From 690699b271858d45587c868c5166cb6d495a953f Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 4 Dec 2018 20:58:33 -0500 Subject: scsi: t10-pi: Return correct ref tag when queue has no integrity profile commit 60a89a3ce0cce515dc663bc1b45ac89202ad6c79 upstream. Commit ddd0bc756983 ("block: move ref_tag calculation func to the block layer") moved ref tag calculation from SCSI to a library function. However, this change broke returning the correct ref tag for devices operating in DIF mode since these do not have an associated block integrity profile. This in turn caused read/write failures on PI-formatted disks attached to an mpt3sas controller. Fixes: ddd0bc756983 ("block: move ref_tag calculation func to the block layer") Cc: stable@vger.kernel.org # 4.19+ Reported-by: John Garry Tested-by: Xiang Chen Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- include/linux/t10-pi.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index b9626aa7e90c..3e2a80cc7b56 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -39,12 +39,13 @@ struct t10_pi_tuple { static inline u32 t10_pi_ref_tag(struct request *rq) { + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + #ifdef CONFIG_BLK_DEV_INTEGRITY - return blk_rq_pos(rq) >> - (rq->q->integrity.interval_exp - 9) & 0xffffffff; -#else - return -1U; + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; #endif + return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } extern const struct blk_integrity_profile t10_pi_type1_crc; -- cgit v1.2.3 From 28a3b553dd31ae447979eec0da7b9e9c83e5d6ee Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:30:23 +0200 Subject: mm: add mm_pxd_folded checks to pgtable_bytes accounting functions [ Upstream commit 6d212db11947ae5464e4717536ed9faf61c01e86 ] The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds() in free_pgtables() if the address range spans a full pud or pmd. If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration settings they blindly subtract the size of the pmd or pud table from pgtable_bytes even if the pud or pmd page table layer is folded. Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds and mm_dec_nr_pmds. As the check for folded page tables can be overwritten by the architecture, this allows to keep a correct pgtable_bytes value for platforms that use a dynamic number of page table levels. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky Signed-off-by: Sasha Levin --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0416a7204be3..e899460f1bc5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1724,11 +1724,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1748,11 +1752,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif -- cgit v1.2.3 From a5e8809697136ec0dfbcb6af2c7375ece49cbeab Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error commit 68600f623d69da428c6163275f97ca126e1a8ec5 upstream. I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/math64.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ -- cgit v1.2.3