /* !CONFIG_LRU_GEN */
++
++static void *lru_gen_eviction(struct page *page)
++{
++ return NULL;
++}
++
++static void lru_gen_refault(struct page *page, void *shadow)
++{
++}
++
++#endif /* CONFIG_LRU_GEN */
++
+ /**
+ * workingset_age_nonresident - age non-resident entries as LRU ages
+ * @lruvec: the lruvec that was aged
+@@ -264,10 +360,14 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
+ VM_BUG_ON_PAGE(page_count(page), page);
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
+
++ if (lru_gen_enabled())
++ return lru_gen_eviction(page);
++
+ lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+ /* XXX: target_memcg can be NULL, go through lruvec */
+ memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
+ eviction = atomic_long_read(&lruvec->nonresident_age);
++ eviction >>= bucket_order;
+ workingset_age_nonresident(lruvec, thp_nr_pages(page));
+ return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
+ }
+@@ -296,7 +396,13 @@ void workingset_refault(struct page *page, void *shadow)
+ bool workingset;
+ int memcgid;
+
++ if (lru_gen_enabled()) {
++ lru_gen_refault(page, shadow);
++ return;
++ }
++
+ unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
++ eviction <<= bucket_order;
+
+ rcu_read_lock();
+ /*
+--
+2.40.0
+
+++ /dev/null
-From 8217cd2238c40cf77208aa27a7cc09879e685890 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Mon, 5 Apr 2021 04:35:07 -0600
-Subject: [PATCH 06/10] mm: multigenerational lru: aging
-
-The aging produces young generations. Given an lruvec, the aging
-traverses lruvec_memcg()->mm_list and calls walk_page_range() to scan
-PTEs for accessed pages. Upon finding one, the aging updates its
-generation number to max_seq (modulo MAX_NR_GENS). After each round of
-traversal, the aging increments max_seq. The aging is due when
-min_seq[] reaches max_seq-1.
-
-The aging uses the following optimizations when walking page tables:
- 1) It skips non-leaf PMD entries that have the accessed bit cleared
- when CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y.
- 2) It does not zigzag between a PGD table and the same PMD or PTE
- table spanning multiple VMAs. In other words, it finishes all the
- VMAs within the range of the same PMD or PTE table before it returns
- to this PGD table. This optimizes workloads that have large numbers
- of tiny VMAs, especially when CONFIG_PGTABLE_LEVELS=5.
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I3ae8abc3100d023cecb3a699d86020ae6fc10a45
----
- include/linux/memcontrol.h | 3 +
- include/linux/mmzone.h | 9 +
- include/linux/oom.h | 16 +
- include/linux/swap.h | 3 +
- mm/memcontrol.c | 5 +
- mm/oom_kill.c | 4 +-
- mm/rmap.c | 8 +
- mm/vmscan.c | 948 +++++++++++++++++++++++++++++++++++++
- 8 files changed, 994 insertions(+), 2 deletions(-)
-
---- a/include/linux/memcontrol.h
-+++ b/include/linux/memcontrol.h
-@@ -1367,10 +1367,13 @@ mem_cgroup_print_oom_meminfo(struct mem_
-
- static inline void lock_page_memcg(struct page *page)
- {
-+ /* to match page_memcg_rcu() */
-+ rcu_read_lock();
- }
-
- static inline void unlock_page_memcg(struct page *page)
- {
-+ rcu_read_unlock();
- }
-
- static inline void mem_cgroup_handle_over_high(void)
---- a/include/linux/mmzone.h
-+++ b/include/linux/mmzone.h
-@@ -295,6 +295,7 @@ enum lruvec_flags {
- };
-
- struct lruvec;
-+struct page_vma_mapped_walk;
-
- #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
- #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
-@@ -393,6 +394,7 @@ struct mm_walk_args {
-
- void lru_gen_init_state(struct mem_cgroup *memcg, struct lruvec *lruvec);
- void lru_gen_change_state(bool enable, bool main, bool swap);
-+void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
-
- #ifdef CONFIG_MEMCG
- void lru_gen_init_memcg(struct mem_cgroup *memcg);
-@@ -409,6 +411,10 @@ static inline void lru_gen_change_state(
- {
- }
-
-+static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
-+{
-+}
-+
- #ifdef CONFIG_MEMCG
- static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
- {
-@@ -1028,6 +1034,9 @@ typedef struct pglist_data {
-
- unsigned long flags;
-
-+#ifdef CONFIG_LRU_GEN
-+ struct mm_walk_args mm_walk_args;
-+#endif
- ZONE_PADDING(_pad2_)
-
- /* Per-node vmstats */
---- a/include/linux/oom.h
-+++ b/include/linux/oom.h
-@@ -57,6 +57,22 @@ struct oom_control {
- extern struct mutex oom_lock;
- extern struct mutex oom_adj_mutex;
-
-+#ifdef CONFIG_MMU
-+extern struct task_struct *oom_reaper_list;
-+extern struct wait_queue_head oom_reaper_wait;
-+
-+static inline bool oom_reaping_in_progress(void)
-+{
-+ /* racy check to see if oom reaping could be in progress */
-+ return READ_ONCE(oom_reaper_list) || !waitqueue_active(&oom_reaper_wait);
-+}
-+#else
-+static inline bool oom_reaping_in_progress(void)
-+{
-+ return false;
-+}
-+#endif
-+
- static inline void set_current_oom_origin(void)
- {
- current->signal->oom_flag_origin = true;
---- a/include/linux/swap.h
-+++ b/include/linux/swap.h
-@@ -137,6 +137,9 @@ union swap_header {
- */
- struct reclaim_state {
- unsigned long reclaimed_slab;
-+#ifdef CONFIG_LRU_GEN
-+ struct mm_walk_args *mm_walk_args;
-+#endif
- };
-
- #ifdef __KERNEL__
---- a/mm/memcontrol.c
-+++ b/mm/memcontrol.c
-@@ -1304,12 +1304,17 @@ void mem_cgroup_update_lru_size(struct l
- *lru_size += nr_pages;
-
- size = *lru_size;
-+#ifdef CONFIG_LRU_GEN
-+ /* unlikely but not a bug when reset_batch_size() is pending */
-+ VM_WARN_ON(size + MAX_BATCH_SIZE < 0);
-+#else
- if (WARN_ONCE(size < 0,
- "%s(%p, %d, %d): lru_size %ld\n",
- __func__, lruvec, lru, nr_pages, size)) {
- VM_BUG_ON(1);
- *lru_size = 0;
- }
-+#endif
-
- if (nr_pages > 0)
- *lru_size += nr_pages;
---- a/mm/oom_kill.c
-+++ b/mm/oom_kill.c
-@@ -508,8 +508,8 @@ bool process_shares_mm(struct task_struc
- * victim (if that is possible) to help the OOM killer to move on.
- */
- static struct task_struct *oom_reaper_th;
--static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
--static struct task_struct *oom_reaper_list;
-+DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait);
-+struct task_struct *oom_reaper_list;
- static DEFINE_SPINLOCK(oom_reaper_lock);
-
- bool __oom_reap_task_mm(struct mm_struct *mm)
---- a/mm/rmap.c
-+++ b/mm/rmap.c
-@@ -73,6 +73,7 @@
- #include <linux/page_idle.h>
- #include <linux/memremap.h>
- #include <linux/userfaultfd_k.h>
-+#include <linux/mm_inline.h>
-
- #include <asm/tlbflush.h>
-
-@@ -793,6 +794,13 @@ static bool page_referenced_one(struct p
- }
-
- if (pvmw.pte) {
-+ /* the multigenerational lru exploits the spatial locality */
-+ if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
-+ !(vma->vm_flags & VM_SEQ_READ)) {
-+ lru_gen_look_around(&pvmw);
-+ referenced++;
-+ }
-+
- if (ptep_clear_flush_young_notify(vma, address,
- pvmw.pte)) {
- /*
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -51,6 +51,8 @@
- #include <linux/dax.h>
- #include <linux/psi.h>
- #include <linux/memory.h>
-+#include <linux/pagewalk.h>
-+#include <linux/shmem_fs.h>
-
- #include <asm/tlbflush.h>
- #include <asm/div64.h>
-@@ -2822,6 +2824,15 @@ static bool can_age_anon_pages(struct pg
- * shorthand helpers
- ******************************************************************************/
-
-+#define DEFINE_MAX_SEQ(lruvec) \
-+ unsigned long max_seq = READ_ONCE((lruvec)->evictable.max_seq)
-+
-+#define DEFINE_MIN_SEQ(lruvec) \
-+ unsigned long min_seq[ANON_AND_FILE] = { \
-+ READ_ONCE((lruvec)->evictable.min_seq[0]), \
-+ READ_ONCE((lruvec)->evictable.min_seq[1]), \
-+ }
-+
- #define for_each_gen_type_zone(gen, type, zone) \
- for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \
- for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
-@@ -2834,6 +2845,12 @@ static int page_lru_gen(struct page *pag
- return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
- }
-
-+static int get_swappiness(struct mem_cgroup *memcg)
-+{
-+ return mem_cgroup_get_nr_swap_pages(memcg) >= MIN_BATCH_SIZE ?
-+ mem_cgroup_swappiness(memcg) : 0;
-+}
-+
- static struct lruvec *get_lruvec(int nid, struct mem_cgroup *memcg)
- {
- struct pglist_data *pgdat = NODE_DATA(nid);
-@@ -3164,6 +3181,926 @@ done:
- }
-
- /******************************************************************************
-+ * the aging
-+ ******************************************************************************/
-+
-+static int page_update_gen(struct page *page, int gen)
-+{
-+ unsigned long old_flags, new_flags;
-+
-+ VM_BUG_ON(gen >= MAX_NR_GENS);
-+
-+ do {
-+ new_flags = old_flags = READ_ONCE(page->flags);
-+
-+ if (!(new_flags & LRU_GEN_MASK)) {
-+ new_flags |= BIT(PG_referenced);
-+ continue;
-+ }
-+
-+ new_flags &= ~LRU_GEN_MASK;
-+ new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
-+ } while (new_flags != old_flags &&
-+ cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-+
-+ return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
-+}
-+
-+static void page_inc_gen(struct page *page, struct lruvec *lruvec, bool reclaiming)
-+{
-+ int old_gen, new_gen;
-+ unsigned long old_flags, new_flags;
-+ int type = page_is_file_lru(page);
-+ int zone = page_zonenum(page);
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
-+
-+ do {
-+ new_flags = old_flags = READ_ONCE(page->flags);
-+ VM_BUG_ON_PAGE(!(new_flags & LRU_GEN_MASK), page);
-+
-+ new_gen = ((new_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
-+ /* page_update_gen() has updated this page? */
-+ if (new_gen >= 0 && new_gen != old_gen) {
-+ list_move(&page->lru, &lrugen->lists[new_gen][type][zone]);
-+ return;
-+ }
-+
-+ new_gen = (old_gen + 1) % MAX_NR_GENS;
-+
-+ new_flags &= ~LRU_GEN_MASK;
-+ new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
-+ /* for end_page_writeback() */
-+ if (reclaiming)
-+ new_flags |= BIT(PG_reclaim);
-+ } while (cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-+
-+ lru_gen_update_size(page, lruvec, old_gen, new_gen);
-+ if (reclaiming)
-+ list_move(&page->lru, &lrugen->lists[new_gen][type][zone]);
-+ else
-+ list_move_tail(&page->lru, &lrugen->lists[new_gen][type][zone]);
-+}
-+
-+static void update_batch_size(struct page *page, int old_gen, int new_gen,
-+ struct mm_walk_args *args)
-+{
-+ int type = page_is_file_lru(page);
-+ int zone = page_zonenum(page);
-+ int delta = thp_nr_pages(page);
-+
-+ VM_BUG_ON(old_gen >= MAX_NR_GENS);
-+ VM_BUG_ON(new_gen >= MAX_NR_GENS);
-+
-+ args->batch_size++;
-+
-+ args->nr_pages[old_gen][type][zone] -= delta;
-+ args->nr_pages[new_gen][type][zone] += delta;
-+}
-+
-+static void reset_batch_size(struct lruvec *lruvec, struct mm_walk_args *args)
-+{
-+ int gen, type, zone;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ args->batch_size = 0;
-+
-+ for_each_gen_type_zone(gen, type, zone) {
-+ enum lru_list lru = type * LRU_FILE;
-+ int delta = args->nr_pages[gen][type][zone];
-+
-+ if (!delta)
-+ continue;
-+
-+ args->nr_pages[gen][type][zone] = 0;
-+ WRITE_ONCE(lrugen->sizes[gen][type][zone],
-+ lrugen->sizes[gen][type][zone] + delta);
-+
-+ if (lru_gen_is_active(lruvec, gen))
-+ lru += LRU_ACTIVE;
-+ update_lru_size(lruvec, lru, zone, delta);
-+ }
-+}
-+
-+static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *walk)
-+{
-+ struct address_space *mapping;
-+ struct vm_area_struct *vma = walk->vma;
-+ struct mm_walk_args *args = walk->private;
-+
-+ if (!vma_is_accessible(vma) || is_vm_hugetlb_page(vma) ||
-+ (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ)))
-+ return true;
-+
-+ if (vma_is_anonymous(vma))
-+ return !args->swappiness;
-+
-+ if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
-+ return true;
-+
-+ mapping = vma->vm_file->f_mapping;
-+ if (!mapping->a_ops->writepage)
-+ return true;
-+
-+ return (shmem_mapping(mapping) && !args->swappiness) || mapping_unevictable(mapping);
-+}
-+
-+/*
-+ * Some userspace memory allocators create many single-page VMAs. So instead of
-+ * returning back to the PGD table for each of such VMAs, we finish at least an
-+ * entire PMD table and therefore avoid many zigzags.
-+ */
-+static bool get_next_vma(struct mm_walk *walk, unsigned long mask, unsigned long size,
-+ unsigned long *start, unsigned long *end)
-+{
-+ unsigned long next = round_up(*end, size);
-+
-+ VM_BUG_ON(mask & size);
-+ VM_BUG_ON(*start >= *end);
-+ VM_BUG_ON((next & mask) != (*start & mask));
-+
-+ while (walk->vma) {
-+ if (next >= walk->vma->vm_end) {
-+ walk->vma = walk->vma->vm_next;
-+ continue;
-+ }
-+
-+ if ((next & mask) != (walk->vma->vm_start & mask))
-+ return false;
-+
-+ if (should_skip_vma(walk->vma->vm_start, walk->vma->vm_end, walk)) {
-+ walk->vma = walk->vma->vm_next;
-+ continue;
-+ }
-+
-+ *start = max(next, walk->vma->vm_start);
-+ next = (next | ~mask) + 1;
-+ /* rounded-up boundaries can wrap to 0 */
-+ *end = next && next < walk->vma->vm_end ? next : walk->vma->vm_end;
-+
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
-+ struct mm_walk *walk)
-+{
-+ int i;
-+ pte_t *pte;
-+ spinlock_t *ptl;
-+ unsigned long addr;
-+ int worth = 0;
-+ struct mm_walk_args *args = walk->private;
-+ int old_gen, new_gen = lru_gen_from_seq(args->max_seq);
-+
-+ VM_BUG_ON(pmd_leaf(*pmd));
-+
-+ pte = pte_offset_map_lock(walk->mm, pmd, start & PMD_MASK, &ptl);
-+ arch_enter_lazy_mmu_mode();
-+restart:
-+ for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) {
-+ struct page *page;
-+ unsigned long pfn = pte_pfn(pte[i]);
-+
-+ args->mm_stats[MM_LEAF_TOTAL]++;
-+
-+ if (!pte_present(pte[i]) || is_zero_pfn(pfn))
-+ continue;
-+
-+ if (WARN_ON_ONCE(pte_devmap(pte[i]) || pte_special(pte[i])))
-+ continue;
-+
-+ if (!pte_young(pte[i])) {
-+ args->mm_stats[MM_LEAF_OLD]++;
-+ continue;
-+ }
-+
-+ VM_BUG_ON(!pfn_valid(pfn));
-+ if (pfn < args->start_pfn || pfn >= args->end_pfn)
-+ continue;
-+
-+ page = compound_head(pfn_to_page(pfn));
-+ if (page_to_nid(page) != args->node_id)
-+ continue;
-+
-+ if (page_memcg_rcu(page) != args->memcg)
-+ continue;
-+
-+ VM_BUG_ON(addr < walk->vma->vm_start || addr >= walk->vma->vm_end);
-+ if (!ptep_test_and_clear_young(walk->vma, addr, pte + i))
-+ continue;
-+
-+ args->mm_stats[MM_LEAF_YOUNG]++;
-+
-+ if (pte_dirty(pte[i]) && !PageDirty(page) &&
-+ !(PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page)))
-+ set_page_dirty(page);
-+
-+ old_gen = page_update_gen(page, new_gen);
-+ if (old_gen >= 0 && old_gen != new_gen)
-+ update_batch_size(page, old_gen, new_gen, args);
-+
-+ worth++;
-+ }
-+
-+ if (i < PTRS_PER_PTE && get_next_vma(walk, PMD_MASK, PAGE_SIZE, &start, &end))
-+ goto restart;
-+
-+ arch_leave_lazy_mmu_mode();
-+ pte_unmap_unlock(pte, ptl);
-+
-+ return worth >= MIN_BATCH_SIZE / 2;
-+}
-+
-+/*
-+ * We scan PMD entries in two passes. The first pass reaches to PTE tables and
-+ * doesn't take the PMD lock. The second pass clears the accessed bit on PMD
-+ * entries and needs to take the PMD lock.
-+ */
-+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
-+static void walk_pmd_range_locked(pud_t *pud, unsigned long start, int offset,
-+ struct vm_area_struct *vma, struct mm_walk *walk)
-+{
-+ int i;
-+ pmd_t *pmd;
-+ spinlock_t *ptl;
-+ struct mm_walk_args *args = walk->private;
-+ int old_gen, new_gen = lru_gen_from_seq(args->max_seq);
-+
-+ VM_BUG_ON(pud_leaf(*pud));
-+
-+ start = (start & PUD_MASK) + offset * PMD_SIZE;
-+ pmd = pmd_offset(pud, start);
-+ ptl = pmd_lock(walk->mm, pmd);
-+ arch_enter_lazy_mmu_mode();
-+
-+ for_each_set_bit(i, args->bitmap, MIN_BATCH_SIZE) {
-+ struct page *page;
-+ unsigned long pfn = pmd_pfn(pmd[i]);
-+ unsigned long addr = start + i * PMD_SIZE;
-+
-+ if (!pmd_present(pmd[i]) || is_huge_zero_pmd(pmd[i]))
-+ continue;
-+
-+ if (WARN_ON_ONCE(pmd_devmap(pmd[i])))
-+ continue;
-+
-+ if (!pmd_trans_huge(pmd[i])) {
-+ if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG))
-+ pmdp_test_and_clear_young(vma, addr, pmd + i);
-+ continue;
-+ }
-+
-+ VM_BUG_ON(!pfn_valid(pfn));
-+ if (pfn < args->start_pfn || pfn >= args->end_pfn)
-+ continue;
-+
-+ page = pfn_to_page(pfn);
-+ VM_BUG_ON_PAGE(PageTail(page), page);
-+ if (page_to_nid(page) != args->node_id)
-+ continue;
-+
-+ if (page_memcg_rcu(page) != args->memcg)
-+ continue;
-+
-+ VM_BUG_ON(addr < vma->vm_start || addr >= vma->vm_end);
-+ if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
-+ continue;
-+
-+ args->mm_stats[MM_LEAF_YOUNG]++;
-+
-+ if (pmd_dirty(pmd[i]) && !PageDirty(page) &&
-+ !(PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page)))
-+ set_page_dirty(page);
-+
-+ old_gen = page_update_gen(page, new_gen);
-+ if (old_gen >= 0 && old_gen != new_gen)
-+ update_batch_size(page, old_gen, new_gen, args);
-+ }
-+
-+ arch_leave_lazy_mmu_mode();
-+ spin_unlock(ptl);
-+
-+ bitmap_zero(args->bitmap, MIN_BATCH_SIZE);
-+}
-+#else
-+static void walk_pmd_range_locked(pud_t *pud, unsigned long start, int offset,
-+ struct vm_area_struct *vma, struct mm_walk *walk)
-+{
-+}
-+#endif
-+
-+static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
-+ struct mm_walk *walk)
-+{
-+ int i;
-+ pmd_t *pmd;
-+ unsigned long next;
-+ unsigned long addr;
-+ struct vm_area_struct *vma;
-+ int offset = -1;
-+ bool reset = false;
-+ struct mm_walk_args *args = walk->private;
-+ struct lruvec *lruvec = get_lruvec(args->node_id, args->memcg);
-+
-+ VM_BUG_ON(pud_leaf(*pud));
-+
-+ pmd = pmd_offset(pud, start & PUD_MASK);
-+restart:
-+ vma = walk->vma;
-+ for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) {
-+ pmd_t val = pmd_read_atomic(pmd + i);
-+
-+ /* for pmd_read_atomic() */
-+ barrier();
-+
-+ next = pmd_addr_end(addr, end);
-+
-+ if (!pmd_present(val)) {
-+ args->mm_stats[MM_LEAF_TOTAL]++;
-+ continue;
-+ }
-+
-+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-+ if (pmd_trans_huge(val)) {
-+ unsigned long pfn = pmd_pfn(val);
-+
-+ args->mm_stats[MM_LEAF_TOTAL]++;
-+
-+ if (is_huge_zero_pmd(val))
-+ continue;
-+
-+ if (!pmd_young(val)) {
-+ args->mm_stats[MM_LEAF_OLD]++;
-+ continue;
-+ }
-+
-+ if (pfn < args->start_pfn || pfn >= args->end_pfn)
-+ continue;
-+
-+ if (offset < 0)
-+ offset = i;
-+ else if (i - offset >= MIN_BATCH_SIZE) {
-+ walk_pmd_range_locked(pud, start, offset, vma, walk);
-+ offset = i;
-+ }
-+ __set_bit(i - offset, args->bitmap);
-+ reset = true;
-+ continue;
-+ }
-+#endif
-+ args->mm_stats[MM_NONLEAF_TOTAL]++;
-+
-+#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
-+ if (!pmd_young(val))
-+ continue;
-+
-+ if (offset < 0)
-+ offset = i;
-+ else if (i - offset >= MIN_BATCH_SIZE) {
-+ walk_pmd_range_locked(pud, start, offset, vma, walk);
-+ offset = i;
-+ reset = false;
-+ }
-+ __set_bit(i - offset, args->bitmap);
-+#endif
-+ if (args->use_filter && !test_bloom_filter(lruvec, args->max_seq, pmd + i))
-+ continue;
-+
-+ args->mm_stats[MM_NONLEAF_PREV]++;
-+
-+ if (!walk_pte_range(&val, addr, next, walk))
-+ continue;
-+
-+ args->mm_stats[MM_NONLEAF_CUR]++;
-+
-+ set_bloom_filter(lruvec, args->max_seq + 1, pmd + i);
-+ }
-+
-+ if (reset) {
-+ walk_pmd_range_locked(pud, start, offset, vma, walk);
-+ offset = -1;
-+ reset = false;
-+ }
-+
-+ if (i < PTRS_PER_PMD && get_next_vma(walk, PUD_MASK, PMD_SIZE, &start, &end))
-+ goto restart;
-+
-+ if (offset >= 0)
-+ walk_pmd_range_locked(pud, start, offset, vma, walk);
-+}
-+
-+static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end,
-+ struct mm_walk *walk)
-+{
-+ int i;
-+ pud_t *pud;
-+ unsigned long addr;
-+ unsigned long next;
-+ struct mm_walk_args *args = walk->private;
-+
-+ VM_BUG_ON(p4d_leaf(*p4d));
-+
-+ pud = pud_offset(p4d, start & P4D_MASK);
-+restart:
-+ for (i = pud_index(start), addr = start; addr != end; i++, addr = next) {
-+ pud_t val = READ_ONCE(pud[i]);
-+
-+ next = pud_addr_end(addr, end);
-+
-+ if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val)))
-+ continue;
-+
-+ walk_pmd_range(&val, addr, next, walk);
-+
-+ if (args->batch_size >= MAX_BATCH_SIZE) {
-+ end = (addr | ~PUD_MASK) + 1;
-+ goto done;
-+ }
-+ }
-+
-+ if (i < PTRS_PER_PUD && get_next_vma(walk, P4D_MASK, PUD_SIZE, &start, &end))
-+ goto restart;
-+
-+ end = round_up(end, P4D_SIZE);
-+done:
-+ /* rounded-up boundaries can wrap to 0 */
-+ args->next_addr = end && walk->vma ? max(end, walk->vma->vm_start) : 0;
-+
-+ return -EAGAIN;
-+}
-+
-+static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct mm_walk_args *args)
-+{
-+ static const struct mm_walk_ops mm_walk_ops = {
-+ .test_walk = should_skip_vma,
-+ .p4d_entry = walk_pud_range,
-+ };
-+
-+ int err;
-+
-+ args->next_addr = FIRST_USER_ADDRESS;
-+
-+ do {
-+ unsigned long start = args->next_addr;
-+ unsigned long end = mm->highest_vm_end;
-+
-+ err = -EBUSY;
-+
-+ rcu_read_lock();
-+#ifdef CONFIG_MEMCG
-+ if (args->memcg && atomic_read(&args->memcg->moving_account))
-+ goto contended;
-+#endif
-+ if (!mmap_read_trylock(mm))
-+ goto contended;
-+
-+ err = walk_page_range(mm, start, end, &mm_walk_ops, args);
-+
-+ mmap_read_unlock(mm);
-+
-+ if (args->batch_size) {
-+ spin_lock_irq(&lruvec->lru_lock);
-+ reset_batch_size(lruvec, args);
-+ spin_unlock_irq(&lruvec->lru_lock);
-+ }
-+contended:
-+ rcu_read_unlock();
-+
-+ cond_resched();
-+ } while (err == -EAGAIN && args->next_addr && !mm_is_oom_victim(mm));
-+}
-+
-+static struct mm_walk_args *alloc_mm_walk_args(void)
-+{
-+ if (!current->reclaim_state || !current->reclaim_state->mm_walk_args)
-+ return kvzalloc(sizeof(struct mm_walk_args), GFP_KERNEL);
-+
-+ return current->reclaim_state->mm_walk_args;
-+}
-+
-+static void free_mm_walk_args(struct mm_walk_args *args)
-+{
-+ if (!current->reclaim_state || !current->reclaim_state->mm_walk_args)
-+ kvfree(args);
-+}
-+
-+static bool inc_min_seq(struct lruvec *lruvec, int type)
-+{
-+ int gen, zone;
-+ int remaining = MAX_BATCH_SIZE;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ VM_BUG_ON(!seq_is_valid(lruvec));
-+
-+ if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
-+ return true;
-+
-+ gen = lru_gen_from_seq(lrugen->min_seq[type]);
-+
-+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-+ struct list_head *head = &lrugen->lists[gen][type][zone];
-+
-+ while (!list_empty(head)) {
-+ struct page *page = lru_to_page(head);
-+
-+ VM_BUG_ON_PAGE(PageTail(page), page);
-+ VM_BUG_ON_PAGE(PageUnevictable(page), page);
-+ VM_BUG_ON_PAGE(PageActive(page), page);
-+ VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
-+ VM_BUG_ON_PAGE(page_zonenum(page) != zone, page);
-+
-+ prefetchw_prev_lru_page(page, head, flags);
-+
-+ page_inc_gen(page, lruvec, false);
-+
-+ if (!--remaining)
-+ return false;
-+ }
-+ }
-+
-+ WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
-+
-+ return true;
-+}
-+
-+static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness)
-+{
-+ int gen, type, zone;
-+ bool success = false;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ VM_BUG_ON(!seq_is_valid(lruvec));
-+
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ while (lrugen->max_seq - min_seq[type] >= MIN_NR_GENS) {
-+ gen = lru_gen_from_seq(min_seq[type]);
-+
-+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-+ if (!list_empty(&lrugen->lists[gen][type][zone]))
-+ goto next;
-+ }
-+
-+ min_seq[type]++;
-+ }
-+next:
-+ ;
-+ }
-+
-+ min_seq[0] = min(min_seq[0], min_seq[1]);
-+ if (swappiness)
-+ min_seq[1] = max(min_seq[0], lrugen->min_seq[1]);
-+
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ if (min_seq[type] == lrugen->min_seq[type])
-+ continue;
-+
-+ WRITE_ONCE(lrugen->min_seq[type], min_seq[type]);
-+ success = true;
-+ }
-+
-+ return success;
-+}
-+
-+static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq)
-+{
-+ int gen, type, zone;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ spin_lock_irq(&lruvec->lru_lock);
-+
-+ VM_BUG_ON(!seq_is_valid(lruvec));
-+
-+ if (max_seq != lrugen->max_seq)
-+ goto unlock;
-+
-+ if (!try_to_inc_min_seq(lruvec, true)) {
-+ for (type = ANON_AND_FILE - 1; type >= 0; type--) {
-+ while (!inc_min_seq(lruvec, type)) {
-+ spin_unlock_irq(&lruvec->lru_lock);
-+ cond_resched();
-+ spin_lock_irq(&lruvec->lru_lock);
-+ }
-+ }
-+ }
-+
-+ gen = lru_gen_from_seq(lrugen->max_seq - 1);
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-+ enum lru_list lru = type * LRU_FILE;
-+ long delta = lrugen->sizes[gen][type][zone];
-+
-+ if (!delta)
-+ continue;
-+
-+ WARN_ON_ONCE(delta != (int)delta);
-+
-+ update_lru_size(lruvec, lru, zone, delta);
-+ update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta);
-+ }
-+ }
-+
-+ gen = lru_gen_from_seq(lrugen->max_seq + 1);
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-+ enum lru_list lru = type * LRU_FILE;
-+ long delta = lrugen->sizes[gen][type][zone];
-+
-+ if (!delta)
-+ continue;
-+
-+ WARN_ON_ONCE(delta != (int)delta);
-+
-+ update_lru_size(lruvec, lru, zone, -delta);
-+ update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
-+ }
-+ }
-+
-+ WRITE_ONCE(lrugen->timestamps[gen], jiffies);
-+ /* make sure all preceding modifications appear first */
-+ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
-+unlock:
-+ spin_unlock_irq(&lruvec->lru_lock);
-+}
-+
-+/* Main function used by the foreground, the background and the user-triggered aging. */
-+static bool try_to_inc_max_seq(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-+ unsigned long max_seq, bool use_filter)
-+{
-+ bool last;
-+ struct mm_walk_args *args;
-+ struct mm_struct *mm = NULL;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-+ int nid = pgdat->node_id;
-+
-+ VM_BUG_ON(max_seq > READ_ONCE(lrugen->max_seq));
-+
-+ /*
-+ * If we are not from run_aging() and clearing the accessed bit may
-+ * trigger page faults, then don't proceed to clearing all accessed
-+ * PTEs. Instead, fallback to lru_gen_look_around(), which only clears a
-+ * handful of accessed PTEs. This is less efficient but causes fewer
-+ * page faults on CPUs that don't have the capability.
-+ */
-+ if ((current->flags & PF_MEMALLOC) && !arch_has_hw_pte_young(false)) {
-+ inc_max_seq(lruvec, max_seq);
-+ return true;
-+ }
-+
-+ args = alloc_mm_walk_args();
-+ if (!args)
-+ return false;
-+
-+ args->memcg = memcg;
-+ args->max_seq = max_seq;
-+ args->start_pfn = pgdat->node_start_pfn;
-+ args->end_pfn = pgdat_end_pfn(pgdat);
-+ args->node_id = nid;
-+ args->swappiness = swappiness;
-+ args->use_filter = use_filter;
-+
-+ do {
-+ last = get_next_mm(lruvec, args, &mm);
-+ if (mm)
-+ walk_mm(lruvec, mm, args);
-+
-+ cond_resched();
-+ } while (mm);
-+
-+ free_mm_walk_args(args);
-+
-+ if (!last) {
-+ /* don't wait unless we may have trouble reclaiming */
-+ if (!current_is_kswapd() && sc->priority < DEF_PRIORITY - 2)
-+ wait_event_killable(lruvec->mm_walk.wait,
-+ max_seq < READ_ONCE(lrugen->max_seq));
-+
-+ return max_seq < READ_ONCE(lrugen->max_seq);
-+ }
-+
-+ VM_BUG_ON(max_seq != READ_ONCE(lrugen->max_seq));
-+
-+ inc_max_seq(lruvec, max_seq);
-+ /* either we see any waiters or they will see updated max_seq */
-+ if (wq_has_sleeper(&lruvec->mm_walk.wait))
-+ wake_up_all(&lruvec->mm_walk.wait);
-+
-+ wakeup_flusher_threads(WB_REASON_VMSCAN);
-+
-+ return true;
-+}
-+
-+static long get_nr_evictable(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-+ unsigned long max_seq, unsigned long *min_seq, bool *low)
-+{
-+ int gen, type, zone;
-+ long max = 0;
-+ long min = 0;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ for (type = !swappiness; type < ANON_AND_FILE; type++) {
-+ unsigned long seq;
-+
-+ for (seq = min_seq[type]; seq <= max_seq; seq++) {
-+ long size = 0;
-+
-+ gen = lru_gen_from_seq(seq);
-+
-+ for (zone = 0; zone <= sc->reclaim_idx; zone++)
-+ size += READ_ONCE(lrugen->sizes[gen][type][zone]);
-+
-+ max += size;
-+ if (type && max_seq - seq >= MIN_NR_GENS)
-+ min += size;
-+ }
-+ }
-+
-+ *low = max_seq - min_seq[1] <= MIN_NR_GENS && min < MIN_BATCH_SIZE;
-+
-+ return max > 0 ? max : 0;
-+}
-+
-+static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc,
-+ unsigned long min_ttl)
-+{
-+ bool low;
-+ long nr_to_scan;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ int swappiness = get_swappiness(memcg);
-+ DEFINE_MAX_SEQ(lruvec);
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ if (mem_cgroup_below_min(memcg))
-+ return false;
-+
-+ if (min_ttl) {
-+ int gen = lru_gen_from_seq(min_seq[1]);
-+ unsigned long birth = READ_ONCE(lruvec->evictable.timestamps[gen]);
-+
-+ if (time_is_after_jiffies(birth + min_ttl))
-+ return false;
-+ }
-+
-+ nr_to_scan = get_nr_evictable(lruvec, sc, swappiness, max_seq, min_seq, &low);
-+ if (!nr_to_scan)
-+ return false;
-+
-+ nr_to_scan >>= sc->priority;
-+
-+ if (!mem_cgroup_online(memcg))
-+ nr_to_scan++;
-+
-+ if (nr_to_scan && low && (!mem_cgroup_below_low(memcg) || sc->memcg_low_reclaim))
-+ try_to_inc_max_seq(lruvec, sc, swappiness, max_seq, true);
-+
-+ return true;
-+}
-+
-+/* Protect the working set accessed within the last N milliseconds. */
-+static unsigned long lru_gen_min_ttl __read_mostly;
-+
-+static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
-+{
-+ struct mem_cgroup *memcg;
-+ bool success = false;
-+ unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
-+
-+ VM_BUG_ON(!current_is_kswapd());
-+
-+ if (!sc->force_deactivate) {
-+ sc->force_deactivate = 1;
-+ return;
-+ }
-+
-+ current->reclaim_state->mm_walk_args = &pgdat->mm_walk_args;
-+
-+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
-+ do {
-+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
-+
-+ if (age_lruvec(lruvec, sc, min_ttl))
-+ success = true;
-+
-+ cond_resched();
-+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
-+
-+ if (!success && mutex_trylock(&oom_lock)) {
-+ struct oom_control oc = {
-+ .gfp_mask = sc->gfp_mask,
-+ .order = sc->order,
-+ };
-+
-+ /* to avoid overkilling */
-+ if (!oom_reaping_in_progress())
-+ out_of_memory(&oc);
-+
-+ mutex_unlock(&oom_lock);
-+ }
-+
-+ current->reclaim_state->mm_walk_args = NULL;
-+}
-+
-+/* Scan the vicinity of an accessed PTE when shrink_page_list() uses the rmap. */
-+void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
-+{
-+ int i;
-+ pte_t *pte;
-+ struct page *page;
-+ int old_gen, new_gen;
-+ unsigned long start;
-+ unsigned long end;
-+ unsigned long addr;
-+ struct mm_walk_args *args;
-+ int worth = 0;
-+ struct mem_cgroup *memcg = page_memcg(pvmw->page);
-+ struct pglist_data *pgdat = page_pgdat(pvmw->page);
-+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
-+ DEFINE_MAX_SEQ(lruvec);
-+
-+ lockdep_assert_held(pvmw->ptl);
-+ VM_BUG_ON_PAGE(PageLRU(pvmw->page), pvmw->page);
-+
-+ args = current->reclaim_state ? current->reclaim_state->mm_walk_args : NULL;
-+ if (!args)
-+ return;
-+
-+ start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start);
-+ end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
-+
-+ if (end - start > MIN_BATCH_SIZE * PAGE_SIZE) {
-+ if (pvmw->address - start < MIN_BATCH_SIZE * PAGE_SIZE / 2)
-+ end = start + MIN_BATCH_SIZE * PAGE_SIZE;
-+ else if (end - pvmw->address < MIN_BATCH_SIZE * PAGE_SIZE / 2)
-+ start = end - MIN_BATCH_SIZE * PAGE_SIZE;
-+ else {
-+ start = pvmw->address - MIN_BATCH_SIZE * PAGE_SIZE / 2;
-+ end = pvmw->address + MIN_BATCH_SIZE * PAGE_SIZE / 2;
-+ }
-+ }
-+
-+ pte = pvmw->pte - (pvmw->address - start) / PAGE_SIZE;
-+ new_gen = lru_gen_from_seq(max_seq);
-+
-+ lock_page_memcg(pvmw->page);
-+ arch_enter_lazy_mmu_mode();
-+
-+ for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) {
-+ unsigned long pfn = pte_pfn(pte[i]);
-+
-+ if (!pte_present(pte[i]) || is_zero_pfn(pfn))
-+ continue;
-+
-+ if (WARN_ON_ONCE(pte_devmap(pte[i]) || pte_special(pte[i])))
-+ continue;
-+
-+ VM_BUG_ON(!pfn_valid(pfn));
-+ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-+ continue;
-+
-+ worth++;
-+
-+ if (!pte_young(pte[i]))
-+ continue;
-+
-+ page = compound_head(pfn_to_page(pfn));
-+ if (page_to_nid(page) != pgdat->node_id)
-+ continue;
-+
-+ if (page_memcg_rcu(page) != memcg)
-+ continue;
-+
-+ VM_BUG_ON(addr < pvmw->vma->vm_start || addr >= pvmw->vma->vm_end);
-+ if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
-+ continue;
-+
-+ if (pte_dirty(pte[i]) && !PageDirty(page) &&
-+ !(PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page)))
-+ __set_bit(i, args->bitmap);
-+
-+ old_gen = page_update_gen(page, new_gen);
-+ if (old_gen >= 0 && old_gen != new_gen)
-+ update_batch_size(page, old_gen, new_gen, args);
-+ }
-+
-+ arch_leave_lazy_mmu_mode();
-+ unlock_page_memcg(pvmw->page);
-+
-+ if (worth >= MIN_BATCH_SIZE / 2)
-+ set_bloom_filter(lruvec, max_seq, pvmw->pmd);
-+
-+ for_each_set_bit(i, args->bitmap, MIN_BATCH_SIZE)
-+ set_page_dirty(pte_page(pte[i]));
-+
-+ bitmap_zero(args->bitmap, MIN_BATCH_SIZE);
-+}
-+
-+/******************************************************************************
- * state change
- ******************************************************************************/
-
-@@ -3412,6 +4349,12 @@ static int __init init_lru_gen(void)
- };
- late_initcall(init_lru_gen);
-
-+#else
-+
-+static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
-+{
-+}
-+
- #endif /* CONFIG_LRU_GEN */
-
- static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-@@ -4266,6 +5209,11 @@ static void age_active_anon(struct pglis
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
-
-+ if (lru_gen_enabled()) {
-+ lru_gen_age_node(pgdat, sc);
-+ return;
-+ }
-+
- if (!can_age_anon_pages(pgdat, sc))
- return;
-
--- /dev/null
+From e4277535f6d6708bb19b88c4bad155832671d69b Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:04 -0600
+Subject: [PATCH 07/29] mm: multi-gen LRU: exploit locality in rmap
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Searching the rmap for PTEs mapping each page on an LRU list (to test and
+clear the accessed bit) can be expensive because pages from different VMAs
+(PA space) are not cache friendly to the rmap (VA space). For workloads
+mostly using mapped pages, searching the rmap can incur the highest CPU
+cost in the reclaim path.
