vchong · pull · Jun 30, 2021 · Jun 2, 2021 · Jun 2, 2021 · Jun 2, 2021
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
@@ -3591,6 +3591,12 @@
 			off: turn off poisoning (default)
 			on: turn on poisoning
 
+	page_reporting.page_reporting_order=
+			[KNL] Minimal page reporting order
+			Format: <integer>
+			Adjust the minimal page reporting order. The page
+			reporting is disabled when it exceeds (MAX_ORDER-1).
+
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
 			timeout = 0: wait forever

diff --git a/Documentation/admin-guide/lockup-watchdogs.rst b/Documentation/admin-guide/lockup-watchdogs.rst
@@ -39,15 +39,15 @@ in principle, they should work in any architecture where these
 subsystems are present.
 
 A periodic hrtimer runs to generate interrupts and kick the watchdog
-task. An NMI perf event is generated every "watchdog_thresh"
+job. An NMI perf event is generated every "watchdog_thresh"
 (compile-time initialized to 10 and configurable through sysctl of the
 same name) seconds to check for hardlockups. If any CPU in the system
 does not receive any hrtimer interrupt during that time the
 'hardlockup detector' (the handler for the NMI perf event) will
 generate a kernel warning or call panic, depending on the
 configuration.
 
-The watchdog task is a high priority kernel thread that updates a
+The watchdog job runs in a stop scheduling thread that updates a
 timestamp every time it is scheduled. If that timestamp is not updated
 for 2*watchdog_thresh seconds (the softlockup threshold) the
 'softlockup detector' (coded inside the hrtimer callback function)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1297,11 +1297,11 @@ This parameter can be used to control the soft lockup detector.
 = =================================
 
 The soft lockup detector monitors CPUs for threads that are hogging the CPUs
-without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads
-from running. The mechanism depends on the CPUs ability to respond to timer
-interrupts which are needed for the 'watchdog/N' threads to be woken up by
-the watchdog timer function, otherwise the NMI watchdog — if enabled — can
-detect a hard lockup condition.
+without rescheduling voluntarily, and thus prevent the 'migration/N' threads
+from running, causing the watchdog work fail to execute. The mechanism depends
+on the CPUs ability to respond to timer interrupts which are needed for the
+watchdog work to be queued by the watchdog timer function, otherwise the NMI
+watchdog — if enabled — can detect a hard lockup condition.
 
 
 stack_erasing

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
@@ -64,7 +64,7 @@ Currently, these files are in /proc/sys/vm:
 - overcommit_ratio
 - page-cluster
 - panic_on_oom
-- percpu_pagelist_fraction
+- percpu_pagelist_high_fraction
 - stat_interval
 - stat_refresh
 - numa_stat
@@ -790,22 +790,24 @@ panic_on_oom=2+kdump gives you very strong tool to investigate
 why oom happens. You can get snapshot.
 
 
-percpu_pagelist_fraction
-========================
+percpu_pagelist_high_fraction
+=============================
 
-This is the fraction of pages at most (high mark pcp->high) in each zone that
-are allocated for each per cpu page list.  The min value for this is 8.  It
-means that we don't allow more than 1/8th of pages in each zone to be
-allocated in any single per_cpu_pagelist.  This entry only changes the value
-of hot per cpu pagelists.  User can specify a number like 100 to allocate
-1/100th of each zone to each per cpu page list.
+This is the fraction of pages in each zone that are can be stored to
+per-cpu page lists. It is an upper boundary that is divided depending
+on the number of online CPUs. The min value for this is 8 which means
+that we do not allow more than 1/8th of pages in each zone to be stored
+on per-cpu page lists. This entry only changes the value of hot per-cpu
+page lists. A user can specify a number like 100 to allocate 1/100th of
+each zone between per-cpu lists.
 
-The batch value of each per cpu pagelist is also updated as a result.  It is
-set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
+The batch value of each per-cpu page list remains the same regardless of
+the value of the high fraction so allocation latencies are unaffected.
 
-The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.  If the user writes '0' to this
-sysctl, it will revert to this default behavior.
+The initial value is zero. Kernel uses this value to set the high pcp->high
+mark based on the low watermark for the zone and the number of local
+online CPUs.  If the user writes '0' to this sysctl, it will revert to
+this default behavior.
 
 
 stat_interval
@@ -936,12 +938,12 @@ allocations, THP and hugetlbfs pages.
 
 To make it sensible with respect to the watermark_scale_factor
 parameter, the unit is in fractions of 10,000. The default value of
-15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
-watermark will be reclaimed in the event of a pageblock being mixed due
-to fragmentation. The level of reclaim is determined by the number of
-fragmentation events that occurred in the recent past. If this value is
-smaller than a pageblock then a pageblocks worth of pages will be reclaimed
-(e.g.  2MB on 64-bit x86). A boost factor of 0 will disable the feature.
+15,000 means that up to 150% of the high watermark will be reclaimed in the
+event of a pageblock being mixed due to fragmentation. The level of reclaim
+is determined by the number of fragmentation events that occurred in the
+recent past. If this value is smaller than a pageblock then a pageblocks
+worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
+of 0 will disable the feature.
 
 
 watermark_scale_factor

diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
@@ -447,11 +447,10 @@ When a test fails due to a failed ``kmalloc``::
 
 When a test fails due to a missing KASAN report::
 
-        # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
-        Expected kasan_data->report_expected == kasan_data->report_found, but
-        kasan_data->report_expected == 1
-        kasan_data->report_found == 0
-        not ok 28 - kmalloc_double_kzfree
+        # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:974
+        KASAN failure expected in "kfree_sensitive(ptr)", but none occurred
+        not ok 44 - kmalloc_double_kzfree
+
 
 At the end the cumulative status of all KASAN tests is printed. On success::
 

diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst
@@ -14,15 +14,11 @@ for the CPU. Then there could be several contiguous ranges at
 completely distinct addresses. And, don't forget about NUMA, where
 different memory banks are attached to different CPUs.
 
