--- /dev/null
+From 74684cce5ebd567b01e9bc0e9a1945c70a32f32f Mon Sep 17 00:00:00 2001
+From: Dinh Nguyen <dinguyen@kernel.org>
+Date: Fri, 7 Jun 2019 10:12:46 -0500
+Subject: clk: socfpga: stratix10: fix divider entry for the emac clocks
+
+From: Dinh Nguyen <dinguyen@kernel.org>
+
+commit 74684cce5ebd567b01e9bc0e9a1945c70a32f32f upstream.
+
+The fixed dividers for the emac clocks should be 2 not 4.
+
+Cc: stable@vger.kernel.org
+Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
+Signed-off-by: Stephen Boyd <sboyd@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/clk/socfpga/clk-s10.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/drivers/clk/socfpga/clk-s10.c
++++ b/drivers/clk/socfpga/clk-s10.c
+@@ -103,9 +103,9 @@ static const struct stratix10_perip_cnt_
+ { STRATIX10_NOC_CLK, "noc_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux),
+ 0, 0, 0, 0x3C, 1},
+ { STRATIX10_EMAC_A_FREE_CLK, "emaca_free_clk", NULL, emaca_free_mux, ARRAY_SIZE(emaca_free_mux),
+- 0, 0, 4, 0xB0, 0},
++ 0, 0, 2, 0xB0, 0},
+ { STRATIX10_EMAC_B_FREE_CLK, "emacb_free_clk", NULL, emacb_free_mux, ARRAY_SIZE(emacb_free_mux),
+- 0, 0, 4, 0xB0, 1},
++ 0, 0, 2, 0xB0, 1},
+ { STRATIX10_EMAC_PTP_FREE_CLK, "emac_ptp_free_clk", NULL, emac_ptp_free_mux,
+ ARRAY_SIZE(emac_ptp_free_mux), 0, 0, 4, 0xB0, 2},
+ { STRATIX10_GPIO_DB_FREE_CLK, "gpio_db_free_clk", NULL, gpio_db_free_mux,
--- /dev/null
+From 211ad4b733037f66f9be0a79eade3da7ab11cbb8 Mon Sep 17 00:00:00 2001
+From: "zhangyi (F)" <yi.zhang@huawei.com>
+Date: Wed, 5 Jun 2019 21:27:08 +0800
+Subject: dm log writes: make sure super sector log updates are written in order
+
+From: zhangyi (F) <yi.zhang@huawei.com>
+
+commit 211ad4b733037f66f9be0a79eade3da7ab11cbb8 upstream.
+
+Currently, although we submit super bios in order (and super.nr_entries
+is incremented by each logged entry), submit_bio() is async so each
+super sector may not be written to log device in order and then the
+final nr_entries may be smaller than it should be.
+
+This problem can be reproduced by the xfstests generic/455 with ext4:
+
+ QA output created by 455
+ -Silence is golden
+ +mark 'end' does not exist
+
+Fix this by serializing submission of super sectors to make sure each
+is written to the log disk in order.
+
+Fixes: 0e9cebe724597 ("dm: add log writes target")
+Cc: stable@vger.kernel.org
+Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
+Suggested-by: Josef Bacik <josef@toxicpanda.com>
+Reviewed-by: Josef Bacik <josef@toxicpanda.com>
+Signed-off-by: Mike Snitzer <snitzer@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/md/dm-log-writes.c | 23 +++++++++++++++++++++--
+ 1 file changed, 21 insertions(+), 2 deletions(-)
+
+--- a/drivers/md/dm-log-writes.c
++++ b/drivers/md/dm-log-writes.c
+@@ -60,6 +60,7 @@
+
+ #define WRITE_LOG_VERSION 1ULL
+ #define WRITE_LOG_MAGIC 0x6a736677736872ULL
++#define WRITE_LOG_SUPER_SECTOR 0
+
+ /*
+ * The disk format for this is braindead simple.