+
+This patch exploits spatial locality to reduce the trips into the rmap.
+When shrink_page_list() walks the rmap and finds a young PTE, a new
+function lru_gen_look_around() scans at most BITS_PER_LONG-1 adjacent
+PTEs. On finding another young PTE, it clears the accessed bit and
+updates the gen counter of the page mapped by this PTE to
+(max_seq%MAX_NR_GENS)+1.
+
+Server benchmark results:
+ Single workload:
+ fio (buffered I/O): no change
+
+ Single workload:
+ memcached (anon): +[3, 5]%
+ Ops/sec KB/sec
+ patch1-6: 1106168.46 43025.04
+ patch1-7: 1147696.57 44640.29
+
+ Configurations:
+ no change
+
+Client benchmark results:
+ kswapd profiles:
+ patch1-6
+ 39.03% lzo1x_1_do_compress (real work)
+ 18.47% page_vma_mapped_walk (overhead)
+ 6.74% _raw_spin_unlock_irq
+ 3.97% do_raw_spin_lock
+ 2.49% ptep_clear_flush
+ 2.48% anon_vma_interval_tree_iter_first
+ 1.92% page_referenced_one
+ 1.88% __zram_bvec_write
+ 1.48% memmove
+ 1.31% vma_interval_tree_iter_next
+
+ patch1-7
+ 48.16% lzo1x_1_do_compress (real work)
+ 8.20% page_vma_mapped_walk (overhead)
+ 7.06% _raw_spin_unlock_irq
+ 2.92% ptep_clear_flush
+ 2.53% __zram_bvec_write
+ 2.11% do_raw_spin_lock
+ 2.02% memmove
+ 1.93% lru_gen_look_around
+ 1.56% free_unref_page_list
+ 1.40% memset
+
+ Configurations:
+ no change
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-8-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Barry Song <baohua@kernel.org>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/memcontrol.h | 31 +++++++
+ include/linux/mmzone.h | 6 ++
+ mm/internal.h | 1 +
+ mm/memcontrol.c | 1 +
+ mm/rmap.c | 7 ++
+ mm/swap.c | 4 +-
+ mm/vmscan.c | 184 +++++++++++++++++++++++++++++++++++++
+ 7 files changed, 232 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
+index 4f189b17dafc..8d6a0329bc59 100644
+--- a/include/linux/memcontrol.h
++++ b/include/linux/memcontrol.h
+@@ -442,6 +442,7 @@ static inline struct obj_cgroup *__page_objcg(struct page *page)
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
++ * - mem_cgroup_trylock_pages()
+ *
+ * For a kmem page a caller should hold an rcu read lock to protect memcg
+ * associated with a kmem page from being released.
+@@ -497,6 +498,7 @@ static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
++ * - mem_cgroup_trylock_pages()
+ *
+ * For a kmem page a caller should hold an rcu read lock to protect memcg
+ * associated with a kmem page from being released.
+@@ -953,6 +955,23 @@ void unlock_page_memcg(struct page *page);
+
+ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
+
++/* try to stablize page_memcg() for all the pages in a memcg */
++static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
++{
++ rcu_read_lock();
++
++ if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account))
++ return true;
++
++ rcu_read_unlock();
++ return false;
++}
++
++static inline void mem_cgroup_unlock_pages(void)
++{
++ rcu_read_unlock();
++}
++
+ /* idx can be of type enum memcg_stat_item or node_stat_item */
+ static inline void mod_memcg_state(struct mem_cgroup *memcg,
+ int idx, int val)
+@@ -1369,6 +1388,18 @@ static inline void unlock_page_memcg(struct page *page)
+ {
+ }
+
++static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
++{
++ /* to match page_memcg_rcu() */
++ rcu_read_lock();
++ return true;
++}
++
++static inline void mem_cgroup_unlock_pages(void)
++{
++ rcu_read_unlock();
++}
++
+ static inline void mem_cgroup_handle_over_high(void)
+ {
+ }
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index fce8945c507c..4db2b877fcf9 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -352,6 +352,7 @@ enum lruvec_flags {
+ #ifndef __GENERATING_BOUNDS_H
+
+ struct lruvec;
++struct page_vma_mapped_walk;
+
+ #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
+ #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
+@@ -407,6 +408,7 @@ struct lru_gen_struct {
+ };
+
+ void lru_gen_init_lruvec(struct lruvec *lruvec);
++void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+
+ #ifdef CONFIG_MEMCG
+ void lru_gen_init_memcg(struct mem_cgroup *memcg);
+@@ -419,6 +421,10 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
+ {
+ }
+
++static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
++{
++}
++
+ #ifdef CONFIG_MEMCG
+ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
+ {
+diff --git a/mm/internal.h b/mm/internal.h
+index cf3cb933eba3..5c73246a092e 100644
+--- a/mm/internal.h
++++ b/mm/internal.h
+@@ -35,6 +35,7 @@
+ void page_writeback_init(void);
+
+ vm_fault_t do_swap_page(struct vm_fault *vmf);
++void activate_page(struct page *page);
+
+ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
+ unsigned long floor, unsigned long ceiling);
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index 8b634dc72e7f..cc3431c5d9ba 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -2798,6 +2798,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
+ * - LRU isolation
+ * - lock_page_memcg()
+ * - exclusive reference
++ * - mem_cgroup_trylock_pages()
+ */
+ page->memcg_data = (unsigned long)memcg;
+ }
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 330b361a460e..22a86122732e 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -73,6 +73,7 @@
+ #include <linux/page_idle.h>
+ #include <linux/memremap.h>
+ #include <linux/userfaultfd_k.h>
++#include <linux/mm_inline.h>
+
+ #include <asm/tlbflush.h>
+
+@@ -793,6 +794,12 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
+ }
+
+ if (pvmw.pte) {
++ if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
++ !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) {
++ lru_gen_look_around(&pvmw);
++ referenced++;
++ }
++
+ if (ptep_clear_flush_young_notify(vma, address,
+ pvmw.pte)) {
+ /*
+diff --git a/mm/swap.c b/mm/swap.c
+index 5d227577b609..966ff2d83343 100644
+--- a/mm/swap.c
++++ b/mm/swap.c
+@@ -325,7 +325,7 @@ static bool need_activate_page_drain(int cpu)
+ return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
+ }
+
+-static void activate_page(struct page *page)
++void activate_page(struct page *page)
+ {
+ page = compound_head(page);
+ if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+@@ -345,7 +345,7 @@ static inline void activate_page_drain(int cpu)
+ {
+ }
+
+-static void activate_page(struct page *page)
++void activate_page(struct page *page)
+ {
+ struct lruvec *lruvec;
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 932abd24c1b3..1d0b25ae378c 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -1409,6 +1409,11 @@ static unsigned int shrink_page_list(struct list_head *page_list,
+ if (!sc->may_unmap && page_mapped(page))
+ goto keep_locked;
+
++ /* page_update_gen() tried to promote this page? */
++ if (lru_gen_enabled() && !ignore_references &&
++ page_mapped(page) && PageReferenced(page))
++ goto keep_locked;
++
+ may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
+ (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
+
+@@ -2990,6 +2995,29 @@ static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
+ * the aging
+ ******************************************************************************/
+
++/* promote pages accessed through page tables */
++static int page_update_gen(struct page *page, int gen)
++{
++ unsigned long new_flags, old_flags = READ_ONCE(page->flags);
++
++ VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
++ VM_WARN_ON_ONCE(!rcu_read_lock_held());
++
++ do {
++ /* lru_gen_del_page() has isolated this page? */
++ if (!(old_flags & LRU_GEN_MASK)) {
++ /* for shrink_page_list() */
++ new_flags = old_flags | BIT(PG_referenced);
++ continue;
++ }
++
++ new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
++ new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
++ } while (!try_cmpxchg(&page->flags, &old_flags, new_flags));
++
++ return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
++}
++
+ /* protect pages accessed multiple times through file descriptors */
+ static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaiming)
+ {
+@@ -3001,6 +3029,11 @@ static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaimin
+ VM_WARN_ON_ONCE_PAGE(!(old_flags & LRU_GEN_MASK), page);
+
+ do {
++ new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
++ /* page_update_gen() has promoted this page? */
++ if (new_gen >= 0 && new_gen != old_gen)
++ return new_gen;
++
+ new_gen = (old_gen + 1) % MAX_NR_GENS;
+
+ new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
+@@ -3015,6 +3048,43 @@ static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaimin
+ return new_gen;
+ }
+
++static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
++{
++ unsigned long pfn = pte_pfn(pte);
++
++ VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end);
++
++ if (!pte_present(pte) || is_zero_pfn(pfn))
++ return -1;
++
++ if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
++ return -1;
++
++ if (WARN_ON_ONCE(!pfn_valid(pfn)))
++ return -1;
++
++ return pfn;
++}
++
++static struct page *get_pfn_page(unsigned long pfn, struct mem_cgroup *memcg,
++ struct pglist_data *pgdat)
++{
++ struct page *page;
++
++ /* try to avoid unnecessary memory loads */
++ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
++ return NULL;
++
++ page = compound_head(pfn_to_page(pfn));
++ if (page_to_nid(page) != pgdat->node_id)
++ return NULL;
++
++ if (page_memcg_rcu(page) != memcg)
++ return NULL;
++
++ return page;
++}
++
+ static void inc_min_seq(struct lruvec *lruvec, int type)
+ {
+ struct lru_gen_struct *lrugen = &lruvec->lrugen;
+@@ -3214,6 +3284,114 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+ }
+
++/*
++ * This function exploits spatial locality when shrink_page_list() walks the
++ * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages.
++ */
++void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
++{
++ int i;
++ pte_t *pte;
++ unsigned long start;
++ unsigned long end;
++ unsigned long addr;
++ unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {};
++ struct page *page = pvmw->page;
++ struct mem_cgroup *memcg = page_memcg(page);
++ struct pglist_data *pgdat = page_pgdat(page);
++ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
++ DEFINE_MAX_SEQ(lruvec);
++ int old_gen, new_gen = lru_gen_from_seq(max_seq);
++
++ lockdep_assert_held(pvmw->ptl);
++ VM_WARN_ON_ONCE_PAGE(PageLRU(page), page);
++
++ if (spin_is_contended(pvmw->ptl))
++ return;
++
++ start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start);
++ end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
++
++ if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
++ if (pvmw->address - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
++ end = start + MIN_LRU_BATCH * PAGE_SIZE;
++ else if (end - pvmw->address < MIN_LRU_BATCH * PAGE_SIZE / 2)
++ start = end - MIN_LRU_BATCH * PAGE_SIZE;
++ else {
++ start = pvmw->address - MIN_LRU_BATCH * PAGE_SIZE / 2;
++ end = pvmw->address + MIN_LRU_BATCH * PAGE_SIZE / 2;
++ }
++ }
++
++ pte = pvmw->pte - (pvmw->address - start) / PAGE_SIZE;
++
++ rcu_read_lock();
++ arch_enter_lazy_mmu_mode();
++
++ for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) {
++ unsigned long pfn;
++
++ pfn = get_pte_pfn(pte[i], pvmw->vma, addr);
++ if (pfn == -1)
++ continue;
++
++ if (!pte_young(pte[i]))
++ continue;
++
++ page = get_pfn_page(pfn, memcg, pgdat);
++ if (!page)
++ continue;
++
++ if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
++ VM_WARN_ON_ONCE(true);
++
++ if (pte_dirty(pte[i]) && !PageDirty(page) &&
++ !(PageAnon(page) && PageSwapBacked(page) &&
++ !PageSwapCache(page)))
++ set_page_dirty(page);
++
++ old_gen = page_lru_gen(page);
++ if (old_gen < 0)
++ SetPageReferenced(page);
++ else if (old_gen != new_gen)
++ __set_bit(i, bitmap);
++ }
++
++ arch_leave_lazy_mmu_mode();
++ rcu_read_unlock();
++
++ if (bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) {
++ for_each_set_bit(i, bitmap, MIN_LRU_BATCH) {
++ page = pte_page(pte[i]);
++ activate_page(page);
++ }
++ return;
++ }
++
++ /* page_update_gen() requires stable page_memcg() */
++ if (!mem_cgroup_trylock_pages(memcg))
++ return;
++
++ spin_lock_irq(&lruvec->lru_lock);
++ new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq);
++
++ for_each_set_bit(i, bitmap, MIN_LRU_BATCH) {
++ page = compound_head(pte_page(pte[i]));
++ if (page_memcg_rcu(page) != memcg)
++ continue;
++
++ old_gen = page_update_gen(page, new_gen);
++ if (old_gen < 0 || old_gen == new_gen)
++ continue;
++
++ lru_gen_update_size(lruvec, page, old_gen, new_gen);
++ }
++
++ spin_unlock_irq(&lruvec->lru_lock);
++
++ mem_cgroup_unlock_pages();
++}
++
+ /******************************************************************************
+ * the eviction
+ ******************************************************************************/
+@@ -3250,6 +3428,12 @@ static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
+ return true;
+ }
+
++ /* promoted */
++ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
++ list_move(&page->lru, &lrugen->lists[gen][type][zone]);
++ return true;
++ }
++
+ /* protected */
+ if (tier > tier_idx) {
+ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
+--
+2.40.0
+
+++ /dev/null
-From f4b881ce07ccb2a519f664afaa2a68225b612ca3 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Tue, 29 Jun 2021 20:46:47 -0600
-Subject: [PATCH 07/10] mm: multigenerational lru: eviction
-
-The eviction consumes old generations. Given an lruvec, the eviction
-scans pages on lrugen->lists indexed by anon and file min_seq[]
-(modulo MAX_NR_GENS). It first tries to select a type based on the
-values of min_seq[]. If they are equal, it selects the type that has
-a lower refaulted %. The eviction sorts a page according to its
-updated generation number if the aging has found this page accessed.
-It also moves a page to the next generation if this page is from an
-upper tier that has a higher refaulted % than the base tier. The
-eviction increments min_seq[] of a selected type when it finds
-lrugen->lists indexed by min_seq[] of this selected type are empty.
-
-Each generation is divided into multiple tiers. Tiers represent
-different ranges of numbers of accesses from file descriptors only.
-Pages accessed N times via file descriptors belong to tier
-order_base_2(N). Each generation contains at most MAX_NR_TIERS tiers,
-and they require additional MAX_NR_TIERS-2 bits in page->flags. In
-contrast to moving between generations which requires list operations,
-moving between tiers only involves operations on page->flags and
-therefore has a negligible cost. A feedback loop modeled after the PID
-controller monitors refaulted % across all tiers and decides when to
-protect pages from which tiers.
-
-Unmapped pages are initially added to the oldest generation and then
-conditionally protected by tiers. Each tier keeps track of how many
-pages from it have refaulted. Tier 0 is the base tier and pages from
-it are evicted unconditionally because there are no better candidates.
-Pages from an upper tier are either evicted or moved to the next
-generation, depending on whether this upper tier has a higher
-refaulted % than the base tier. This model has the following
-advantages:
- 1) It removes the cost in the buffered access path and reduces the
- overall cost of protection because pages are conditionally protected
- in the reclaim path.
- 2) It takes mapped pages into account and avoids overprotecting
- pages accessed multiple times via file descriptors.
- 3 Additional tiers improve the protection of pages accessed more
- than twice.
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I64c06d8f2cdb83ac7d56c7e1d07f043483956cac
----
- include/linux/mm_inline.h | 10 +
- include/linux/mmzone.h | 33 +++
- mm/swap.c | 42 +++
- mm/vmscan.c | 555 +++++++++++++++++++++++++++++++++++++-
- mm/workingset.c | 120 ++++++++-
- 5 files changed, 757 insertions(+), 3 deletions(-)
-
---- a/include/linux/mm_inline.h
-+++ b/include/linux/mm_inline.h
-@@ -106,6 +106,14 @@ static inline int lru_hist_from_seq(unsi
- return seq % NR_HIST_GENS;
- }
-
-+/* Convert the number of accesses to a tier. See the comment on MAX_NR_TIERS. */
-+static inline int lru_tier_from_refs(int refs)
-+{
-+ VM_BUG_ON(refs > BIT(LRU_REFS_WIDTH));
-+
-+ return order_base_2(refs + 1);
-+}
-+
- /* The youngest and the second youngest generations are counted as active. */
- static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
- {
-@@ -226,6 +234,8 @@ static inline bool lru_gen_del_page(stru
- gen = ((new_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
-
- new_flags &= ~LRU_GEN_MASK;
-+ if ((new_flags & LRU_REFS_FLAGS) != LRU_REFS_FLAGS)
-+ new_flags &= ~(LRU_REFS_MASK | LRU_REFS_FLAGS);
- /* for shrink_page_list() */
- if (reclaiming)
- new_flags &= ~(BIT(PG_referenced) | BIT(PG_reclaim));
---- a/include/linux/mmzone.h
-+++ b/include/linux/mmzone.h
-@@ -319,6 +319,30 @@ struct page_vma_mapped_walk;
- #define MIN_NR_GENS 2
- #define MAX_NR_GENS ((unsigned int)CONFIG_NR_LRU_GENS)
-
-+/*
-+ * Each generation is divided into multiple tiers. Tiers represent different
-+ * ranges of numbers of accesses from file descriptors, i.e.,
-+ * mark_page_accessed(). In contrast to moving between generations which
-+ * requires the lru lock, moving between tiers only involves an atomic
-+ * operation on page->flags and therefore has a negligible cost.
-+ *
-+ * The purposes of tiers are to:
-+ * 1) estimate whether pages accessed multiple times via file descriptors are
-+ * more active than pages accessed only via page tables by separating the two
-+ * access types into upper tiers and the base tier, and comparing refaulted %
-+ * across all tiers.
-+ * 2) improve buffered io performance by deferring the protection of pages
-+ * accessed multiple times until the eviction. That is the protection happens
-+ * in the reclaim path, not the access path.
-+ *
-+ * Pages accessed N times via file descriptors belong to tier order_base_2(N).
-+ * The base tier may be marked by PageReferenced(). All upper tiers are marked
-+ * by PageReferenced() && PageWorkingset(). Additional bits from page->flags are
-+ * used to support more than one upper tier.
-+ */
-+#define MAX_NR_TIERS ((unsigned int)CONFIG_TIERS_PER_GEN)
-+#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset))
-+
- /* Whether to keep stats for historical generations. */
- #ifdef CONFIG_LRU_GEN_STATS
- #define NR_HIST_GENS ((unsigned int)CONFIG_NR_LRU_GENS)
-@@ -337,6 +361,15 @@ struct lrugen {
- struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
- /* the sizes of the multigenerational lru lists in pages */
- unsigned long sizes[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
-+ /* the exponential moving average of refaulted */
-+ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
-+ /* the exponential moving average of protected+evicted */
-+ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
-+ /* the base tier isn't protected, hence the minus one */
-+ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
-+ /* incremented without holding the lru lock */
-+ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
-+ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
- /* whether the multigenerational lru is enabled */
- bool enabled[ANON_AND_FILE];
- };
---- a/mm/swap.c
-+++ b/mm/swap.c
-@@ -389,6 +389,43 @@ static void __lru_cache_activate_page(st
- local_unlock(&lru_pvecs.lock);
- }
-
-+#ifdef CONFIG_LRU_GEN
-+static void page_inc_refs(struct page *page)
-+{
-+ unsigned long refs;
-+ unsigned long old_flags, new_flags;
-+
-+ if (PageUnevictable(page))
-+ return;
-+
-+ /* see the comment on MAX_NR_TIERS */
-+ do {
-+ new_flags = old_flags = READ_ONCE(page->flags);
-+
-+ if (!(new_flags & BIT(PG_referenced))) {
-+ new_flags |= BIT(PG_referenced);
-+ continue;
-+ }
-+
-+ if (!(new_flags & BIT(PG_workingset))) {
-+ new_flags |= BIT(PG_workingset);
-+ continue;
-+ }
-+
-+ refs = new_flags & LRU_REFS_MASK;
-+ refs = min(refs + BIT(LRU_REFS_PGOFF), LRU_REFS_MASK);
-+
-+ new_flags &= ~LRU_REFS_MASK;
-+ new_flags |= refs;
-+ } while (new_flags != old_flags &&
-+ cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-+}
-+#else
-+static void page_inc_refs(struct page *page)
-+{
-+}
-+#endif /* CONFIG_LRU_GEN */
-+
- /*
- * Mark a page as having seen activity.
- *
-@@ -403,6 +440,11 @@ void mark_page_accessed(struct page *pag
- {
- page = compound_head(page);
-
-+ if (lru_gen_enabled()) {
-+ page_inc_refs(page);
-+ return;
-+ }
-+
- if (!PageReferenced(page)) {
- SetPageReferenced(page);
- } else if (PageUnevictable(page)) {
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -1145,9 +1145,11 @@ static int __remove_mapping(struct addre
-
- if (PageSwapCache(page)) {
- swp_entry_t swap = { .val = page_private(page) };
-- mem_cgroup_swapout(page, swap);
-+
-+ /* get a shadow entry before page_memcg() is cleared */
- if (reclaimed && !mapping_exiting(mapping))
- shadow = workingset_eviction(page, target_memcg);
-+ mem_cgroup_swapout(page, swap);
- __delete_from_swap_cache(page, swap, shadow);
- xa_unlock_irq(&mapping->i_pages);
- put_swap_page(page, swap);
-@@ -1410,6 +1412,11 @@ retry:
- if (!sc->may_unmap && page_mapped(page))
- goto keep_locked;
-
-+ /* lru_gen_look_around() has updated this page? */
-+ if (lru_gen_enabled() && !ignore_references &&
-+ page_mapped(page) && PageReferenced(page))
-+ goto keep_locked;
-+
- may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
- (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
-
-@@ -2505,6 +2512,9 @@ static void prepare_scan_count(pg_data_t
- unsigned long file;
- struct lruvec *target_lruvec;
-
-+ if (lru_gen_enabled())
-+ return;
-+
- target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
-
- /*
-@@ -2845,6 +2855,17 @@ static int page_lru_gen(struct page *pag
- return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
- }
-
-+static int page_lru_tier(struct page *page)
-+{
-+ int refs;
-+ unsigned long flags = READ_ONCE(page->flags);
-+
-+ refs = (flags & LRU_REFS_FLAGS) == LRU_REFS_FLAGS ?
-+ ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1 : 0;
-+
-+ return lru_tier_from_refs(refs);
-+}
-+
- static int get_swappiness(struct mem_cgroup *memcg)
- {
- return mem_cgroup_get_nr_swap_pages(memcg) >= MIN_BATCH_SIZE ?
-@@ -3181,6 +3202,91 @@ done:
- }
-
- /******************************************************************************
-+ * refault feedback loop
-+ ******************************************************************************/
-+
-+/*
-+ * A feedback loop modeled after the PID controller. Currently supports the
-+ * proportional (P) and the integral (I) terms; the derivative (D) term can be
-+ * added if necessary. The setpoint (SP) is the desired position; the process
-+ * variable (PV) is the measured position. The error is the difference between
-+ * the SP and the PV. A positive error results in a positive control output
-+ * correction, which, in our case, is to allow eviction.
-+ *
-+ * The P term is refaulted % of the current generation being evicted. The I
-+ * term is the exponential moving average of refaulted % of previously evicted
-+ * generations, using the smoothing factor 1/2.
-+ *
-+ * Our goal is to maintain proportional refaulted % across all tiers.
-+ */
-+struct ctrl_pos {
-+ unsigned long refaulted;
-+ unsigned long total;
-+ int gain;
-+};
-+
-+static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
-+ struct ctrl_pos *pos)
-+{
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
-+
-+ pos->refaulted = lrugen->avg_refaulted[type][tier] +
-+ atomic_long_read(&lrugen->refaulted[hist][type][tier]);
-+ pos->total = lrugen->avg_total[type][tier] +
-+ atomic_long_read(&lrugen->evicted[hist][type][tier]);
-+ if (tier)
-+ pos->total += lrugen->protected[hist][type][tier - 1];
-+ pos->gain = gain;
-+}
-+
-+static void reset_ctrl_pos(struct lruvec *lruvec, int gen, int type)
-+{
-+ int tier;
-+ int hist = lru_hist_from_seq(gen);
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ bool carryover = gen == lru_gen_from_seq(lrugen->min_seq[type]);
-+ bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1;
-+
-+ if (!carryover && !clear)
-+ return;
-+
-+ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
-+ if (carryover) {
-+ unsigned long sum;
-+
-+ sum = lrugen->avg_refaulted[type][tier] +
-+ atomic_long_read(&lrugen->refaulted[hist][type][tier]);
-+ WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);
-+
-+ sum = lrugen->avg_total[type][tier] +
-+ atomic_long_read(&lrugen->evicted[hist][type][tier]);
-+ if (tier)
-+ sum += lrugen->protected[hist][type][tier - 1];
-+ WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
-+ }
-+
-+ if (clear) {
-+ atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
-+ atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
-+ if (tier)
-+ WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
-+ }
-+ }
-+}
-+
-+static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv)
-+{
-+ /*
-+ * Allow eviction if the PV has a limited number of refaulted pages or a
-+ * lower refaulted % than the SP.
-+ */
-+ return pv->refaulted < MIN_BATCH_SIZE ||
-+ pv->refaulted * max(sp->total, 1UL) * sp->gain <=
-+ sp->refaulted * max(pv->total, 1UL) * pv->gain;
-+}
-+
-+/******************************************************************************
- * the aging
- ******************************************************************************/
-
-@@ -3200,6 +3306,7 @@ static int page_update_gen(struct page *
-
- new_flags &= ~LRU_GEN_MASK;
- new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
-+ new_flags &= ~(LRU_REFS_MASK | LRU_REFS_FLAGS);
- } while (new_flags != old_flags &&
- cmpxchg(&page->flags, old_flags, new_flags) != old_flags);
-
-@@ -3231,6 +3338,7 @@ static void page_inc_gen(struct page *pa
-
- new_flags &= ~LRU_GEN_MASK;
- new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
-+ new_flags &= ~(LRU_REFS_MASK | LRU_REFS_FLAGS);
- /* for end_page_writeback() */
- if (reclaiming)
- new_flags |= BIT(PG_reclaim);
-@@ -3722,6 +3830,7 @@ static bool inc_min_seq(struct lruvec *l
- }
- }
-
-+ reset_ctrl_pos(lruvec, gen, type);
- WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
-
- return true;
-@@ -3759,6 +3868,8 @@ next:
- if (min_seq[type] == lrugen->min_seq[type])
- continue;
-
-+ gen = lru_gen_from_seq(lrugen->min_seq[type]);
-+ reset_ctrl_pos(lruvec, gen, type);
- WRITE_ONCE(lrugen->min_seq[type], min_seq[type]);
- success = true;
- }
-@@ -3820,6 +3931,9 @@ static void inc_max_seq(struct lruvec *l
- }
- }
-
-+ for (type = 0; type < ANON_AND_FILE; type++)
-+ reset_ctrl_pos(lruvec, gen, type);
-+
- WRITE_ONCE(lrugen->timestamps[gen], jiffies);
- /* make sure all preceding modifications appear first */
- smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
-@@ -4101,6 +4215,433 @@ void lru_gen_look_around(struct page_vma
- }
-
- /******************************************************************************
-+ * the eviction
-+ ******************************************************************************/
-+
-+static bool sort_page(struct page *page, struct lruvec *lruvec, int tier_idx)
-+{
-+ bool success;
-+ int gen = page_lru_gen(page);
-+ int type = page_is_file_lru(page);
-+ int zone = page_zonenum(page);
-+ int tier = page_lru_tier(page);
-+ int delta = thp_nr_pages(page);
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ VM_BUG_ON_PAGE(gen >= MAX_NR_GENS, page);
-+
-+ /* an mlocked page? */
-+ if (!page_evictable(page)) {
-+ success = lru_gen_del_page(page, lruvec, true);
-+ VM_BUG_ON_PAGE(!success, page);
-+ SetPageUnevictable(page);
-+ add_page_to_lru_list(page, lruvec);
-+ __count_vm_events(UNEVICTABLE_PGCULLED, delta);
-+ return true;
-+ }
-+
-+ /* a lazy-free page that has been written into? */
-+ if (type && PageDirty(page) && PageAnon(page)) {
-+ success = lru_gen_del_page(page, lruvec, true);
-+ VM_BUG_ON_PAGE(!success, page);
-+ SetPageSwapBacked(page);
-+ add_page_to_lru_list_tail(page, lruvec);
-+ return true;
-+ }
-+
-+ /* page_update_gen() has updated this page? */
-+ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
-+ list_move(&page->lru, &lrugen->lists[gen][type][zone]);
-+ return true;
-+ }
-+
-+ /* protect this page if its tier has a higher refaulted % */
-+ if (tier > tier_idx) {
-+ int hist = lru_hist_from_seq(gen);
-+
-+ page_inc_gen(page, lruvec, false);
-+ WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
-+ lrugen->protected[hist][type][tier - 1] + delta);
-+ __mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
-+ return true;
-+ }
-+
-+ /* mark this page for reclaim if it's pending writeback */
-+ if (PageWriteback(page) || (type && PageDirty(page))) {
-+ page_inc_gen(page, lruvec, true);
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+static bool isolate_page(struct page *page, struct lruvec *lruvec, struct scan_control *sc)
-+{
-+ bool success;
-+
-+ if (!sc->may_unmap && page_mapped(page))
-+ return false;
-+
-+ if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
-+ (PageDirty(page) || (PageAnon(page) && !PageSwapCache(page))))
-+ return false;
-+
-+ if (!get_page_unless_zero(page))
-+ return false;
-+
-+ if (!TestClearPageLRU(page)) {
-+ put_page(page);
-+ return false;
-+ }
-+
-+ success = lru_gen_del_page(page, lruvec, true);
-+ VM_BUG_ON_PAGE(!success, page);
-+
-+ return true;
-+}
-+
-+static int scan_pages(struct lruvec *lruvec, struct scan_control *sc,
-+ int type, int tier, struct list_head *list)
-+{
-+ int gen, zone;
-+ enum vm_event_item item;
-+ int sorted = 0;
-+ int scanned = 0;
-+ int isolated = 0;
-+ int remaining = MAX_BATCH_SIZE;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+
-+ VM_BUG_ON(!list_empty(list));
-+
-+ if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
-+ return 0;
-+
-+ gen = lru_gen_from_seq(lrugen->min_seq[type]);
-+
-+ for (zone = sc->reclaim_idx; zone >= 0; zone--) {
-+ LIST_HEAD(moved);
-+ int skipped = 0;
-+ struct list_head *head = &lrugen->lists[gen][type][zone];
-+
-+ while (!list_empty(head)) {
-+ struct page *page = lru_to_page(head);
-+ int delta = thp_nr_pages(page);
-+
-+ VM_BUG_ON_PAGE(PageTail(page), page);
-+ VM_BUG_ON_PAGE(PageUnevictable(page), page);
-+ VM_BUG_ON_PAGE(PageActive(page), page);
-+ VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
-+ VM_BUG_ON_PAGE(page_zonenum(page) != zone, page);
-+
-+ prefetchw_prev_lru_page(page, head, flags);
-+
-+ scanned += delta;
-+
-+ if (sort_page(page, lruvec, tier))
-+ sorted += delta;
-+ else if (isolate_page(page, lruvec, sc)) {
-+ list_add(&page->lru, list);
-+ isolated += delta;
-+ } else {
-+ list_move(&page->lru, &moved);
-+ skipped += delta;
-+ }
-+
-+ if (!--remaining || max(isolated, skipped) >= MIN_BATCH_SIZE)
-+ break;
-+ }
-+
-+ if (skipped) {
-+ list_splice(&moved, head);
-+ __count_zid_vm_events(PGSCAN_SKIP, zone, skipped);
-+ }
-+
-+ if (!remaining || isolated >= MIN_BATCH_SIZE)
-+ break;
-+ }
-+
-+ item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
-+ if (!cgroup_reclaim(sc)) {
-+ __count_vm_events(item, isolated);
-+ __count_vm_events(PGREFILL, sorted);
-+ }
-+ __count_memcg_events(memcg, item, isolated);
-+ __count_memcg_events(memcg, PGREFILL, sorted);
-+ __count_vm_events(PGSCAN_ANON + type, isolated);
-+
-+ /*
-+ * We may have trouble finding eligible pages due to reclaim_idx,
-+ * may_unmap and may_writepage. Check `remaining` to make sure we won't
-+ * be stuck if we aren't making enough progress.
-+ */
-+ return isolated || !remaining ? scanned : 0;
-+}
-+
-+static int get_tier_idx(struct lruvec *lruvec, int type)
-+{
-+ int tier;
-+ struct ctrl_pos sp, pv;
-+
-+ /*
-+ * Ideally we don't want to evict upper tiers that have higher refaulted
-+ * %. However, we need to leave a margin for the fluctuation in
-+ * refaulted %. So we use a larger gain factor to make sure upper tiers
-+ * are indeed more active. We choose 2 because the lowest upper tier
-+ * would have twice of refaulted % of the base tier, according to their
-+ * numbers of accesses.
-+ */
-+ read_ctrl_pos(lruvec, type, 0, 1, &sp);
-+ for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-+ read_ctrl_pos(lruvec, type, tier, 2, &pv);
-+ if (!positive_ctrl_err(&sp, &pv))
-+ break;
-+ }
-+
-+ return tier - 1;
-+}
-+
-+static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
-+{
-+ int type, tier;
-+ struct ctrl_pos sp, pv;
-+ int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness };
-+
-+ /*
-+ * Compare refaulted % between the base tiers of anon and file to
-+ * determine which type to evict. Also need to compare refaulted % of
-+ * the upper tiers of the selected type with that of the base tier of
-+ * the other type to determine which tier of the selected type to evict.
-+ */
-+ read_ctrl_pos(lruvec, 0, 0, gain[0], &sp);
-+ read_ctrl_pos(lruvec, 1, 0, gain[1], &pv);
-+ type = positive_ctrl_err(&sp, &pv);
-+
-+ read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
-+ for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-+ read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
-+ if (!positive_ctrl_err(&sp, &pv))
-+ break;
-+ }
-+
-+ *tier_idx = tier - 1;
-+
-+ return type;
-+}
-+
-+static int isolate_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-+ int *type_scanned, struct list_head *list)
-+{
-+ int i;
-+ int type;
-+ int scanned;
-+ int tier = -1;
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ VM_BUG_ON(!seq_is_valid(lruvec));
-+
-+ /*
-+ * Try to select a type based on generations and swappiness, and if that
-+ * fails, fall back to get_type_to_scan(). When anon and file are both
-+ * available from the same generation, swappiness 200 is interpreted as
-+ * anon first and swappiness 1 is interpreted as file first.
