--- /dev/null
+From 982bae43f11c37b51d2f1961bb25ef7cac3746fa Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 3 Aug 2022 22:49:55 +0000
+Subject: KVM: x86: Tag kvm_mmu_x86_module_init() with __init
+
+From: Sean Christopherson <seanjc@google.com>
+
+commit 982bae43f11c37b51d2f1961bb25ef7cac3746fa upstream.
+
+Mark kvm_mmu_x86_module_init() with __init, the entire reason it exists
+is to initialize variables when kvm.ko is loaded, i.e. it must never be
+called after module initialization.
+
+Fixes: 1d0e84806047 ("KVM: x86/mmu: Resolve nx_huge_pages when kvm.ko is loaded")
+Cc: stable@vger.kernel.org
+Reviewed-by: Kai Huang <kai.huang@intel.com>
+Tested-by: Michael Roth <michael.roth@amd.com>
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20220803224957.1285926-2-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/x86/include/asm/kvm_host.h | 2 +-
+ arch/x86/kvm/mmu/mmu.c | 2 +-
+ 2 files changed, 2 insertions(+), 2 deletions(-)
+
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1340,7 +1340,7 @@ static inline int kvm_arch_flush_remote_
+ return -ENOTSUPP;
+ }
+
+-void kvm_mmu_x86_module_init(void);
++void __init kvm_mmu_x86_module_init(void);
+ int kvm_mmu_vendor_module_init(void);
+ void kvm_mmu_vendor_module_exit(void);
+
+--- a/arch/x86/kvm/mmu/mmu.c
++++ b/arch/x86/kvm/mmu/mmu.c
+@@ -5886,7 +5886,7 @@ static int set_nx_huge_pages(const char
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+-void kvm_mmu_x86_module_init(void)
++void __init kvm_mmu_x86_module_init(void)
+ {
+ if (nx_huge_pages == -1)
+ __set_nx_huge_pages(get_nx_auto_mode());
--- /dev/null
+From foo@baz Fri Aug 12 05:38:47 PM CEST 2022
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Wed, 10 Aug 2022 16:15:50 +0200
+Subject: mm: Add kvrealloc()
+To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Cc: Sasha Levin <sashal@kernel.org>, "Darrick J . Wong" <djwong@kernel.org>, Leah Rumancik <leah.rumancik@gmail.com>, Chandan Babu R <chandan.babu@oracle.com>, Luis Chamberlain <mcgrof@kernel.org>, Adam Manzanares <a.manzanares@samsung.com>, linux-xfs@vger.kernel.org, stable@vger.kernel.org, Dave Chinner <dchinner@redhat.com>, Mel Gorman <mgorman@techsingularity.net>
+Message-ID: <20220810141552.168763-2-amir73il@gmail.com>
+
+From: Dave Chinner <dchinner@redhat.com>
+
+commit de2860f4636256836450c6543be744a50118fc66 upstream.
+
+During log recovery of an XFS filesystem with 64kB directory
+buffers, rebuilding a buffer split across two log records results
+in a memory allocation warning from krealloc like this:
+
+xfs filesystem being mounted at /mnt/scratch supports timestamps until 2038 (0x7fffffff)
+XFS (dm-0): Unmounting Filesystem
+XFS (dm-0): Mounting V5 Filesystem
+XFS (dm-0): Starting recovery (logdev: internal)
+------------[ cut here ]------------
+WARNING: CPU: 5 PID: 3435170 at mm/page_alloc.c:3539 get_page_from_freelist+0xdee/0xe40
+.....
+RIP: 0010:get_page_from_freelist+0xdee/0xe40
+Call Trace:
+ ? complete+0x3f/0x50
+ __alloc_pages+0x16f/0x300
+ alloc_pages+0x87/0x110
+ kmalloc_order+0x2c/0x90
+ kmalloc_order_trace+0x1d/0x90
+ __kmalloc_track_caller+0x215/0x270
+ ? xlog_recover_add_to_cont_trans+0x63/0x1f0
+ krealloc+0x54/0xb0
+ xlog_recover_add_to_cont_trans+0x63/0x1f0
+ xlog_recovery_process_trans+0xc1/0xd0
+ xlog_recover_process_ophdr+0x86/0x130
+ xlog_recover_process_data+0x9f/0x160
+ xlog_recover_process+0xa2/0x120
+ xlog_do_recovery_pass+0x40b/0x7d0
+ ? __irq_work_queue_local+0x4f/0x60
+ ? irq_work_queue+0x3a/0x50
+ xlog_do_log_recovery+0x70/0x150
+ xlog_do_recover+0x38/0x1d0
+ xlog_recover+0xd8/0x170
+ xfs_log_mount+0x181/0x300
+ xfs_mountfs+0x4a1/0x9b0
+ xfs_fs_fill_super+0x3c0/0x7b0
+ get_tree_bdev+0x171/0x270
+ ? suffix_kstrtoint.constprop.0+0xf0/0xf0
+ xfs_fs_get_tree+0x15/0x20
+ vfs_get_tree+0x24/0xc0
+ path_mount+0x2f5/0xaf0
+ __x64_sys_mount+0x108/0x140
+ do_syscall_64+0x3a/0x70
+ entry_SYSCALL_64_after_hwframe+0x44/0xae
+
+Essentially, we are taking a multi-order allocation from kmem_alloc()
+(which has an open coded no fail, no warn loop) and then
+reallocating it out to 64kB using krealloc(__GFP_NOFAIL) and that is
+then triggering the above warning.
