[rocky8_10] History rebuild for kernel-4.18.0-553.81.1.el8_10

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 10
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 553.80.1
+RHEL_RELEASE = 553.81.1
 
 #
 # ZSTREAM

arch/arm64/include/asm/pgtable.h

@@ -188,7 +188,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
 	 * clear), set the PTE_DIRTY bit.
 	 */
 	if (pte_hw_dirty(pte))
-		pte = pte_mkdirty(pte);
+		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
 
 	pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
 	pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
@@ -675,8 +675,15 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
-		pte = pte_mkdirty(pte);
+		pte = set_pte_bit(pte, __pgprot(PTE_DIRTY));
+
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	/*
+	 * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware
+	 * dirtiness again.
+	 */
+	if (pte_sw_dirty(pte))
+		pte = pte_mkdirty(pte);
 	return pte;
 }
 

arch/arm64/kernel/setup.c

@@ -353,9 +353,6 @@ void __init setup_arch(char **cmdline_p)
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
-	/* Init percpu seeds for random tags after cpus are set up. */
-	kasan_init_sw_tags();
-
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Make sure init_thread_info.ttbr0 always generates translation

arch/arm64/kernel/smp.c

@@ -474,6 +474,8 @@ void __init smp_prepare_boot_cpu(void)
 		init_gic_priority_masking();
 
 	kasan_init_hw_tags();
+	/* Init percpu seeds for random tags after cpus are set up. */
+	kasan_init_sw_tags();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)

arch/arm64/mm/mmu.c

@@ -1434,7 +1434,8 @@ int arch_add_memory(int nid, u64 start, u64 size,
 		__remove_pgd_mapping(swapper_pg_dir,
 				     __phys_to_virt(start), size);
 	else {
-		max_pfn = PFN_UP(start + size);
+		/* Address of hotplugged memory can be smaller */
+		max_pfn = max(max_pfn, PFN_UP(start + size));
 		max_low_pfn = max_pfn;
 	}
 

arch/powerpc/include/asm/pgtable.h

@@ -68,13 +68,9 @@ static inline void mark_initmem_nx(void) { }
 #define is_ioremap_addr is_ioremap_addr
 static inline bool is_ioremap_addr(const void *x)
 {
-#ifdef CONFIG_MMU
 	unsigned long addr = (unsigned long)x;
 
 	return addr >= IOREMAP_BASE && addr < IOREMAP_END;
-#else
-	return false;
-#endif
 }
 #endif /* CONFIG_PPC64 */
 

arch/powerpc/mm/init_64.c

@@ -198,7 +198,7 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star
 	unsigned long nr_pfn = page_size / sizeof(struct page);
 	unsigned long start_pfn = page_to_pfn((struct page *)start);
 
-	if ((start_pfn + nr_pfn) > altmap->end_pfn)
+	if ((start_pfn + nr_pfn - 1) > altmap->end_pfn)
 		return true;
 
 	if (start_pfn < altmap->base_pfn)
@@ -305,8 +305,7 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 	start = ALIGN_DOWN(start, page_size);
 	if (altmap) {
 		alt_start = altmap->base_pfn;
-		alt_end = altmap->base_pfn + altmap->reserve +
-			  altmap->free + altmap->alloc + altmap->align;
+		alt_end = altmap->base_pfn + altmap->reserve + altmap->free;
 	}
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);

arch/powerpc/mm/pgtable_64.c

@@ -99,7 +99,6 @@ EXPORT_SYMBOL(__vmalloc_end);
 unsigned long __kernel_io_start;
 EXPORT_SYMBOL(__kernel_io_start);
 unsigned long __kernel_io_end;
-EXPORT_SYMBOL(__kernel_io_end);
 struct page *vmemmap;
 EXPORT_SYMBOL(vmemmap);
 unsigned long __pte_frag_nr;

arch/powerpc/platforms/pseries/lpar.c

@@ -521,8 +521,10 @@ static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
 
 	if (cmd) {
 		rc = init_cpu_associativity();
-		if (rc)
+		if (rc) {
+			destroy_cpu_associativity();
 			goto out;
+		}
 
 		for_each_possible_cpu(cpu) {
 			disp = per_cpu_ptr(&vcpu_disp_data, cpu);

arch/s390/include/asm/extable.h

@@ -71,8 +71,13 @@ static inline void swap_ex_entry_fixup(struct exception_table_entry *a,
 {
 	a->fixup = b->fixup + delta;
 	b->fixup = tmp.fixup - delta;
-	a->handler = b->handler + delta;
-	b->handler = tmp.handler - delta;
+	a->handler = b->handler;
+	if (a->handler)
+		a->handler += delta;
+	b->handler = tmp.handler;
+	if (b->handler)
+		b->handler -= delta;
 }
+#define swap_ex_entry_fixup swap_ex_entry_fixup
 
 #endif

arch/s390/mm/gmap.c

@@ -2652,7 +2652,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 		return 0;
 
 	start = pmd_val(*pmd) & HPAGE_MASK;
-	end = start + HPAGE_SIZE - 1;
+	end = start + HPAGE_SIZE;
 	__storage_key_init_range(start, end);
 	set_bit(PG_arch_1, &page->flags);
 	cond_resched();

arch/s390/mm/hugetlbpage.c

@@ -146,7 +146,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
 	}
 
 	if (!test_and_set_bit(PG_arch_1, &page->flags))
-		__storage_key_init_range(paddr, paddr + size - 1);
+		__storage_key_init_range(paddr, paddr + size);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,

arch/x86/include/asm/tlbflush.h

@@ -571,7 +571,7 @@ struct flush_tlb_info {
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,

arch/x86/mm/kaslr.c

@@ -182,11 +182,11 @@ static void __meminit init_trampoline_pud(void)
 		set_p4d(p4d_tramp,
 			__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
 