-+ */
-+ if (!swappiness)
-+ type = 1;
-+ else if (min_seq[0] < min_seq[1])
-+ type = 0;
-+ else if (swappiness == 1)
-+ type = 1;
-+ else if (swappiness == 200)
-+ type = 0;
-+ else
-+ type = get_type_to_scan(lruvec, swappiness, &tier);
-+
-+ for (i = !swappiness; i < ANON_AND_FILE; i++) {
-+ if (tier < 0)
-+ tier = get_tier_idx(lruvec, type);
-+
-+ scanned = scan_pages(lruvec, sc, type, tier, list);
-+ if (scanned)
-+ break;
-+
-+ type = !type;
-+ tier = -1;
-+ }
-+
-+ *type_scanned = type;
-+
-+ return scanned;
-+}
-+
-+/* Main function used by the foreground, the background and the user-triggered eviction. */
-+static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
-+{
-+ int type;
-+ int scanned;
-+ int reclaimed;
-+ LIST_HEAD(list);
-+ struct page *page;
-+ enum vm_event_item item;
-+ struct reclaim_stat stat;
-+ struct mm_walk_args *args;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-+
-+ spin_lock_irq(&lruvec->lru_lock);
-+
-+ scanned = isolate_pages(lruvec, sc, swappiness, &type, &list);
-+
-+ if (try_to_inc_min_seq(lruvec, swappiness))
-+ scanned++;
-+
-+ if (get_nr_gens(lruvec, 1) == MIN_NR_GENS)
-+ scanned = 0;
-+
-+ spin_unlock_irq(&lruvec->lru_lock);
-+
-+ if (list_empty(&list))
-+ return scanned;
-+
-+ reclaimed = shrink_page_list(&list, pgdat, sc, &stat, false);
-+ /*
-+ * We need to prevent rejected pages from being added back to the same
-+ * lists they were isolated from. Otherwise we may risk looping on them
-+ * forever.
-+ */
-+ list_for_each_entry(page, &list, lru) {
-+ if (!PageReclaim(page) || !(PageDirty(page) || PageWriteback(page)))
-+ SetPageActive(page);
-+
-+ ClearPageReferenced(page);
-+ ClearPageWorkingset(page);
-+ }
-+
-+ spin_lock_irq(&lruvec->lru_lock);
-+
-+ move_pages_to_lru(lruvec, &list);
-+
-+ args = current->reclaim_state ? current->reclaim_state->mm_walk_args : NULL;
-+ if (args && args->batch_size)
-+ reset_batch_size(lruvec, args);
-+
-+ item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
-+ if (!cgroup_reclaim(sc))
-+ __count_vm_events(item, reclaimed);
-+ __count_memcg_events(memcg, item, reclaimed);
-+ __count_vm_events(PGSTEAL_ANON + type, reclaimed);
-+
-+ spin_unlock_irq(&lruvec->lru_lock);
-+
-+ mem_cgroup_uncharge_list(&list);
-+ free_unref_page_list(&list);
-+
-+ sc->nr_reclaimed += reclaimed;
-+
-+ return scanned;
-+}
-+
-+static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
-+{
-+ bool low;
-+ long nr_to_scan;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ int priority = sc->priority;
-+ DEFINE_MAX_SEQ(lruvec);
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ if (mem_cgroup_below_min(memcg) ||
-+ (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
-+ return 0;
-+
-+ if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
-+ priority = DEF_PRIORITY;
-+ sc->force_deactivate = 0;
-+ }
-+
-+ nr_to_scan = get_nr_evictable(lruvec, sc, swappiness, max_seq, min_seq, &low);
-+ if (!nr_to_scan)
-+ return 0;
-+
-+ nr_to_scan >>= priority;
-+
-+ if (!mem_cgroup_online(memcg))
-+ nr_to_scan++;
-+
-+ if (!nr_to_scan)
-+ return 0;
-+
-+ if (current_is_kswapd()) {
-+ /* leave the work to lru_gen_age_node() */
-+ if (max_seq - min_seq[1] < MIN_NR_GENS)
-+ return 0;
-+
-+ if (!low)
-+ sc->force_deactivate = 0;
-+
-+ return nr_to_scan;
-+ }
-+
-+ if (max_seq - min_seq[1] >= MIN_NR_GENS)
-+ return nr_to_scan;
-+
-+ /* move onto slab and other memcgs if we haven't tried them all */
-+ if (!sc->force_deactivate) {
-+ sc->skipped_deactivate = 1;
-+ return 0;
-+ }
-+
-+ return try_to_inc_max_seq(lruvec, sc, swappiness, max_seq, true) ? nr_to_scan : 0;
-+}
-+
-+static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-+{
-+ struct blk_plug plug;
-+ long scanned = 0;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-+
-+ lru_add_drain();
-+
-+ if (current_is_kswapd())
-+ current->reclaim_state->mm_walk_args = &pgdat->mm_walk_args;
-+
-+ blk_start_plug(&plug);
-+
-+ while (true) {
-+ int delta;
-+ int swappiness;
-+ long nr_to_scan;
-+
-+ if (sc->may_swap)
-+ swappiness = get_swappiness(memcg);
-+ else if (!cgroup_reclaim(sc) && get_swappiness(memcg))
-+ swappiness = 1;
-+ else
-+ swappiness = 0;
-+
-+ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
-+ if (!nr_to_scan)
-+ break;
-+
-+ delta = evict_pages(lruvec, sc, swappiness);
-+ if (!delta)
-+ break;
-+
-+ scanned += delta;
-+ if (scanned >= nr_to_scan)
-+ break;
-+
-+ cond_resched();
-+ }
-+
-+ blk_finish_plug(&plug);
-+
-+ if (current_is_kswapd())
-+ current->reclaim_state->mm_walk_args = NULL;
-+}
-+
-+/******************************************************************************
- * state change
- ******************************************************************************/
-
-@@ -4355,6 +4896,10 @@ static void lru_gen_age_node(struct pgli
- {
- }
-
-+static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-+{
-+}
-+
- #endif /* CONFIG_LRU_GEN */
-
- static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-@@ -4368,6 +4913,11 @@ static void shrink_lruvec(struct lruvec
- bool proportional_reclaim;
- struct blk_plug plug;
-
-+ if (lru_gen_enabled()) {
-+ lru_gen_shrink_lruvec(lruvec, sc);
-+ return;
-+ }
-+
- get_scan_count(lruvec, sc, nr);
-
- /* Record the original scan target for proportional adjustments later */
-@@ -4839,6 +5389,9 @@ static void snapshot_refaults(struct mem
- struct lruvec *target_lruvec;
- unsigned long refaults;
-
-+ if (lru_gen_enabled())
-+ return;
-+
- target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
- refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
- target_lruvec->refaults[0] = refaults;
---- a/mm/workingset.c
-+++ b/mm/workingset.c
-@@ -187,7 +187,6 @@ static unsigned int bucket_order __read_
- static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction,
- bool workingset)
- {
-- eviction >>= bucket_order;
- eviction &= EVICTION_MASK;
- eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
- eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
-@@ -212,10 +211,117 @@ static void unpack_shadow(void *shadow,
-
- *memcgidp = memcgid;
- *pgdat = NODE_DATA(nid);
-- *evictionp = entry << bucket_order;
-+ *evictionp = entry;
- *workingsetp = workingset;
- }
-
-+#ifdef CONFIG_LRU_GEN
-+
-+static int page_lru_refs(struct page *page)
-+{
-+ unsigned long flags = READ_ONCE(page->flags);
-+
-+ BUILD_BUG_ON(LRU_GEN_WIDTH + LRU_REFS_WIDTH > BITS_PER_LONG - EVICTION_SHIFT);
-+
-+ /* see the comment on MAX_NR_TIERS */
-+ return flags & BIT(PG_workingset) ? (flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF : 0;
-+}
-+
-+/* Return a token to be stored in the shadow entry of a page being evicted. */
-+static void *lru_gen_eviction(struct page *page)
-+{
-+ int hist, tier;
-+ unsigned long token;
-+ unsigned long min_seq;
-+ struct lruvec *lruvec;
-+ struct lrugen *lrugen;
-+ int type = page_is_file_lru(page);
-+ int refs = page_lru_refs(page);
-+ int delta = thp_nr_pages(page);
-+ bool workingset = PageWorkingset(page);
-+ struct mem_cgroup *memcg = page_memcg(page);
-+ struct pglist_data *pgdat = page_pgdat(page);
-+
-+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
-+ lrugen = &lruvec->evictable;
-+ min_seq = READ_ONCE(lrugen->min_seq[type]);
-+ token = (min_seq << LRU_REFS_WIDTH) | refs;
-+
-+ hist = lru_hist_from_seq(min_seq);
-+ tier = lru_tier_from_refs(refs + workingset);
-+ atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);
-+
-+ return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset);
-+}
-+
-+/* Count a refaulted page based on the token stored in its shadow entry. */
-+static void lru_gen_refault(struct page *page, void *shadow)
-+{
-+ int hist, tier, refs;
-+ int memcg_id;
-+ bool workingset;
-+ unsigned long token;
-+ unsigned long min_seq;
-+ struct lruvec *lruvec;
-+ struct lrugen *lrugen;
-+ struct mem_cgroup *memcg;
-+ struct pglist_data *pgdat;
-+ int type = page_is_file_lru(page);
-+ int delta = thp_nr_pages(page);
-+
-+ unpack_shadow(shadow, &memcg_id, &pgdat, &token, &workingset);
-+ if (page_pgdat(page) != pgdat)
-+ return;
-+
-+ rcu_read_lock();
-+ memcg = page_memcg_rcu(page);
-+ if (mem_cgroup_id(memcg) != memcg_id)
-+ goto unlock;
-+
-+ refs = token & (BIT(LRU_REFS_WIDTH) - 1);
-+ if (refs && !workingset)
-+ goto unlock;
-+
-+ token >>= LRU_REFS_WIDTH;
-+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
-+ lrugen = &lruvec->evictable;
-+ min_seq = READ_ONCE(lrugen->min_seq[type]);
-+ if (token != (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH)))
-+ goto unlock;
-+
-+ hist = lru_hist_from_seq(min_seq);
-+ tier = lru_tier_from_refs(refs + workingset);
-+ atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
-+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + type, delta);
-+
-+ /*
-+ * Tiers don't offer any protection to pages accessed via page tables.
-+ * That's what generations do. Tiers can't fully protect pages after
-+ * their numbers of accesses has exceeded the max value. Conservatively
-+ * count these two conditions as stalls even though they might not
-+ * indicate any real memory pressure.
-+ */
-+ if (task_in_nonseq_fault() || refs + workingset == BIT(LRU_REFS_WIDTH)) {
-+ SetPageWorkingset(page);
-+ mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
-+ }
-+unlock:
-+ rcu_read_unlock();
-+}
-+
-+#else
-+
-+static void *lru_gen_eviction(struct page *page)
-+{
-+ return NULL;
-+}
-+
-+static void lru_gen_refault(struct page *page, void *shadow)
-+{
-+}
-+
-+#endif /* CONFIG_LRU_GEN */
-+
- /**
- * workingset_age_nonresident - age non-resident entries as LRU ages
- * @lruvec: the lruvec that was aged
-@@ -264,10 +370,14 @@ void *workingset_eviction(struct page *p
- VM_BUG_ON_PAGE(page_count(page), page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
-
-+ if (lru_gen_enabled())
-+ return lru_gen_eviction(page);
-+
- lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
- /* XXX: target_memcg can be NULL, go through lruvec */
- memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
- eviction = atomic_long_read(&lruvec->nonresident_age);
-+ eviction >>= bucket_order;
- workingset_age_nonresident(lruvec, thp_nr_pages(page));
- return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
- }
-@@ -296,7 +406,13 @@ void workingset_refault(struct page *pag
- bool workingset;
- int memcgid;
-
-+ if (lru_gen_enabled()) {
-+ lru_gen_refault(page, shadow);
-+ return;
-+ }
-+
- unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
-+ eviction <<= bucket_order;
-
- rcu_read_lock();
- /*
--- /dev/null
+From 05223c4e80b34e29f2255c04ffebc2c4475e7593 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:05 -0600
+Subject: [PATCH 08/29] mm: multi-gen LRU: support page table walks
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+To further exploit spatial locality, the aging prefers to walk page tables
+to search for young PTEs and promote hot pages. A kill switch will be
+added in the next patch to disable this behavior. When disabled, the
+aging relies on the rmap only.
+
+NB: this behavior has nothing similar with the page table scanning in the
+2.4 kernel [1], which searches page tables for old PTEs, adds cold pages
+to swapcache and unmaps them.
+
+To avoid confusion, the term "iteration" specifically means the traversal
+of an entire mm_struct list; the term "walk" will be applied to page
+tables and the rmap, as usual.
+
+An mm_struct list is maintained for each memcg, and an mm_struct follows
+its owner task to the new memcg when this task is migrated. Given an
+lruvec, the aging iterates lruvec_memcg()->mm_list and calls
+walk_page_range() with each mm_struct on this list to promote hot pages
+before it increments max_seq.
+
+When multiple page table walkers iterate the same list, each of them gets
+a unique mm_struct; therefore they can run concurrently. Page table
+walkers ignore any misplaced pages, e.g., if an mm_struct was migrated,
+pages it left in the previous memcg will not be promoted when its current
+memcg is under reclaim. Similarly, page table walkers will not promote
+pages from nodes other than the one under reclaim.
+
+This patch uses the following optimizations when walking page tables:
+1. It tracks the usage of mm_struct's between context switches so that
+ page table walkers can skip processes that have been sleeping since
+ the last iteration.
+2. It uses generational Bloom filters to record populated branches so
+ that page table walkers can reduce their search space based on the
+ query results, e.g., to skip page tables containing mostly holes or
+ misplaced pages.
+3. It takes advantage of the accessed bit in non-leaf PMD entries when
+ CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y.
+4. It does not zigzag between a PGD table and the same PMD table
+ spanning multiple VMAs. IOW, it finishes all the VMAs within the
+ range of the same PMD table before it returns to a PGD table. This
+ improves the cache performance for workloads that have large
+ numbers of tiny VMAs [2], especially when CONFIG_PGTABLE_LEVELS=5.
+
+Server benchmark results:
+ Single workload:
+ fio (buffered I/O): no change
+
+ Single workload:
+ memcached (anon): +[8, 10]%
+ Ops/sec KB/sec
+ patch1-7: 1147696.57 44640.29
+ patch1-8: 1245274.91 48435.66
+
+ Configurations:
+ no change
+
+Client benchmark results:
+ kswapd profiles:
+ patch1-7
+ 48.16% lzo1x_1_do_compress (real work)
+ 8.20% page_vma_mapped_walk (overhead)
+ 7.06% _raw_spin_unlock_irq
+ 2.92% ptep_clear_flush
+ 2.53% __zram_bvec_write
+ 2.11% do_raw_spin_lock
+ 2.02% memmove
+ 1.93% lru_gen_look_around
+ 1.56% free_unref_page_list
+ 1.40% memset
+
+ patch1-8
+ 49.44% lzo1x_1_do_compress (real work)
+ 6.19% page_vma_mapped_walk (overhead)
+ 5.97% _raw_spin_unlock_irq
+ 3.13% get_pfn_page
+ 2.85% ptep_clear_flush
+ 2.42% __zram_bvec_write
+ 2.08% do_raw_spin_lock
+ 1.92% memmove
+ 1.44% alloc_zspage
+ 1.36% memset
+
+ Configurations:
+ no change
+
+Thanks to the following developers for their efforts [3].
+ kernel test robot <lkp@intel.com>
+
+[1] https://lwn.net/Articles/23732/
+[2] https://llvm.org/docs/ScudoHardenedAllocator.html
+[3] https://lore.kernel.org/r/202204160827.ekEARWQo-lkp@intel.com/
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-9-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ fs/exec.c | 2 +
+ include/linux/memcontrol.h | 5 +
+ include/linux/mm_types.h | 76 +++
+ include/linux/mmzone.h | 56 +-
+ include/linux/swap.h | 4 +
+ kernel/exit.c | 1 +
+ kernel/fork.c | 9 +
+ kernel/sched/core.c | 1 +
+ mm/memcontrol.c | 25 +
+ mm/vmscan.c | 1010 +++++++++++++++++++++++++++++++++++-
+ 10 files changed, 1172 insertions(+), 17 deletions(-)
+
+diff --git a/fs/exec.c b/fs/exec.c
+index 881390b44cfd..1afa15a07d26 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -1013,6 +1013,7 @@ static int exec_mmap(struct mm_struct *mm)
+ active_mm = tsk->active_mm;
+ tsk->active_mm = mm;
+ tsk->mm = mm;
++ lru_gen_add_mm(mm);
+ /*
+ * This prevents preemption while active_mm is being loaded and
+ * it and mm are being updated, which could cause problems for
+@@ -1028,6 +1029,7 @@ static int exec_mmap(struct mm_struct *mm)
+ tsk->mm->vmacache_seqnum = 0;
+ vmacache_flush(tsk);
+ task_unlock(tsk);
++ lru_gen_use_mm(mm);
+ if (old_mm) {
+ mmap_read_unlock(old_mm);
+ BUG_ON(active_mm != old_mm);
+diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
+index 8d6a0329bc59..3736405cbcf6 100644
+--- a/include/linux/memcontrol.h
++++ b/include/linux/memcontrol.h
+@@ -348,6 +348,11 @@ struct mem_cgroup {
+ struct deferred_split deferred_split_queue;
+ #endif
+
++#ifdef CONFIG_LRU_GEN
++ /* per-memcg mm_struct list */
++ struct lru_gen_mm_list mm_list;
++#endif
++
+ struct mem_cgroup_per_node *nodeinfo[];
+ };
+
+diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
+index 7f8ee09c711f..33c142d31261 100644
+--- a/include/linux/mm_types.h
++++ b/include/linux/mm_types.h
+@@ -580,6 +580,22 @@ struct mm_struct {
+ #ifdef CONFIG_IOMMU_SUPPORT
+ u32 pasid;
+ #endif
++#ifdef CONFIG_LRU_GEN
++ struct {
++ /* this mm_struct is on lru_gen_mm_list */
++ struct list_head list;
++ /*
++ * Set when switching to this mm_struct, as a hint of
++ * whether it has been used since the last time per-node
++ * page table walkers cleared the corresponding bits.
++ */
++ unsigned long bitmap;
++#ifdef CONFIG_MEMCG
++ /* points to the memcg of "owner" above */
++ struct mem_cgroup *memcg;
++#endif
++ } lru_gen;
++#endif /* CONFIG_LRU_GEN */
+ } __randomize_layout;
+
+ /*
+@@ -606,6 +622,66 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
+ return (struct cpumask *)&mm->cpu_bitmap;
+ }
+
++#ifdef CONFIG_LRU_GEN
++
++struct lru_gen_mm_list {
++ /* mm_struct list for page table walkers */
++ struct list_head fifo;
++ /* protects the list above */
++ spinlock_t lock;
++};
++
++void lru_gen_add_mm(struct mm_struct *mm);
++void lru_gen_del_mm(struct mm_struct *mm);
++#ifdef CONFIG_MEMCG
++void lru_gen_migrate_mm(struct mm_struct *mm);
++#endif
++
++static inline void lru_gen_init_mm(struct mm_struct *mm)
++{
++ INIT_LIST_HEAD(&mm->lru_gen.list);
++ mm->lru_gen.bitmap = 0;
++#ifdef CONFIG_MEMCG
++ mm->lru_gen.memcg = NULL;
++#endif
++}
++
++static inline void lru_gen_use_mm(struct mm_struct *mm)
++{
++ /*
++ * When the bitmap is set, page reclaim knows this mm_struct has been
++ * used since the last time it cleared the bitmap. So it might be worth
++ * walking the page tables of this mm_struct to clear the accessed bit.
++ */
++ WRITE_ONCE(mm->lru_gen.bitmap, -1);
++}
++
++#else /* !CONFIG_LRU_GEN */
++
++static inline void lru_gen_add_mm(struct mm_struct *mm)
++{
++}
++
++static inline void lru_gen_del_mm(struct mm_struct *mm)
++{
++}
++
++#ifdef CONFIG_MEMCG
++static inline void lru_gen_migrate_mm(struct mm_struct *mm)
++{
++}
++#endif
++
++static inline void lru_gen_init_mm(struct mm_struct *mm)
++{
++}
++
++static inline void lru_gen_use_mm(struct mm_struct *mm)
++{
++}
++
++#endif /* CONFIG_LRU_GEN */
++
+ struct mmu_gather;
+ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
+ extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 4db2b877fcf9..659bab633bdf 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -385,7 +385,7 @@ enum {
+ * min_seq behind.
+ *
+ * The number of pages in each generation is eventually consistent and therefore
+- * can be transiently negative.
++ * can be transiently negative when reset_batch_size() is pending.
+ */
+ struct lru_gen_struct {
+ /* the aging increments the youngest generation number */
+@@ -407,6 +407,53 @@ struct lru_gen_struct {
+ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+ };
+
++enum {
++ MM_LEAF_TOTAL, /* total leaf entries */
++ MM_LEAF_OLD, /* old leaf entries */
++ MM_LEAF_YOUNG, /* young leaf entries */
++ MM_NONLEAF_TOTAL, /* total non-leaf entries */
++ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */
++ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */
++ NR_MM_STATS
++};
++
++/* double-buffering Bloom filters */
++#define NR_BLOOM_FILTERS 2
++
++struct lru_gen_mm_state {
++ /* set to max_seq after each iteration */
++ unsigned long seq;
++ /* where the current iteration continues (inclusive) */
++ struct list_head *head;
++ /* where the last iteration ended (exclusive) */
++ struct list_head *tail;
++ /* to wait for the last page table walker to finish */
++ struct wait_queue_head wait;
++ /* Bloom filters flip after each iteration */
++ unsigned long *filters[NR_BLOOM_FILTERS];
++ /* the mm stats for debugging */
++ unsigned long stats[NR_HIST_GENS][NR_MM_STATS];
++ /* the number of concurrent page table walkers */
++ int nr_walkers;
++};
++
++struct lru_gen_mm_walk {
++ /* the lruvec under reclaim */
++ struct lruvec *lruvec;
++ /* unstable max_seq from lru_gen_struct */
++ unsigned long max_seq;
++ /* the next address within an mm to scan */
++ unsigned long next_addr;
++ /* to batch promoted pages */
++ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
++ /* to batch the mm stats */
++ int mm_stats[NR_MM_STATS];
++ /* total batched items */
++ int batched;
++ bool can_swap;
++ bool force_scan;
++};
++
+ void lru_gen_init_lruvec(struct lruvec *lruvec);
+ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+
+@@ -457,6 +504,8 @@ struct lruvec {
+ #ifdef CONFIG_LRU_GEN
+ /* evictable pages divided into generations */
+ struct lru_gen_struct lrugen;
++ /* to concurrently iterate lru_gen_mm_list */
++ struct lru_gen_mm_state mm_state;
+ #endif
+ #ifdef CONFIG_MEMCG
+ struct pglist_data *pgdat;
+@@ -1042,6 +1091,11 @@ typedef struct pglist_data {
+
+ unsigned long flags;
+
++#ifdef CONFIG_LRU_GEN
++ /* kswap mm walk data */
++ struct lru_gen_mm_walk mm_walk;
++#endif
++
+ ZONE_PADDING(_pad2_)
+
+ /* Per-node vmstats */
+diff --git a/include/linux/swap.h b/include/linux/swap.h
+index 4efd267e2937..e970fca4f178 100644
+--- a/include/linux/swap.h
++++ b/include/linux/swap.h
+@@ -137,6 +137,10 @@ union swap_header {
+ */
+ struct reclaim_state {
+ unsigned long reclaimed_slab;
++#ifdef CONFIG_LRU_GEN
++ /* per-thread mm walk data */
++ struct lru_gen_mm_walk *mm_walk;
++#endif
+ };
+
+ #ifdef __KERNEL__
+diff --git a/kernel/exit.c b/kernel/exit.c
+index 80efdfda6662..06b477395012 100644
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -469,6 +469,7 @@ void mm_update_next_owner(struct mm_struct *mm)
+ goto retry;
+ }
+ WRITE_ONCE(mm->owner, c);
++ lru_gen_migrate_mm(mm);
+ task_unlock(c);
+ put_task_struct(c);
+ }
+diff --git a/kernel/fork.c b/kernel/fork.c
+index 68eab6ce3085..d8f37ecdde87 100644
+--- a/kernel/fork.c
++++ b/kernel/fork.c
+@@ -1083,6 +1083,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
+ goto fail_nocontext;
+
+ mm->user_ns = get_user_ns(user_ns);
++ lru_gen_init_mm(mm);
+ return mm;
+
+ fail_nocontext:
+@@ -1125,6 +1126,7 @@ static inline void __mmput(struct mm_struct *mm)
+ }
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
++ lru_gen_del_mm(mm);
+ mmdrop(mm);
+ }
+
+@@ -2622,6 +2624,13 @@ pid_t kernel_clone(struct kernel_clone_args *args)
+ get_task_struct(p);
+ }
+
++ if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
++ /* lock the task to synchronize with memcg migration */
++ task_lock(p);
++ lru_gen_add_mm(p->mm);
++ task_unlock(p);
++ }
++
+ wake_up_new_task(p);
+
+ /* forking complete and child started to run, tell ptracer */
+diff --git a/kernel/sched/core.c b/kernel/sched/core.c
+index c1458fa8beb3..fe4d60474d4a 100644
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -5007,6 +5007,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
+ * finish_task_switch()'s mmdrop().
+ */
+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
++ lru_gen_use_mm(next->mm);
+
+ if (!prev->mm) { // from kernel
+ /* will mmdrop() in finish_task_switch(). */
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index cc3431c5d9ba..ed87d1256f0e 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -6212,6 +6212,30 @@ static void mem_cgroup_move_task(void)
+ }
+ #endif
+
++#ifdef CONFIG_LRU_GEN
++static void mem_cgroup_attach(struct cgroup_taskset *tset)
++{
++ struct task_struct *task;
++ struct cgroup_subsys_state *css;
++
++ /* find the first leader if there is any */
++ cgroup_taskset_for_each_leader(task, css, tset)
++ break;
++
++ if (!task)
++ return;
++
++ task_lock(task);
++ if (task->mm && READ_ONCE(task->mm->owner) == task)
++ lru_gen_migrate_mm(task->mm);
++ task_unlock(task);
++}
++#else
++static void mem_cgroup_attach(struct cgroup_taskset *tset)
++{
++}
++#endif /* CONFIG_LRU_GEN */
++
+ static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
+ {
+ if (value == PAGE_COUNTER_MAX)
+@@ -6555,6 +6579,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
+ .css_reset = mem_cgroup_css_reset,
+ .css_rstat_flush = mem_cgroup_css_rstat_flush,
+ .can_attach = mem_cgroup_can_attach,
++ .attach = mem_cgroup_attach,
+ .cancel_attach = mem_cgroup_cancel_attach,
+ .post_attach = mem_cgroup_move_task,
+ .dfl_cftypes = memory_files,
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 1d0b25ae378c..a7844c689522 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -50,6 +50,8 @@
+ #include <linux/printk.h>
+ #include <linux/dax.h>
+ #include <linux/psi.h>
++#include <linux/pagewalk.h>
++#include <linux/shmem_fs.h>
+
+ #include <asm/tlbflush.h>
+ #include <asm/div64.h>
+@@ -2853,7 +2855,7 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
+ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
+ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
+
+-static struct lruvec __maybe_unused *get_lruvec(struct mem_cgroup *memcg, int nid)
++static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
+ {
+ struct pglist_data *pgdat = NODE_DATA(nid);
+
+@@ -2898,6 +2900,371 @@ static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
+ get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
+ }
+
++/******************************************************************************
++ * mm_struct list
++ ******************************************************************************/
++
++static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
++{
++ static struct lru_gen_mm_list mm_list = {
++ .fifo = LIST_HEAD_INIT(mm_list.fifo),
++ .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock),
++ };
++
++#ifdef CONFIG_MEMCG
++ if (memcg)
++ return &memcg->mm_list;
++#endif
++ VM_WARN_ON_ONCE(!mem_cgroup_disabled());
++
++ return &mm_list;
++}
++
++void lru_gen_add_mm(struct mm_struct *mm)
++{
++ int nid;
++ struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
++ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
++
++ VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list));
++#ifdef CONFIG_MEMCG
++ VM_WARN_ON_ONCE(mm->lru_gen.memcg);
++ mm->lru_gen.memcg = memcg;
++#endif
++ spin_lock(&mm_list->lock);
++
++ for_each_node_state(nid, N_MEMORY) {
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ if (!lruvec)
++ continue;
++
++ /* the first addition since the last iteration */
++ if (lruvec->mm_state.tail == &mm_list->fifo)
++ lruvec->mm_state.tail = &mm->lru_gen.list;
++ }
++
++ list_add_tail(&mm->lru_gen.list, &mm_list->fifo);
++
++ spin_unlock(&mm_list->lock);
++}
++
++void lru_gen_del_mm(struct mm_struct *mm)
++{
++ int nid;
++ struct lru_gen_mm_list *mm_list;
++ struct mem_cgroup *memcg = NULL;
++
++ if (list_empty(&mm->lru_gen.list))
++ return;
++
++#ifdef CONFIG_MEMCG
++ memcg = mm->lru_gen.memcg;
++#endif
++ mm_list = get_mm_list(memcg);
++
++ spin_lock(&mm_list->lock);
++
++ for_each_node(nid) {
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ if (!lruvec)
++ continue;
++
++ /* where the last iteration ended (exclusive) */
++ if (lruvec->mm_state.tail == &mm->lru_gen.list)
++ lruvec->mm_state.tail = lruvec->mm_state.tail->next;
++
++ /* where the current iteration continues (inclusive) */
++ if (lruvec->mm_state.head != &mm->lru_gen.list)
++ continue;
++
++ lruvec->mm_state.head = lruvec->mm_state.head->next;
++ /* the deletion ends the current iteration */
++ if (lruvec->mm_state.head == &mm_list->fifo)
++ WRITE_ONCE(lruvec->mm_state.seq, lruvec->mm_state.seq + 1);
++ }
++
++ list_del_init(&mm->lru_gen.list);
++
++ spin_unlock(&mm_list->lock);
++
++#ifdef CONFIG_MEMCG
++ mem_cgroup_put(mm->lru_gen.memcg);
++ mm->lru_gen.memcg = NULL;
++#endif
++}
++
++#ifdef CONFIG_MEMCG
++void lru_gen_migrate_mm(struct mm_struct *mm)
++{
++ struct mem_cgroup *memcg;
++ struct task_struct *task = rcu_dereference_protected(mm->owner, true);
++
++ VM_WARN_ON_ONCE(task->mm != mm);
++ lockdep_assert_held(&task->alloc_lock);
++
++ /* for mm_update_next_owner() */
++ if (mem_cgroup_disabled())
++ return;
++
++ rcu_read_lock();
++ memcg = mem_cgroup_from_task(task);
++ rcu_read_unlock();
++ if (memcg == mm->lru_gen.memcg)
++ return;
++
++ VM_WARN_ON_ONCE(!mm->lru_gen.memcg);
++ VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));
++
++ lru_gen_del_mm(mm);
++ lru_gen_add_mm(mm);
++}
++#endif
++
++/*
++ * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when
++ * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of
++ * bits in a bitmap, k is the number of hash functions and n is the number of
++ * inserted items.
++ *
++ * Page table walkers use one of the two filters to reduce their search space.
++ * To get rid of non-leaf entries that no longer have enough leaf entries, the
++ * aging uses the double-buffering technique to flip to the other filter each
++ * time it produces a new generation. For non-leaf entries that have enough
++ * leaf entries, the aging carries them over to the next generation in
++ * walk_pmd_range(); the eviction also report them when walking the rmap
++ * in lru_gen_look_around().
++ *
++ * For future optimizations:
++ * 1. It's not necessary to keep both filters all the time. The spare one can be
++ * freed after the RCU grace period and reallocated if needed again.
++ * 2. And when reallocating, it's worth scaling its size according to the number
++ * of inserted entries in the other filter, to reduce the memory overhead on
++ * small systems and false positives on large systems.
++ * 3. Jenkins' hash function is an alternative to Knuth's.
++ */
++#define BLOOM_FILTER_SHIFT 15
++
++static inline int filter_gen_from_seq(unsigned long seq)
++{
++ return seq % NR_BLOOM_FILTERS;
++}
++
++static void get_item_key(void *item, int *key)
++{
++ u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2);
++
++ BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32));
++
++ key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1);
++ key[1] = hash >> BLOOM_FILTER_SHIFT;
++}
++
++static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
++{
++ unsigned long *filter;
++ int gen = filter_gen_from_seq(seq);
++
++ filter = lruvec->mm_state.filters[gen];
++ if (filter) {
++ bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
++ return;
++ }
++
++ filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT),
++ __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
++ WRITE_ONCE(lruvec->mm_state.filters[gen], filter);
++}
++
++static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
++{
++ int key[2];
++ unsigned long *filter;
++ int gen = filter_gen_from_seq(seq);
++
++ filter = READ_ONCE(lruvec->mm_state.filters[gen]);
++ if (!filter)
++ return;
++
++ get_item_key(item, key);
++
++ if (!test_bit(key[0], filter))
++ set_bit(key[0], filter);
++ if (!test_bit(key[1], filter))
++ set_bit(key[1], filter);
++}
++
++static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
++{
++ int key[2];
++ unsigned long *filter;
++ int gen = filter_gen_from_seq(seq);
++
++ filter = READ_ONCE(lruvec->mm_state.filters[gen]);
++ if (!filter)
++ return true;
++
++ get_item_key(item, key);
++
++ return test_bit(key[0], filter) && test_bit(key[1], filter);
++}
++
++static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last)
++{
++ int i;
++ int hist;
++
++ lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
++
++ if (walk) {
++ hist = lru_hist_from_seq(walk->max_seq);
++
++ for (i = 0; i < NR_MM_STATS; i++) {
++ WRITE_ONCE(lruvec->mm_state.stats[hist][i],
++ lruvec->mm_state.stats[hist][i] + walk->mm_stats[i]);
++ walk->mm_stats[i] = 0;
++ }
++ }
++
++ if (NR_HIST_GENS > 1 && last) {
++ hist = lru_hist_from_seq(lruvec->mm_state.seq + 1);
++
++ for (i = 0; i < NR_MM_STATS; i++)
++ WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0);
++ }
++}
++
++static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk)
++{
++ int type;
++ unsigned long size = 0;
++ struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
++ int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
++
++ if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
++ return true;
++
++ clear_bit(key, &mm->lru_gen.bitmap);
++
++ for (type = !walk->can_swap; type < ANON_AND_FILE; type++) {
++ size += type ? get_mm_counter(mm, MM_FILEPAGES) :
++ get_mm_counter(mm, MM_ANONPAGES) +
++ get_mm_counter(mm, MM_SHMEMPAGES);
++ }
++
++ if (size < MIN_LRU_BATCH)
++ return true;
++
++ return !mmget_not_zero(mm);
++}
++
++static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
++ struct mm_struct **iter)
++{
++ bool first = false;
++ bool last = true;
++ struct mm_struct *mm = NULL;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
++ struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
++
++ /*
++ * There are four interesting cases for this page table walker:
++ * 1. It tries to start a new iteration of mm_list with a stale max_seq;
++ * there is nothing left to do.
++ * 2. It's the first of the current generation, and it needs to reset
++ * the Bloom filter for the next generation.
++ * 3. It reaches the end of mm_list, and it needs to increment
++ * mm_state->seq; the iteration is done.
++ * 4. It's the last of the current generation, and it needs to reset the
++ * mm stats counters for the next generation.
++ */
++ spin_lock(&mm_list->lock);
++
++ VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq);
++ VM_WARN_ON_ONCE(*iter && mm_state->seq > walk->max_seq);
++ VM_WARN_ON_ONCE(*iter && !mm_state->nr_walkers);
++
++ if (walk->max_seq <= mm_state->seq) {
++ if (!*iter)
++ last = false;
++ goto done;
++ }
++
++ if (!mm_state->nr_walkers) {
++ VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo);
++
++ mm_state->head = mm_list->fifo.next;
++ first = true;
++ }
++
++ while (!mm && mm_state->head != &mm_list->fifo) {
++ mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
++
++ mm_state->head = mm_state->head->next;
++
++ /* force scan for those added after the last iteration */
++ if (!mm_state->tail || mm_state->tail == &mm->lru_gen.list) {
++ mm_state->tail = mm_state->head;
++ walk->force_scan = true;
++ }
++
++ if (should_skip_mm(mm, walk))
++ mm = NULL;
++ }
++
++ if (mm_state->head == &mm_list->fifo)
++ WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
++done:
++ if (*iter && !mm)
++ mm_state->nr_walkers--;
++ if (!*iter && mm)
++ mm_state->nr_walkers++;
++
++ if (mm_state->nr_walkers)
++ last = false;
++
++ if (*iter || last)
++ reset_mm_stats(lruvec, walk, last);
++
++ spin_unlock(&mm_list->lock);
++
++ if (mm && first)
++ reset_bloom_filter(lruvec, walk->max_seq + 1);
++
++ if (*iter)
++ mmput_async(*iter);
++
++ *iter = mm;
++
++ return last;
++}
++
++static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq)
++{
++ bool success = false;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
++ struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
++
++ spin_lock(&mm_list->lock);
++
++ VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq);
++
++ if (max_seq > mm_state->seq && !mm_state->nr_walkers) {
++ VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo);
++
++ WRITE_ONCE(mm_state->seq, mm_state->seq + 1);
++ reset_mm_stats(lruvec, NULL, true);
++ success = true;
++ }
++
++ spin_unlock(&mm_list->lock);
++
++ return success;
++}
++
+ /******************************************************************************
+ * refault feedback loop
+ ******************************************************************************/
+@@ -3048,6 +3415,118 @@ static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaimin
+ return new_gen;
+ }
+
++static void update_batch_size(struct lru_gen_mm_walk *walk, struct page *page,
++ int old_gen, int new_gen)
++{
++ int type = page_is_file_lru(page);
++ int zone = page_zonenum(page);
++ int delta = thp_nr_pages(page);
++
++ VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS);
++ VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS);
++
++ walk->batched++;
++
++ walk->nr_pages[old_gen][type][zone] -= delta;
++ walk->nr_pages[new_gen][type][zone] += delta;
++}
++
++static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk)
++{
++ int gen, type, zone;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ walk->batched = 0;
++
++ for_each_gen_type_zone(gen, type, zone) {
++ enum lru_list lru = type * LRU_INACTIVE_FILE;
++ int delta = walk->nr_pages[gen][type][zone];
++
++ if (!delta)
++ continue;
++
++ walk->nr_pages[gen][type][zone] = 0;
++ WRITE_ONCE(lrugen->nr_pages[gen][type][zone],
++ lrugen->nr_pages[gen][type][zone] + delta);
++
++ if (lru_gen_is_active(lruvec, gen))
++ lru += LRU_ACTIVE;
++ __update_lru_size(lruvec, lru, zone, delta);
++ }
++}
++
++static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args)
++{
++ struct address_space *mapping;
++ struct vm_area_struct *vma = args->vma;
++ struct lru_gen_mm_walk *walk = args->private;
++
++ if (!vma_is_accessible(vma))
++ return true;
++
++ if (is_vm_hugetlb_page(vma))
++ return true;
++
++ if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ))
++ return true;
++
++ if (vma == get_gate_vma(vma->vm_mm))
++ return true;
++
++ if (vma_is_anonymous(vma))
++ return !walk->can_swap;
++
++ if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
++ return true;
++
++ mapping = vma->vm_file->f_mapping;
++ if (mapping_unevictable(mapping))
++ return true;
++
++ if (shmem_mapping(mapping))
++ return !walk->can_swap;
++
++ /* to exclude special mappings like dax, etc. */
++ return !mapping->a_ops->readpage;
++}
++
++/*
++ * Some userspace memory allocators map many single-page VMAs. Instead of
++ * returning back to the PGD table for each of such VMAs, finish an entire PMD
++ * table to reduce zigzags and improve cache performance.