+@@ -115,6 +116,7 @@ struct log_writes_c {
+ struct list_head logging_blocks;
+ wait_queue_head_t wait;
+ struct task_struct *log_kthread;
++ struct completion super_done;
+ };
+
+ struct pending_block {
+@@ -180,6 +182,14 @@ static void log_end_io(struct bio *bio)
+ bio_put(bio);
+ }
+
++static void log_end_super(struct bio *bio)
++{
++ struct log_writes_c *lc = bio->bi_private;
++
++ complete(&lc->super_done);
++ log_end_io(bio);
++}
++
+ /*
+ * Meant to be called if there is an error, it will free all the pages
+ * associated with the block.
+@@ -215,7 +225,8 @@ static int write_metadata(struct log_wri
+ bio->bi_iter.bi_size = 0;
+ bio->bi_iter.bi_sector = sector;
+ bio_set_dev(bio, lc->logdev->bdev);
+- bio->bi_end_io = log_end_io;
++ bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ?
++ log_end_super : log_end_io;
+ bio->bi_private = lc;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+@@ -418,11 +429,18 @@ static int log_super(struct log_writes_c
+ super.nr_entries = cpu_to_le64(lc->logged_entries);
+ super.sectorsize = cpu_to_le32(lc->sectorsize);
+
+- if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) {
++ if (write_metadata(lc, &super, sizeof(super), NULL, 0,
++ WRITE_LOG_SUPER_SECTOR)) {
+ DMERR("Couldn't write super");
+ return -1;
+ }
+
++ /*
++ * Super sector should be writen in-order, otherwise the
++ * nr_entries could be rewritten incorrectly by an old bio.
++ */
++ wait_for_completion_io(&lc->super_done);
++
+ return 0;
+ }
+
+@@ -531,6 +549,7 @@ static int log_writes_ctr(struct dm_targ
+ INIT_LIST_HEAD(&lc->unflushed_blocks);
+ INIT_LIST_HEAD(&lc->logging_blocks);
+ init_waitqueue_head(&lc->wait);
++ init_completion(&lc->super_done);
+ atomic_set(&lc->io_blocks, 0);
+ atomic_set(&lc->pending_blocks, 0);
+
--- /dev/null
+From faf53def3b143df11062d87c12afe6afeb6f8cc7 Mon Sep 17 00:00:00 2001
+From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Date: Fri, 28 Jun 2019 12:06:56 -0700
+Subject: mm: hugetlb: soft-offline: dissolve_free_huge_page() return zero on !PageHuge
+
+From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+
+commit faf53def3b143df11062d87c12afe6afeb6f8cc7 upstream.
+
+madvise(MADV_SOFT_OFFLINE) often returns -EBUSY when calling soft offline
+for hugepages with overcommitting enabled. That was caused by the
+suboptimal code in current soft-offline code. See the following part:
+
+ ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
+ MIGRATE_SYNC, MR_MEMORY_FAILURE);
+ if (ret) {
+ ...
+ } else {
+ /*
+ * We set PG_hwpoison only when the migration source hugepage
+ * was successfully dissolved, because otherwise hwpoisoned
+ * hugepage remains on free hugepage list, then userspace will
+ * find it as SIGBUS by allocation failure. That's not expected
+ * in soft-offlining.
+ */
+ ret = dissolve_free_huge_page(page);
+ if (!ret) {
+ if (set_hwpoison_free_buddy_page(page))
+ num_poisoned_pages_inc();
+ }
+ }
+ return ret;
+
+Here dissolve_free_huge_page() returns -EBUSY if the migration source page
+was freed into buddy in migrate_pages(), but even in that case we actually
+has a chance that set_hwpoison_free_buddy_page() succeeds. So that means
+current code gives up offlining too early now.
+
+dissolve_free_huge_page() checks that a given hugepage is suitable for
+dissolving, where we should return success for !PageHuge() case because
+the given hugepage is considered as already dissolved.
+
+This change also affects other callers of dissolve_free_huge_page(), which
+are cleaned up together.