-Linux abstracts this diversity using one of the three memory models:
-FLATMEM, DISCONTIGMEM and SPARSEMEM. Each architecture defines what
+Linux abstracts this diversity using one of the two memory models:
+FLATMEM and SPARSEMEM. Each architecture defines what
 memory models it supports, what the default memory model is and
 whether it is possible to manually override that default.
 
-.. note::
-   At time of this writing, DISCONTIGMEM is considered deprecated,
-   although it is still in use by several architectures.
-
 All the memory models track the status of physical page frames using
 struct page arranged in one or more arrays.
 
@@ -63,43 +59,6 @@ straightforward: `PFN - ARCH_PFN_OFFSET` is an index to the
 The `ARCH_PFN_OFFSET` defines the first page frame number for
 systems with physical memory starting at address different from 0.
 
-DISCONTIGMEM
-============
-
-The DISCONTIGMEM model treats the physical memory as a collection of
-`nodes` similarly to how Linux NUMA support does. For each node Linux
-constructs an independent memory management subsystem represented by
-`struct pglist_data` (or `pg_data_t` for short). Among other
-things, `pg_data_t` holds the `node_mem_map` array that maps
-physical pages belonging to that node. The `node_start_pfn` field of
-`pg_data_t` is the number of the first page frame belonging to that
-node.
-
-The architecture setup code should call :c:func:`free_area_init_node` for
-each node in the system to initialize the `pg_data_t` object and its
-`node_mem_map`.
-
-Every `node_mem_map` behaves exactly as FLATMEM's `mem_map` -
-every physical page frame in a node has a `struct page` entry in the
-`node_mem_map` array. When DISCONTIGMEM is enabled, a portion of the
-`flags` field of the `struct page` encodes the node number of the
-node hosting that page.
-
-The conversion between a PFN and the `struct page` in the
-DISCONTIGMEM model became slightly more complex as it has to determine
-which node hosts the physical page and which `pg_data_t` object
-holds the `struct page`.
-
-Architectures that support DISCONTIGMEM provide :c:func:`pfn_to_nid`
-to convert PFN to the node number. The opposite conversion helper
-:c:func:`page_to_nid` is generic as it uses the node number encoded in
-page->flags.
-
-Once the node number is known, the PFN can be used to index
-appropriate `node_mem_map` array to access the `struct page` and
-the offset of the `struct page` from the `node_mem_map` plus
-`node_start_pfn` is the PFN of that page.
-
 SPARSEMEM
 =========
 

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
@@ -549,29 +549,12 @@ config NR_CPUS
 	  MARVEL support can handle a maximum of 32 CPUs, all the others
 	  with working support have a maximum of 4 CPUs.
 
-config ARCH_DISCONTIGMEM_ENABLE
-	bool "Discontiguous Memory Support"
-	depends on BROKEN
-	help
-	  Say Y to support efficient handling of discontiguous physical memory,
-	  for architectures which are either NUMA (Non-Uniform Memory Access)
-	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa.rst> for more.
-
 config ARCH_SPARSEMEM_ENABLE
 	bool "Sparse Memory Support"
 	help
 	  Say Y to support efficient handling of discontiguous physical memory,
 	  for systems that have huge holes in the physical address space.
 
-config NUMA
-	bool "NUMA Support (EXPERIMENTAL)"
-	depends on DISCONTIGMEM && BROKEN
-	help
-	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
-	  Access).  This option is for configuring high-end multiprocessor
-	  server machines.  If in doubt, say N.
-
 config ALPHA_WTINT
 	bool "Use WTINT" if ALPHA_SRM || ALPHA_GENERIC
 	default y if ALPHA_QEMU
@@ -596,11 +579,6 @@ config ALPHA_WTINT
 
 	  If unsure, say N.
 
-config NODES_SHIFT
-	int
-	default "7"
-	depends on NEED_MULTIPLE_NODES
-
 # LARGE_VMALLOC is racy, if you *really* need it then fix it first
 config ALPHA_LARGE_VMALLOC
 	bool

diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h
@@ -99,12 +99,6 @@ struct alpha_machine_vector
 
 	const char *vector_name;
 
-	/* NUMA information */
-	int (*pa_to_nid)(unsigned long);
-	int (*cpuid_to_nid)(int);
-	unsigned long (*node_mem_start)(int);
-	unsigned long (*node_mem_size)(int);
-
 	/* System specific parameters.  */
 	union {
 	    struct {

diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
@@ -206,7 +206,6 @@ extern unsigned long __zero_page(void);
 #define page_to_pa(page)	(page_to_pfn(page) << PAGE_SHIFT)
 #define pte_pfn(pte)	(pte_val(pte) >> 32)
 
-#ifndef CONFIG_DISCONTIGMEM
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 #define mk_pte(page, pgprot)						\
 ({									\
@@ -215,7 +214,6 @@ extern unsigned long __zero_page(void);
 	pte_val(pte) = (page_to_pfn(page) << 32) | pgprot_val(pgprot);	\
 	pte;								\
 })
-#endif
 
 extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot)
 { pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; }
@@ -330,9 +328,7 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-#ifndef CONFIG_DISCONTIGMEM
 #define kern_addr_valid(addr)	(1)
-#endif
 
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))