++ */
++static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args,
++ unsigned long *vm_start, unsigned long *vm_end)
++{
++ unsigned long start = round_up(*vm_end, size);
++ unsigned long end = (start | ~mask) + 1;
++
++ VM_WARN_ON_ONCE(mask & size);
++ VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask));
++
++ while (args->vma) {
++ if (start >= args->vma->vm_end) {
++ args->vma = args->vma->vm_next;
++ continue;
++ }
++
++ if (end && end <= args->vma->vm_start)
++ return false;
++
++ if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) {
++ args->vma = args->vma->vm_next;
++ continue;
++ }
++
++ *vm_start = max(start, args->vma->vm_start);
++ *vm_end = min(end - 1, args->vma->vm_end - 1) + 1;
++
++ return true;
++ }
++
++ return false;
++}
++
+ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
+ {
+ unsigned long pfn = pte_pfn(pte);
+@@ -3066,8 +3545,28 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
+ return pfn;
+ }
+
++#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
++static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
++{
++ unsigned long pfn = pmd_pfn(pmd);
++
++ VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end);
++
++ if (!pmd_present(pmd) || is_huge_zero_pmd(pmd))
++ return -1;
++
++ if (WARN_ON_ONCE(pmd_devmap(pmd)))
++ return -1;
++
++ if (WARN_ON_ONCE(!pfn_valid(pfn)))
++ return -1;
++
++ return pfn;
++}
++#endif
++
+ static struct page *get_pfn_page(unsigned long pfn, struct mem_cgroup *memcg,
+- struct pglist_data *pgdat)
++ struct pglist_data *pgdat, bool can_swap)
+ {
+ struct page *page;
+
+@@ -3082,9 +3581,375 @@ static struct page *get_pfn_page(unsigned long pfn, struct mem_cgroup *memcg,
+ if (page_memcg_rcu(page) != memcg)
+ return NULL;
+
++ /* file VMAs can contain anon pages from COW */
++ if (!page_is_file_lru(page) && !can_swap)
++ return NULL;
++
+ return page;
+ }
+
++static bool suitable_to_scan(int total, int young)
++{
++ int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8);
++
++ /* suitable if the average number of young PTEs per cacheline is >=1 */
++ return young * n >= total;
++}
++
++static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
++ struct mm_walk *args)
++{
++ int i;
++ pte_t *pte;
++ spinlock_t *ptl;
++ unsigned long addr;
++ int total = 0;
++ int young = 0;
++ struct lru_gen_mm_walk *walk = args->private;
++ struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
++ struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
++ int old_gen, new_gen = lru_gen_from_seq(walk->max_seq);
++
++ VM_WARN_ON_ONCE(pmd_leaf(*pmd));
++
++ ptl = pte_lockptr(args->mm, pmd);
++ if (!spin_trylock(ptl))
++ return false;
++
++ arch_enter_lazy_mmu_mode();
++
++ pte = pte_offset_map(pmd, start & PMD_MASK);
++restart:
++ for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) {
++ unsigned long pfn;
++ struct page *page;
++
++ total++;
++ walk->mm_stats[MM_LEAF_TOTAL]++;
++
++ pfn = get_pte_pfn(pte[i], args->vma, addr);
++ if (pfn == -1)
++ continue;
++
++ if (!pte_young(pte[i])) {
++ walk->mm_stats[MM_LEAF_OLD]++;
++ continue;
++ }
++
++ page = get_pfn_page(pfn, memcg, pgdat, walk->can_swap);
++ if (!page)
++ continue;
++
++ if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
++ VM_WARN_ON_ONCE(true);
++
++ young++;
++ walk->mm_stats[MM_LEAF_YOUNG]++;
++
++ if (pte_dirty(pte[i]) && !PageDirty(page) &&
++ !(PageAnon(page) && PageSwapBacked(page) &&
++ !PageSwapCache(page)))
++ set_page_dirty(page);
++
++ old_gen = page_update_gen(page, new_gen);
++ if (old_gen >= 0 && old_gen != new_gen)
++ update_batch_size(walk, page, old_gen, new_gen);
++ }
++
++ if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end))
++ goto restart;
++
++ pte_unmap(pte);
++
++ arch_leave_lazy_mmu_mode();
++ spin_unlock(ptl);
++
++ return suitable_to_scan(total, young);
++}
++
++#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
++static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma,
++ struct mm_walk *args, unsigned long *bitmap, unsigned long *start)
++{
++ int i;
++ pmd_t *pmd;
++ spinlock_t *ptl;
++ struct lru_gen_mm_walk *walk = args->private;
++ struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
++ struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
++ int old_gen, new_gen = lru_gen_from_seq(walk->max_seq);
++
++ VM_WARN_ON_ONCE(pud_leaf(*pud));
++
++ /* try to batch at most 1+MIN_LRU_BATCH+1 entries */
++ if (*start == -1) {
++ *start = next;
++ return;
++ }
++
++ i = next == -1 ? 0 : pmd_index(next) - pmd_index(*start);
++ if (i && i <= MIN_LRU_BATCH) {
++ __set_bit(i - 1, bitmap);
++ return;
++ }
++
++ pmd = pmd_offset(pud, *start);
++
++ ptl = pmd_lockptr(args->mm, pmd);
++ if (!spin_trylock(ptl))
++ goto done;
++
++ arch_enter_lazy_mmu_mode();
++
++ do {
++ unsigned long pfn;
++ struct page *page;
++ unsigned long addr = i ? (*start & PMD_MASK) + i * PMD_SIZE : *start;
++
++ pfn = get_pmd_pfn(pmd[i], vma, addr);
++ if (pfn == -1)
++ goto next;
++
++ if (!pmd_trans_huge(pmd[i])) {
++ if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG))
++ pmdp_test_and_clear_young(vma, addr, pmd + i);
++ goto next;
++ }
++
++ page = get_pfn_page(pfn, memcg, pgdat, walk->can_swap);
++ if (!page)
++ goto next;
++
++ if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
++ goto next;
++
++ walk->mm_stats[MM_LEAF_YOUNG]++;
++
++ if (pmd_dirty(pmd[i]) && !PageDirty(page) &&
++ !(PageAnon(page) && PageSwapBacked(page) &&
++ !PageSwapCache(page)))
++ set_page_dirty(page);
++
++ old_gen = page_update_gen(page, new_gen);
++ if (old_gen >= 0 && old_gen != new_gen)
++ update_batch_size(walk, page, old_gen, new_gen);
++next:
++ i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1;
++ } while (i <= MIN_LRU_BATCH);
++
++ arch_leave_lazy_mmu_mode();
++ spin_unlock(ptl);
++done:
++ *start = -1;
++ bitmap_zero(bitmap, MIN_LRU_BATCH);
++}
++#else
++static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area_struct *vma,
++ struct mm_walk *args, unsigned long *bitmap, unsigned long *start)
++{
++}
++#endif
++
++static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
++ struct mm_walk *args)
++{
++ int i;
++ pmd_t *pmd;
++ unsigned long next;
++ unsigned long addr;
++ struct vm_area_struct *vma;
++ unsigned long pos = -1;
++ struct lru_gen_mm_walk *walk = args->private;
++ unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {};
++
++ VM_WARN_ON_ONCE(pud_leaf(*pud));
++
++ /*
++ * Finish an entire PMD in two passes: the first only reaches to PTE
++ * tables to avoid taking the PMD lock; the second, if necessary, takes
++ * the PMD lock to clear the accessed bit in PMD entries.
++ */
++ pmd = pmd_offset(pud, start & PUD_MASK);
++restart:
++ /* walk_pte_range() may call get_next_vma() */
++ vma = args->vma;
++ for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) {
++ pmd_t val = pmd_read_atomic(pmd + i);
++
++ /* for pmd_read_atomic() */
++ barrier();
++
++ next = pmd_addr_end(addr, end);
++
++ if (!pmd_present(val) || is_huge_zero_pmd(val)) {
++ walk->mm_stats[MM_LEAF_TOTAL]++;
++ continue;
++ }
++
++#ifdef CONFIG_TRANSPARENT_HUGEPAGE
++ if (pmd_trans_huge(val)) {
++ unsigned long pfn = pmd_pfn(val);
++ struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
++
++ walk->mm_stats[MM_LEAF_TOTAL]++;
++
++ if (!pmd_young(val)) {
++ walk->mm_stats[MM_LEAF_OLD]++;
++ continue;
++ }
++
++ /* try to avoid unnecessary memory loads */
++ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
++ continue;
++
++ walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
++ continue;
++ }
++#endif
++ walk->mm_stats[MM_NONLEAF_TOTAL]++;
++
++#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
++ if (!pmd_young(val))
++ continue;
++
++ walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
++#endif
++ if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
++ continue;
++
++ walk->mm_stats[MM_NONLEAF_FOUND]++;
++
++ if (!walk_pte_range(&val, addr, next, args))
++ continue;
++
++ walk->mm_stats[MM_NONLEAF_ADDED]++;
++
++ /* carry over to the next generation */
++ update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i);
++ }
++
++ walk_pmd_range_locked(pud, -1, vma, args, bitmap, &pos);
++
++ if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end))
++ goto restart;
++}
++
++static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end,
++ struct mm_walk *args)
++{
++ int i;
++ pud_t *pud;
++ unsigned long addr;
++ unsigned long next;
++ struct lru_gen_mm_walk *walk = args->private;
++
++ VM_WARN_ON_ONCE(p4d_leaf(*p4d));
++
++ pud = pud_offset(p4d, start & P4D_MASK);
++restart:
++ for (i = pud_index(start), addr = start; addr != end; i++, addr = next) {
++ pud_t val = READ_ONCE(pud[i]);
++
++ next = pud_addr_end(addr, end);
++
++ if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val)))
++ continue;
++
++ walk_pmd_range(&val, addr, next, args);
++
++ /* a racy check to curtail the waiting time */
++ if (wq_has_sleeper(&walk->lruvec->mm_state.wait))
++ return 1;
++
++ if (need_resched() || walk->batched >= MAX_LRU_BATCH) {
++ end = (addr | ~PUD_MASK) + 1;
++ goto done;
++ }
++ }
++
++ if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end))
++ goto restart;
++
++ end = round_up(end, P4D_SIZE);
++done:
++ if (!end || !args->vma)
++ return 1;
++
++ walk->next_addr = max(end, args->vma->vm_start);
++
++ return -EAGAIN;
++}
++
++static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_mm_walk *walk)
++{
++ static const struct mm_walk_ops mm_walk_ops = {
++ .test_walk = should_skip_vma,
++ .p4d_entry = walk_pud_range,
++ };
++
++ int err;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++
++ walk->next_addr = FIRST_USER_ADDRESS;
++
++ do {
++ err = -EBUSY;
++
++ /* page_update_gen() requires stable page_memcg() */
++ if (!mem_cgroup_trylock_pages(memcg))
++ break;
++
++ /* the caller might be holding the lock for write */
++ if (mmap_read_trylock(mm)) {
++ err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk);
++
++ mmap_read_unlock(mm);
++ }
++
++ mem_cgroup_unlock_pages();
++
++ if (walk->batched) {
++ spin_lock_irq(&lruvec->lru_lock);
++ reset_batch_size(lruvec, walk);
++ spin_unlock_irq(&lruvec->lru_lock);
++ }
++
++ cond_resched();
++ } while (err == -EAGAIN);
++}
++
++static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat)
++{
++ struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
++
++ if (pgdat && current_is_kswapd()) {
++ VM_WARN_ON_ONCE(walk);
++
++ walk = &pgdat->mm_walk;
++ } else if (!pgdat && !walk) {
++ VM_WARN_ON_ONCE(current_is_kswapd());
++
++ walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
++ }
++
++ current->reclaim_state->mm_walk = walk;
++
++ return walk;
++}
++
++static void clear_mm_walk(void)
++{
++ struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
++
++ VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages)));
++ VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats)));
++
++ current->reclaim_state->mm_walk = NULL;
++
++ if (!current_is_kswapd())
++ kfree(walk);
++}
++
+ static void inc_min_seq(struct lruvec *lruvec, int type)
+ {
+ struct lru_gen_struct *lrugen = &lruvec->lrugen;
+@@ -3136,7 +4001,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+ return success;
+ }
+
+-static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_swap)
++static void inc_max_seq(struct lruvec *lruvec, bool can_swap)
+ {
+ int prev, next;
+ int type, zone;
+@@ -3146,9 +4011,6 @@ static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_s
+
+ VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
+
+- if (max_seq != lrugen->max_seq)
+- goto unlock;
+-
+ for (type = ANON_AND_FILE - 1; type >= 0; type--) {
+ if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
+ continue;
+@@ -3186,10 +4048,76 @@ static void inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_s
+
+ /* make sure preceding modifications appear */
+ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
+-unlock:
++
+ spin_unlock_irq(&lruvec->lru_lock);
+ }
+
++static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
++ struct scan_control *sc, bool can_swap)
++{
++ bool success;
++ struct lru_gen_mm_walk *walk;
++ struct mm_struct *mm = NULL;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq));
++
++ /* see the comment in iterate_mm_list() */
++ if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) {
++ success = false;
++ goto done;
++ }
++
++ /*
++ * If the hardware doesn't automatically set the accessed bit, fallback
++ * to lru_gen_look_around(), which only clears the accessed bit in a
++ * handful of PTEs. Spreading the work out over a period of time usually
++ * is less efficient, but it avoids bursty page faults.
++ */
++ if (!arch_has_hw_pte_young()) {
++ success = iterate_mm_list_nowalk(lruvec, max_seq);
++ goto done;
++ }
++
++ walk = set_mm_walk(NULL);
++ if (!walk) {
++ success = iterate_mm_list_nowalk(lruvec, max_seq);
++ goto done;
++ }
++
++ walk->lruvec = lruvec;
++ walk->max_seq = max_seq;
++ walk->can_swap = can_swap;
++ walk->force_scan = false;
++
++ do {
++ success = iterate_mm_list(lruvec, walk, &mm);
++ if (mm)
++ walk_mm(lruvec, mm, walk);
++
++ cond_resched();
++ } while (mm);
++done:
++ if (!success) {
++ if (sc->priority <= DEF_PRIORITY - 2)
++ wait_event_killable(lruvec->mm_state.wait,
++ max_seq < READ_ONCE(lrugen->max_seq));
++
++ return max_seq < READ_ONCE(lrugen->max_seq);
++ }
++
++ VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq));
++
++ inc_max_seq(lruvec, can_swap);
++ /* either this sees any waiters or they will see updated max_seq */
++ if (wq_has_sleeper(&lruvec->mm_state.wait))
++ wake_up_all(&lruvec->mm_state.wait);
++
++ wakeup_flusher_threads(WB_REASON_VMSCAN);
++
++ return true;
++}
++
+ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq,
+ struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
+ {
+@@ -3265,7 +4193,7 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+
+ need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
+ if (need_aging)
+- inc_max_seq(lruvec, max_seq, swappiness);
++ try_to_inc_max_seq(lruvec, max_seq, sc, swappiness);
+ }
+
+ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+@@ -3274,6 +4202,8 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
++ set_mm_walk(pgdat);
++
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+@@ -3282,11 +4212,16 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
++
++ clear_mm_walk();
+ }
+
+ /*
+ * This function exploits spatial locality when shrink_page_list() walks the
+- * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages.
++ * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If
++ * the scan was done cacheline efficiently, it adds the PMD entry pointing to
++ * the PTE table to the Bloom filter. This forms a feedback loop between the
++ * eviction and the aging.
+ */
+ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ {
+@@ -3295,6 +4230,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ unsigned long start;
+ unsigned long end;
+ unsigned long addr;
++ struct lru_gen_mm_walk *walk;
++ int young = 0;
+ unsigned long bitmap[BITS_TO_LONGS(MIN_LRU_BATCH)] = {};
+ struct page *page = pvmw->page;
+ struct mem_cgroup *memcg = page_memcg(page);
+@@ -3309,6 +4246,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ if (spin_is_contended(pvmw->ptl))
+ return;
+
++ /* avoid taking the LRU lock under the PTL when possible */
++ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
++
+ start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start);
+ end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
+
+@@ -3338,13 +4278,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ if (!pte_young(pte[i]))
+ continue;
+
+- page = get_pfn_page(pfn, memcg, pgdat);
++ page = get_pfn_page(pfn, memcg, pgdat, !walk || walk->can_swap);
+ if (!page)
+ continue;
+
+ if (!ptep_test_and_clear_young(pvmw->vma, addr, pte + i))
+ VM_WARN_ON_ONCE(true);
+
++ young++;
++
+ if (pte_dirty(pte[i]) && !PageDirty(page) &&
+ !(PageAnon(page) && PageSwapBacked(page) &&
+ !PageSwapCache(page)))
+@@ -3360,7 +4302,11 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ arch_leave_lazy_mmu_mode();
+ rcu_read_unlock();
+
+- if (bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) {
++ /* feedback from rmap walkers to page table walkers */
++ if (suitable_to_scan(i, young))
++ update_bloom_filter(lruvec, max_seq, pvmw->pmd);
++
++ if (!walk && bitmap_weight(bitmap, MIN_LRU_BATCH) < PAGEVEC_SIZE) {
+ for_each_set_bit(i, bitmap, MIN_LRU_BATCH) {
+ page = pte_page(pte[i]);
+ activate_page(page);
+@@ -3372,8 +4318,10 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ if (!mem_cgroup_trylock_pages(memcg))
+ return;
+
+- spin_lock_irq(&lruvec->lru_lock);
+- new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq);
++ if (!walk) {
++ spin_lock_irq(&lruvec->lru_lock);
++ new_gen = lru_gen_from_seq(lruvec->lrugen.max_seq);
++ }
+
+ for_each_set_bit(i, bitmap, MIN_LRU_BATCH) {
+ page = compound_head(pte_page(pte[i]));
+@@ -3384,10 +4332,14 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ if (old_gen < 0 || old_gen == new_gen)
+ continue;
+
+- lru_gen_update_size(lruvec, page, old_gen, new_gen);
++ if (walk)
++ update_batch_size(walk, page, old_gen, new_gen);
++ else
++ lru_gen_update_size(lruvec, page, old_gen, new_gen);
+ }
+
+- spin_unlock_irq(&lruvec->lru_lock);
++ if (!walk)
++ spin_unlock_irq(&lruvec->lru_lock);
+
+ mem_cgroup_unlock_pages();
+ }
+@@ -3670,6 +4622,7 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ struct page *page;
+ enum vm_event_item item;
+ struct reclaim_stat stat;
++ struct lru_gen_mm_walk *walk;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+@@ -3706,6 +4659,10 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+
+ move_pages_to_lru(lruvec, &list);
+
++ walk = current->reclaim_state->mm_walk;
++ if (walk && walk->batched)
++ reset_batch_size(lruvec, walk);
++
+ item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+ if (!cgroup_reclaim(sc))
+ __count_vm_events(item, reclaimed);
+@@ -3722,6 +4679,11 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ return scanned;
+ }
+
++/*
++ * For future optimizations:
++ * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
++ * reclaim.
++ */
+ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+ bool can_swap)
+ {
+@@ -3747,7 +4709,8 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ if (current_is_kswapd())
+ return 0;
+
+- inc_max_seq(lruvec, max_seq, can_swap);
++ if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap))
++ return nr_to_scan;
+ done:
+ return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+ }
+@@ -3761,6 +4724,8 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+
+ blk_start_plug(&plug);
+
++ set_mm_walk(lruvec_pgdat(lruvec));
++
+ while (true) {
+ int delta;
+ int swappiness;
+@@ -3788,6 +4753,8 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ cond_resched();
+ }
+
++ clear_mm_walk();
++
+ blk_finish_plug(&plug);
+ }
+
+@@ -3804,15 +4771,21 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
+
+ for_each_gen_type_zone(gen, type, zone)
+ INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
++
++ lruvec->mm_state.seq = MIN_NR_GENS;
++ init_waitqueue_head(&lruvec->mm_state.wait);
+ }
+
+ #ifdef CONFIG_MEMCG
+ void lru_gen_init_memcg(struct mem_cgroup *memcg)
+ {
++ INIT_LIST_HEAD(&memcg->mm_list.fifo);
++ spin_lock_init(&memcg->mm_list.lock);
+ }
+
+ void lru_gen_exit_memcg(struct mem_cgroup *memcg)
+ {
++ int i;
+ int nid;
+
+ for_each_node(nid) {
+@@ -3820,6 +4793,11 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg)
+
+ VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0,
+ sizeof(lruvec->lrugen.nr_pages)));
++
++ for (i = 0; i < NR_BLOOM_FILTERS; i++) {
++ bitmap_free(lruvec->mm_state.filters[i]);
++ lruvec->mm_state.filters[i] = NULL;
++ }
+ }
+ }
+ #endif
+--
+2.40.0
+
+++ /dev/null
-From 5cc7fdec54e87e32b4fb0f07d84b21769d5f8d92 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Mon, 25 Jan 2021 21:38:02 -0700
-Subject: [PATCH 08/10] mm: multigenerational lru: user interface
-
-Add /sys/kernel/mm/lru_gen/enabled to enable and disable the
-multigenerational lru at runtime.
-
-Add /sys/kernel/mm/lru_gen/min_ttl_ms to protect the working set of a
-given number of milliseconds. The OOM killer is invoked if this
-working set cannot be kept in memory.
-
-Add /sys/kernel/debug/lru_gen to monitor the multigenerational lru and
-invoke the aging and the eviction. This file has the following output:
- memcg memcg_id memcg_path
- node node_id
- min_gen birth_time anon_size file_size
- ...
- max_gen birth_time anon_size file_size
-
-min_gen is the oldest generation number and max_gen is the youngest
-generation number. birth_time is in milliseconds. anon_size and
-file_size are in pages.
-
-This file takes the following input:
- + memcg_id node_id max_gen [swappiness] [use_bloom_filter]
- - memcg_id node_id min_gen [swappiness] [nr_to_reclaim]
-
-The first command line invokes the aging, which scans PTEs for
-accessed pages and then creates the next generation max_gen+1. A swap
-file and a non-zero swappiness, which overrides vm.swappiness, are
-required to scan PTEs mapping anon pages. The second command line
-invokes the eviction, which evicts generations less than or equal to
-min_gen. min_gen should be less than max_gen-1 as max_gen and
-max_gen-1 are not fully aged and therefore cannot be evicted.
-Setting nr_to_reclaim to N limits the number of pages to evict.
-Setting use_bloom_filter to 0 overrides the default behavior which
-only scans PTE tables found populated. Multiple command lines are
-supported, as is concatenation with delimiters "," and ";".
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I4448e60029badbe347aa3b624f429b280cc3a3d3
----
- include/linux/nodemask.h | 1 +
- mm/vmscan.c | 415 +++++++++++++++++++++++++++++++++++++++
- 2 files changed, 416 insertions(+)
-
---- a/include/linux/nodemask.h
-+++ b/include/linux/nodemask.h
-@@ -485,6 +485,7 @@ static inline int num_node_state(enum no
- #define first_online_node 0
- #define first_memory_node 0
- #define next_online_node(nid) (MAX_NUMNODES)
-+#define next_memory_node(nid) (MAX_NUMNODES)
- #define nr_node_ids 1U
- #define nr_online_nodes 1U
-
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -53,6 +53,8 @@
- #include <linux/memory.h>
- #include <linux/pagewalk.h>
- #include <linux/shmem_fs.h>
-+#include <linux/ctype.h>
-+#include <linux/debugfs.h>
-
- #include <asm/tlbflush.h>
- #include <asm/div64.h>
-@@ -4817,6 +4819,413 @@ unlock:
- }
-
- /******************************************************************************
-+ * sysfs interface
-+ ******************************************************************************/
-+
-+static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
-+{
-+ return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
-+}
-+
-+static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
-+ const char *buf, size_t len)
-+{
-+ unsigned int msecs;
-+
-+ if (kstrtouint(buf, 10, &msecs))
-+ return -EINVAL;
-+
-+ WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs));
-+
-+ return len;
-+}
-+
-+static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
-+ min_ttl_ms, 0644, show_min_ttl, store_min_ttl
-+);
-+
-+static ssize_t show_enable(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
-+{
-+ return snprintf(buf, PAGE_SIZE, "%d\n", lru_gen_enabled());
-+}
-+
-+static ssize_t store_enable(struct kobject *kobj, struct kobj_attribute *attr,
-+ const char *buf, size_t len)
-+{
-+ bool enable;
-+
-+ if (kstrtobool(buf, &enable))
-+ return -EINVAL;
-+
-+ lru_gen_change_state(enable, true, false);
-+
-+ return len;
-+}
-+
-+static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
-+ enabled, 0644, show_enable, store_enable
-+);
-+
-+static struct attribute *lru_gen_attrs[] = {
-+ &lru_gen_min_ttl_attr.attr,
-+ &lru_gen_enabled_attr.attr,
-+ NULL
-+};
-+
-+static struct attribute_group lru_gen_attr_group = {
-+ .name = "lru_gen",
-+ .attrs = lru_gen_attrs,
-+};
-+
-+/******************************************************************************
-+ * debugfs interface
-+ ******************************************************************************/
-+
-+static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos)
-+{
-+ struct mem_cgroup *memcg;
-+ loff_t nr_to_skip = *pos;
-+
-+ m->private = kvmalloc(PATH_MAX, GFP_KERNEL);
-+ if (!m->private)
-+ return ERR_PTR(-ENOMEM);
-+
-+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
-+ do {
-+ int nid;
-+
-+ for_each_node_state(nid, N_MEMORY) {
-+ if (!nr_to_skip--)
-+ return get_lruvec(nid, memcg);
-+ }
-+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
-+
-+ return NULL;
-+}
-+
-+static void lru_gen_seq_stop(struct seq_file *m, void *v)
-+{
-+ if (!IS_ERR_OR_NULL(v))
-+ mem_cgroup_iter_break(NULL, lruvec_memcg(v));
-+
-+ kvfree(m->private);
-+ m->private = NULL;
-+}
-+
-+static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos)
-+{
-+ int nid = lruvec_pgdat(v)->node_id;
-+ struct mem_cgroup *memcg = lruvec_memcg(v);
-+
-+ ++*pos;
-+
-+ nid = next_memory_node(nid);
-+ if (nid == MAX_NUMNODES) {
-+ memcg = mem_cgroup_iter(NULL, memcg, NULL);
-+ if (!memcg)
-+ return NULL;
-+
-+ nid = first_memory_node;
-+ }
-+
-+ return get_lruvec(nid, memcg);
-+}
-+
-+static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
-+ unsigned long max_seq, unsigned long *min_seq,
-+ unsigned long seq)
-+{
-+ int i;
-+ int type, tier;
-+ int hist = lru_hist_from_seq(seq);
-+ struct lrugen *lrugen = &lruvec->evictable;
-+
-+ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
-+ seq_printf(m, " %10d", tier);
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ unsigned long n[3] = {};
-+
-+ if (seq == max_seq) {
-+ n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
-+ n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
-+
-+ seq_printf(m, " %10luR %10luT %10lu ", n[0], n[1], n[2]);
-+ } else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
-+ n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
-+ n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
-+ if (tier)
-+ n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
-+
-+ seq_printf(m, " %10lur %10lue %10lup", n[0], n[1], n[2]);
-+ } else
-+ seq_puts(m, " 0 0 0 ");
-+ }
-+ seq_putc(m, '\n');
-+ }
-+
-+ seq_puts(m, " ");
-+ for (i = 0; i < NR_MM_STATS; i++) {
-+ if (seq == max_seq && NR_HIST_GENS == 1)
-+ seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_walk.stats[hist][i]),
-+ toupper(MM_STAT_CODES[i]));
-+ else if (seq != max_seq && NR_HIST_GENS > 1)
-+ seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_walk.stats[hist][i]),
-+ MM_STAT_CODES[i]);
-+ else
-+ seq_puts(m, " 0 ");
-+ }
-+ seq_putc(m, '\n');
-+}
-+
-+static int lru_gen_seq_show(struct seq_file *m, void *v)
-+{
-+ unsigned long seq;
-+ bool full = !debugfs_real_fops(m->file)->write;
-+ struct lruvec *lruvec = v;
-+ struct lrugen *lrugen = &lruvec->evictable;
-+ int nid = lruvec_pgdat(lruvec)->node_id;
-+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
-+ DEFINE_MAX_SEQ(lruvec);
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ if (nid == first_memory_node) {
-+ const char *path = memcg ? m->private : "";
-+
-+#ifdef CONFIG_MEMCG
-+ if (memcg)
-+ cgroup_path(memcg->css.cgroup, m->private, PATH_MAX);
-+#endif
-+ seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path);
-+ }
-+
-+ seq_printf(m, " node %5d\n", nid);
-+
-+ if (!full)
-+ seq = min_seq[0];
-+ else if (max_seq >= MAX_NR_GENS)
-+ seq = max_seq - MAX_NR_GENS + 1;
-+ else
-+ seq = 0;
-+
-+ for (; seq <= max_seq; seq++) {
-+ int gen, type, zone;
-+ unsigned int msecs;
-+
-+ gen = lru_gen_from_seq(seq);
-+ msecs = jiffies_to_msecs(jiffies - READ_ONCE(lrugen->timestamps[gen]));
-+
-+ seq_printf(m, " %10lu %10u", seq, msecs);
-+
-+ for (type = 0; type < ANON_AND_FILE; type++) {
-+ long size = 0;
-+
-+ if (seq < min_seq[type]) {
-+ seq_puts(m, " -0 ");
-+ continue;
-+ }
-+
-+ for (zone = 0; zone < MAX_NR_ZONES; zone++)
-+ size += READ_ONCE(lrugen->sizes[gen][type][zone]);
-+
-+ seq_printf(m, " %10lu ", max(size, 0L));
-+ }
-+
-+ seq_putc(m, '\n');
-+
-+ if (full)
-+ lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq);
-+ }
-+
-+ return 0;
-+}
-+
-+static const struct seq_operations lru_gen_seq_ops = {
-+ .start = lru_gen_seq_start,
-+ .stop = lru_gen_seq_stop,
-+ .next = lru_gen_seq_next,
-+ .show = lru_gen_seq_show,
-+};
-+
-+static int run_aging(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-+ unsigned long seq, bool use_filter)
-+{
-+ DEFINE_MAX_SEQ(lruvec);
-+
-+ if (seq == max_seq)
-+ try_to_inc_max_seq(lruvec, sc, swappiness, max_seq, use_filter);
-+
-+ return seq > max_seq ? -EINVAL : 0;
-+}
-+
-+static int run_eviction(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
-+ unsigned long seq, unsigned long nr_to_reclaim)
-+{
-+ struct blk_plug plug;
-+ int err = -EINTR;
-+ DEFINE_MAX_SEQ(lruvec);
-+
-+ if (seq >= max_seq - 1)
-+ return -EINVAL;
-+
-+ sc->nr_reclaimed = 0;
-+
-+ blk_start_plug(&plug);
-+
-+ while (!signal_pending(current)) {
-+ DEFINE_MIN_SEQ(lruvec);
-+
-+ if (seq < min_seq[!swappiness] || sc->nr_reclaimed >= nr_to_reclaim ||
-+ !evict_pages(lruvec, sc, swappiness)) {
-+ err = 0;
-+ break;
-+ }
-+
-+ cond_resched();
-+ }
-+
-+ blk_finish_plug(&plug);
-+
-+ return err;
-+}
-+
-+static int run_cmd(char cmd, int memcg_id, int nid, struct scan_control *sc,
-+ int swappiness, unsigned long seq, unsigned long opt)
-+{
-+ struct lruvec *lruvec;
-+ int err = -EINVAL;
-+ struct mem_cgroup *memcg = NULL;
-+
-+ if (!mem_cgroup_disabled()) {
-+ rcu_read_lock();
-+ memcg = mem_cgroup_from_id(memcg_id);
-+#ifdef CONFIG_MEMCG
-+ if (memcg && !css_tryget(&memcg->css))
-+ memcg = NULL;
-+#endif
-+ rcu_read_unlock();
-+
-+ if (!memcg)
-+ goto done;
-+ }
-+ if (memcg_id != mem_cgroup_id(memcg))
-+ goto done;
-+
-+ if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY))
-+ goto done;
-+
-+ lruvec = get_lruvec(nid, memcg);
-+
-+ if (swappiness < 0)
-+ swappiness = get_swappiness(memcg);
-+ else if (swappiness > 200)
-+ goto done;
-+
-+ switch (cmd) {
-+ case '+':
-+ err = run_aging(lruvec, sc, swappiness, seq, opt);
-+ break;
-+ case '-':
-+ err = run_eviction(lruvec, sc, swappiness, seq, opt);
-+ break;
-+ }
-+done:
-+ mem_cgroup_put(memcg);
-+
-+ return err;
-+}
-+
-+static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
-+ size_t len, loff_t *pos)
-+{
-+ void *buf;
-+ char *cur, *next;
-+ unsigned int flags;
-+ int err = 0;
-+ struct scan_control sc = {
-+ .may_writepage = 1,
-+ .may_unmap = 1,
-+ .may_swap = 1,
-+ .reclaim_idx = MAX_NR_ZONES - 1,
-+ .gfp_mask = GFP_KERNEL,
-+ };
-+
-+ buf = kvmalloc(len + 1, GFP_KERNEL);
-+ if (!buf)
-+ return -ENOMEM;
-+
-+ if (copy_from_user(buf, src, len)) {
-+ kvfree(buf);
-+ return -EFAULT;
-+ }
-+
-+ next = buf;
-+ next[len] = '\0';
-+
-+ sc.reclaim_state.mm_walk_args = alloc_mm_walk_args();
-+ if (!sc.reclaim_state.mm_walk_args) {
-+ kvfree(buf);
-+ return -ENOMEM;
-+ }
-+
-+ flags = memalloc_noreclaim_save();
-+ set_task_reclaim_state(current, &sc.reclaim_state);
-+
-+ while ((cur = strsep(&next, ",;\n"))) {
-+ int n;
-+ int end;
-+ char cmd;
-+ unsigned int memcg_id;
-+ unsigned int nid;
-+ unsigned long seq;
-+ unsigned int swappiness = -1;
-+ unsigned long opt = -1;
-+
-+ cur = skip_spaces(cur);
-+ if (!*cur)
-+ continue;
-+
-+ n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid,
-+ &seq, &end, &swappiness, &end, &opt, &end);
-+ if (n < 4 || cur[end]) {
-+ err = -EINVAL;
-+ break;
-+ }
-+
-+ err = run_cmd(cmd, memcg_id, nid, &sc, swappiness, seq, opt);
-+ if (err)
-+ break;
-+ }
-+
-+ set_task_reclaim_state(current, NULL);
-+ memalloc_noreclaim_restore(flags);
-+
-+ free_mm_walk_args(sc.reclaim_state.mm_walk_args);
-+ kvfree(buf);
-+
-+ return err ? : len;
-+}
-+
-+static int lru_gen_seq_open(struct inode *inode, struct file *file)
-+{
-+ return seq_open(file, &lru_gen_seq_ops);
-+}
-+
-+static const struct file_operations lru_gen_rw_fops = {
-+ .open = lru_gen_seq_open,
-+ .read = seq_read,
-+ .write = lru_gen_seq_write,
-+ .llseek = seq_lseek,
-+ .release = seq_release,
-+};
-+
-+static const struct file_operations lru_gen_ro_fops = {
-+ .open = lru_gen_seq_open,
-+ .read = seq_read,
-+ .llseek = seq_lseek,
-+ .release = seq_release,
-+};
-+
-+/******************************************************************************
- * initialization
- ******************************************************************************/
-
-@@ -4886,6 +5295,12 @@ static int __init init_lru_gen(void)
- BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
- BUILD_BUG_ON(sizeof(MM_STAT_CODES) != NR_MM_STATS + 1);
-
-+ if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
-+ pr_err("lru_gen: failed to create sysfs group\n");
-+
-+ debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops);
-+ debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops);
-+
- return 0;
- };
- late_initcall(init_lru_gen);
--- /dev/null
+From 36a18a68ea458e8f4db2ca86b00091daf32c6c74 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:06 -0600
+Subject: [PATCH 09/29] mm: multi-gen LRU: optimize multiple memcgs
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+When multiple memcgs are available, it is possible to use generations as a
+frame of reference to make better choices and improve overall performance
+under global memory pressure. This patch adds a basic optimization to
+select memcgs that can drop single-use unmapped clean pages first. Doing
+so reduces the chance of going into the aging path or swapping, which can
+be costly.
+
+A typical example that benefits from this optimization is a server running
+mixed types of workloads, e.g., heavy anon workload in one memcg and heavy
+buffered I/O workload in the other.
+
+Though this optimization can be applied to both kswapd and direct reclaim,
+it is only added to kswapd to keep the patchset manageable. Later
+improvements may cover the direct reclaim path.