+
+[n-horiguchi@ah.jp.nec.com: v3]
+ Link: http://lkml.kernel.org/r/1560761476-4651-3-git-send-email-n-horiguchi@ah.jp.nec.comLink: http://lkml.kernel.org/r/1560154686-18497-3-git-send-email-n-horiguchi@ah.jp.nec.com
+Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining")
+Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Reported-by: Chen, Jerry T <jerry.t.chen@intel.com>
+Tested-by: Chen, Jerry T <jerry.t.chen@intel.com>
+Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
+Reviewed-by: Oscar Salvador <osalvador@suse.de>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Xishi Qiu <xishi.qiuxishi@alibaba-inc.com>
+Cc: "Chen, Jerry T" <jerry.t.chen@intel.com>
+Cc: "Zhuo, Qiuxu" <qiuxu.zhuo@intel.com>
+Cc: <stable@vger.kernel.org> [4.19+]
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/hugetlb.c | 29 ++++++++++++++++++++---------
+ mm/memory-failure.c | 5 +----
+ 2 files changed, 21 insertions(+), 13 deletions(-)
+
+--- a/mm/hugetlb.c
++++ b/mm/hugetlb.c
+@@ -1489,16 +1489,29 @@ static int free_pool_huge_page(struct hs
+
+ /*
+ * Dissolve a given free hugepage into free buddy pages. This function does
+- * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
+- * dissolution fails because a give page is not a free hugepage, or because
+- * free hugepages are fully reserved.
++ * nothing for in-use hugepages and non-hugepages.
++ * This function returns values like below:
++ *
++ * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
++ * (allocated or reserved.)
++ * 0: successfully dissolved free hugepages or the page is not a
++ * hugepage (considered as already dissolved)
+ */
+ int dissolve_free_huge_page(struct page *page)
+ {
+ int rc = -EBUSY;
+
++ /* Not to disrupt normal path by vainly holding hugetlb_lock */
++ if (!PageHuge(page))
++ return 0;
++
+ spin_lock(&hugetlb_lock);
+- if (PageHuge(page) && !page_count(page)) {
++ if (!PageHuge(page)) {
++ rc = 0;
++ goto out;
++ }
++
++ if (!page_count(page)) {
+ struct page *head = compound_head(page);
+ struct hstate *h = page_hstate(head);
+ int nid = page_to_nid(head);
+@@ -1543,11 +1556,9 @@ int dissolve_free_huge_pages(unsigned lo
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
+ page = pfn_to_page(pfn);
+- if (PageHuge(page) && !page_count(page)) {
+- rc = dissolve_free_huge_page(page);
+- if (rc)
+- break;
+- }
++ rc = dissolve_free_huge_page(page);
++ if (rc)
++ break;
+ }
+
+ return rc;
+--- a/mm/memory-failure.c
++++ b/mm/memory-failure.c
+@@ -1857,11 +1857,8 @@ static int soft_offline_in_use_page(stru
+
+ static int soft_offline_free_page(struct page *page)
+ {
+- int rc = 0;
+- struct page *head = compound_head(page);
++ int rc = dissolve_free_huge_page(page);
+
+- if (PageHuge(head))
+- rc = dissolve_free_huge_page(page);
+ if (!rc) {
+ if (set_hwpoison_free_buddy_page(page))
+ num_poisoned_pages_inc();
--- /dev/null
+From 7298e3b0a149c91323b3205d325e942c3b3b9ef6 Mon Sep 17 00:00:00 2001
+From: Colin Ian King <colin.king@canonical.com>
+Date: Fri, 28 Jun 2019 12:07:05 -0700
+Subject: mm/page_idle.c: fix oops because end_pfn is larger than max_pfn
+
+From: Colin Ian King <colin.king@canonical.com>
+
+commit 7298e3b0a149c91323b3205d325e942c3b3b9ef6 upstream.
+
+Currently the calcuation of end_pfn can round up the pfn number to more
+than the actual maximum number of pfns, causing an Oops. Fix this by
+ensuring end_pfn is never more than max_pfn.