-		set_pgd(&trampoline_pgd_entry,
-			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+		trampoline_pgd_entry =
+			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp));
 	} else {
-		set_pgd(&trampoline_pgd_entry,
-			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+		trampoline_pgd_entry =
+			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp));
 	}
 }
 

arch/x86/mm/pat/cpa-test.c

@@ -184,7 +184,7 @@ static int pageattr_test(void)
 			break;
 
 		case 1:
-			err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
 			break;
 
 		case 2:

ciq/ciq_backports/kernel-4.18.0-553.81.1.el8_10/287d5fed.failed

@@ -0,0 +1,97 @@
+mm: memcg: use larger batches for proactive reclaim
+
+jira LE-4623
+Rebuild_History Non-Buildable kernel-4.18.0-553.81.1.el8_10
+commit-author T.J. Mercier <tjmercier@google.com>
+commit 287d5fedb377ddc232b216b882723305b27ae31a
+Empty-Commit: Cherry-Pick Conflicts during history rebuild.
+Will be included in final tarball splat. Ref for failed cherry-pick at:
+ciq/ciq_backports/kernel-4.18.0-553.81.1.el8_10/287d5fed.failed
+
+Before 388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive
+reclaim") we passed the number of pages for the reclaim request directly
+to try_to_free_mem_cgroup_pages, which could lead to significant
+overreclaim.  After 0388536ac291 the number of pages was limited to a
+maximum 32 (SWAP_CLUSTER_MAX) to reduce the amount of overreclaim. 
+However such a small batch size caused a regression in reclaim performance
+due to many more reclaim start/stop cycles inside memory_reclaim.  The
+restart cost is amortized over more pages with larger batch sizes, and
+becomes a significant component of the runtime if the batch size is too
+small.
+
+Reclaim tries to balance nr_to_reclaim fidelity with fairness across nodes
+and cgroups over which the pages are spread.  As such, the bigger the
+request, the bigger the absolute overreclaim error.  Historic in-kernel
+users of reclaim have used fixed, small sized requests to approach an
+appropriate reclaim rate over time.  When we reclaim a user request of
+arbitrary size, use decaying batch sizes to manage error while maintaining
+reasonable throughput.
+
+MGLRU enabled - memcg LRU used
+root - full reclaim       pages/sec   time (sec)
+pre-0388536ac291      :    68047        10.46
+post-0388536ac291     :    13742        inf
+(reclaim-reclaimed)/4 :    67352        10.51
+
+MGLRU enabled - memcg LRU not used
+/uid_0 - 1G reclaim       pages/sec   time (sec)  overreclaim (MiB)
+pre-0388536ac291      :    258822       1.12            107.8
+post-0388536ac291     :    105174       2.49            3.5
+(reclaim-reclaimed)/4 :    233396       1.12            -7.4
+
+MGLRU enabled - memcg LRU not used
+/uid_0 - full reclaim     pages/sec   time (sec)
+pre-0388536ac291      :    72334        7.09
+post-0388536ac291     :    38105        14.45
+(reclaim-reclaimed)/4 :    72914        6.96
+
+[tjmercier@google.com: v4]
+  Link: https://lkml.kernel.org/r/20240206175251.3364296-1-tjmercier@google.com
+Link: https://lkml.kernel.org/r/20240202233855.1236422-1-tjmercier@google.com
+Fixes: 0388536ac291 ("mm:vmscan: fix inaccurate reclaim during proactive reclaim")
+	Signed-off-by: T.J. Mercier <tjmercier@google.com>
+	Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
+	Acked-by: Johannes Weiner <hannes@cmpxchg.org>
+	Reviewed-by: Michal Koutny <mkoutny@suse.com>
+	Acked-by: Shakeel Butt <shakeelb@google.com>
+	Acked-by: Michal Hocko <mhocko@suse.com>
+	Cc: Roman Gushchin <roman.gushchin@linux.dev>
+	Cc: Shakeel Butt <shakeelb@google.com>
+	Cc: Muchun Song <songmuchun@bytedance.com>
+	Cc: Efly Young <yangyifei03@kuaishou.com>
+	Cc: Yu Zhao <yuzhao@google.com>
+	Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+(cherry picked from commit 287d5fedb377ddc232b216b882723305b27ae31a)
+	Signed-off-by: Jonathan Maple <jmaple@ciq.com>
+
+# Conflicts:
+#	mm/memcontrol.c
+diff --cc mm/memcontrol.c
+index e3d7fee03b47,cb216d30a221..000000000000
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@@ -6753,7 -6979,10 +6753,9 @@@ static ssize_t memory_reclaim(struct ke
+  	if (err)
+  		return err;
+
+ -	reclaim_options	= MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
+  	while (nr_reclaimed < nr_to_reclaim) {
++ 		/* Will converge on zero, but reclaim enforces a minimum */
++ 		unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
+  		unsigned long reclaimed;
+
+  		if (signal_pending(current))
+@@@ -6768,8 -6997,7 +6770,12 @@@
+  			lru_add_drain_all();
+
+  		reclaimed = try_to_free_mem_cgroup_pages(memcg,
+++<<<<<<< HEAD
+ +					min(nr_to_reclaim - nr_reclaimed, SWAP_CLUSTER_MAX),
+ +					GFP_KERNEL, true);
+++=======
++ 					batch_size, GFP_KERNEL, reclaim_options);
+++>>>>>>> 287d5fedb377 (mm: memcg: use larger batches for proactive reclaim)
+
+  		if (!reclaimed && !nr_retries--)
+  			return -EAGAIN;
+* Unmerged path mm/memcontrol.c