+
+While ensuring certain fairness to all eligible memcgs, proportional scans
+of individual memcgs also require proper backoff to avoid overshooting
+their aggregate reclaim target by too much. Otherwise it can cause high
+direct reclaim latency. The conditions for backoff are:
+
+1. At low priorities, for direct reclaim, if aging fairness or direct
+ reclaim latency is at risk, i.e., aging one memcg multiple times or
+ swapping after the target is met.
+2. At high priorities, for global reclaim, if per-zone free pages are
+ above respective watermarks.
+
+Server benchmark results:
+ Mixed workloads:
+ fio (buffered I/O): +[19, 21]%
+ IOPS BW
+ patch1-8: 1880k 7343MiB/s
+ patch1-9: 2252k 8796MiB/s
+
+ memcached (anon): +[119, 123]%
+ Ops/sec KB/sec
+ patch1-8: 862768.65 33514.68
+ patch1-9: 1911022.12 74234.54
+
+ Mixed workloads:
+ fio (buffered I/O): +[75, 77]%
+ IOPS BW
+ 5.19-rc1: 1279k 4996MiB/s
+ patch1-9: 2252k 8796MiB/s
+
+ memcached (anon): +[13, 15]%
+ Ops/sec KB/sec
+ 5.19-rc1: 1673524.04 65008.87
+ patch1-9: 1911022.12 74234.54
+
+ Configurations:
+ (changes since patch 6)
+
+ cat mixed.sh
+ modprobe brd rd_nr=2 rd_size=56623104
+
+ swapoff -a
+ mkswap /dev/ram0
+ swapon /dev/ram0
+
+ mkfs.ext4 /dev/ram1
+ mount -t ext4 /dev/ram1 /mnt
+
+ memtier_benchmark -S /var/run/memcached/memcached.sock \
+ -P memcache_binary -n allkeys --key-minimum=1 \
+ --key-maximum=50000000 --key-pattern=P:P -c 1 -t 36 \
+ --ratio 1:0 --pipeline 8 -d 2000
+
+ fio -name=mglru --numjobs=36 --directory=/mnt --size=1408m \
+ --buffered=1 --ioengine=io_uring --iodepth=128 \
+ --iodepth_batch_submit=32 --iodepth_batch_complete=32 \
+ --rw=randread --random_distribution=random --norandommap \
+ --time_based --ramp_time=10m --runtime=90m --group_reporting &
+ pid=$!
+
+ sleep 200
+
+ memtier_benchmark -S /var/run/memcached/memcached.sock \
+ -P memcache_binary -n allkeys --key-minimum=1 \
+ --key-maximum=50000000 --key-pattern=R:R -c 1 -t 36 \
+ --ratio 0:1 --pipeline 8 --randomize --distinct-client-seed
+
+ kill -INT $pid
+ wait
+
+Client benchmark results:
+ no change (CONFIG_MEMCG=n)
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-10-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++-----
+ 1 file changed, 96 insertions(+), 9 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index a7844c689522..b6f6fc2585e1 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -127,6 +127,12 @@ struct scan_control {
+ /* Always discard instead of demoting to lower tier memory */
+ unsigned int no_demotion:1;
+
++#ifdef CONFIG_LRU_GEN
++ /* help kswapd make better choices among multiple memcgs */
++ unsigned int memcgs_need_aging:1;
++ unsigned long last_reclaimed;
++#endif
++
+ /* Allocation order */
+ s8 order;
+
+@@ -4202,6 +4208,19 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
++ sc->last_reclaimed = sc->nr_reclaimed;
++
++ /*
++ * To reduce the chance of going into the aging path, which can be
++ * costly, optimistically skip it if the flag below was cleared in the
++ * eviction path. This improves the overall performance when multiple
++ * memcgs are available.
++ */
++ if (!sc->memcgs_need_aging) {
++ sc->memcgs_need_aging = true;
++ return;
++ }
++
+ set_mm_walk(pgdat);
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+@@ -4613,7 +4632,8 @@ static int isolate_pages(struct lruvec *lruvec, struct scan_control *sc, int swa
+ return scanned;
+ }
+
+-static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
++static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
++ bool *need_swapping)
+ {
+ int type;
+ int scanned;
+@@ -4676,6 +4696,9 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+
+ sc->nr_reclaimed += reclaimed;
+
++ if (need_swapping && type == LRU_GEN_ANON)
++ *need_swapping = true;
++
+ return scanned;
+ }
+
+@@ -4685,9 +4708,8 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ * reclaim.
+ */
+ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+- bool can_swap)
++ bool can_swap, bool *need_aging)
+ {
+- bool need_aging;
+ unsigned long nr_to_scan;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+@@ -4697,8 +4719,8 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
+ return 0;
+
+- need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
+- if (!need_aging)
++ *need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
++ if (!*need_aging)
+ return nr_to_scan;
+
+ /* skip the aging path at the default priority */
+@@ -4715,10 +4737,68 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+ }
+
++static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq,
++ struct scan_control *sc, bool need_swapping)
++{
++ int i;
++ DEFINE_MAX_SEQ(lruvec);
++
++ if (!current_is_kswapd()) {
++ /* age each memcg once to ensure fairness */
++ if (max_seq - seq > 1)
++ return true;
++
++ /* over-swapping can increase allocation latency */
++ if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping)
++ return true;
++
++ /* give this thread a chance to exit and free its memory */
++ if (fatal_signal_pending(current)) {
++ sc->nr_reclaimed += MIN_LRU_BATCH;
++ return true;
++ }
++
++ if (cgroup_reclaim(sc))
++ return false;
++ } else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim)
++ return false;
++
++ /* keep scanning at low priorities to ensure fairness */
++ if (sc->priority > DEF_PRIORITY - 2)
++ return false;
++
++ /*
++ * A minimum amount of work was done under global memory pressure. For
++ * kswapd, it may be overshooting. For direct reclaim, the target isn't
++ * met, and yet the allocation may still succeed, since kswapd may have
++ * caught up. In either case, it's better to stop now, and restart if
++ * necessary.
++ */
++ for (i = 0; i <= sc->reclaim_idx; i++) {
++ unsigned long wmark;
++ struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
++
++ if (!managed_zone(zone))
++ continue;
++
++ wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone);
++ if (wmark > zone_page_state(zone, NR_FREE_PAGES))
++ return false;
++ }
++
++ sc->nr_reclaimed += MIN_LRU_BATCH;
++
++ return true;
++}
++
+ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ struct blk_plug plug;
++ bool need_aging = false;
++ bool need_swapping = false;
+ unsigned long scanned = 0;
++ unsigned long reclaimed = sc->nr_reclaimed;
++ DEFINE_MAX_SEQ(lruvec);
+
+ lru_add_drain();
+
+@@ -4738,21 +4818,28 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ else
+ swappiness = 0;
+
+- nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
++ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness, &need_aging);
+ if (!nr_to_scan)
+- break;
++ goto done;
+
+- delta = evict_pages(lruvec, sc, swappiness);
++ delta = evict_pages(lruvec, sc, swappiness, &need_swapping);
+ if (!delta)
+- break;
++ goto done;
+
+ scanned += delta;
+ if (scanned >= nr_to_scan)
+ break;
+
++ if (should_abort_scan(lruvec, max_seq, sc, need_swapping))
++ break;
++
+ cond_resched();
+ }
+
++ /* see the comment in lru_gen_age_node() */
++ if (sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH && !need_aging)
++ sc->memcgs_need_aging = false;
++done:
+ clear_mm_walk();
+
+ blk_finish_plug(&plug);
+--
+2.40.0
+
+++ /dev/null
-From 3008095eb835d207dd7e5b60899aad17f32aa9f7 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Mon, 25 Jan 2021 21:47:24 -0700
-Subject: [PATCH 09/10] mm: multigenerational lru: Kconfig
-
-Add configuration options for the multigenerational lru.
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: Ic74ea07f8fb5f56e6904a1b80c3c286bc2911635
----
- mm/Kconfig | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
- 1 file changed, 59 insertions(+)
-
---- a/mm/Kconfig
-+++ b/mm/Kconfig
-@@ -899,4 +899,63 @@ config SECRETMEM
-
- source "mm/damon/Kconfig"
-
-+# the multigenerational lru {
-+config LRU_GEN
-+ bool "Multigenerational LRU"
-+ depends on MMU
-+ # the following options may leave not enough spare bits in page->flags
-+ depends on !MAXSMP && (64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP)
-+ help
-+ A high performance LRU implementation to heavily overcommit workloads
-+ that are not IO bound. See Documentation/vm/multigen_lru.rst for
-+ details.
-+
-+ Warning: do not enable this option unless you plan to use it because
-+ it introduces a small per-process and per-memcg and per-node memory
-+ overhead.
-+
-+config LRU_GEN_ENABLED
-+ bool "Turn on by default"
-+ depends on LRU_GEN
-+ help
-+ The default value of /sys/kernel/mm/lru_gen/enabled is 0. This option
-+ changes it to 1.
-+
-+ Warning: the default value is the fast path. See
-+ Documentation/static-keys.txt for details.
-+
-+config LRU_GEN_STATS
-+ bool "Full stats for debugging"
-+ depends on LRU_GEN
-+ help
-+ This option keeps full stats for each generation, which can be read
-+ from /sys/kernel/debug/lru_gen_full.
-+
-+ Warning: do not enable this option unless you plan to use it because
-+ it introduces an additional small per-process and per-memcg and
-+ per-node memory overhead.
-+
-+config NR_LRU_GENS
-+ int "Max number of generations"
-+ depends on LRU_GEN
-+ range 4 31
-+ default 7
-+ help
-+ This will use order_base_2(N+1) spare bits from page flags.
-+
-+ Warning: do not use numbers larger than necessary because each
-+ generation introduces a small per-node and per-memcg memory overhead.
-+
-+config TIERS_PER_GEN
-+ int "Number of tiers per generation"
-+ depends on LRU_GEN
-+ range 2 5
-+ default 4
-+ help
-+ This will use N-2 spare bits from page flags.
-+
-+ Larger values generally offer better protection to active pages under
-+ heavy buffered I/O workloads.
-+# }
-+
- endmenu
--- /dev/null
+From 640db3a029dca909af47157ca18f52b29d34a1b9 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:07 -0600
+Subject: [PATCH 10/29] mm: multi-gen LRU: kill switch
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Add /sys/kernel/mm/lru_gen/enabled as a kill switch. Components that
+can be disabled include:
+ 0x0001: the multi-gen LRU core
+ 0x0002: walking page table, when arch_has_hw_pte_young() returns
+ true
+ 0x0004: clearing the accessed bit in non-leaf PMD entries, when
+ CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y
+ [yYnN]: apply to all the components above
+E.g.,
+ echo y >/sys/kernel/mm/lru_gen/enabled
+ cat /sys/kernel/mm/lru_gen/enabled
+ 0x0007
+ echo 5 >/sys/kernel/mm/lru_gen/enabled
+ cat /sys/kernel/mm/lru_gen/enabled
+ 0x0005
+
+NB: the page table walks happen on the scale of seconds under heavy memory
+pressure, in which case the mmap_lock contention is a lesser concern,
+compared with the LRU lock contention and the I/O congestion. So far the
+only well-known case of the mmap_lock contention happens on Android, due
+to Scudo [1] which allocates several thousand VMAs for merely a few
+hundred MBs. The SPF and the Maple Tree also have provided their own
+assessments [2][3]. However, if walking page tables does worsen the
+mmap_lock contention, the kill switch can be used to disable it. In this
+case the multi-gen LRU will suffer a minor performance degradation, as
+shown previously.
+
+Clearing the accessed bit in non-leaf PMD entries can also be disabled,
+since this behavior was not tested on x86 varieties other than Intel and
+AMD.
+
+[1] https://source.android.com/devices/tech/debug/scudo
+[2] https://lore.kernel.org/r/20220128131006.67712-1-michel@lespinasse.org/
+[3] https://lore.kernel.org/r/20220426150616.3937571-1-Liam.Howlett@oracle.com/
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-11-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/cgroup.h | 15 ++-
+ include/linux/mm_inline.h | 15 ++-
+ include/linux/mmzone.h | 9 ++
+ kernel/cgroup/cgroup-internal.h | 1 -
+ mm/Kconfig | 6 +
+ mm/vmscan.c | 228 +++++++++++++++++++++++++++++++-
+ 6 files changed, 265 insertions(+), 9 deletions(-)
+
+diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
+index 45cdb12243e3..f9a5d6a81101 100644
+--- a/include/linux/cgroup.h
++++ b/include/linux/cgroup.h
+@@ -433,6 +433,18 @@ static inline void cgroup_put(struct cgroup *cgrp)
+ css_put(&cgrp->self);
+ }
+
++extern struct mutex cgroup_mutex;
++
++static inline void cgroup_lock(void)
++{
++ mutex_lock(&cgroup_mutex);
++}
++
++static inline void cgroup_unlock(void)
++{
++ mutex_unlock(&cgroup_mutex);
++}
++
+ /**
+ * task_css_set_check - obtain a task's css_set with extra access conditions
+ * @task: the task to obtain css_set for
+@@ -447,7 +459,6 @@ static inline void cgroup_put(struct cgroup *cgrp)
+ * as locks used during the cgroup_subsys::attach() methods.
+ */
+ #ifdef CONFIG_PROVE_RCU
+-extern struct mutex cgroup_mutex;
+ extern spinlock_t css_set_lock;
+ #define task_css_set_check(task, __c) \
+ rcu_dereference_check((task)->cgroups, \
+@@ -708,6 +719,8 @@ struct cgroup;
+ static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; }
+ static inline void css_get(struct cgroup_subsys_state *css) {}
+ static inline void css_put(struct cgroup_subsys_state *css) {}
++static inline void cgroup_lock(void) {}
++static inline void cgroup_unlock(void) {}
+ static inline int cgroup_attach_task_all(struct task_struct *from,
+ struct task_struct *t) { return 0; }
+ static inline int cgroupstats_build(struct cgroupstats *stats,
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 58aabb1ba020..e095c1c24311 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -91,10 +91,21 @@ static __always_inline enum lru_list page_lru(struct page *page)
+
+ #ifdef CONFIG_LRU_GEN
+
++#ifdef CONFIG_LRU_GEN_ENABLED
+ static inline bool lru_gen_enabled(void)
+ {
+- return true;
++ DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]);
++
++ return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]);
++}
++#else
++static inline bool lru_gen_enabled(void)
++{
++ DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]);
++
++ return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]);
+ }
++#endif
+
+ static inline bool lru_gen_in_fault(void)
+ {
+@@ -207,7 +218,7 @@ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bo
+
+ VM_WARN_ON_ONCE_PAGE(gen != -1, page);
+
+- if (PageUnevictable(page))
++ if (PageUnevictable(page) || !lrugen->enabled)
+ return false;
+ /*
+ * There are three common cases for this page:
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 659bab633bdf..edaf035503ed 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -364,6 +364,13 @@ enum {
+ LRU_GEN_FILE,
+ };
+
++enum {
++ LRU_GEN_CORE,
++ LRU_GEN_MM_WALK,
++ LRU_GEN_NONLEAF_YOUNG,
++ NR_LRU_GEN_CAPS
++};
++
+ #define MIN_LRU_BATCH BITS_PER_LONG
+ #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64)
+
+@@ -405,6 +412,8 @@ struct lru_gen_struct {
+ /* can be modified without holding the LRU lock */
+ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
++ /* whether the multi-gen LRU is enabled */
++ bool enabled;
+ };
+
+ enum {
+diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
+index d8fcc139ac05..28c32a01da7d 100644
+--- a/kernel/cgroup/cgroup-internal.h
++++ b/kernel/cgroup/cgroup-internal.h
+@@ -165,7 +165,6 @@ struct cgroup_mgctx {
+ #define DEFINE_CGROUP_MGCTX(name) \
+ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
+
+-extern struct mutex cgroup_mutex;
+ extern spinlock_t css_set_lock;
+ extern struct cgroup_subsys *cgroup_subsys[];
+ extern struct list_head cgroup_roots;
+diff --git a/mm/Kconfig b/mm/Kconfig
+index 62433f3cd7ae..4a7d0af3c39b 100644
+--- a/mm/Kconfig
++++ b/mm/Kconfig
+@@ -906,6 +906,12 @@ config LRU_GEN
+ help
+ A high performance LRU implementation to overcommit memory.
+
++config LRU_GEN_ENABLED
++ bool "Enable by default"
++ depends on LRU_GEN
++ help
++ This option enables the multi-gen LRU by default.
++
+ config LRU_GEN_STATS
+ bool "Full stats for debugging"
+ depends on LRU_GEN
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index b6f6fc2585e1..be37d996bc92 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -52,6 +52,7 @@
+ #include <linux/psi.h>
+ #include <linux/pagewalk.h>
+ #include <linux/shmem_fs.h>
++#include <linux/ctype.h>
+
+ #include <asm/tlbflush.h>
+ #include <asm/div64.h>
+@@ -2841,6 +2842,14 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
+
+ #ifdef CONFIG_LRU_GEN
+
++#ifdef CONFIG_LRU_GEN_ENABLED
++DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS);
++#define get_cap(cap) static_branch_likely(&lru_gen_caps[cap])
++#else
++DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
++#define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap])
++#endif
++
+ /******************************************************************************
+ * shorthand helpers
+ ******************************************************************************/
+@@ -3717,7 +3726,8 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
+ goto next;
+
+ if (!pmd_trans_huge(pmd[i])) {
+- if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG))
++ if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
++ get_cap(LRU_GEN_NONLEAF_YOUNG))
+ pmdp_test_and_clear_young(vma, addr, pmd + i);
+ goto next;
+ }
+@@ -3815,10 +3825,12 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
+ walk->mm_stats[MM_NONLEAF_TOTAL]++;
+
+ #ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+- if (!pmd_young(val))
+- continue;
++ if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
++ if (!pmd_young(val))
++ continue;
+
+- walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
++ walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
++ }
+ #endif
+ if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
+ continue;
+@@ -4080,7 +4092,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ * handful of PTEs. Spreading the work out over a period of time usually
+ * is less efficient, but it avoids bursty page faults.
+ */
+- if (!arch_has_hw_pte_young()) {
++ if (!(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) {
+ success = iterate_mm_list_nowalk(lruvec, max_seq);
+ goto done;
+ }
+@@ -4845,6 +4857,208 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ blk_finish_plug(&plug);
+ }
+
++/******************************************************************************
++ * state change
++ ******************************************************************************/
++
++static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
++{
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ if (lrugen->enabled) {
++ enum lru_list lru;
++
++ for_each_evictable_lru(lru) {
++ if (!list_empty(&lruvec->lists[lru]))
++ return false;
++ }
++ } else {
++ int gen, type, zone;
++
++ for_each_gen_type_zone(gen, type, zone) {
++ if (!list_empty(&lrugen->lists[gen][type][zone]))
++ return false;
++ }
++ }
++
++ return true;
++}
++
++static bool fill_evictable(struct lruvec *lruvec)
++{
++ enum lru_list lru;
++ int remaining = MAX_LRU_BATCH;
++
++ for_each_evictable_lru(lru) {
++ int type = is_file_lru(lru);
++ bool active = is_active_lru(lru);
++ struct list_head *head = &lruvec->lists[lru];
++
++ while (!list_empty(head)) {
++ bool success;
++ struct page *page = lru_to_page(head);
++
++ VM_WARN_ON_ONCE_PAGE(PageUnevictable(page), page);
++ VM_WARN_ON_ONCE_PAGE(PageActive(page) != active, page);
++ VM_WARN_ON_ONCE_PAGE(page_is_file_lru(page) != type, page);
++ VM_WARN_ON_ONCE_PAGE(page_lru_gen(page) != -1, page);
++
++ del_page_from_lru_list(page, lruvec);
++ success = lru_gen_add_page(lruvec, page, false);
++ VM_WARN_ON_ONCE(!success);
++
++ if (!--remaining)
++ return false;
++ }
++ }
++
++ return true;
++}
++
++static bool drain_evictable(struct lruvec *lruvec)
++{
++ int gen, type, zone;
++ int remaining = MAX_LRU_BATCH;
++
++ for_each_gen_type_zone(gen, type, zone) {
++ struct list_head *head = &lruvec->lrugen.lists[gen][type][zone];
++
++ while (!list_empty(head)) {
++ bool success;
++ struct page *page = lru_to_page(head);
++
++ VM_WARN_ON_ONCE_PAGE(PageUnevictable(page), page);
++ VM_WARN_ON_ONCE_PAGE(PageActive(page), page);
++ VM_WARN_ON_ONCE_PAGE(page_is_file_lru(page) != type, page);
++ VM_WARN_ON_ONCE_PAGE(page_zonenum(page) != zone, page);
++
++ success = lru_gen_del_page(lruvec, page, false);
++ VM_WARN_ON_ONCE(!success);
++ add_page_to_lru_list(page, lruvec);
++
++ if (!--remaining)
++ return false;
++ }
++ }
++
++ return true;
++}
++
++static void lru_gen_change_state(bool enabled)
++{
++ static DEFINE_MUTEX(state_mutex);
++
++ struct mem_cgroup *memcg;
++
++ cgroup_lock();
++ cpus_read_lock();
++ get_online_mems();
++ mutex_lock(&state_mutex);
++
++ if (enabled == lru_gen_enabled())
++ goto unlock;
++
++ if (enabled)
++ static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
++ else
++ static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
++
++ memcg = mem_cgroup_iter(NULL, NULL, NULL);
++ do {
++ int nid;
++
++ for_each_node(nid) {
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ if (!lruvec)
++ continue;
++
++ spin_lock_irq(&lruvec->lru_lock);
++
++ VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
++ VM_WARN_ON_ONCE(!state_is_valid(lruvec));
++
++ lruvec->lrugen.enabled = enabled;
++
++ while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) {
++ spin_unlock_irq(&lruvec->lru_lock);
++ cond_resched();
++ spin_lock_irq(&lruvec->lru_lock);
++ }
++
++ spin_unlock_irq(&lruvec->lru_lock);
++ }
++
++ cond_resched();
++ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
++unlock:
++ mutex_unlock(&state_mutex);
++ put_online_mems();
++ cpus_read_unlock();
++ cgroup_unlock();
++}
++
++/******************************************************************************
++ * sysfs interface
++ ******************************************************************************/
++
++static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
++{
++ unsigned int caps = 0;
++
++ if (get_cap(LRU_GEN_CORE))
++ caps |= BIT(LRU_GEN_CORE);
++
++ if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
++ caps |= BIT(LRU_GEN_MM_WALK);
++
++ if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
++ caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
++
++ return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);
++}
++
++static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr,
++ const char *buf, size_t len)
++{
++ int i;
++ unsigned int caps;
++
++ if (tolower(*buf) == 'n')
++ caps = 0;
++ else if (tolower(*buf) == 'y')
++ caps = -1;
++ else if (kstrtouint(buf, 0, &caps))
++ return -EINVAL;
++
++ for (i = 0; i < NR_LRU_GEN_CAPS; i++) {
++ bool enabled = caps & BIT(i);
++
++ if (i == LRU_GEN_CORE)
++ lru_gen_change_state(enabled);
++ else if (enabled)
++ static_branch_enable(&lru_gen_caps[i]);
++ else
++ static_branch_disable(&lru_gen_caps[i]);
++ }
++
++ return len;
++}
++
++static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
++ enabled, 0644, show_enabled, store_enabled
++);
++
++static struct attribute *lru_gen_attrs[] = {
++ &lru_gen_enabled_attr.attr,
++ NULL
++};
++
++static struct attribute_group lru_gen_attr_group = {
++ .name = "lru_gen",
++ .attrs = lru_gen_attrs,
++};
++
+ /******************************************************************************
+ * initialization
+ ******************************************************************************/
+@@ -4855,6 +5069,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
+ struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+ lrugen->max_seq = MIN_NR_GENS + 1;
++ lrugen->enabled = lru_gen_enabled();
+
+ for_each_gen_type_zone(gen, type, zone)
+ INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
+@@ -4894,6 +5109,9 @@ static int __init init_lru_gen(void)
+ BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
+ BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
+
++ if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
++ pr_err("lru_gen: failed to create sysfs group\n");
++
+ return 0;
+ };
+ late_initcall(init_lru_gen);
+--
+2.40.0
+
+++ /dev/null
-From f59c618ed70a1e48accc4cad91a200966f2569c9 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Tue, 2 Feb 2021 01:27:45 -0700
-Subject: [PATCH 10/10] mm: multigenerational lru: documentation
-
-Add Documentation/vm/multigen_lru.rst.
-
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
-Change-Id: I1902178bcbb5adfa0a748c4d284a6456059bdd7e
----
- Documentation/vm/index.rst | 1 +
- Documentation/vm/multigen_lru.rst | 132 ++++++++++++++++++++++++++++++
- 2 files changed, 133 insertions(+)
- create mode 100644 Documentation/vm/multigen_lru.rst
-
---- a/Documentation/vm/index.rst
-+++ b/Documentation/vm/index.rst
-@@ -17,6 +17,7 @@ various features of the Linux memory man
-
- swap_numa
- zswap
-+ multigen_lru
-
- Kernel developers MM documentation
- ==================================
---- /dev/null
-+++ b/Documentation/vm/multigen_lru.rst
-@@ -0,0 +1,132 @@
-+.. SPDX-License-Identifier: GPL-2.0
-+
-+=====================
-+Multigenerational LRU
-+=====================
-+
-+Quick Start
-+===========
-+Build Configurations
-+--------------------
-+:Required: Set ``CONFIG_LRU_GEN=y``.
-+
-+:Optional: Set ``CONFIG_LRU_GEN_ENABLED=y`` to turn the feature on by
-+ default.
-+
-+Runtime Configurations
-+----------------------
-+:Required: Write ``1`` to ``/sys/kernel/mm/lru_gen/enable`` if the
-+ feature was not turned on by default.
-+
-+:Optional: Write ``N`` to ``/sys/kernel/mm/lru_gen/min_ttl_ms`` to
-+ protect the working set of ``N`` milliseconds. The OOM killer is
-+ invoked if this working set cannot be kept in memory.
-+
-+:Optional: Read ``/sys/kernel/debug/lru_gen`` to confirm the feature
-+ is turned on. This file has the following output:
-+
-+::
-+
-+ memcg memcg_id memcg_path
-+ node node_id
-+ min_gen birth_time anon_size file_size
-+ ...
-+ max_gen birth_time anon_size file_size
-+
-+``min_gen`` is the oldest generation number and ``max_gen`` is the
-+youngest generation number. ``birth_time`` is in milliseconds.
-+``anon_size`` and ``file_size`` are in pages.
-+
-+Phones/Laptops/Workstations
-+---------------------------
-+No additional configurations required.
-+
-+Servers/Data Centers
-+--------------------
-+:To support more generations: Change ``CONFIG_NR_LRU_GENS`` to a
-+ larger number.
-+
-+:To support more tiers: Change ``CONFIG_TIERS_PER_GEN`` to a larger
-+ number.
-+
-+:To support full stats: Set ``CONFIG_LRU_GEN_STATS=y``.
-+
-+:Working set estimation: Write ``+ memcg_id node_id max_gen
-+ [swappiness] [use_bloom_filter]`` to ``/sys/kernel/debug/lru_gen`` to
-+ invoke the aging, which scans PTEs for accessed pages and then
-+ creates the next generation ``max_gen+1``. A swap file and a non-zero
-+ ``swappiness``, which overrides ``vm.swappiness``, are required to
-+ scan PTEs mapping anon pages. Set ``use_bloom_filter`` to 0 to
-+ override the default behavior which only scans PTE tables found
-+ populated.
-+
-+:Proactive reclaim: Write ``- memcg_id node_id min_gen [swappiness]
-+ [nr_to_reclaim]`` to ``/sys/kernel/debug/lru_gen`` to invoke the
-+ eviction, which evicts generations less than or equal to ``min_gen``.
-+ ``min_gen`` should be less than ``max_gen-1`` as ``max_gen`` and
-+ ``max_gen-1`` are not fully aged and therefore cannot be evicted.
-+ Use ``nr_to_reclaim`` to limit the number of pages to evict. Multiple
-+ command lines are supported, so does concatenation with delimiters
-+ ``,`` and ``;``.
-+
-+Framework
-+=========
-+For each ``lruvec``, evictable pages are divided into multiple
-+generations. The youngest generation number is stored in
-+``lrugen->max_seq`` for both anon and file types as they are aged on
-+an equal footing. The oldest generation numbers are stored in
-+``lrugen->min_seq[]`` separately for anon and file types as clean
-+file pages can be evicted regardless of swap and writeback
-+constraints. These three variables are monotonically increasing.
-+Generation numbers are truncated into
-+``order_base_2(CONFIG_NR_LRU_GENS+1)`` bits in order to fit into
-+``page->flags``. The sliding window technique is used to prevent
-+truncated generation numbers from overlapping. Each truncated
-+generation number is an index to an array of per-type and per-zone
-+lists ``lrugen->lists``.
-+
-+Each generation is divided into multiple tiers. Tiers represent
-+different ranges of numbers of accesses from file descriptors only.
-+Pages accessed ``N`` times via file descriptors belong to tier
-+``order_base_2(N)``. Each generation contains at most
-+``CONFIG_TIERS_PER_GEN`` tiers, and they require additional
-+``CONFIG_TIERS_PER_GEN-2`` bits in ``page->flags``. In contrast to
-+moving between generations which requires list operations, moving
-+between tiers only involves operations on ``page->flags`` and
-+therefore has a negligible cost. A feedback loop modeled after the PID
-+controller monitors refaulted % across all tiers and decides when to
-+protect pages from which tiers.
-+
-+The framework comprises two conceptually independent components: the
-+aging and the eviction, which can be invoked separately from user
-+space for the purpose of working set estimation and proactive reclaim.
-+
-+Aging
-+-----
-+The aging produces young generations. Given an ``lruvec``, the aging
-+traverses ``lruvec_memcg()->mm_list`` and calls ``walk_page_range()``
-+to scan PTEs for accessed pages (a ``mm_struct`` list is maintained
-+for each ``memcg``). Upon finding one, the aging updates its
-+generation number to ``max_seq`` (modulo ``CONFIG_NR_LRU_GENS``).
-+After each round of traversal, the aging increments ``max_seq``. The
-+aging is due when ``min_seq[]`` reaches ``max_seq-1``.
-+
-+Eviction
-+--------
-+The eviction consumes old generations. Given an ``lruvec``, the
-+eviction scans pages on the per-zone lists indexed by anon and file
-+``min_seq[]`` (modulo ``CONFIG_NR_LRU_GENS``). It first tries to
-+select a type based on the values of ``min_seq[]``. If they are
-+equal, it selects the type that has a lower refaulted %. The eviction
-+sorts a page according to its updated generation number if the aging
-+has found this page accessed. It also moves a page to the next
-+generation if this page is from an upper tier that has a higher
-+refaulted % than the base tier. The eviction increments ``min_seq[]``
-+of a selected type when it finds all the per-zone lists indexed by
-+``min_seq[]`` of this selected type are empty.
-+
-+To-do List
-+==========
-+KVM Optimization
-+----------------
-+Support shadow page table walk.
--- /dev/null
+From 73d1ff551760f0c79c47ab70faa4c2ca91413f5c Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:08 -0600
+Subject: [PATCH 11/29] mm: multi-gen LRU: thrashing prevention
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Add /sys/kernel/mm/lru_gen/min_ttl_ms for thrashing prevention, as
+requested by many desktop users [1].
+
+When set to value N, it prevents the working set of N milliseconds from
+getting evicted. The OOM killer is triggered if this working set cannot
+be kept in memory. Based on the average human detectable lag (~100ms),
+N=1000 usually eliminates intolerable lags due to thrashing. Larger
+values like N=3000 make lags less noticeable at the risk of premature OOM
+kills.
+
+Compared with the size-based approach [2], this time-based approach
+has the following advantages:
+
+1. It is easier to configure because it is agnostic to applications
+ and memory sizes.
+2. It is more reliable because it is directly wired to the OOM killer.
+
+[1] https://lore.kernel.org/r/Ydza%2FzXKY9ATRoh6@google.com/
+[2] https://lore.kernel.org/r/20101028191523.GA14972@google.com/
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-12-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Qi Zheng <zhengqi.arch@bytedance.com>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mmzone.h | 2 ++
+ mm/vmscan.c | 74 ++++++++++++++++++++++++++++++++++++++++--
+ 2 files changed, 73 insertions(+), 3 deletions(-)
+
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index edaf035503ed..6b85ba1f4e18 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -399,6 +399,8 @@ struct lru_gen_struct {
+ unsigned long max_seq;
+ /* the eviction increments the oldest generation numbers */
+ unsigned long min_seq[ANON_AND_FILE];
++ /* the birth time of each generation in jiffies */
++ unsigned long timestamps[MAX_NR_GENS];
+ /* the multi-gen LRU lists, lazily sorted on eviction */
+ struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+ /* the multi-gen LRU sizes, eventually consistent */
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index be37d996bc92..642ee7bef61d 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4064,6 +4064,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap)
+ for (type = 0; type < ANON_AND_FILE; type++)
+ reset_ctrl_pos(lruvec, type, false);
+
++ WRITE_ONCE(lrugen->timestamps[next], jiffies);
+ /* make sure preceding modifications appear */
+ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
+
+@@ -4193,7 +4194,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig
+ return false;
+ }
+
+-static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl)
+ {
+ bool need_aging;
+ unsigned long nr_to_scan;
+@@ -4207,16 +4208,36 @@ static void age_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ mem_cgroup_calculate_protection(NULL, memcg);
+
+ if (mem_cgroup_below_min(memcg))
+- return;
++ return false;
+
+ need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
++
++ if (min_ttl) {
++ int gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
++ unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
++
++ if (time_is_after_jiffies(birth + min_ttl))
++ return false;
++
++ /* the size is likely too small to be helpful */
++ if (!nr_to_scan && sc->priority != DEF_PRIORITY)
++ return false;
++ }
++
+ if (need_aging)
+ try_to_inc_max_seq(lruvec, max_seq, sc, swappiness);
++
++ return true;
+ }
+
++/* to protect the working set of the last N jiffies */
++static unsigned long lru_gen_min_ttl __read_mostly;
++
+ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ {
+ struct mem_cgroup *memcg;
++ bool success = false;
++ unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
+@@ -4239,12 +4260,32 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+- age_lruvec(lruvec, sc);
++ if (age_lruvec(lruvec, sc, min_ttl))
++ success = true;
+
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+ clear_mm_walk();
++
++ /* check the order to exclude compaction-induced reclaim */
++ if (success || !min_ttl || sc->order)
++ return;
++
++ /*
++ * The main goal is to OOM kill if every generation from all memcgs is
++ * younger than min_ttl. However, another possibility is all memcgs are
++ * either below min or empty.
++ */
++ if (mutex_trylock(&oom_lock)) {
++ struct oom_control oc = {
++ .gfp_mask = sc->gfp_mask,
++ };
++
++ out_of_memory(&oc);
++
++ mutex_unlock(&oom_lock);
++ }
+ }
+
+ /*
+@@ -5002,6 +5043,28 @@ static void lru_gen_change_state(bool enabled)
+ * sysfs interface
+ ******************************************************************************/
+
++static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
++}
++
++static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
++ const char *buf, size_t len)
++{
++ unsigned int msecs;
++
++ if (kstrtouint(buf, 0, &msecs))
++ return -EINVAL;
++
++ WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs));
++
++ return len;
++}
++
++static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
++ min_ttl_ms, 0644, show_min_ttl, store_min_ttl
++);
++
+ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+ {
+ unsigned int caps = 0;
+@@ -5050,6 +5113,7 @@ static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
+ );
+
+ static struct attribute *lru_gen_attrs[] = {
++ &lru_gen_min_ttl_attr.attr,
+ &lru_gen_enabled_attr.attr,
+ NULL
+ };
+@@ -5065,12 +5129,16 @@ static struct attribute_group lru_gen_attr_group = {
+
+ void lru_gen_init_lruvec(struct lruvec *lruvec)
+ {
++ int i;
+ int gen, type, zone;
+ struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+ lrugen->max_seq = MIN_NR_GENS + 1;
+ lrugen->enabled = lru_gen_enabled();
+
++ for (i = 0; i <= MIN_NR_GENS + 1; i++)
++ lrugen->timestamps[i] = jiffies;
++
+ for_each_gen_type_zone(gen, type, zone)
+ INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
+
+--
+2.40.0
+
--- /dev/null
+From 530716d008ca26315f246cd70dc1cefc636beaa4 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 18 Sep 2022 02:00:09 -0600
+Subject: [PATCH 12/29] mm: multi-gen LRU: debugfs interface
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Add /sys/kernel/debug/lru_gen for working set estimation and proactive
+reclaim. These techniques are commonly used to optimize job scheduling
+(bin packing) in data centers [1][2].
+
+Compared with the page table-based approach and the PFN-based
+approach, this lruvec-based approach has the following advantages:
+1. It offers better choices because it is aware of memcgs, NUMA nodes,
+ shared mappings and unmapped page cache.
+2. It is more scalable because it is O(nr_hot_pages), whereas the
+ PFN-based approach is O(nr_total_pages).
+
+Add /sys/kernel/debug/lru_gen_full for debugging.