+
+This can be easily triggered when on systems where the end_pfn gets
+rounded up to more than max_pfn using the idle-page stress-ng stress test:
+
+sudo stress-ng --idle-page 0
+
+ BUG: unable to handle kernel paging request at 00000000000020d8
+ #PF error: [normal kernel read fault]
+ PGD 0 P4D 0
+ Oops: 0000 [#1] SMP PTI
+ CPU: 1 PID: 11039 Comm: stress-ng-idle- Not tainted 5.0.0-5-generic #6-Ubuntu
+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
+ RIP: 0010:page_idle_get_page+0xc8/0x1a0
+ Code: 0f b1 0a 75 7d 48 8b 03 48 89 c2 48 c1 e8 33 83 e0 07 48 c1 ea 36 48 8d 0c 40 4c 8d 24 88 49 c1 e4 07 4c 03 24 d5 00 89 c3 be <49> 8b 44 24 58 48 8d b8 80 a1 02 00 e8 07 d5 77 00 48 8b 53 08 48
+ RSP: 0018:ffffafd7c672fde8 EFLAGS: 00010202
+ RAX: 0000000000000005 RBX: ffffe36341fff700 RCX: 000000000000000f
+ RDX: 0000000000000284 RSI: 0000000000000275 RDI: 0000000001fff700
+ RBP: ffffafd7c672fe00 R08: ffffa0bc34056410 R09: 0000000000000276
+ R10: ffffa0bc754e9b40 R11: ffffa0bc330f6400 R12: 0000000000002080
+ R13: ffffe36341fff700 R14: 0000000000080000 R15: ffffa0bc330f6400
+ FS: 00007f0ec1ea5740(0000) GS:ffffa0bc7db00000(0000) knlGS:0000000000000000
+ CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+ CR2: 00000000000020d8 CR3: 0000000077d68000 CR4: 00000000000006e0
+ Call Trace:
+ page_idle_bitmap_write+0x8c/0x140
+ sysfs_kf_bin_write+0x5c/0x70
+ kernfs_fop_write+0x12e/0x1b0
+ __vfs_write+0x1b/0x40
+ vfs_write+0xab/0x1b0
+ ksys_write+0x55/0xc0
+ __x64_sys_write+0x1a/0x20
+ do_syscall_64+0x5a/0x110
+ entry_SYSCALL_64_after_hwframe+0x44/0xa9
+
+Link: http://lkml.kernel.org/r/20190618124352.28307-1-colin.king@canonical.com
+Fixes: 33c3fc71c8cf ("mm: introduce idle page tracking")
+Signed-off-by: Colin Ian King <colin.king@canonical.com>
+Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
+Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
+Cc: Michal Hocko <mhocko@suse.com>
+Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
+Cc: Mel Gorman <mgorman@techsingularity.net>
+Cc: Stephen Rothwell <sfr@canb.auug.org.au>
+Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/page_idle.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/mm/page_idle.c
++++ b/mm/page_idle.c
+@@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(str
+
+ end_pfn = pfn + count * BITS_PER_BYTE;
+ if (end_pfn > max_pfn)
+- end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
++ end_pfn = max_pfn;
+
+ for (; pfn < end_pfn; pfn++) {
+ bit = pfn % BITMAP_CHUNK_BITS;
+@@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(st
+
+ end_pfn = pfn + count * BITS_PER_BYTE;
+ if (end_pfn > max_pfn)
+- end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
++ end_pfn = max_pfn;
+
+ for (; pfn < end_pfn; pfn++) {
+ bit = pfn % BITMAP_CHUNK_BITS;
--- /dev/null
+From b38e5962f8ed0d2a2b28a887fc2221f7f41db119 Mon Sep 17 00:00:00 2001
+From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Date: Fri, 28 Jun 2019 12:06:53 -0700
+Subject: mm: soft-offline: return -EBUSY if set_hwpoison_free_buddy_page() fails
+
+From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+
+commit b38e5962f8ed0d2a2b28a887fc2221f7f41db119 upstream.
+
+The pass/fail of soft offline should be judged by checking whether the
+raw error page was finally contained or not (i.e. the result of
+set_hwpoison_free_buddy_page()), but current code do not work like
+that. It might lead us to misjudge the test result when
+set_hwpoison_free_buddy_page() fails.
+
+Without this fix, there are cases where madvise(MADV_SOFT_OFFLINE) may
+not offline the original page and will not return an error.
