From 554b0f3ca6f4948fdbab5f199858d902061318d0 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 5 Nov 2021 13:35:27 -0700 Subject: mm: disable NUMA_BALANCING_DEFAULT_ENABLED and TRANSPARENT_HUGEPAGE on PREEMPT_RT TRANSPARENT_HUGEPAGE: There are potential non-deterministic delays to an RT thread if a critical memory region is not THP-aligned and a non-RT buffer is located in the same hugepage-aligned region. It's also possible for an unrelated thread to migrate pages belonging to an RT task incurring unexpected page faults due to memory defragmentation even if khugepaged is disabled. Regular HUGEPAGEs are not affected by this can be used. NUMA_BALANCING: There is a non-deterministic delay to mark PTEs PROT_NONE to gather NUMA fault samples, increased page faults of regions even if mlocked and non-deterministic delays when migrating pages. [Mel Gorman worded 99% of the commit description]. Link: https://lore.kernel.org/all/20200304091159.GN3818@techsingularity.net/ Link: https://lore.kernel.org/all/20211026165100.ahz5bkx44lrrw5pt@linutronix.de/ Link: https://lkml.kernel.org/r/20211028143327.hfbxjze7palrpfgp@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Acked-by: Mel Gorman Reviewed-by: David Hildenbrand Cc: Vlastimil Babka Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 11f8a845f259..21b1f4870c80 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -901,7 +901,7 @@ config NUMA_BALANCING bool "Memory placement aware NUMA scheduler" depends on ARCH_SUPPORTS_NUMA_BALANCING depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY - depends on SMP && NUMA && MIGRATION + depends on SMP && NUMA && MIGRATION && !PREEMPT_RT help This option adds support for automatic NUMA aware memory/task placement. The mechanism is quite primitive and is based on migrating memory when -- cgit v1.2.3 From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index 3c4054a95545..767ee2672176 100644 --- a/init/main.c +++ b/init/main.c @@ -1506,6 +1506,8 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + + system_state = SYSTEM_FREEING_INITMEM; kprobe_free_init_mem(); ftrace_free_init_mem(); kgdb_free_init_mem(); -- cgit v1.2.3 From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/initramfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index a842c0544745..1a971f070dd4 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, -- cgit v1.2.3 From 4421cca0a3e4833b3bf0f20de98eb580ab8c7290 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:22 -0700 Subject: memblock: use memblock_free for freeing virtual pointers Rename memblock_free_ptr() to memblock_free() and use memblock_free() when freeing a virtual pointer so that memblock_free() will be a counterpart of memblock_alloc() The callers are updated with the below semantic patch and manual addition of (void *) casting to pointers that are represented by unsigned long variables. @@ identifier vaddr; expression size; @@ ( - memblock_phys_free(__pa(vaddr), size); + memblock_free(vaddr, size); | - memblock_free_ptr(vaddr, size); + memblock_free(vaddr, size); ) [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20211018192940.3d1d532f@canb.auug.org.au Link: https://lkml.kernel.org/r/20210930185031.18648-7-rppt@kernel.org Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/initramfs.c | 2 +- init/main.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index 1a971f070dd4..2f3d96dc3db6 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_free((void *)aligned_start, aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, diff --git a/init/main.c b/init/main.c index 767ee2672176..f0001af8ebb9 100644 --- a/init/main.c +++ b/init/main.c @@ -382,7 +382,7 @@ static char * __init xbc_make_cmdline(const char *key) ret = xbc_snprint_cmdline(new_cmdline, len + 1, root); if (ret < 0 || ret > len) { pr_err("Failed to print extra kernel cmdline.\n"); - memblock_free_ptr(new_cmdline, len + 1); + memblock_free(new_cmdline, len + 1); return NULL; } @@ -925,7 +925,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free_ptr(unknown_options, len); + memblock_free(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) -- cgit v1.2.3