+
+[1] https://dl.acm.org/doi/10.1145/3297858.3304053
+[2] https://dl.acm.org/doi/10.1145/3503222.3507731
+
+Link: https://lkml.kernel.org/r/20220918080010.2920238-13-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reviewed-by: Qi Zheng <zhengqi.arch@bytedance.com>
+Acked-by: Brian Geffon <bgeffon@google.com>
+Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
+Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
+Acked-by: Steven Barrett <steven@liquorix.net>
+Acked-by: Suleiman Souhlal <suleiman@google.com>
+Tested-by: Daniel Byrne <djbyrne@mtu.edu>
+Tested-by: Donald Carr <d@chaos-reins.com>
+Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
+Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
+Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
+Tested-by: Sofia Trinh <sofia.trinh@edi.works>
+Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
+Cc: Andi Kleen <ak@linux.intel.com>
+Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Cc: Barry Song <baohua@kernel.org>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Hillf Danton <hdanton@sina.com>
+Cc: Jens Axboe <axboe@kernel.dk>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Matthew Wilcox <willy@infradead.org>
+Cc: Mel Gorman <mgorman@suse.de>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Mike Rapoport <rppt@linux.ibm.com>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Tejun Heo <tj@kernel.org>
+Cc: Vlastimil Babka <vbabka@suse.cz>
+Cc: Will Deacon <will@kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/nodemask.h | 1 +
+ mm/vmscan.c | 411 ++++++++++++++++++++++++++++++++++++++-
+ 2 files changed, 402 insertions(+), 10 deletions(-)
+
+diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
+index 0f233b76c9ce..292ec0ce0d63 100644
+--- a/include/linux/nodemask.h
++++ b/include/linux/nodemask.h
+@@ -485,6 +485,7 @@ static inline int num_node_state(enum node_states state)
+ #define first_online_node 0
+ #define first_memory_node 0
+ #define next_online_node(nid) (MAX_NUMNODES)
++#define next_memory_node(nid) (MAX_NUMNODES)
+ #define nr_node_ids 1U
+ #define nr_online_nodes 1U
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 642ee7bef61d..b74b334488d8 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -53,6 +53,7 @@
+ #include <linux/pagewalk.h>
+ #include <linux/shmem_fs.h>
+ #include <linux/ctype.h>
++#include <linux/debugfs.h>
+
+ #include <asm/tlbflush.h>
+ #include <asm/div64.h>
+@@ -3968,12 +3969,40 @@ static void clear_mm_walk(void)
+ kfree(walk);
+ }
+
+-static void inc_min_seq(struct lruvec *lruvec, int type)
++static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+ {
++ int zone;
++ int remaining = MAX_LRU_BATCH;
+ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
++
++ if (type == LRU_GEN_ANON && !can_swap)
++ goto done;
++
++ /* prevent cold/hot inversion if force_scan is true */
++ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
++ struct list_head *head = &lrugen->lists[old_gen][type][zone];
++
++ while (!list_empty(head)) {
++ struct page *page = lru_to_page(head);
++
++ VM_WARN_ON_ONCE_PAGE(PageUnevictable(page), page);
++ VM_WARN_ON_ONCE_PAGE(PageActive(page), page);
++ VM_WARN_ON_ONCE_PAGE(page_is_file_lru(page) != type, page);
++ VM_WARN_ON_ONCE_PAGE(page_zonenum(page) != zone, page);
+
++ new_gen = page_inc_gen(lruvec, page, false);
++ list_move_tail(&page->lru, &lrugen->lists[new_gen][type][zone]);
++
++ if (!--remaining)
++ return false;
++ }
++ }
++done:
+ reset_ctrl_pos(lruvec, type, true);
+ WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1);
++
++ return true;
+ }
+
+ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+@@ -4019,7 +4048,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+ return success;
+ }
+
+-static void inc_max_seq(struct lruvec *lruvec, bool can_swap)
++static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
+ {
+ int prev, next;
+ int type, zone;
+@@ -4033,9 +4062,13 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap)
+ if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
+ continue;
+
+- VM_WARN_ON_ONCE(type == LRU_GEN_FILE || can_swap);
++ VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap));
+
+- inc_min_seq(lruvec, type);
++ while (!inc_min_seq(lruvec, type, can_swap)) {
++ spin_unlock_irq(&lruvec->lru_lock);
++ cond_resched();
++ spin_lock_irq(&lruvec->lru_lock);
++ }
+ }
+
+ /*
+@@ -4072,7 +4105,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap)
+ }
+
+ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+- struct scan_control *sc, bool can_swap)
++ struct scan_control *sc, bool can_swap, bool force_scan)
+ {
+ bool success;
+ struct lru_gen_mm_walk *walk;
+@@ -4093,7 +4126,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ * handful of PTEs. Spreading the work out over a period of time usually
+ * is less efficient, but it avoids bursty page faults.
+ */
+- if (!(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) {
++ if (!force_scan && !(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) {
+ success = iterate_mm_list_nowalk(lruvec, max_seq);
+ goto done;
+ }
+@@ -4107,7 +4140,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ walk->lruvec = lruvec;
+ walk->max_seq = max_seq;
+ walk->can_swap = can_swap;
+- walk->force_scan = false;
++ walk->force_scan = force_scan;
+
+ do {
+ success = iterate_mm_list(lruvec, walk, &mm);
+@@ -4127,7 +4160,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+
+ VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq));
+
+- inc_max_seq(lruvec, can_swap);
++ inc_max_seq(lruvec, can_swap, force_scan);
+ /* either this sees any waiters or they will see updated max_seq */
+ if (wq_has_sleeper(&lruvec->mm_state.wait))
+ wake_up_all(&lruvec->mm_state.wait);
+@@ -4225,7 +4258,7 @@ static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned
+ }
+
+ if (need_aging)
+- try_to_inc_max_seq(lruvec, max_seq, sc, swappiness);
++ try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false);
+
+ return true;
+ }
+@@ -4784,7 +4817,7 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ if (current_is_kswapd())
+ return 0;
+
+- if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap))
++ if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false))
+ return nr_to_scan;
+ done:
+ return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+@@ -5123,6 +5156,361 @@ static struct attribute_group lru_gen_attr_group = {
+ .attrs = lru_gen_attrs,
+ };
+
++/******************************************************************************
++ * debugfs interface
++ ******************************************************************************/
++
++static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos)
++{
++ struct mem_cgroup *memcg;
++ loff_t nr_to_skip = *pos;
++
++ m->private = kvmalloc(PATH_MAX, GFP_KERNEL);
++ if (!m->private)
++ return ERR_PTR(-ENOMEM);
++
++ memcg = mem_cgroup_iter(NULL, NULL, NULL);
++ do {
++ int nid;
++
++ for_each_node_state(nid, N_MEMORY) {
++ if (!nr_to_skip--)
++ return get_lruvec(memcg, nid);
++ }
++ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
++
++ return NULL;
++}
++
++static void lru_gen_seq_stop(struct seq_file *m, void *v)
++{
++ if (!IS_ERR_OR_NULL(v))
++ mem_cgroup_iter_break(NULL, lruvec_memcg(v));
++
++ kvfree(m->private);
++ m->private = NULL;
++}
++
++static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos)
++{
++ int nid = lruvec_pgdat(v)->node_id;
++ struct mem_cgroup *memcg = lruvec_memcg(v);
++
++ ++*pos;
++
++ nid = next_memory_node(nid);
++ if (nid == MAX_NUMNODES) {
++ memcg = mem_cgroup_iter(NULL, memcg, NULL);
++ if (!memcg)
++ return NULL;
++
++ nid = first_memory_node;
++ }
++
++ return get_lruvec(memcg, nid);
++}
++
++static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
++ unsigned long max_seq, unsigned long *min_seq,
++ unsigned long seq)
++{
++ int i;
++ int type, tier;
++ int hist = lru_hist_from_seq(seq);
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++
++ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
++ seq_printf(m, " %10d", tier);
++ for (type = 0; type < ANON_AND_FILE; type++) {
++ const char *s = " ";
++ unsigned long n[3] = {};
++
++ if (seq == max_seq) {
++ s = "RT ";
++ n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
++ n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
++ } else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
++ s = "rep";
++ n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
++ n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
++ if (tier)
++ n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
++ }
++
++ for (i = 0; i < 3; i++)
++ seq_printf(m, " %10lu%c", n[i], s[i]);
++ }
++ seq_putc(m, '\n');
++ }
++
++ seq_puts(m, " ");
++ for (i = 0; i < NR_MM_STATS; i++) {
++ const char *s = " ";
++ unsigned long n = 0;
++
++ if (seq == max_seq && NR_HIST_GENS == 1) {
++ s = "LOYNFA";
++ n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
++ } else if (seq != max_seq && NR_HIST_GENS > 1) {
++ s = "loynfa";
++ n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
++ }
++
++ seq_printf(m, " %10lu%c", n, s[i]);
++ }
++ seq_putc(m, '\n');
++}
++
++static int lru_gen_seq_show(struct seq_file *m, void *v)
++{
++ unsigned long seq;
++ bool full = !debugfs_real_fops(m->file)->write;
++ struct lruvec *lruvec = v;
++ struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ int nid = lruvec_pgdat(lruvec)->node_id;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MAX_SEQ(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ if (nid == first_memory_node) {
++ const char *path = memcg ? m->private : "";
++
++#ifdef CONFIG_MEMCG
++ if (memcg)
++ cgroup_path(memcg->css.cgroup, m->private, PATH_MAX);
++#endif
++ seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path);
++ }
++
++ seq_printf(m, " node %5d\n", nid);
++
++ if (!full)
++ seq = min_seq[LRU_GEN_ANON];
++ else if (max_seq >= MAX_NR_GENS)
++ seq = max_seq - MAX_NR_GENS + 1;
++ else
++ seq = 0;
++
++ for (; seq <= max_seq; seq++) {
++ int type, zone;
++ int gen = lru_gen_from_seq(seq);
++ unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
++
++ seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth));
++
++ for (type = 0; type < ANON_AND_FILE; type++) {
++ unsigned long size = 0;
++ char mark = full && seq < min_seq[type] ? 'x' : ' ';
++
++ for (zone = 0; zone < MAX_NR_ZONES; zone++)
++ size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
++
++ seq_printf(m, " %10lu%c", size, mark);
++ }
++
++ seq_putc(m, '\n');
++
++ if (full)
++ lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq);
++ }
++
++ return 0;
++}
++
++static const struct seq_operations lru_gen_seq_ops = {
++ .start = lru_gen_seq_start,
++ .stop = lru_gen_seq_stop,
++ .next = lru_gen_seq_next,
++ .show = lru_gen_seq_show,
++};
++
++static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
++ bool can_swap, bool force_scan)
++{
++ DEFINE_MAX_SEQ(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ if (seq < max_seq)
++ return 0;
++
++ if (seq > max_seq)
++ return -EINVAL;
++
++ if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq)
++ return -ERANGE;
++
++ try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, force_scan);
++
++ return 0;
++}
++
++static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
++ int swappiness, unsigned long nr_to_reclaim)
++{
++ DEFINE_MAX_SEQ(lruvec);
++
++ if (seq + MIN_NR_GENS > max_seq)
++ return -EINVAL;
++
++ sc->nr_reclaimed = 0;
++
++ while (!signal_pending(current)) {
++ DEFINE_MIN_SEQ(lruvec);
++
++ if (seq < min_seq[!swappiness])
++ return 0;
++
++ if (sc->nr_reclaimed >= nr_to_reclaim)
++ return 0;
++
++ if (!evict_pages(lruvec, sc, swappiness, NULL))
++ return 0;
++
++ cond_resched();
++ }
++
++ return -EINTR;
++}
++
++static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
++ struct scan_control *sc, int swappiness, unsigned long opt)
++{
++ struct lruvec *lruvec;
++ int err = -EINVAL;
++ struct mem_cgroup *memcg = NULL;
++
++ if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY))
++ return -EINVAL;
++
++ if (!mem_cgroup_disabled()) {
++ rcu_read_lock();
++ memcg = mem_cgroup_from_id(memcg_id);
++#ifdef CONFIG_MEMCG
++ if (memcg && !css_tryget(&memcg->css))
++ memcg = NULL;
++#endif
++ rcu_read_unlock();
++
++ if (!memcg)
++ return -EINVAL;
++ }
++
++ if (memcg_id != mem_cgroup_id(memcg))
++ goto done;
++
++ lruvec = get_lruvec(memcg, nid);
++
++ if (swappiness < 0)
++ swappiness = get_swappiness(lruvec, sc);
++ else if (swappiness > 200)
++ goto done;
++
++ switch (cmd) {
++ case '+':
++ err = run_aging(lruvec, seq, sc, swappiness, opt);
++ break;
++ case '-':
++ err = run_eviction(lruvec, seq, sc, swappiness, opt);
++ break;
++ }
++done:
++ mem_cgroup_put(memcg);
++
++ return err;
++}
++
++static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
++ size_t len, loff_t *pos)
++{
++ void *buf;
++ char *cur, *next;
++ unsigned int flags;
++ struct blk_plug plug;
++ int err = -EINVAL;
++ struct scan_control sc = {
++ .may_writepage = true,
++ .may_unmap = true,
++ .may_swap = true,
++ .reclaim_idx = MAX_NR_ZONES - 1,
++ .gfp_mask = GFP_KERNEL,
++ };
++
++ buf = kvmalloc(len + 1, GFP_KERNEL);
++ if (!buf)
++ return -ENOMEM;
++
++ if (copy_from_user(buf, src, len)) {
++ kvfree(buf);
++ return -EFAULT;
++ }
++
++ set_task_reclaim_state(current, &sc.reclaim_state);
++ flags = memalloc_noreclaim_save();
++ blk_start_plug(&plug);
++ if (!set_mm_walk(NULL)) {
++ err = -ENOMEM;
++ goto done;
++ }
++
++ next = buf;
++ next[len] = '\0';
++
++ while ((cur = strsep(&next, ",;\n"))) {
++ int n;
++ int end;
++ char cmd;
++ unsigned int memcg_id;
++ unsigned int nid;
++ unsigned long seq;
++ unsigned int swappiness = -1;
++ unsigned long opt = -1;
++
++ cur = skip_spaces(cur);
++ if (!*cur)
++ continue;
++
++ n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid,
++ &seq, &end, &swappiness, &end, &opt, &end);
++ if (n < 4 || cur[end]) {
++ err = -EINVAL;
++ break;
++ }
++
++ err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt);
++ if (err)
++ break;
++ }
++done:
++ clear_mm_walk();
++ blk_finish_plug(&plug);
++ memalloc_noreclaim_restore(flags);
++ set_task_reclaim_state(current, NULL);
++
++ kvfree(buf);
++
++ return err ? : len;
++}
++
++static int lru_gen_seq_open(struct inode *inode, struct file *file)
++{
++ return seq_open(file, &lru_gen_seq_ops);
++}
++
++static const struct file_operations lru_gen_rw_fops = {
++ .open = lru_gen_seq_open,
++ .read = seq_read,
++ .write = lru_gen_seq_write,
++ .llseek = seq_lseek,
++ .release = seq_release,
++};
++
++static const struct file_operations lru_gen_ro_fops = {
++ .open = lru_gen_seq_open,
++ .read = seq_read,
++ .llseek = seq_lseek,
++ .release = seq_release,
++};
++
+ /******************************************************************************
+ * initialization
+ ******************************************************************************/
+@@ -5180,6 +5568,9 @@ static int __init init_lru_gen(void)
+ if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
+ pr_err("lru_gen: failed to create sysfs group\n");
+
++ debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops);
++ debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops);
++
+ return 0;
+ };
+ late_initcall(init_lru_gen);
+--
+2.40.0
+
--- /dev/null
+From 92d430e8955c976eacb7cc91d7ff849c0dd009af Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 28 Sep 2022 13:36:58 -0600
+Subject: [PATCH 13/29] mm/mglru: don't sync disk for each aging cycle
+
+wakeup_flusher_threads() was added under the assumption that if a system
+runs out of clean cold pages, it might want to write back dirty pages more
+aggressively so that they can become clean and be dropped.
+
+However, doing so can breach the rate limit a system wants to impose on
+writeback, resulting in early SSD wearout.
+
+Link: https://lkml.kernel.org/r/YzSiWq9UEER5LKup@google.com
+Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reported-by: Axel Rasmussen <axelrasmussen@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 2 --
+ 1 file changed, 2 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index b74b334488d8..1c0875e6514a 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4165,8 +4165,6 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ if (wq_has_sleeper(&lruvec->mm_state.wait))
+ wake_up_all(&lruvec->mm_state.wait);
+
+- wakeup_flusher_threads(WB_REASON_VMSCAN);
+-
+ return true;
+ }
+
+--
+2.40.0
+
--- /dev/null
+From 6f315879ad750391a0b1fab8c9170bc054a5f5d7 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Tue, 15 Nov 2022 18:38:07 -0700
+Subject: [PATCH 14/29] mm: multi-gen LRU: retry pages written back while
+ isolated
+
+The page reclaim isolates a batch of pages from the tail of one of the
+LRU lists and works on those pages one by one. For a suitable
+swap-backed page, if the swap device is async, it queues that page for
+writeback. After the page reclaim finishes an entire batch, it puts back
+the pages it queued for writeback to the head of the original LRU list.
+
+In the meantime, the page writeback flushes the queued pages also by
+batches. Its batching logic is independent from that of the page reclaim.
+For each of the pages it writes back, the page writeback calls
+rotate_reclaimable_page() which tries to rotate a page to the tail.
+
+rotate_reclaimable_page() only works for a page after the page reclaim
+has put it back. If an async swap device is fast enough, the page
+writeback can finish with that page while the page reclaim is still
+working on the rest of the batch containing it. In this case, that page
+will remain at the head and the page reclaim will not retry it before
+reaching there.
+
+This patch adds a retry to evict_pages(). After evict_pages() has
+finished an entire batch and before it puts back pages it cannot free
+immediately, it retries those that may have missed the rotation.
+
+Before this patch, ~60% of pages swapped to an Intel Optane missed
+rotate_reclaimable_page(). After this patch, ~99% of missed pages were
+reclaimed upon retry.
+
+This problem affects relatively slow async swap devices like Samsung 980
+Pro much less and does not affect sync swap devices like zram or zswap at
+all.
+
+Link: https://lkml.kernel.org/r/20221116013808.3995280-1-yuzhao@google.com
+Fixes: ac35a4902374 ("mm: multi-gen LRU: minimal implementation")
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: "Yin, Fengwei" <fengwei.yin@intel.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 48 +++++++++++++++++++++++++++++++++++++-----------
+ 1 file changed, 37 insertions(+), 11 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 1c0875e6514a..27bc525380f9 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4723,10 +4723,13 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ int scanned;
+ int reclaimed;
+ LIST_HEAD(list);
++ LIST_HEAD(clean);
+ struct page *page;
++ struct page *next;
+ enum vm_event_item item;
+ struct reclaim_stat stat;
+ struct lru_gen_mm_walk *walk;
++ bool skip_retry = false;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+@@ -4743,20 +4746,37 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+
+ if (list_empty(&list))
+ return scanned;
+-
++retry:
+ reclaimed = shrink_page_list(&list, pgdat, sc, &stat, false);
++ sc->nr_reclaimed += reclaimed;
+
+- list_for_each_entry(page, &list, lru) {
+- /* restore LRU_REFS_FLAGS cleared by isolate_page() */
+- if (PageWorkingset(page))
+- SetPageReferenced(page);
++ list_for_each_entry_safe_reverse(page, next, &list, lru) {
++ if (!page_evictable(page)) {
++ list_del(&page->lru);
++ putback_lru_page(page);
++ continue;
++ }
+
+- /* don't add rejected pages to the oldest generation */
+ if (PageReclaim(page) &&
+- (PageDirty(page) || PageWriteback(page)))
+- ClearPageActive(page);
+- else
+- SetPageActive(page);
++ (PageDirty(page) || PageWriteback(page))) {
++ /* restore LRU_REFS_FLAGS cleared by isolate_page() */
++ if (PageWorkingset(page))
++ SetPageReferenced(page);
++ continue;
++ }
++
++ if (skip_retry || PageActive(page) || PageReferenced(page) ||
++ page_mapped(page) || PageLocked(page) ||
++ PageDirty(page) || PageWriteback(page)) {
++ /* don't add rejected pages to the oldest generation */
++ set_mask_bits(&page->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
++ BIT(PG_active));
++ continue;
++ }
++
++ /* retry pages that may have missed rotate_reclaimable_page() */
++ list_move(&page->lru, &clean);
++ sc->nr_scanned -= thp_nr_pages(page);
+ }
+
+ spin_lock_irq(&lruvec->lru_lock);
+@@ -4778,7 +4798,13 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ mem_cgroup_uncharge_list(&list);
+ free_unref_page_list(&list);
+
+- sc->nr_reclaimed += reclaimed;
++ INIT_LIST_HEAD(&list);
++ list_splice_init(&clean, &list);
++
++ if (!list_empty(&list)) {
++ skip_retry = true;
++ goto retry;
++ }
+
+ if (need_swapping && type == LRU_GEN_ANON)
+ *need_swapping = true;
+--
+2.40.0
+
--- /dev/null
+From 255bb0ac393f1c2818cd75af45a9226300ab3daf Mon Sep 17 00:00:00 2001
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Date: Wed, 26 Oct 2022 15:48:30 +0200
+Subject: [PATCH 15/29] mm: multi-gen LRU: move lru_gen_add_mm() out of IRQ-off
+ region
+
+lru_gen_add_mm() has been added within an IRQ-off region in the commit
+mentioned below. The other invocations of lru_gen_add_mm() are not within
+an IRQ-off region.
+
+The invocation within IRQ-off region is problematic on PREEMPT_RT because
+the function is using a spin_lock_t which must not be used within
+IRQ-disabled regions.
+
+The other invocations of lru_gen_add_mm() occur while
+task_struct::alloc_lock is acquired. Move lru_gen_add_mm() after
+interrupts are enabled and before task_unlock().
+
+Link: https://lkml.kernel.org/r/20221026134830.711887-1-bigeasy@linutronix.de
+Fixes: bd74fdaea1460 ("mm: multi-gen LRU: support page table walks")
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Acked-by: Yu Zhao <yuzhao@google.com>
+Cc: Al Viro <viro@zeniv.linux.org.uk>
+Cc: "Eric W . Biederman" <ebiederm@xmission.com>
+Cc: Kees Cook <keescook@chromium.org>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ fs/exec.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/fs/exec.c b/fs/exec.c
+index 1afa15a07d26..718c58947be1 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -1013,7 +1013,6 @@ static int exec_mmap(struct mm_struct *mm)
+ active_mm = tsk->active_mm;
+ tsk->active_mm = mm;
+ tsk->mm = mm;
+- lru_gen_add_mm(mm);
+ /*
+ * This prevents preemption while active_mm is being loaded and
+ * it and mm are being updated, which could cause problems for
+@@ -1028,6 +1027,7 @@ static int exec_mmap(struct mm_struct *mm)
+ local_irq_enable();
+ tsk->mm->vmacache_seqnum = 0;
+ vmacache_flush(tsk);
++ lru_gen_add_mm(mm);
+ task_unlock(tsk);
+ lru_gen_use_mm(mm);
+ if (old_mm) {
+--
+2.40.0
+
--- /dev/null
+From c5ec455ebd2b488d91de9d8915a0c8036a2a04dd Mon Sep 17 00:00:00 2001
+From: Juergen Gross <jgross@suse.com>
+Date: Wed, 30 Nov 2022 14:49:41 -0800
+Subject: [PATCH 17/29] mm: add dummy pmd_young() for architectures not having
+ it
+
+In order to avoid #ifdeffery add a dummy pmd_young() implementation as a
+fallback. This is required for the later patch "mm: introduce
+arch_has_hw_nonleaf_pmd_young()".
+
+Link: https://lkml.kernel.org/r/fd3ac3cd-7349-6bbd-890a-71a9454ca0b3@suse.com
+Signed-off-by: Juergen Gross <jgross@suse.com>
+Acked-by: Yu Zhao <yuzhao@google.com>
+Cc: Borislav Petkov <bp@alien8.de>
+Cc: Dave Hansen <dave.hansen@linux.intel.com>
+Cc: Geert Uytterhoeven <geert@linux-m68k.org>
+Cc: "H. Peter Anvin" <hpa@zytor.com>
+Cc: Ingo Molnar <mingo@redhat.com>
+Cc: Sander Eikelenboom <linux@eikelenboom.it>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ arch/mips/include/asm/pgtable.h | 1 +
+ arch/riscv/include/asm/pgtable.h | 1 +
+ arch/s390/include/asm/pgtable.h | 1 +
+ arch/sparc/include/asm/pgtable_64.h | 1 +
+ arch/x86/include/asm/pgtable.h | 1 +
+ include/linux/pgtable.h | 7 +++++++
+ 6 files changed, 12 insertions(+)
+
+diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
+index 804889b70965..89ab8b4cf971 100644
+--- a/arch/mips/include/asm/pgtable.h
++++ b/arch/mips/include/asm/pgtable.h
+@@ -632,6 +632,7 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
+ return pmd;
+ }
+
++#define pmd_young pmd_young
+ static inline int pmd_young(pmd_t pmd)
+ {
+ return !!(pmd_val(pmd) & _PAGE_ACCESSED);
+diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
+index 39b550310ec6..4a64e03dcdd4 100644
+--- a/arch/riscv/include/asm/pgtable.h
++++ b/arch/riscv/include/asm/pgtable.h
+@@ -531,6 +531,7 @@ static inline int pmd_dirty(pmd_t pmd)
+ return pte_dirty(pmd_pte(pmd));
+ }
+
++#define pmd_young pmd_young
+ static inline int pmd_young(pmd_t pmd)
+ {
+ return pte_young(pmd_pte(pmd));
+diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
+index b61426c9ef17..55ff4f22da2d 100644
+--- a/arch/s390/include/asm/pgtable.h
++++ b/arch/s390/include/asm/pgtable.h
+@@ -748,6 +748,7 @@ static inline int pmd_dirty(pmd_t pmd)
+ return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
+ }
+
++#define pmd_young pmd_young
+ static inline int pmd_young(pmd_t pmd)
+ {
+ return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0;
+diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
+index 4679e45c8348..bfd10179c137 100644
+--- a/arch/sparc/include/asm/pgtable_64.h
++++ b/arch/sparc/include/asm/pgtable_64.h
+@@ -712,6 +712,7 @@ static inline unsigned long pmd_dirty(pmd_t pmd)
+ return pte_dirty(pte);
+ }
+
++#define pmd_young pmd_young
+ static inline unsigned long pmd_young(pmd_t pmd)
+ {
+ pte_t pte = __pte(pmd_val(pmd));
+diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
+index 01a1763123ff..c4b64ee357fd 100644
+--- a/arch/x86/include/asm/pgtable.h
++++ b/arch/x86/include/asm/pgtable.h
+@@ -136,6 +136,7 @@ static inline int pmd_dirty(pmd_t pmd)
+ return pmd_flags(pmd) & _PAGE_DIRTY;
+ }
+
++#define pmd_young pmd_young
+ static inline int pmd_young(pmd_t pmd)
+ {
+ return pmd_flags(pmd) & _PAGE_ACCESSED;
+diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
+index e6889556e0bf..dec3d890e814 100644
+--- a/include/linux/pgtable.h
++++ b/include/linux/pgtable.h
+@@ -164,6 +164,13 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr)
+ return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
+ }
+
++#ifndef pmd_young
++static inline int pmd_young(pmd_t pmd)
++{
++ return 0;
++}
++#endif
++
+ #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+ extern int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+--
+2.40.0
+
--- /dev/null
+From 46cbda7b65998a5af4493f745d94417af697bd68 Mon Sep 17 00:00:00 2001
+From: Juergen Gross <jgross@suse.com>
+Date: Wed, 23 Nov 2022 07:45:10 +0100
+Subject: [PATCH 18/29] mm: introduce arch_has_hw_nonleaf_pmd_young()
+
+When running as a Xen PV guests commit eed9a328aa1a ("mm: x86: add
+CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG") can cause a protection violation in
+pmdp_test_and_clear_young():
+
+ BUG: unable to handle page fault for address: ffff8880083374d0
+ #PF: supervisor write access in kernel mode
+ #PF: error_code(0x0003) - permissions violation
+ PGD 3026067 P4D 3026067 PUD 3027067 PMD 7fee5067 PTE 8010000008337065
+ Oops: 0003 [#1] PREEMPT SMP NOPTI
+ CPU: 7 PID: 158 Comm: kswapd0 Not tainted 6.1.0-rc5-20221118-doflr+ #1
+ RIP: e030:pmdp_test_and_clear_young+0x25/0x40
+
+This happens because the Xen hypervisor can't emulate direct writes to
+page table entries other than PTEs.
+
+This can easily be fixed by introducing arch_has_hw_nonleaf_pmd_young()
+similar to arch_has_hw_pte_young() and test that instead of
+CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG.
+
+Link: https://lkml.kernel.org/r/20221123064510.16225-1-jgross@suse.com
+Fixes: eed9a328aa1a ("mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG")
+Signed-off-by: Juergen Gross <jgross@suse.com>
+Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
+Acked-by: Yu Zhao <yuzhao@google.com>
+Tested-by: Sander Eikelenboom <linux@eikelenboom.it>
+Acked-by: David Hildenbrand <david@redhat.com> [core changes]
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ arch/x86/include/asm/pgtable.h | 8 ++++++++
+ include/linux/pgtable.h | 11 +++++++++++
+ mm/vmscan.c | 10 +++++-----
+ 3 files changed, 24 insertions(+), 5 deletions(-)
+
+diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
+index c4b64ee357fd..d8363c676496 100644
+--- a/arch/x86/include/asm/pgtable.h
++++ b/arch/x86/include/asm/pgtable.h
+@@ -1405,6 +1405,14 @@ static inline bool arch_has_hw_pte_young(void)
+ return true;
+ }
+
++#ifdef CONFIG_XEN_PV
++#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
++static inline bool arch_has_hw_nonleaf_pmd_young(void)
++{
++ return !cpu_feature_enabled(X86_FEATURE_XENPV);
++}
++#endif
++
+ #endif /* __ASSEMBLY__ */
+
+ #endif /* _ASM_X86_PGTABLE_H */
+diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
+index dec3d890e814..562b4cc82b33 100644
+--- a/include/linux/pgtable.h
++++ b/include/linux/pgtable.h
+@@ -266,6 +266,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
+ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+ #endif
+
++#ifndef arch_has_hw_nonleaf_pmd_young
++/*
++ * Return whether the accessed bit in non-leaf PMD entries is supported on the
++ * local CPU.
++ */
++static inline bool arch_has_hw_nonleaf_pmd_young(void)
++{
++ return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
++}
++#endif
++
+ #ifndef arch_has_hw_pte_young
+ /*
+ * Return whether the accessed bit is supported on the local CPU.
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index d310e0b9e520..96f1af44bb77 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -3730,7 +3730,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
+ goto next;
+
+ if (!pmd_trans_huge(pmd[i])) {
+- if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
++ if (arch_has_hw_nonleaf_pmd_young() &&
+ get_cap(LRU_GEN_NONLEAF_YOUNG))
+ pmdp_test_and_clear_young(vma, addr, pmd + i);
+ goto next;
+@@ -3828,14 +3828,14 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
+ #endif
+ walk->mm_stats[MM_NONLEAF_TOTAL]++;
+
+-#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+- if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
++ if (arch_has_hw_nonleaf_pmd_young() &&
++ get_cap(LRU_GEN_NONLEAF_YOUNG)) {
+ if (!pmd_young(val))
+ continue;
+
+ walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
+ }
+-#endif
++
+ if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
+ continue;
+
+@@ -5135,7 +5135,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
+ if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
+ caps |= BIT(LRU_GEN_MM_WALK);
+
+- if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
++ if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
+ caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
+
+ return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);
+--
+2.40.0
+
--- /dev/null
+From c7dfefd4bdfba3d5171038d1cc2d4160288e6ee4 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Sun, 15 Jan 2023 20:44:05 -0700
+Subject: [PATCH 16/29] mm: multi-gen LRU: fix crash during cgroup migration
+
+lru_gen_migrate_mm() assumes lru_gen_add_mm() runs prior to itself. This
+isn't true for the following scenario:
+
+ CPU 1 CPU 2
+
+ clone()
+ cgroup_can_fork()
+ cgroup_procs_write()
+ cgroup_post_fork()
+ task_lock()
+ lru_gen_migrate_mm()
+ task_unlock()
+ task_lock()
+ lru_gen_add_mm()
+ task_unlock()
+
+And when the above happens, kernel crashes because of linked list
+corruption (mm_struct->lru_gen.list).
+
+Link: https://lore.kernel.org/r/20230115134651.30028-1-msizanoen@qtmlabs.xyz/
+Link: https://lkml.kernel.org/r/20230116034405.2960276-1-yuzhao@google.com
+Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reported-by: msizanoen <msizanoen@qtmlabs.xyz>
+Tested-by: msizanoen <msizanoen@qtmlabs.xyz>
+Cc: <stable@vger.kernel.org> [6.1+]
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 5 ++++-
+ 1 file changed, 4 insertions(+), 1 deletion(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 27bc525380f9..d310e0b9e520 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -3024,13 +3024,16 @@ void lru_gen_migrate_mm(struct mm_struct *mm)
+ if (mem_cgroup_disabled())
+ return;
+
++ /* migration can happen before addition */
++ if (!mm->lru_gen.memcg)
++ return;
++
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(task);
+ rcu_read_unlock();
+ if (memcg == mm->lru_gen.memcg)
+ return;
+
+- VM_WARN_ON_ONCE(!mm->lru_gen.memcg);
+ VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));
+
+ lru_gen_del_mm(mm);
+--
+2.40.0
+
--- /dev/null
+From 6c7f552a48b49a8612786a28a2239fbc24fac289 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Fri, 30 Dec 2022 14:52:51 -0700
+Subject: [PATCH 19/29] mm: add vma_has_recency()
+
+Add vma_has_recency() to indicate whether a VMA may exhibit temporal
+locality that the LRU algorithm relies on.
+
+This function returns false for VMAs marked by VM_SEQ_READ or
+VM_RAND_READ. While the former flag indicates linear access, i.e., a
+special case of spatial locality, both flags indicate a lack of temporal
+locality, i.e., the reuse of an area within a relatively small duration.
+
+"Recency" is chosen over "locality" to avoid confusion between temporal
+and spatial localities.
+
+Before this patch, the active/inactive LRU only ignored the accessed bit
+from VMAs marked by VM_SEQ_READ. After this patch, the active/inactive
+LRU and MGLRU share the same logic: they both ignore the accessed bit if
+vma_has_recency() returns false.
+
+For the active/inactive LRU, the following fio test showed a [6, 8]%
+increase in IOPS when randomly accessing mapped files under memory
+pressure.
+
+ kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo)
+ kb=$((kb - 8*1024*1024))
+
+ modprobe brd rd_nr=1 rd_size=$kb
+ dd if=/dev/zero of=/dev/ram0 bs=1M
+
+ mkfs.ext4 /dev/ram0
+ mount /dev/ram0 /mnt/
+ swapoff -a
+
+ fio --name=test --directory=/mnt/ --ioengine=mmap --numjobs=8 \
+ --size=8G --rw=randrw --time_based --runtime=10m \
+ --group_reporting
+
+The discussion that led to this patch is here [1]. Additional test
+results are available in that thread.
+
+[1] https://lore.kernel.org/r/Y31s%2FK8T85jh05wH@google.com/
+
+Link: https://lkml.kernel.org/r/20221230215252.2628425-1-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Alexander Viro <viro@zeniv.linux.org.uk>
+Cc: Andrea Righi <andrea.righi@canonical.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mm_inline.h | 9 +++++++++
+ mm/memory.c | 8 ++++----
+ mm/rmap.c | 42 +++++++++++++++++----------------------
+ mm/vmscan.c | 5 ++++-
+ 4 files changed, 35 insertions(+), 29 deletions(-)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index e095c1c24311..e8c723053a52 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -333,4 +333,13 @@ static __always_inline void del_page_from_lru_list(struct page *page,
+ update_lru_size(lruvec, page_lru(page), page_zonenum(page),
+ -thp_nr_pages(page));
+ }
++
++static inline bool vma_has_recency(struct vm_area_struct *vma)
++{
++ if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
++ return false;
++
++ return true;
++}
++
+ #endif
+diff --git a/mm/memory.c b/mm/memory.c
+index 7d5be951de9e..1306b1ff0c10 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -41,6 +41,7 @@
+
+ #include <linux/kernel_stat.h>
+ #include <linux/mm.h>
++#include <linux/mm_inline.h>
+ #include <linux/sched/mm.h>
+ #include <linux/sched/coredump.h>
+ #include <linux/sched/numa_balancing.h>
+@@ -1353,8 +1354,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
+ force_flush = 1;
+ set_page_dirty(page);
+ }
+- if (pte_young(ptent) &&
+- likely(!(vma->vm_flags & VM_SEQ_READ)))
++ if (pte_young(ptent) && likely(vma_has_recency(vma)))
+ mark_page_accessed(page);
+ }
+ rss[mm_counter(page)]--;
+@@ -4781,8 +4781,8 @@ static inline void mm_account_fault(struct pt_regs *regs,
+ #ifdef CONFIG_LRU_GEN
+ static void lru_gen_enter_fault(struct vm_area_struct *vma)
+ {
+- /* the LRU algorithm doesn't apply to sequential or random reads */
+- current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ));
++ /* the LRU algorithm only applies to accesses with recency */
++ current->in_lru_fault = vma_has_recency(vma);
+ }
+
+ static void lru_gen_exit_fault(void)
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 22a86122732e..53df47753f3c 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -794,25 +794,14 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
+ }
+
+ if (pvmw.pte) {
+- if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
+- !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) {
++ if (lru_gen_enabled() && pte_young(*pvmw.pte)) {
+ lru_gen_look_around(&pvmw);
+ referenced++;
+ }
+
+ if (ptep_clear_flush_young_notify(vma, address,
+- pvmw.pte)) {
+- /*
+- * Don't treat a reference through
+- * a sequentially read mapping as such.
+- * If the page has been used in another mapping,
+- * we will catch it; if this other mapping is
+- * already gone, the unmap path will have set
+- * PG_referenced or activated the page.
+- */
+- if (likely(!(vma->vm_flags & VM_SEQ_READ)))
+- referenced++;
+- }
++ pvmw.pte))
++ referenced++;
+ } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
+ if (pmdp_clear_flush_young_notify(vma, address,
+ pvmw.pmd))
+@@ -846,7 +835,20 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
+ struct page_referenced_arg *pra = arg;
+ struct mem_cgroup *memcg = pra->memcg;
+
+- if (!mm_match_cgroup(vma->vm_mm, memcg))
++ /*
++ * Ignore references from this mapping if it has no recency. If the
++ * page has been used in another mapping, we will catch it; if this
++ * other mapping is already gone, the unmap path will have set the
++ * referenced flag or activated the page in zap_pte_range().
++ */
++ if (!vma_has_recency(vma))
++ return true;
++
++ /*
++ * If we are reclaiming on behalf of a cgroup, skip counting on behalf
++ * of references from different cgroups.