+
+Link: http://lkml.kernel.org/r/1560154686-18497-2-git-send-email-n-horiguchi@ah.jp.nec.com
+Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining")
+Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
+Reviewed-by: Oscar Salvador <osalvador@suse.de>
+Cc: Michal Hocko <mhocko@kernel.org>
+Cc: Xishi Qiu <xishi.qiuxishi@alibaba-inc.com>
+Cc: "Chen, Jerry T" <jerry.t.chen@intel.com>
+Cc: "Zhuo, Qiuxu" <qiuxu.zhuo@intel.com>
+Cc: <stable@vger.kernel.org> [4.19+]
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ mm/memory-failure.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+--- a/mm/memory-failure.c
++++ b/mm/memory-failure.c
+@@ -1731,6 +1731,8 @@ static int soft_offline_huge_page(struct
+ if (!ret) {
+ if (set_hwpoison_free_buddy_page(page))
+ num_poisoned_pages_inc();
++ else
++ ret = -EBUSY;
+ }
+ }
+ return ret;
--- /dev/null
+From 240b4cc8fd5db138b675297d4226ec46594d9b3b Mon Sep 17 00:00:00 2001
+From: Jan Kara <jack@suse.cz>
+Date: Wed, 19 Jun 2019 09:05:41 +0200
+Subject: scsi: vmw_pscsi: Fix use-after-free in pvscsi_queue_lck()
+
+From: Jan Kara <jack@suse.cz>
+
+commit 240b4cc8fd5db138b675297d4226ec46594d9b3b upstream.
+
+Once we unlock adapter->hw_lock in pvscsi_queue_lck() nothing prevents just
+queued scsi_cmnd from completing and freeing the request. Thus cmd->cmnd[0]
+dereference can dereference already freed request leading to kernel crashes
+or other issues (which one of our customers observed). Store cmd->cmnd[0]
+in a local variable before unlocking adapter->hw_lock to fix the issue.
+
+CC: <stable@vger.kernel.org>
+Signed-off-by: Jan Kara <jack@suse.cz>
+Reviewed-by: Ewan D. Milne <emilne@redhat.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ drivers/scsi/vmw_pvscsi.c | 6 ++++--
+ 1 file changed, 4 insertions(+), 2 deletions(-)
+
+--- a/drivers/scsi/vmw_pvscsi.c
++++ b/drivers/scsi/vmw_pvscsi.c
+@@ -763,6 +763,7 @@ static int pvscsi_queue_lck(struct scsi_
+ struct pvscsi_adapter *adapter = shost_priv(host);
+ struct pvscsi_ctx *ctx;
+ unsigned long flags;
++ unsigned char op;
+
+ spin_lock_irqsave(&adapter->hw_lock, flags);
+
+@@ -775,13 +776,14 @@ static int pvscsi_queue_lck(struct scsi_
+ }
+
+ cmd->scsi_done = done;
++ op = cmd->cmnd[0];
+
+ dev_dbg(&cmd->device->sdev_gendev,
+- "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, cmd->cmnd[0]);
++ "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, op);
+
+ spin_unlock_irqrestore(&adapter->hw_lock, flags);
+
+- pvscsi_kick_io(adapter, cmd->cmnd[0]);
++ pvscsi_kick_io(adapter, op);
+
+ return 0;
+ }
fs-proc-array.c-allow-reporting-eip-esp-for-all-coredumping-threads.patch
mm-mempolicy.c-fix-an-incorrect-rebind-node-in-mpol_rebind_nodemask.patch
fs-binfmt_flat.c-make-load_flat_shared_library-work.patch
+clk-socfpga-stratix10-fix-divider-entry-for-the-emac-clocks.patch
+mm-soft-offline-return-ebusy-if-set_hwpoison_free_buddy_page-fails.patch
+mm-hugetlb-soft-offline-dissolve_free_huge_page-return-zero-on-pagehuge.patch
+mm-page_idle.c-fix-oops-because-end_pfn-is-larger-than-max_pfn.patch
+dm-log-writes-make-sure-super-sector-log-updates-are-written-in-order.patch
+scsi-vmw_pscsi-fix-use-after-free-in-pvscsi_queue_lck.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