++ */
++ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
+ return true;
+
+ return false;
+@@ -876,6 +878,7 @@ int page_referenced(struct page *page,
+ .rmap_one = page_referenced_one,
+ .arg = (void *)&pra,
+ .anon_lock = page_lock_anon_vma_read,
++ .invalid_vma = invalid_page_referenced_vma,
+ };
+
+ *vm_flags = 0;
+@@ -891,15 +894,6 @@ int page_referenced(struct page *page,
+ return 1;
+ }
+
+- /*
+- * If we are reclaiming on behalf of a cgroup, skip
+- * counting on behalf of references from different
+- * cgroups
+- */
+- if (memcg) {
+- rwc.invalid_vma = invalid_page_referenced_vma;
+- }
+-
+ rmap_walk(page, &rwc);
+ *vm_flags = pra.vm_flags;
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 96f1af44bb77..4ab376abeaae 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -3486,7 +3486,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
+ if (is_vm_hugetlb_page(vma))
+ return true;
+
+- if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ))
++ if (!vma_has_recency(vma))
++ return true;
++
++ if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL))
+ return true;
+
+ if (vma == get_gate_vma(vma->vm_mm))
+--
+2.40.0
+
--- /dev/null
+From 686c3d4f71de9e0e7a27f03a5617a712385f90cd Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Fri, 30 Dec 2022 14:52:52 -0700
+Subject: [PATCH 20/29] mm: support POSIX_FADV_NOREUSE
+
+This patch adds POSIX_FADV_NOREUSE to vma_has_recency() so that the LRU
+algorithm can ignore access to mapped files marked by this flag.
+
+The advantages of POSIX_FADV_NOREUSE are:
+1. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not alter the
+ default readahead behavior.
+2. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not split VMAs and
+ therefore does not take mmap_lock.
+3. Unlike MADV_COLD, setting it has a negligible cost, regardless of
+ how many pages it affects.
+
+Its limitations are:
+1. Like POSIX_FADV_RANDOM and POSIX_FADV_SEQUENTIAL, it currently does
+ not support range. IOW, its scope is the entire file.
+2. It currently does not ignore access through file descriptors.
+ Specifically, for the active/inactive LRU, given a file page shared
+ by two users and one of them having set POSIX_FADV_NOREUSE on the
+ file, this page will be activated upon the second user accessing
+ it. This corner case can be covered by checking POSIX_FADV_NOREUSE
+ before calling mark_page_accessed() on the read path. But it is
+ considered not worth the effort.
+
+There have been a few attempts to support POSIX_FADV_NOREUSE, e.g., [1].
+This time the goal is to fill a niche: a few desktop applications, e.g.,
+large file transferring and video encoding/decoding, want fast file
+streaming with mmap() rather than direct IO. Among those applications, an
+SVT-AV1 regression was reported when running with MGLRU [2]. The
+following test can reproduce that regression.
+
+ kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo)
+ kb=$((kb - 8*1024*1024))
+
+ modprobe brd rd_nr=1 rd_size=$kb
+ dd if=/dev/zero of=/dev/ram0 bs=1M
+
+ mkfs.ext4 /dev/ram0
+ mount /dev/ram0 /mnt/
+ swapoff -a
+
+ fallocate -l 8G /mnt/swapfile
+ mkswap /mnt/swapfile
+ swapon /mnt/swapfile
+
+ wget http://ultravideo.cs.tut.fi/video/Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
+ 7z e -o/mnt/ Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
+ SvtAv1EncApp --preset 12 -w 3840 -h 2160 \
+ -i /mnt/Bosphorus_3840x2160.y4m
+
+For MGLRU, the following change showed a [9-11]% increase in FPS,
+which makes it on par with the active/inactive LRU.
+
+ patch Source/App/EncApp/EbAppMain.c <<EOF
+ 31a32
+ > #include <fcntl.h>
+ 35d35
+ < #include <fcntl.h> /* _O_BINARY */
+ 117a118
+ > posix_fadvise(config->mmap.fd, 0, 0, POSIX_FADV_NOREUSE);
+ EOF
+
+[1] https://lore.kernel.org/r/1308923350-7932-1-git-send-email-andrea@betterlinux.com/
+[2] https://openbenchmarking.org/result/2209259-PTS-MGLRU8GB57
+
+Link: https://lkml.kernel.org/r/20221230215252.2628425-2-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Alexander Viro <viro@zeniv.linux.org.uk>
+Cc: Andrea Righi <andrea.righi@canonical.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/fs.h | 2 ++
+ include/linux/mm_inline.h | 3 +++
+ mm/fadvise.c | 5 ++++-
+ 3 files changed, 9 insertions(+), 1 deletion(-)
+
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 23ecfecdc450..601e52991f4a 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -167,6 +167,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
+ /* File is stream-like */
+ #define FMODE_STREAM ((__force fmode_t)0x200000)
+
++#define FMODE_NOREUSE ((__force fmode_t)0x400000)
++
+ /* File was opened by fanotify and shouldn't generate fanotify events */
+ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index e8c723053a52..8a6a2a23f9b6 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -339,6 +339,9 @@ static inline bool vma_has_recency(struct vm_area_struct *vma)
+ if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
+ return false;
+
++ if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE))
++ return false;
++
+ return true;
+ }
+
+diff --git a/mm/fadvise.c b/mm/fadvise.c
+index d6baa4f451c5..e8023c69f219 100644
+--- a/mm/fadvise.c
++++ b/mm/fadvise.c
+@@ -80,7 +80,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+ case POSIX_FADV_NORMAL:
+ file->f_ra.ra_pages = bdi->ra_pages;
+ spin_lock(&file->f_lock);
+- file->f_mode &= ~FMODE_RANDOM;
++ file->f_mode &= ~(FMODE_RANDOM | FMODE_NOREUSE);
+ spin_unlock(&file->f_lock);
+ break;
+ case POSIX_FADV_RANDOM:
+@@ -107,6 +107,9 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+ force_page_cache_readahead(mapping, file, start_index, nrpages);
+ break;
+ case POSIX_FADV_NOREUSE:
++ spin_lock(&file->f_lock);
++ file->f_mode |= FMODE_NOREUSE;
++ spin_unlock(&file->f_lock);
+ break;
+ case POSIX_FADV_DONTNEED:
+ if (!inode_write_congested(mapping->host))
+--
+2.40.0
+
--- /dev/null
+From 348fdbada9fb3f0bf1a53651be46319105af187f Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:18:59 -0700
+Subject: [PATCH 21/29] mm: multi-gen LRU: rename lru_gen_struct to
+ lru_gen_page
+
+Patch series "mm: multi-gen LRU: memcg LRU", v3.
+
+Overview
+========
+
+An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs,
+since each node and memcg combination has an LRU of pages (see
+mem_cgroup_lruvec()).
+
+Its goal is to improve the scalability of global reclaim, which is
+critical to system-wide memory overcommit in data centers. Note that
+memcg reclaim is currently out of scope.
+
+Its memory bloat is a pointer to each lruvec and negligible to each
+pglist_data. In terms of traversing memcgs during global reclaim, it
+improves the best-case complexity from O(n) to O(1) and does not affect
+the worst-case complexity O(n). Therefore, on average, it has a sublinear
+complexity in contrast to the current linear complexity.
+
+The basic structure of an memcg LRU can be understood by an analogy to
+the active/inactive LRU (of pages):
+1. It has the young and the old (generations), i.e., the counterparts
+ to the active and the inactive;
+2. The increment of max_seq triggers promotion, i.e., the counterpart
+ to activation;
+3. Other events trigger similar operations, e.g., offlining an memcg
+ triggers demotion, i.e., the counterpart to deactivation.
+
+In terms of global reclaim, it has two distinct features:
+1. Sharding, which allows each thread to start at a random memcg (in
+ the old generation) and improves parallelism;
+2. Eventual fairness, which allows direct reclaim to bail out at will
+ and reduces latency without affecting fairness over some time.
+
+The commit message in patch 6 details the workflow:
+https://lore.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com/
+
+The following is a simple test to quickly verify its effectiveness.
+
+ Test design:
+ 1. Create multiple memcgs.
+ 2. Each memcg contains a job (fio).
+ 3. All jobs access the same amount of memory randomly.
+ 4. The system does not experience global memory pressure.
+ 5. Periodically write to the root memory.reclaim.
+
+ Desired outcome:
+ 1. All memcgs have similar pgsteal counts, i.e., stddev(pgsteal)
+ over mean(pgsteal) is close to 0%.
+ 2. The total pgsteal is close to the total requested through
+ memory.reclaim, i.e., sum(pgsteal) over sum(requested) is close
+ to 100%.
+
+ Actual outcome [1]:
+ MGLRU off MGLRU on
+ stddev(pgsteal) / mean(pgsteal) 75% 20%
+ sum(pgsteal) / sum(requested) 425% 95%
+
+ ####################################################################
+ MEMCGS=128
+
+ for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
+ mkdir /sys/fs/cgroup/memcg$memcg
+ done
+
+ start() {
+ echo $BASHPID > /sys/fs/cgroup/memcg$memcg/cgroup.procs
+
+ fio -name=memcg$memcg --numjobs=1 --ioengine=mmap \
+ --filename=/dev/zero --size=1920M --rw=randrw \
+ --rate=64m,64m --random_distribution=random \
+ --fadvise_hint=0 --time_based --runtime=10h \
+ --group_reporting --minimal
+ }
+
+ for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
+ start &
+ done
+
+ sleep 600
+
+ for ((i = 0; i < 600; i++)); do
+ echo 256m >/sys/fs/cgroup/memory.reclaim
+ sleep 6
+ done
+
+ for ((memcg = 0; memcg < $MEMCGS; memcg++)); do
+ grep "pgsteal " /sys/fs/cgroup/memcg$memcg/memory.stat
+ done
+ ####################################################################
+
+[1]: This was obtained from running the above script (touches less
+ than 256GB memory) on an EPYC 7B13 with 512GB DRAM for over an
+ hour.
+
+This patch (of 8):
+
+The new name lru_gen_page will be more distinct from the coming
+lru_gen_memcg.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-1-yuzhao@google.com
+Link: https://lkml.kernel.org/r/20221222041905.2431096-2-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mm_inline.h | 4 ++--
+ include/linux/mmzone.h | 6 +++---
+ mm/vmscan.c | 34 +++++++++++++++++-----------------
+ mm/workingset.c | 4 ++--
+ 4 files changed, 24 insertions(+), 24 deletions(-)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 8a6a2a23f9b6..27c4890503c5 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -168,7 +168,7 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct page *page,
+ int zone = page_zonenum(page);
+ int delta = thp_nr_pages(page);
+ enum lru_list lru = type * LRU_INACTIVE_FILE;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS);
+ VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS);
+@@ -214,7 +214,7 @@ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bo
+ int gen = page_lru_gen(page);
+ int type = page_is_file_lru(page);
+ int zone = page_zonenum(page);
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ VM_WARN_ON_ONCE_PAGE(gen != -1, page);
+
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 6b85ba1f4e18..5856b026c089 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -394,7 +394,7 @@ enum {
+ * The number of pages in each generation is eventually consistent and therefore
+ * can be transiently negative when reset_batch_size() is pending.
+ */
+-struct lru_gen_struct {
++struct lru_gen_page {
+ /* the aging increments the youngest generation number */
+ unsigned long max_seq;
+ /* the eviction increments the oldest generation numbers */
+@@ -451,7 +451,7 @@ struct lru_gen_mm_state {
+ struct lru_gen_mm_walk {
+ /* the lruvec under reclaim */
+ struct lruvec *lruvec;
+- /* unstable max_seq from lru_gen_struct */
++ /* unstable max_seq from lru_gen_page */
+ unsigned long max_seq;
+ /* the next address within an mm to scan */
+ unsigned long next_addr;
+@@ -514,7 +514,7 @@ struct lruvec {
+ unsigned long flags;
+ #ifdef CONFIG_LRU_GEN
+ /* evictable pages divided into generations */
+- struct lru_gen_struct lrugen;
++ struct lru_gen_page lrugen;
+ /* to concurrently iterate lru_gen_mm_list */
+ struct lru_gen_mm_state mm_state;
+ #endif
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 4ab376abeaae..3b1b5bd9736a 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -2910,7 +2910,7 @@ static int get_nr_gens(struct lruvec *lruvec, int type)
+
+ static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
+ {
+- /* see the comment on lru_gen_struct */
++ /* see the comment on lru_gen_page */
+ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
+ get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
+ get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
+@@ -3316,7 +3316,7 @@ struct ctrl_pos {
+ static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
+ struct ctrl_pos *pos)
+ {
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
+
+ pos->refaulted = lrugen->avg_refaulted[type][tier] +
+@@ -3331,7 +3331,7 @@ static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
+ static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
+ {
+ int hist, tier;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1;
+ unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1;
+
+@@ -3408,7 +3408,7 @@ static int page_update_gen(struct page *page, int gen)
+ static int page_inc_gen(struct lruvec *lruvec, struct page *page, bool reclaiming)
+ {
+ int type = page_is_file_lru(page);
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
+ unsigned long new_flags, old_flags = READ_ONCE(page->flags);
+
+@@ -3453,7 +3453,7 @@ static void update_batch_size(struct lru_gen_mm_walk *walk, struct page *page,
+ static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk)
+ {
+ int gen, type, zone;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ walk->batched = 0;
+
+@@ -3979,7 +3979,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+ {
+ int zone;
+ int remaining = MAX_LRU_BATCH;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
+
+ if (type == LRU_GEN_ANON && !can_swap)
+@@ -4015,7 +4015,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+ {
+ int gen, type, zone;
+ bool success = false;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ DEFINE_MIN_SEQ(lruvec);
+
+ VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
+@@ -4036,7 +4036,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+ ;
+ }
+
+- /* see the comment on lru_gen_struct */
++ /* see the comment on lru_gen_page */
+ if (can_swap) {
+ min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
+ min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
+@@ -4058,7 +4058,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
+ {
+ int prev, next;
+ int type, zone;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ spin_lock_irq(&lruvec->lru_lock);
+
+@@ -4116,7 +4116,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ bool success;
+ struct lru_gen_mm_walk *walk;
+ struct mm_struct *mm = NULL;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq));
+
+@@ -4181,7 +4181,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig
+ unsigned long old = 0;
+ unsigned long young = 0;
+ unsigned long total = 0;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+
+ for (type = !can_swap; type < ANON_AND_FILE; type++) {
+@@ -4466,7 +4466,7 @@ static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
+ int delta = thp_nr_pages(page);
+ int refs = page_lru_refs(page);
+ int tier = lru_tier_from_refs(refs);
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ VM_WARN_ON_ONCE_PAGE(gen >= MAX_NR_GENS, page);
+
+@@ -4566,7 +4566,7 @@ static int scan_pages(struct lruvec *lruvec, struct scan_control *sc,
+ int scanned = 0;
+ int isolated = 0;
+ int remaining = MAX_LRU_BATCH;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+
+ VM_WARN_ON_ONCE(!list_empty(list));
+@@ -4967,7 +4967,7 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+
+ static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
+ {
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ if (lrugen->enabled) {
+ enum lru_list lru;
+@@ -5247,7 +5247,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
+ int i;
+ int type, tier;
+ int hist = lru_hist_from_seq(seq);
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
+ seq_printf(m, " %10d", tier);
+@@ -5296,7 +5296,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
+ unsigned long seq;
+ bool full = !debugfs_real_fops(m->file)->write;
+ struct lruvec *lruvec = v;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ int nid = lruvec_pgdat(lruvec)->node_id;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+@@ -5549,7 +5549,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
+ {
+ int i;
+ int gen, type, zone;
+- struct lru_gen_struct *lrugen = &lruvec->lrugen;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+
+ lrugen->max_seq = MIN_NR_GENS + 1;
+ lrugen->enabled = lru_gen_enabled();
+diff --git a/mm/workingset.c b/mm/workingset.c
+index aeba62cebf8c..a5e1798c6d60 100644
+--- a/mm/workingset.c
++++ b/mm/workingset.c
+@@ -223,7 +223,7 @@ static void *lru_gen_eviction(struct page *page)
+ unsigned long token;
+ unsigned long min_seq;
+ struct lruvec *lruvec;
+- struct lru_gen_struct *lrugen;
++ struct lru_gen_page *lrugen;
+ int type = page_is_file_lru(page);
+ int delta = thp_nr_pages(page);
+ int refs = page_lru_refs(page);
+@@ -252,7 +252,7 @@ static void lru_gen_refault(struct page *page, void *shadow)
+ unsigned long token;
+ unsigned long min_seq;
+ struct lruvec *lruvec;
+- struct lru_gen_struct *lrugen;
++ struct lru_gen_page *lrugen;
+ struct mem_cgroup *memcg;
+ struct pglist_data *pgdat;
+ int type = page_is_file_lru(page);
+--
+2.40.0
+
--- /dev/null
+From afd37e73db04c7e6b47411120ac5f6a7eca51fec Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:00 -0700
+Subject: [PATCH 22/29] mm: multi-gen LRU: rename lrugen->lists[] to
+ lrugen->pages[]
+
+lru_gen_page will be chained into per-node lists by the coming
+lrugen->list.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-3-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/mm_inline.h | 4 ++--
+ include/linux/mmzone.h | 8 ++++----
+ mm/vmscan.c | 20 ++++++++++----------
+ 3 files changed, 16 insertions(+), 16 deletions(-)
+
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 27c4890503c5..4adc9ba59569 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -246,9 +246,9 @@ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bo
+ lru_gen_update_size(lruvec, page, -1, gen);
+ /* for rotate_reclaimable_page() */
+ if (reclaiming)
+- list_add_tail(&page->lru, &lrugen->lists[gen][type][zone]);
++ list_add_tail(&page->lru, &lrugen->pages[gen][type][zone]);
+ else
+- list_add(&page->lru, &lrugen->lists[gen][type][zone]);
++ list_add(&page->lru, &lrugen->pages[gen][type][zone]);
+
+ return true;
+ }
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 5856b026c089..7b8a26aaf381 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -302,7 +302,7 @@ enum lruvec_flags {
+ * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
+ * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
+ * corresponding generation. The gen counter in page->flags stores gen+1 while
+- * a page is on one of lrugen->lists[]. Otherwise it stores 0.
++ * a page is on one of lrugen->pages[]. Otherwise it stores 0.
+ *
+ * A page is added to the youngest generation on faulting. The aging needs to
+ * check the accessed bit at least twice before handing this page over to the
+@@ -314,8 +314,8 @@ enum lruvec_flags {
+ * rest of generations, if they exist, are considered inactive. See
+ * lru_gen_is_active().
+ *
+- * PG_active is always cleared while a page is on one of lrugen->lists[] so that
+- * the aging needs not to worry about it. And it's set again when a page
++ * PG_active is always cleared while a page is on one of lrugen->pages[] so
++ * that the aging needs not to worry about it. And it's set again when a page
+ * considered active is isolated for non-reclaiming purposes, e.g., migration.
+ * See lru_gen_add_page() and lru_gen_del_page().
+ *
+@@ -402,7 +402,7 @@ struct lru_gen_page {
+ /* the birth time of each generation in jiffies */
+ unsigned long timestamps[MAX_NR_GENS];
+ /* the multi-gen LRU lists, lazily sorted on eviction */
+- struct list_head lists[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
++ struct list_head pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+ /* the multi-gen LRU sizes, eventually consistent */
+ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+ /* the exponential moving average of refaulted */
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 3b1b5bd9736a..2322c913aa64 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -3987,7 +3987,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+
+ /* prevent cold/hot inversion if force_scan is true */
+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+- struct list_head *head = &lrugen->lists[old_gen][type][zone];
++ struct list_head *head = &lrugen->pages[old_gen][type][zone];
+
+ while (!list_empty(head)) {
+ struct page *page = lru_to_page(head);
+@@ -3998,7 +3998,7 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+ VM_WARN_ON_ONCE_PAGE(page_zonenum(page) != zone, page);
+
+ new_gen = page_inc_gen(lruvec, page, false);
+- list_move_tail(&page->lru, &lrugen->lists[new_gen][type][zone]);
++ list_move_tail(&page->lru, &lrugen->pages[new_gen][type][zone]);
+
+ if (!--remaining)
+ return false;
+@@ -4026,7 +4026,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+ gen = lru_gen_from_seq(min_seq[type]);
+
+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+- if (!list_empty(&lrugen->lists[gen][type][zone]))
++ if (!list_empty(&lrugen->pages[gen][type][zone]))
+ goto next;
+ }
+
+@@ -4491,7 +4491,7 @@ static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
+
+ /* promoted */
+ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
+- list_move(&page->lru, &lrugen->lists[gen][type][zone]);
++ list_move(&page->lru, &lrugen->pages[gen][type][zone]);
+ return true;
+ }
+
+@@ -4500,7 +4500,7 @@ static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
+ int hist = lru_hist_from_seq(lrugen->min_seq[type]);
+
+ gen = page_inc_gen(lruvec, page, false);
+- list_move_tail(&page->lru, &lrugen->lists[gen][type][zone]);
++ list_move_tail(&page->lru, &lrugen->pages[gen][type][zone]);
+
+ WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
+ lrugen->protected[hist][type][tier - 1] + delta);
+@@ -4512,7 +4512,7 @@ static bool sort_page(struct lruvec *lruvec, struct page *page, int tier_idx)
+ if (PageLocked(page) || PageWriteback(page) ||
+ (type == LRU_GEN_FILE && PageDirty(page))) {
+ gen = page_inc_gen(lruvec, page, true);
+- list_move(&page->lru, &lrugen->lists[gen][type][zone]);
++ list_move(&page->lru, &lrugen->pages[gen][type][zone]);
+ return true;
+ }
+
+@@ -4579,7 +4579,7 @@ static int scan_pages(struct lruvec *lruvec, struct scan_control *sc,
+ for (zone = sc->reclaim_idx; zone >= 0; zone--) {
+ LIST_HEAD(moved);
+ int skipped = 0;
+- struct list_head *head = &lrugen->lists[gen][type][zone];
++ struct list_head *head = &lrugen->pages[gen][type][zone];
+
+ while (!list_empty(head)) {
+ struct page *page = lru_to_page(head);
+@@ -4980,7 +4980,7 @@ static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
+ int gen, type, zone;
+
+ for_each_gen_type_zone(gen, type, zone) {
+- if (!list_empty(&lrugen->lists[gen][type][zone]))
++ if (!list_empty(&lrugen->pages[gen][type][zone]))
+ return false;
+ }
+ }
+@@ -5025,7 +5025,7 @@ static bool drain_evictable(struct lruvec *lruvec)
+ int remaining = MAX_LRU_BATCH;
+
+ for_each_gen_type_zone(gen, type, zone) {
+- struct list_head *head = &lruvec->lrugen.lists[gen][type][zone];
++ struct list_head *head = &lruvec->lrugen.pages[gen][type][zone];
+
+ while (!list_empty(head)) {
+ bool success;
+@@ -5558,7 +5558,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
+ lrugen->timestamps[i] = jiffies;
+
+ for_each_gen_type_zone(gen, type, zone)
+- INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
++ INIT_LIST_HEAD(&lrugen->pages[gen][type][zone]);
+
+ lruvec->mm_state.seq = MIN_NR_GENS;
+ init_waitqueue_head(&lruvec->mm_state.wait);
+--
+2.40.0
+
--- /dev/null
+From ce45f1c4b32cf69b166f56ef5bc6c761e06ed4e5 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:01 -0700
+Subject: [PATCH 23/29] mm: multi-gen LRU: remove eviction fairness safeguard
+
+Recall that the eviction consumes the oldest generation: first it
+bucket-sorts pages whose gen counters were updated by the aging and
+reclaims the rest; then it increments lrugen->min_seq.
+
+The current eviction fairness safeguard for global reclaim has a
+dilemma: when there are multiple eligible memcgs, should it continue
+or stop upon meeting the reclaim goal? If it continues, it overshoots
+and increases direct reclaim latency; if it stops, it loses fairness
+between memcgs it has taken memory away from and those it has yet to.
+
+With memcg LRU, the eviction, while ensuring eventual fairness, will
+stop upon meeting its goal. Therefore the current eviction fairness
+safeguard for global reclaim will not be needed.
+
+Note that memcg LRU only applies to global reclaim. For memcg reclaim,
+the eviction will continue, even if it is overshooting. This becomes
+unconditional due to code simplification.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-4-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 82 +++++++++++++++--------------------------------------
+ 1 file changed, 23 insertions(+), 59 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 2322c913aa64..40e7a947c5c7 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -443,6 +443,11 @@ static bool cgroup_reclaim(struct scan_control *sc)
+ return sc->target_mem_cgroup;
+ }
+
++static bool global_reclaim(struct scan_control *sc)
++{
++ return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup);
++}
++
+ /**
+ * writeback_throttling_sane - is the usual dirty throttling mechanism available?
+ * @sc: scan_control in question
+@@ -493,6 +498,11 @@ static bool cgroup_reclaim(struct scan_control *sc)
+ return false;
+ }
+
++static bool global_reclaim(struct scan_control *sc)
++{
++ return true;
++}
++
+ static bool writeback_throttling_sane(struct scan_control *sc)
+ {
+ return true;
+@@ -4722,8 +4732,7 @@ static int isolate_pages(struct lruvec *lruvec, struct scan_control *sc, int swa
+ return scanned;
+ }
+
+-static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
+- bool *need_swapping)
++static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
+ {
+ int type;
+ int scanned;
+@@ -4812,9 +4821,6 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ goto retry;
+ }
+
+- if (need_swapping && type == LRU_GEN_ANON)
+- *need_swapping = true;
+-
+ return scanned;
+ }
+
+@@ -4853,68 +4859,26 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+ }
+
+-static bool should_abort_scan(struct lruvec *lruvec, unsigned long seq,
+- struct scan_control *sc, bool need_swapping)
++static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+ {
+- int i;
+- DEFINE_MAX_SEQ(lruvec);
+-
+- if (!current_is_kswapd()) {
+- /* age each memcg once to ensure fairness */
+- if (max_seq - seq > 1)
+- return true;
+-
+- /* over-swapping can increase allocation latency */
+- if (sc->nr_reclaimed >= sc->nr_to_reclaim && need_swapping)
+- return true;
+-
+- /* give this thread a chance to exit and free its memory */
+- if (fatal_signal_pending(current)) {
+- sc->nr_reclaimed += MIN_LRU_BATCH;
+- return true;
+- }
+-
+- if (cgroup_reclaim(sc))
+- return false;
+- } else if (sc->nr_reclaimed - sc->last_reclaimed < sc->nr_to_reclaim)
+- return false;
+-
+- /* keep scanning at low priorities to ensure fairness */
+- if (sc->priority > DEF_PRIORITY - 2)
+- return false;
+-
+- /*
+- * A minimum amount of work was done under global memory pressure. For
+- * kswapd, it may be overshooting. For direct reclaim, the target isn't
+- * met, and yet the allocation may still succeed, since kswapd may have
+- * caught up. In either case, it's better to stop now, and restart if
+- * necessary.
+- */
+- for (i = 0; i <= sc->reclaim_idx; i++) {
+- unsigned long wmark;
+- struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+-
+- if (!managed_zone(zone))
+- continue;
+-
+- wmark = current_is_kswapd() ? high_wmark_pages(zone) : low_wmark_pages(zone);
+- if (wmark > zone_page_state(zone, NR_FREE_PAGES))
+- return false;
+- }
++ /* don't abort memcg reclaim to ensure fairness */
++ if (!global_reclaim(sc))
++ return -1;
+
+- sc->nr_reclaimed += MIN_LRU_BATCH;
++ /* discount the previous progress for kswapd */
++ if (current_is_kswapd())
++ return sc->nr_to_reclaim + sc->last_reclaimed;
+
+- return true;
++ return max(sc->nr_to_reclaim, compact_gap(sc->order));
+ }
+
+ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ struct blk_plug plug;
+ bool need_aging = false;
+- bool need_swapping = false;
+ unsigned long scanned = 0;
+ unsigned long reclaimed = sc->nr_reclaimed;
+- DEFINE_MAX_SEQ(lruvec);
++ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+
+ lru_add_drain();
+
+@@ -4938,7 +4902,7 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ if (!nr_to_scan)
+ goto done;
+
+- delta = evict_pages(lruvec, sc, swappiness, &need_swapping);
++ delta = evict_pages(lruvec, sc, swappiness);
+ if (!delta)
+ goto done;
+
+@@ -4946,7 +4910,7 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ if (scanned >= nr_to_scan)
+ break;
+
+- if (should_abort_scan(lruvec, max_seq, sc, need_swapping))
++ if (sc->nr_reclaimed >= nr_to_reclaim)
+ break;
+
+ cond_resched();
+@@ -5393,7 +5357,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
+ if (sc->nr_reclaimed >= nr_to_reclaim)
+ return 0;
+
+- if (!evict_pages(lruvec, sc, swappiness, NULL))
++ if (!evict_pages(lruvec, sc, swappiness))
+ return 0;
+
+ cond_resched();
+--
+2.40.0
+
--- /dev/null
+From e20b7386fccc18c791796eb1dc1a91eee3ccf801 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:02 -0700
+Subject: [PATCH 24/29] mm: multi-gen LRU: remove aging fairness safeguard
+
+Recall that the aging produces the youngest generation: first it scans
+for accessed pages and updates their gen counters; then it increments
+lrugen->max_seq.
+
+The current aging fairness safeguard for kswapd uses two passes to
+ensure the fairness to multiple eligible memcgs. On the first pass,
+which is shared with the eviction, it checks whether all eligible
+memcgs are low on cold pages. If so, it requires a second pass, on
+which it ages all those memcgs at the same time.
+
+With memcg LRU, the aging, while ensuring eventual fairness, will run
+when necessary. Therefore the current aging fairness safeguard for
+kswapd will not be needed.
+
+Note that memcg LRU only applies to global reclaim. For memcg reclaim,
+the aging can be unfair to different memcgs, i.e., their
+lrugen->max_seq can be incremented at different paces.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-5-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 126 ++++++++++++++++++++++++----------------------------
+ 1 file changed, 59 insertions(+), 67 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 40e7a947c5c7..7159436872ba 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -131,7 +131,6 @@ struct scan_control {
+
+ #ifdef CONFIG_LRU_GEN
+ /* help kswapd make better choices among multiple memcgs */
+- unsigned int memcgs_need_aging:1;
+ unsigned long last_reclaimed;
+ #endif
+
+@@ -4184,7 +4183,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ return true;
+ }
+
+-static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq,
++static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
+ struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
+ {
+ int gen, type, zone;
+@@ -4193,6 +4192,13 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig
+ unsigned long total = 0;
+ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ /* whether this lruvec is completely out of cold pages */
++ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
++ *nr_to_scan = 0;
++ return true;
++ }
+
+ for (type = !can_swap; type < ANON_AND_FILE; type++) {
+ unsigned long seq;
+@@ -4221,8 +4227,6 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig
+ * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
+ * ideal number of generations is MIN_NR_GENS+1.
+ */
+- if (min_seq[!can_swap] + MIN_NR_GENS > max_seq)
+- return true;
+ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
+ return false;
+
+@@ -4241,40 +4245,54 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, unsig
+ return false;
+ }
+
+-static bool age_lruvec(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl)
++static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
+ {
+- bool need_aging;
+- unsigned long nr_to_scan;
+- int swappiness = get_swappiness(lruvec, sc);
++ int gen, type, zone;
++ unsigned long total = 0;
++ bool can_swap = get_swappiness(lruvec, sc);
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+ DEFINE_MIN_SEQ(lruvec);
+
+- VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
++ for (type = !can_swap; type < ANON_AND_FILE; type++) {
++ unsigned long seq;
+
+- mem_cgroup_calculate_protection(NULL, memcg);
++ for (seq = min_seq[type]; seq <= max_seq; seq++) {
++ gen = lru_gen_from_seq(seq);
+
+- if (mem_cgroup_below_min(memcg))
+- return false;
++ for (zone = 0; zone < MAX_NR_ZONES; zone++)
++ total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
++ }
++ }
+
+- need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, swappiness, &nr_to_scan);
++ /* whether the size is big enough to be helpful */
++ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
++}
+
+- if (min_ttl) {
+- int gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
+- unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
++static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc,
++ unsigned long min_ttl)
++{
++ int gen;
++ unsigned long birth;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
+
+- if (time_is_after_jiffies(birth + min_ttl))
+- return false;
++ VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
+
+- /* the size is likely too small to be helpful */
+- if (!nr_to_scan && sc->priority != DEF_PRIORITY)
+- return false;
+- }
++ /* see the comment on lru_gen_page */
++ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
++ birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+
+- if (need_aging)
+- try_to_inc_max_seq(lruvec, max_seq, sc, swappiness, false);
++ if (time_is_after_jiffies(birth + min_ttl))
++ return false;
+
+- return true;
++ if (!lruvec_is_sizable(lruvec, sc))
++ return false;
++
++ mem_cgroup_calculate_protection(NULL, memcg);
++
++ return !mem_cgroup_below_min(memcg);
+ }
+
+ /* to protect the working set of the last N jiffies */
+@@ -4283,46 +4301,32 @@ static unsigned long lru_gen_min_ttl __read_mostly;
+ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ {
+ struct mem_cgroup *memcg;
+- bool success = false;
+ unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
+ sc->last_reclaimed = sc->nr_reclaimed;
+
+- /*
+- * To reduce the chance of going into the aging path, which can be
+- * costly, optimistically skip it if the flag below was cleared in the
+- * eviction path. This improves the overall performance when multiple
+- * memcgs are available.
+- */
+- if (!sc->memcgs_need_aging) {
+- sc->memcgs_need_aging = true;
++ /* check the order to exclude compaction-induced reclaim */
++ if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY)
+ return;
+- }
+-
+- set_mm_walk(pgdat);
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+- if (age_lruvec(lruvec, sc, min_ttl))
+- success = true;
++ if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) {
++ mem_cgroup_iter_break(NULL, memcg);
++ return;
++ }
+
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+- clear_mm_walk();
+-
+- /* check the order to exclude compaction-induced reclaim */
+- if (success || !min_ttl || sc->order)
+- return;
+-
+ /*
+ * The main goal is to OOM kill if every generation from all memcgs is
+ * younger than min_ttl. However, another possibility is all memcgs are
+- * either below min or empty.
++ * either too small or below min.
+ */
+ if (mutex_trylock(&oom_lock)) {
+ struct oom_control oc = {
+@@ -4830,33 +4834,27 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ * reclaim.
+ */
+ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+- bool can_swap, bool *need_aging)
++ bool can_swap)
+ {
+ unsigned long nr_to_scan;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+- DEFINE_MIN_SEQ(lruvec);
+
+ if (mem_cgroup_below_min(memcg) ||
+ (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
+ return 0;
+
+- *need_aging = should_run_aging(lruvec, max_seq, min_seq, sc, can_swap, &nr_to_scan);
+- if (!*need_aging)
++ if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
+ return nr_to_scan;
+
+ /* skip the aging path at the default priority */
+ if (sc->priority == DEF_PRIORITY)
+- goto done;
++ return nr_to_scan;
+
+- /* leave the work to lru_gen_age_node() */
+- if (current_is_kswapd())
+- return 0;
++ try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false);
+
+- if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false))
+- return nr_to_scan;
+-done:
+- return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
++ /* skip this lruvec as it's low on cold pages */
++ return 0;
+ }
+
+ static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+@@ -4875,9 +4873,7 @@ static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ struct blk_plug plug;
+- bool need_aging = false;
+ unsigned long scanned = 0;
+- unsigned long reclaimed = sc->nr_reclaimed;
+ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+
+ lru_add_drain();
+@@ -4898,13 +4894,13 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ else
+ swappiness = 0;
+
+- nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness, &need_aging);
++ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+ if (!nr_to_scan)
+- goto done;
++ break;
+
+ delta = evict_pages(lruvec, sc, swappiness);
+ if (!delta)
+- goto done;
++ break;
+
+ scanned += delta;
+ if (scanned >= nr_to_scan)
+@@ -4916,10 +4912,6 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ cond_resched();
+ }
+
+- /* see the comment in lru_gen_age_node() */
+- if (sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH && !need_aging)
+- sc->memcgs_need_aging = false;
+-done:
+ clear_mm_walk();
+
+ blk_finish_plug(&plug);
+--
+2.40.0
+
--- /dev/null
+From 107d54931df3c28d81648122e219bf0034ef4e99 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:03 -0700
+Subject: [PATCH 25/29] mm: multi-gen LRU: shuffle should_run_aging()
+
+Move should_run_aging() next to its only caller left.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-6-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 124 ++++++++++++++++++++++++++--------------------------
+ 1 file changed, 62 insertions(+), 62 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 7159436872ba..cb026e2714d7 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4183,68 +4183,6 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ return true;
+ }
+
+-static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
+- struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
+-{
+- int gen, type, zone;
+- unsigned long old = 0;
+- unsigned long young = 0;
+- unsigned long total = 0;
+- struct lru_gen_page *lrugen = &lruvec->lrugen;
+- struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+- DEFINE_MIN_SEQ(lruvec);
+-
+- /* whether this lruvec is completely out of cold pages */
+- if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
+- *nr_to_scan = 0;
+- return true;
+- }
+-
+- for (type = !can_swap; type < ANON_AND_FILE; type++) {
+- unsigned long seq;
+-
+- for (seq = min_seq[type]; seq <= max_seq; seq++) {
+- unsigned long size = 0;
+-
+- gen = lru_gen_from_seq(seq);
+-
+- for (zone = 0; zone < MAX_NR_ZONES; zone++)
+- size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+-
+- total += size;
+- if (seq == max_seq)
+- young += size;
+- else if (seq + MIN_NR_GENS == max_seq)
+- old += size;
+- }
+- }
+-
+- /* try to scrape all its memory if this memcg was deleted */
+- *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+-
+- /*
+- * The aging tries to be lazy to reduce the overhead, while the eviction
+- * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
+- * ideal number of generations is MIN_NR_GENS+1.
+- */
+- if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
+- return false;
+-
+- /*
+- * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
+- * of the total number of pages for each generation. A reasonable range
+- * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
+- * aging cares about the upper bound of hot pages, while the eviction
+- * cares about the lower bound of cold pages.
+- */
+- if (young * MIN_NR_GENS > total)
+- return true;
+- if (old * (MIN_NR_GENS + 2) < total)
+- return true;
+-
+- return false;
+-}
+-
+ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ int gen, type, zone;
+@@ -4828,6 +4766,68 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
+ return scanned;
+ }
+
++static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
++ struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan)
++{
++ int gen, type, zone;
++ unsigned long old = 0;
++ unsigned long young = 0;
++ unsigned long total = 0;
++ struct lru_gen_page *lrugen = &lruvec->lrugen;
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ DEFINE_MIN_SEQ(lruvec);
++
++ /* whether this lruvec is completely out of cold pages */
++ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
++ *nr_to_scan = 0;
++ return true;
++ }
++
++ for (type = !can_swap; type < ANON_AND_FILE; type++) {
++ unsigned long seq;
++
++ for (seq = min_seq[type]; seq <= max_seq; seq++) {
++ unsigned long size = 0;
++
++ gen = lru_gen_from_seq(seq);
++
++ for (zone = 0; zone < MAX_NR_ZONES; zone++)
++ size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
++
++ total += size;
++ if (seq == max_seq)
++ young += size;
++ else if (seq + MIN_NR_GENS == max_seq)
++ old += size;
++ }
++ }
++
++ /* try to scrape all its memory if this memcg was deleted */
++ *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
++
++ /*
++ * The aging tries to be lazy to reduce the overhead, while the eviction
++ * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
++ * ideal number of generations is MIN_NR_GENS+1.
++ */
++ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
++ return false;
++
++ /*
++ * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
++ * of the total number of pages for each generation. A reasonable range
++ * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
++ * aging cares about the upper bound of hot pages, while the eviction
++ * cares about the lower bound of cold pages.
++ */
++ if (young * MIN_NR_GENS > total)
++ return true;
++ if (old * (MIN_NR_GENS + 2) < total)
++ return true;
++
++ return false;
++}
++
+ /*
+ * For future optimizations:
+ * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
+--
+2.40.0
+
--- /dev/null
+From fa6363828d314e837c5f79e97ea5e8c0d2f7f062 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:04 -0700
+Subject: [PATCH 26/29] mm: multi-gen LRU: per-node lru_gen_page lists
+
+For each node, memcgs are divided into two generations: the old and
+the young. For each generation, memcgs are randomly sharded into
+multiple bins to improve scalability. For each bin, an RCU hlist_nulls
+is virtually divided into three segments: the head, the tail and the
+default.
+
+An onlining memcg is added to the tail of a random bin in the old
+generation. The eviction starts at the head of a random bin in the old
+generation. The per-node memcg generation counter, whose reminder (mod
+2) indexes the old generation, is incremented when all its bins become
+empty.
+
+There are four operations:
+1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in
+ its current generation (old or young) and updates its "seg" to
+ "head";
+2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in
+ its current generation (old or young) and updates its "seg" to
+ "tail";
+3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in
+ the old generation, updates its "gen" to "old" and resets its "seg"
+ to "default";
+4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin
+ in the young generation, updates its "gen" to "young" and resets
+ its "seg" to "default".
+
+The events that trigger the above operations are:
+1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
+2. The first attempt to reclaim an memcg below low, which triggers
+ MEMCG_LRU_TAIL;
+3. The first attempt to reclaim an memcg below reclaimable size
+ threshold, which triggers MEMCG_LRU_TAIL;
+4. The second attempt to reclaim an memcg below reclaimable size
+ threshold, which triggers MEMCG_LRU_YOUNG;
+5. Attempting to reclaim an memcg below min, which triggers
+ MEMCG_LRU_YOUNG;
+6. Finishing the aging on the eviction path, which triggers
+ MEMCG_LRU_YOUNG;
+7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+
+Note that memcg LRU only applies to global reclaim, and the
+round-robin incrementing of their max_seq counters ensures the
+eventual fairness to all eligible memcgs. For memcg reclaim, it still
+relies on mem_cgroup_iter().
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-7-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ include/linux/memcontrol.h | 10 +
+ include/linux/mm_inline.h | 17 ++
+ include/linux/mmzone.h | 117 +++++++++++-
+ mm/memcontrol.c | 16 ++
+ mm/page_alloc.c | 1 +
+ mm/vmscan.c | 373 +++++++++++++++++++++++++++++++++----
+ 6 files changed, 499 insertions(+), 35 deletions(-)
+
+diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
+index 3736405cbcf6..2e405fd88846 100644
+--- a/include/linux/memcontrol.h
++++ b/include/linux/memcontrol.h
+@@ -818,6 +818,11 @@ static inline void obj_cgroup_put(struct obj_cgroup *objcg)
+ percpu_ref_put(&objcg->refcnt);
+ }
+
++static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
++{
++ return !memcg || css_tryget(&memcg->css);
++}
++
+ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+ {
+ if (memcg)
+@@ -1283,6 +1288,11 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
+ return NULL;
+ }
+
++static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
++{
++ return true;
++}
++
+ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+ {
+ }
+diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
+index 4adc9ba59569..9138c2e638ce 100644
+--- a/include/linux/mm_inline.h
++++ b/include/linux/mm_inline.h
+@@ -112,6 +112,18 @@ static inline bool lru_gen_in_fault(void)
+ return current->in_lru_fault;
+ }
+
++#ifdef CONFIG_MEMCG
++static inline int lru_gen_memcg_seg(struct lruvec *lruvec)
++{
++ return READ_ONCE(lruvec->lrugen.seg);
++}
++#else
++static inline int lru_gen_memcg_seg(struct lruvec *lruvec)
++{
++ return 0;
++}
++#endif
++
+ static inline int lru_gen_from_seq(unsigned long seq)
+ {
+ return seq % MAX_NR_GENS;
+@@ -287,6 +299,11 @@ static inline bool lru_gen_in_fault(void)
+ return false;
+ }
+
++static inline int lru_gen_memcg_seg(struct lruvec *lruvec)
++{
++ return 0;
++}
++
+ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bool reclaiming)
+ {
+ return false;
+diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
+index 7b8a26aaf381..4bbf191517e2 100644
+--- a/include/linux/mmzone.h
++++ b/include/linux/mmzone.h
+@@ -7,6 +7,7 @@
+
+ #include <linux/spinlock.h>
+ #include <linux/list.h>
++#include <linux/list_nulls.h>
+ #include <linux/wait.h>
+ #include <linux/bitops.h>
+ #include <linux/cache.h>
+@@ -357,6 +358,15 @@ struct page_vma_mapped_walk;
+ #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
+ #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
+
++/* see the comment on MEMCG_NR_GENS */
++enum {
++ MEMCG_LRU_NOP,
++ MEMCG_LRU_HEAD,
++ MEMCG_LRU_TAIL,
++ MEMCG_LRU_OLD,
++ MEMCG_LRU_YOUNG,
++};
++
+ #ifdef CONFIG_LRU_GEN
+
+ enum {
+@@ -416,6 +426,14 @@ struct lru_gen_page {
+ atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+ /* whether the multi-gen LRU is enabled */
+ bool enabled;
++#ifdef CONFIG_MEMCG
++ /* the memcg generation this lru_gen_page belongs to */
++ u8 gen;
++ /* the list segment this lru_gen_page belongs to */
++ u8 seg;
++ /* per-node lru_gen_page list for global reclaim */
++ struct hlist_nulls_node list;
++#endif
+ };
+
+ enum {
+@@ -469,12 +487,87 @@ void lru_gen_init_lruvec(struct lruvec *lruvec);
+ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+
+ #ifdef CONFIG_MEMCG
++
++/*
++ * For each node, memcgs are divided into two generations: the old and the
++ * young. For each generation, memcgs are randomly sharded into multiple bins
++ * to improve scalability. For each bin, the hlist_nulls is virtually divided
++ * into three segments: the head, the tail and the default.
++ *
++ * An onlining memcg is added to the tail of a random bin in the old generation.
++ * The eviction starts at the head of a random bin in the old generation. The
++ * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes
++ * the old generation, is incremented when all its bins become empty.
++ *
++ * There are four operations:
++ * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
++ * current generation (old or young) and updates its "seg" to "head";
++ * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
++ * current generation (old or young) and updates its "seg" to "tail";
++ * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
++ * generation, updates its "gen" to "old" and resets its "seg" to "default";
++ * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
++ * young generation, updates its "gen" to "young" and resets its "seg" to
++ * "default".
++ *
++ * The events that trigger the above operations are:
++ * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
++ * 2. The first attempt to reclaim an memcg below low, which triggers
++ * MEMCG_LRU_TAIL;
++ * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
++ * which triggers MEMCG_LRU_TAIL;
++ * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
++ * which triggers MEMCG_LRU_YOUNG;
++ * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
++ * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
++ * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
++ *
++ * Note that memcg LRU only applies to global reclaim, and the round-robin
++ * incrementing of their max_seq counters ensures the eventual fairness to all
++ * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
++ */
++#define MEMCG_NR_GENS 2
++#define MEMCG_NR_BINS 8
++
++struct lru_gen_memcg {
++ /* the per-node memcg generation counter */
++ unsigned long seq;
++ /* each memcg has one lru_gen_page per node */
++ unsigned long nr_memcgs[MEMCG_NR_GENS];
++ /* per-node lru_gen_page list for global reclaim */
++ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS];
++ /* protects the above */
++ spinlock_t lock;
++};
++
++void lru_gen_init_pgdat(struct pglist_data *pgdat);
++
+ void lru_gen_init_memcg(struct mem_cgroup *memcg);
+ void lru_gen_exit_memcg(struct mem_cgroup *memcg);
+-#endif
++void lru_gen_online_memcg(struct mem_cgroup *memcg);
++void lru_gen_offline_memcg(struct mem_cgroup *memcg);
++void lru_gen_release_memcg(struct mem_cgroup *memcg);
++void lru_gen_rotate_memcg(struct lruvec *lruvec, int op);
++
++#else /* !CONFIG_MEMCG */
++
++#define MEMCG_NR_GENS 1
++
++struct lru_gen_memcg {
++};
++
++static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
++{
++}
++
++#endif /* CONFIG_MEMCG */
+
+ #else /* !CONFIG_LRU_GEN */
+
++static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
++{
++}
++
+ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
+ {
+ }
+@@ -484,6 +577,7 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+ }
+
+ #ifdef CONFIG_MEMCG
++
+ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
+ {
+ }
+@@ -491,7 +585,24 @@ static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
+ static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg)
+ {
+ }
+-#endif
++
++static inline void lru_gen_online_memcg(struct mem_cgroup *memcg)
++{
++}
++
++static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg)
++{
++}
++
++static inline void lru_gen_release_memcg(struct mem_cgroup *memcg)
++{
++}
++
++static inline void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
++{
++}
++
++#endif /* CONFIG_MEMCG */
+
+ #endif /* CONFIG_LRU_GEN */
+
+@@ -1105,6 +1216,8 @@ typedef struct pglist_data {
+ #ifdef CONFIG_LRU_GEN
+ /* kswap mm walk data */
+ struct lru_gen_mm_walk mm_walk;
++ /* lru_gen_page list */
++ struct lru_gen_memcg memcg_lru;
+ #endif
+
+ ZONE_PADDING(_pad2_)
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index ed87d1256f0e..172adfbee06e 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -549,6 +549,16 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+ struct mem_cgroup_per_node *mz;
+ struct mem_cgroup_tree_per_node *mctz;
+
++ if (lru_gen_enabled()) {
++ struct lruvec *lruvec = &mem_cgroup_page_nodeinfo(memcg, page)->lruvec;
++
++ /* see the comment on MEMCG_NR_GENS */
++ if (soft_limit_excess(memcg) && lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD)
++ lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD);
++
++ return;
++ }
++
+ mctz = soft_limit_tree_from_page(page);
+ if (!mctz)
+ return;
+@@ -3433,6 +3443,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
+ unsigned long excess;
+ unsigned long nr_scanned;
+
++ if (lru_gen_enabled())
++ return 0;
++
+ if (order > 0)
+ return 0;
+
+@@ -5321,6 +5334,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
+ if (unlikely(mem_cgroup_is_root(memcg)))
+ queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
+ 2UL*HZ);
++ lru_gen_online_memcg(memcg);
+ return 0;
+ }
+
+@@ -5347,6 +5361,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
+ memcg_offline_kmem(memcg);
+ reparent_shrinker_deferred(memcg);
+ wb_memcg_offline(memcg);
++ lru_gen_offline_memcg(memcg);
+
+ drain_all_stock(memcg);
+
+@@ -5358,6 +5373,7 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
+ struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+ invalidate_reclaim_iterators(memcg);
++ lru_gen_release_memcg(memcg);
+ }
+
+ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index c929357fbefe..6459d9c018be 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -7645,6 +7645,7 @@ static void __init free_area_init_node(int nid)
+ pgdat_set_deferred_range(pgdat);
+
+ free_area_init_core(pgdat);
++ lru_gen_init_pgdat(pgdat);
+ }
+
+ void __init free_area_init_memoryless_node(int nid)
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index cb026e2714d7..3d8e0665186c 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -54,6 +54,8 @@
+ #include <linux/shmem_fs.h>
+ #include <linux/ctype.h>
+ #include <linux/debugfs.h>
++#include <linux/rculist_nulls.h>
++#include <linux/random.h>
+
+ #include <asm/tlbflush.h>
+ #include <asm/div64.h>
+@@ -129,11 +131,6 @@ struct scan_control {
+ /* Always discard instead of demoting to lower tier memory */
+ unsigned int no_demotion:1;
+
+-#ifdef CONFIG_LRU_GEN
+- /* help kswapd make better choices among multiple memcgs */
+- unsigned long last_reclaimed;
+-#endif
+-
+ /* Allocation order */
+ s8 order;
+
+@@ -2880,6 +2877,9 @@ DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
+ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \
+ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
+
++#define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS)
++#define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS)
++
+ static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
+ {
+ struct pglist_data *pgdat = NODE_DATA(nid);
+@@ -4169,8 +4169,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ if (sc->priority <= DEF_PRIORITY - 2)
+ wait_event_killable(lruvec->mm_state.wait,
+ max_seq < READ_ONCE(lrugen->max_seq));
+-
+- return max_seq < READ_ONCE(lrugen->max_seq);
++ return false;
+ }
+
+ VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq));
+@@ -4243,8 +4242,6 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
+- sc->last_reclaimed = sc->nr_reclaimed;
+-
+ /* check the order to exclude compaction-induced reclaim */
+ if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY)
+ return;
+@@ -4833,8 +4830,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
+ * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
+ * reclaim.
+ */
+-static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc,
+- bool can_swap)
++static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap)
+ {
+ unsigned long nr_to_scan;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+@@ -4851,10 +4847,8 @@ static unsigned long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *
+ if (sc->priority == DEF_PRIORITY)
+ return nr_to_scan;
+
+- try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false);
+-
+ /* skip this lruvec as it's low on cold pages */
+- return 0;
++ return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
+ }
+
+ static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+@@ -4863,29 +4857,18 @@ static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+ if (!global_reclaim(sc))
+ return -1;
+
+- /* discount the previous progress for kswapd */
+- if (current_is_kswapd())
+- return sc->nr_to_reclaim + sc->last_reclaimed;
+-
+ return max(sc->nr_to_reclaim, compact_gap(sc->order));
+ }
+
+-static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ {
+- struct blk_plug plug;
++ long nr_to_scan;
+ unsigned long scanned = 0;
+ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+
+- lru_add_drain();
+-
+- blk_start_plug(&plug);
+-
+- set_mm_walk(lruvec_pgdat(lruvec));
+-
+ while (true) {
+ int delta;
+ int swappiness;
+- unsigned long nr_to_scan;
+
+ if (sc->may_swap)
+ swappiness = get_swappiness(lruvec, sc);
+@@ -4895,7 +4878,7 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ swappiness = 0;
+
+ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+- if (!nr_to_scan)
++ if (nr_to_scan <= 0)
+ break;
+
+ delta = evict_pages(lruvec, sc, swappiness);
+@@ -4912,11 +4895,251 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ cond_resched();
+ }
+
++ /* whether try_to_inc_max_seq() was successful */
++ return nr_to_scan < 0;
++}
++
++static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
++{
++ bool success;
++ unsigned long scanned = sc->nr_scanned;
++ unsigned long reclaimed = sc->nr_reclaimed;
++ int seg = lru_gen_memcg_seg(lruvec);
++ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
++ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
++
++ /* see the comment on MEMCG_NR_GENS */
++ if (!lruvec_is_sizable(lruvec, sc))
++ return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
++
++ mem_cgroup_calculate_protection(NULL, memcg);
++
++ if (mem_cgroup_below_min(memcg))
++ return MEMCG_LRU_YOUNG;
++
++ if (mem_cgroup_below_low(memcg)) {
++ /* see the comment on MEMCG_NR_GENS */
++ if (seg != MEMCG_LRU_TAIL)
++ return MEMCG_LRU_TAIL;
++
++ memcg_memory_event(memcg, MEMCG_LOW);
++ }
++
++ success = try_to_shrink_lruvec(lruvec, sc);
++
++ shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority);
++
++ vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned,
++ sc->nr_reclaimed - reclaimed);
++
++ sc->nr_reclaimed += current->reclaim_state->reclaimed_slab;
++ current->reclaim_state->reclaimed_slab = 0;
++
++ return success ? MEMCG_LRU_YOUNG : 0;
++}
++
++#ifdef CONFIG_MEMCG
++
++static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ int gen;
++ int bin;
++ int first_bin;
++ struct lruvec *lruvec;
++ struct lru_gen_page *lrugen;
++ const struct hlist_nulls_node *pos;
++ int op = 0;
++ struct mem_cgroup *memcg = NULL;
++ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
++
++ bin = first_bin = prandom_u32_max(MEMCG_NR_BINS);
++restart:
++ gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
++
++ rcu_read_lock();
++
++ hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) {
++ if (op)
++ lru_gen_rotate_memcg(lruvec, op);
++
++ mem_cgroup_put(memcg);
++
++ lruvec = container_of(lrugen, struct lruvec, lrugen);
++ memcg = lruvec_memcg(lruvec);
++
++ if (!mem_cgroup_tryget(memcg)) {
++ op = 0;
++ memcg = NULL;
++ continue;
++ }
++
++ rcu_read_unlock();
++
++ op = shrink_one(lruvec, sc);
++
++ if (sc->nr_reclaimed >= nr_to_reclaim)
++ goto success;
++
++ rcu_read_lock();
++ }
++
++ rcu_read_unlock();
++
++ /* restart if raced with lru_gen_rotate_memcg() */
++ if (gen != get_nulls_value(pos))
++ goto restart;
++
++ /* try the rest of the bins of the current generation */
++ bin = get_memcg_bin(bin + 1);
++ if (bin != first_bin)
++ goto restart;
++success:
++ if (op)
++ lru_gen_rotate_memcg(lruvec, op);
++
++ mem_cgroup_put(memcg);
++}
++
++static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++{
++ struct blk_plug plug;
++
++ VM_WARN_ON_ONCE(global_reclaim(sc));
++
++ lru_add_drain();
++
++ blk_start_plug(&plug);
++
++ set_mm_walk(lruvec_pgdat(lruvec));
++
++ if (try_to_shrink_lruvec(lruvec, sc))
++ lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG);
++
++ clear_mm_walk();
++
++ blk_finish_plug(&plug);
++}
++
++#else /* !CONFIG_MEMCG */
++
++static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ BUILD_BUG();
++}
++
++static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
++{
++ BUILD_BUG();
++}
++
++#endif
++
++static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ int priority;
++ unsigned long reclaimable;
++ struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
++
++ if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
++ return;
++ /*
++ * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
++ * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
++ * estimated reclaimed_to_scanned_ratio = inactive / total.
++ */
++ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
++ if (get_swappiness(lruvec, sc))
++ reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
++
++ reclaimable /= MEMCG_NR_GENS;
++
++ /* round down reclaimable and round up sc->nr_to_reclaim */
++ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
++
++ sc->priority = clamp(priority, 0, DEF_PRIORITY);
++}
++
++static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ struct blk_plug plug;
++ unsigned long reclaimed = sc->nr_reclaimed;
++
++ VM_WARN_ON_ONCE(!global_reclaim(sc));
++
++ lru_add_drain();
++
++ blk_start_plug(&plug);
++
++ set_mm_walk(pgdat);
++
++ set_initial_priority(pgdat, sc);
++
++ if (current_is_kswapd())
++ sc->nr_reclaimed = 0;
++
++ if (mem_cgroup_disabled())
++ shrink_one(&pgdat->__lruvec, sc);
++ else
++ shrink_many(pgdat, sc);
++
++ if (current_is_kswapd())
++ sc->nr_reclaimed += reclaimed;
++
+ clear_mm_walk();
+
+ blk_finish_plug(&plug);
++
++ /* kswapd should never fail */
++ pgdat->kswapd_failures = 0;
+ }
+
++#ifdef CONFIG_MEMCG
++void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
++{
++ int seg;
++ int old, new;
++ int bin = prandom_u32_max(MEMCG_NR_BINS);
++ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
++
++ spin_lock(&pgdat->memcg_lru.lock);
++
++ VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
++
++ seg = 0;
++ new = old = lruvec->lrugen.gen;
++
++ /* see the comment on MEMCG_NR_GENS */
++ if (op == MEMCG_LRU_HEAD)
++ seg = MEMCG_LRU_HEAD;
++ else if (op == MEMCG_LRU_TAIL)
++ seg = MEMCG_LRU_TAIL;
++ else if (op == MEMCG_LRU_OLD)
++ new = get_memcg_gen(pgdat->memcg_lru.seq);
++ else if (op == MEMCG_LRU_YOUNG)
++ new = get_memcg_gen(pgdat->memcg_lru.seq + 1);
++ else
++ VM_WARN_ON_ONCE(true);
++
++ hlist_nulls_del_rcu(&lruvec->lrugen.list);
++
++ if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
++ hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]);
++ else
++ hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]);
++
++ pgdat->memcg_lru.nr_memcgs[old]--;
++ pgdat->memcg_lru.nr_memcgs[new]++;
++
++ lruvec->lrugen.gen = new;
++ WRITE_ONCE(lruvec->lrugen.seg, seg);
++
++ if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
++ WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
++
++ spin_unlock(&pgdat->memcg_lru.lock);
++}
++#endif
++
+ /******************************************************************************
+ * state change
+ ******************************************************************************/
+@@ -5370,11 +5593,11 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
+
+ if (!mem_cgroup_disabled()) {
+ rcu_read_lock();
++
+ memcg = mem_cgroup_from_id(memcg_id);
+-#ifdef CONFIG_MEMCG
+- if (memcg && !css_tryget(&memcg->css))
++ if (!mem_cgroup_tryget(memcg))
+ memcg = NULL;
+-#endif
++
+ rcu_read_unlock();
+
+ if (!memcg)
+@@ -5521,6 +5744,19 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
+ }
+
+ #ifdef CONFIG_MEMCG
++
++void lru_gen_init_pgdat(struct pglist_data *pgdat)
++{
++ int i, j;
++
++ spin_lock_init(&pgdat->memcg_lru.lock);
++
++ for (i = 0; i < MEMCG_NR_GENS; i++) {
++ for (j = 0; j < MEMCG_NR_BINS; j++)
++ INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
++ }
++}
++
+ void lru_gen_init_memcg(struct mem_cgroup *memcg)
+ {
+ INIT_LIST_HEAD(&memcg->mm_list.fifo);
+@@ -5544,7 +5780,69 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg)
+ }
+ }
+ }
+-#endif
++
++void lru_gen_online_memcg(struct mem_cgroup *memcg)
++{
++ int gen;
++ int nid;
++ int bin = prandom_u32_max(MEMCG_NR_BINS);
++
++ for_each_node(nid) {
++ struct pglist_data *pgdat = NODE_DATA(nid);
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ spin_lock(&pgdat->memcg_lru.lock);
++
++ VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list));
++
++ gen = get_memcg_gen(pgdat->memcg_lru.seq);
++
++ hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
++ pgdat->memcg_lru.nr_memcgs[gen]++;
++
++ lruvec->lrugen.gen = gen;
++
++ spin_unlock(&pgdat->memcg_lru.lock);
++ }
++}
++
++void lru_gen_offline_memcg(struct mem_cgroup *memcg)
++{
++ int nid;
++
++ for_each_node(nid) {
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD);
++ }
++}
++
++void lru_gen_release_memcg(struct mem_cgroup *memcg)
++{
++ int gen;
++ int nid;
++
++ for_each_node(nid) {
++ struct pglist_data *pgdat = NODE_DATA(nid);
++ struct lruvec *lruvec = get_lruvec(memcg, nid);
++
++ spin_lock(&pgdat->memcg_lru.lock);
++
++ VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list));
++
++ gen = lruvec->lrugen.gen;
++
++ hlist_nulls_del_rcu(&lruvec->lrugen.list);
++ pgdat->memcg_lru.nr_memcgs[gen]--;
++
++ if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq))
++ WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
++
++ spin_unlock(&pgdat->memcg_lru.lock);
++ }
++}
++
++#endif /* CONFIG_MEMCG */
+
+ static int __init init_lru_gen(void)
+ {
+@@ -5571,6 +5869,10 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ {
+ }
+
++static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
++{
++}
++
+ #endif /* CONFIG_LRU_GEN */
+
+ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+@@ -5584,7 +5886,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ bool proportional_reclaim;
+ struct blk_plug plug;
+
+- if (lru_gen_enabled()) {
++ if (lru_gen_enabled() && !global_reclaim(sc)) {
+ lru_gen_shrink_lruvec(lruvec, sc);
+ return;
+ }
+@@ -5826,6 +6128,11 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+ struct lruvec *target_lruvec;
+ bool reclaimable = false;
+
++ if (lru_gen_enabled() && global_reclaim(sc)) {
++ lru_gen_shrink_node(pgdat, sc);
++ return;
++ }
++
+ target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
+
+ again:
+--
+2.40.0
+
--- /dev/null
+From 93147736b5b3a21bea24313bfc7a696829932009 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:05 -0700
+Subject: [PATCH 27/29] mm: multi-gen LRU: clarify scan_control flags
+
+Among the flags in scan_control:
+1. sc->may_swap, which indicates swap constraint due to memsw.max, is
+ supported as usual.
+2. sc->proactive, which indicates reclaim by memory.reclaim, may not
+ opportunistically skip the aging path, since it is considered less
+ latency sensitive.
+3. !(sc->gfp_mask & __GFP_IO), which indicates IO constraint, lowers
+ swappiness to prioritize file LRU, since clean file pages are more
+ likely to exist.
+4. sc->may_writepage and sc->may_unmap, which indicates opportunistic
+ reclaim, are rejected, since unmapped clean pages are already
+ prioritized. Scanning for more of them is likely futile and can
+ cause high reclaim latency when there is a large number of memcgs.
+
+The rest are handled by the existing code.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-8-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 55 +++++++++++++++++++++++++++--------------------------
+ 1 file changed, 28 insertions(+), 27 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 3d8e0665186c..4bcb93df316c 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -2905,6 +2905,9 @@ static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
++ if (!sc->may_swap)
++ return 0;
++
+ if (!can_demote(pgdat->node_id, sc) &&
+ mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
+ return 0;
+@@ -3952,7 +3955,7 @@ static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_
+ } while (err == -EAGAIN);
+ }
+
+-static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat)
++static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc)
+ {
+ struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk;
+
+@@ -3960,7 +3963,7 @@ static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat)
+ VM_WARN_ON_ONCE(walk);
+
+ walk = &pgdat->mm_walk;
+- } else if (!pgdat && !walk) {
++ } else if (!walk && force_alloc) {
+ VM_WARN_ON_ONCE(current_is_kswapd());
+
+ walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
+@@ -4146,7 +4149,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ goto done;
+ }
+
+- walk = set_mm_walk(NULL);
++ walk = set_mm_walk(NULL, true);
+ if (!walk) {
+ success = iterate_mm_list_nowalk(lruvec, max_seq);
+ goto done;
+@@ -4215,8 +4218,6 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MIN_SEQ(lruvec);
+
+- VM_WARN_ON_ONCE(sc->memcg_low_reclaim);
+-
+ /* see the comment on lru_gen_page */
+ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
+ birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+@@ -4472,12 +4473,8 @@ static bool isolate_page(struct lruvec *lruvec, struct page *page, struct scan_c
+ {
+ bool success;
+
+- /* unmapping inhibited */
+- if (!sc->may_unmap && page_mapped(page))
+- return false;
+-
+ /* swapping inhibited */
+- if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
++ if (!(sc->gfp_mask & __GFP_IO) &&
+ (PageDirty(page) ||
+ (PageAnon(page) && !PageSwapCache(page))))
+ return false;
+@@ -4574,9 +4571,8 @@ static int scan_pages(struct lruvec *lruvec, struct scan_control *sc,
+ __count_vm_events(PGSCAN_ANON + type, isolated);
+
+ /*
+- * There might not be eligible pages due to reclaim_idx, may_unmap and
+- * may_writepage. Check the remaining to prevent livelock if it's not
+- * making progress.
++ * There might not be eligible pages due to reclaim_idx. Check the
++ * remaining to prevent livelock if it's not making progress.
+ */
+ return isolated || !remaining ? scanned : 0;
+ }
+@@ -4836,8 +4832,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+
+- if (mem_cgroup_below_min(memcg) ||
+- (mem_cgroup_below_low(memcg) && !sc->memcg_low_reclaim))
++ if (mem_cgroup_below_min(memcg))
+ return 0;
+
+ if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
+@@ -4865,17 +4860,14 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+ long nr_to_scan;
+ unsigned long scanned = 0;
+ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
++ int swappiness = get_swappiness(lruvec, sc);
++
++ /* clean file pages are more likely to exist */
++ if (swappiness && !(sc->gfp_mask & __GFP_IO))
++ swappiness = 1;
+
+ while (true) {
+ int delta;
+- int swappiness;
+-
+- if (sc->may_swap)
+- swappiness = get_swappiness(lruvec, sc);
+- else if (!cgroup_reclaim(sc) && get_swappiness(lruvec, sc))
+- swappiness = 1;
+- else
+- swappiness = 0;
+
+ nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+ if (nr_to_scan <= 0)
+@@ -5005,12 +4997,13 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ struct blk_plug plug;
+
+ VM_WARN_ON_ONCE(global_reclaim(sc));
++ VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap);
+
+ lru_add_drain();
+
+ blk_start_plug(&plug);
+
+- set_mm_walk(lruvec_pgdat(lruvec));
++ set_mm_walk(NULL, false);
+
+ if (try_to_shrink_lruvec(lruvec, sc))
+ lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG);
+@@ -5066,11 +5059,19 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *
+
+ VM_WARN_ON_ONCE(!global_reclaim(sc));
+
++ /*
++ * Unmapped clean pages are already prioritized. Scanning for more of
++ * them is likely futile and can cause high reclaim latency when there
++ * is a large number of memcgs.
++ */
++ if (!sc->may_writepage || !sc->may_unmap)
++ goto done;
++
+ lru_add_drain();
+
+ blk_start_plug(&plug);
+
+- set_mm_walk(pgdat);
++ set_mm_walk(pgdat, false);
+
+ set_initial_priority(pgdat, sc);
+
+@@ -5088,7 +5089,7 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *
+ clear_mm_walk();
+
+ blk_finish_plug(&plug);
+-
++done:
+ /* kswapd should never fail */
+ pgdat->kswapd_failures = 0;
+ }
+@@ -5656,7 +5657,7 @@ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
+ set_task_reclaim_state(current, &sc.reclaim_state);
+ flags = memalloc_noreclaim_save();
+ blk_start_plug(&plug);
+- if (!set_mm_walk(NULL)) {
++ if (!set_mm_walk(NULL, true)) {
+ err = -ENOMEM;
+ goto done;
+ }
+--
+2.40.0
+
--- /dev/null
+From cf3297e4c7a928da8b2b2f0baff2f9c69ea57952 Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Wed, 21 Dec 2022 21:19:06 -0700
+Subject: [PATCH 28/29] mm: multi-gen LRU: simplify arch_has_hw_pte_young()
+ check
+
+Scanning page tables when hardware does not set the accessed bit has
+no real use cases.
+
+Link: https://lkml.kernel.org/r/20221222041905.2431096-9-yuzhao@google.com
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Cc: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Jonathan Corbet <corbet@lwn.net>
+Cc: Michael Larabel <Michael@MichaelLarabel.com>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Mike Rapoport <rppt@kernel.org>
+Cc: Roman Gushchin <roman.gushchin@linux.dev>
+Cc: Suren Baghdasaryan <surenb@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 4bcb93df316c..3f6874a69886 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4144,7 +4144,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+ * handful of PTEs. Spreading the work out over a period of time usually
+ * is less efficient, but it avoids bursty page faults.
+ */
+- if (!force_scan && !(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) {
++ if (!arch_has_hw_pte_young() || !get_cap(LRU_GEN_MM_WALK)) {
+ success = iterate_mm_list_nowalk(lruvec, max_seq);
+ goto done;
+ }
+--
+2.40.0
+
--- /dev/null
+From cc67f962cc53f6e1dfa92eb85b7b26fe83a3c66f Mon Sep 17 00:00:00 2001
+From: Yu Zhao <yuzhao@google.com>
+Date: Mon, 13 Feb 2023 00:53:22 -0700
+Subject: [PATCH 29/29] mm: multi-gen LRU: avoid futile retries
+
+Recall that the per-node memcg LRU has two generations and they alternate
+when the last memcg (of a given node) is moved from one to the other.
+Each generation is also sharded into multiple bins to improve scalability.
+A reclaimer starts with a random bin (in the old generation) and, if it
+fails, it will retry, i.e., to try the rest of the bins.
+
+If a reclaimer fails with the last memcg, it should move this memcg to the
+young generation first, which causes the generations to alternate, and
+then retry. Otherwise, the retries will be futile because all other bins
+are empty.
+
+Link: https://lkml.kernel.org/r/20230213075322.1416966-1-yuzhao@google.com
+Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
+Signed-off-by: Yu Zhao <yuzhao@google.com>
+Reported-by: T.J. Mercier <tjmercier@google.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+---
+ mm/vmscan.c | 25 +++++++++++++++----------
+ 1 file changed, 15 insertions(+), 10 deletions(-)
+
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 3f6874a69886..0b76774963ff 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -4934,18 +4934,20 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
+
+ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
+ {
++ int op;
+ int gen;
+ int bin;
+ int first_bin;
+ struct lruvec *lruvec;
+ struct lru_gen_page *lrugen;
++ struct mem_cgroup *memcg;
+ const struct hlist_nulls_node *pos;
+- int op = 0;
+- struct mem_cgroup *memcg = NULL;
+ unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+
+ bin = first_bin = prandom_u32_max(MEMCG_NR_BINS);
+ restart:
++ op = 0;
++ memcg = NULL;
+ gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
+
+ rcu_read_lock();
+@@ -4969,14 +4971,22 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
+
+ op = shrink_one(lruvec, sc);
+
+- if (sc->nr_reclaimed >= nr_to_reclaim)
+- goto success;
+-
+ rcu_read_lock();
++
++ if (sc->nr_reclaimed >= nr_to_reclaim)
++ break;
+ }
+
+ rcu_read_unlock();
+
++ if (op)
++ lru_gen_rotate_memcg(lruvec, op);
++
++ mem_cgroup_put(memcg);
++
++ if (sc->nr_reclaimed >= nr_to_reclaim)
++ return;
++
+ /* restart if raced with lru_gen_rotate_memcg() */
+ if (gen != get_nulls_value(pos))
+ goto restart;
+@@ -4985,11 +4995,6 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
+ bin = get_memcg_bin(bin + 1);
+ if (bin != first_bin)
+ goto restart;
+-success:
+- if (op)
+- lru_gen_rotate_memcg(lruvec, op);
+-
+- mem_cgroup_put(memcg);
+ }
+
+ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
+--
+2.40.0
+
+++ /dev/null
-From 14aa8b2d5c2ebead01b542f62d68029023054774 Mon Sep 17 00:00:00 2001
-From: Yu Zhao <yuzhao@google.com>
-Date: Wed, 28 Sep 2022 13:36:58 -0600
-Subject: [PATCH 1/1] mm/mglru: don't sync disk for each aging cycle
-
-wakeup_flusher_threads() was added under the assumption that if a system
-runs out of clean cold pages, it might want to write back dirty pages more
-aggressively so that they can become clean and be dropped.
-
-However, doing so can breach the rate limit a system wants to impose on
-writeback, resulting in early SSD wearout.
-
-Link: https://lkml.kernel.org/r/YzSiWq9UEER5LKup@google.com
-Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
-Signed-off-by: Yu Zhao <yuzhao@google.com>
-Reported-by: Axel Rasmussen <axelrasmussen@google.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
----
- mm/vmscan.c | 2 --
- 1 file changed, 2 deletions(-)
-
---- a/mm/vmscan.c
-+++ b/mm/vmscan.c
-@@ -4007,8 +4007,6 @@ static bool try_to_inc_max_seq(struct lr
- if (wq_has_sleeper(&lruvec->mm_walk.wait))
- wake_up_all(&lruvec->mm_walk.wait);
-
-- wakeup_flusher_threads(WB_REASON_VMSCAN);
--
- return true;
- }
-
# CONFIG_NO_HZ is not set
# CONFIG_NO_HZ_FULL is not set
# CONFIG_NO_HZ_IDLE is not set
-CONFIG_NR_LRU_GENS=7
# CONFIG_NS83820 is not set
# CONFIG_NTB is not set
# CONFIG_NTFS3_64BIT_CLUSTER is not set
# CONFIG_THUNDER_NIC_VF is not set
# CONFIG_TICK_CPU_ACCOUNTING is not set
CONFIG_TICK_ONESHOT=y
-CONFIG_TIERS_PER_GEN=4
# CONFIG_TIFM_CORE is not set
# CONFIG_TIGON3 is not set
# CONFIG_TIMB_DMA is not set
projects / openwrt / staging / nbd.git / commitdiff