+
+This is a regression caused by converting this code from an open
+coded no fail/no warn reallocation loop to using __GFP_NOFAIL.
+
+What we actually need here is kvrealloc(), so that if contiguous
+page allocation fails we fall back to vmalloc() and we don't
+get nasty warnings happening in XFS.
+
+Fixes: 771915c4f688 ("xfs: remove kmem_realloc()")
+Signed-off-by: Dave Chinner <dchinner@redhat.com>
+Acked-by: Mel Gorman <mgorman@techsingularity.net>
+Reviewed-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Acked-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/xfs/xfs_log_recover.c | 4 +++-
+ include/linux/mm.h | 2 ++
+ mm/util.c | 15 +++++++++++++++
+ 3 files changed, 20 insertions(+), 1 deletion(-)
+
+--- a/fs/xfs/xfs_log_recover.c
++++ b/fs/xfs/xfs_log_recover.c
+@@ -2061,7 +2061,9 @@ xlog_recover_add_to_cont_trans(
+ old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
+ old_len = item->ri_buf[item->ri_cnt-1].i_len;
+
+- ptr = krealloc(old_ptr, len + old_len, GFP_KERNEL | __GFP_NOFAIL);
++ ptr = kvrealloc(old_ptr, old_len, len + old_len, GFP_KERNEL);
++ if (!ptr)
++ return -ENOMEM;
+ memcpy(&ptr[old_len], dp, len);
+ item->ri_buf[item->ri_cnt-1].i_len += len;
+ item->ri_buf[item->ri_cnt-1].i_addr = ptr;
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -788,6 +788,8 @@ static inline void *kvcalloc(size_t n, s
+ return kvmalloc_array(n, size, flags | __GFP_ZERO);
+ }
+
++extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize,
++ gfp_t flags);
+ extern void kvfree(const void *addr);
+ extern void kvfree_sensitive(const void *addr, size_t len);
+
+--- a/mm/util.c
++++ b/mm/util.c
+@@ -661,6 +661,21 @@ void kvfree_sensitive(const void *addr,
+ }
+ EXPORT_SYMBOL(kvfree_sensitive);
+
++void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
++{
++ void *newp;
++
++ if (oldsize >= newsize)
++ return (void *)p;
++ newp = kvmalloc(newsize, flags);
++ if (!newp)
++ return NULL;
++ memcpy(newp, p, oldsize);
++ kvfree(p);
++ return newp;
++}
++EXPORT_SYMBOL(kvrealloc);
++
+ static inline void *__page_rmapping(struct page *page)
+ {
+ unsigned long mapping;
--- /dev/null
+From f2928e224d85e7cc139009ab17cefdfec2df5d11 Mon Sep 17 00:00:00 2001
+From: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
+Date: Tue, 7 Sep 2021 01:28:47 +0100
+Subject: riscv: set default pm_power_off to NULL
+
+From: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
+
+commit f2928e224d85e7cc139009ab17cefdfec2df5d11 upstream.
+
+Set pm_power_off to NULL like on all other architectures, check if it
+is set in machine_halt() and machine_power_off() and fallback to
+default_power_off if no other power driver got registered.
+
+This brings riscv architecture inline with all other architectures,
+and allows to reuse exiting power drivers unmodified.
+
+Kernels without legacy SBI v0.1 extensions (CONFIG_RISCV_SBI_V01 is
+not set), do not set pm_power_off to sbi_shutdown(). There is no
+support for SBI v0.3 system reset extension either. This prevents
+using gpio_poweroff on SiFive HiFive Unmatched.
+
+Tested on SiFive HiFive unmatched, with a dtb specifying gpio-poweroff
+node and kernel complied without CONFIG_RISCV_SBI_V01.
+
+BugLink: https://bugs.launchpad.net/bugs/1942806
+Signed-off-by: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
+Reviewed-by: Anup Patel <anup@brainfault.org>
+Tested-by: Ron Economos <w6rz@comcast.net>
+Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
+Cc: Nathan Chancellor <nathan@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ arch/riscv/kernel/reset.c | 12 +++++++++---
+ 1 file changed, 9 insertions(+), 3 deletions(-)
+
+--- a/arch/riscv/kernel/reset.c
++++ b/arch/riscv/kernel/reset.c
+@@ -12,7 +12,7 @@ static void default_power_off(void)
+ wait_for_interrupt();
+ }
+
+-void (*pm_power_off)(void) = default_power_off;
++void (*pm_power_off)(void) = NULL;
+ EXPORT_SYMBOL(pm_power_off);
+
+ void machine_restart(char *cmd)
+@@ -23,10 +23,16 @@ void machine_restart(char *cmd)
+
+ void machine_halt(void)
+ {
+- pm_power_off();
++ if (pm_power_off != NULL)
++ pm_power_off();
++ else
++ default_power_off();
+ }
+
+ void machine_power_off(void)
+ {
+- pm_power_off();
++ if (pm_power_off != NULL)
++ pm_power_off();
++ else
++ default_power_off();
+ }
kvm-nvmx-let-userspace-set-nvmx-msr-to-any-_host_-supported-value.patch
kvm-x86-mark-tss-busy-during-ltr-emulation-_after_-all-fault-checks.patch
kvm-x86-set-error-code-to-segment-selector-on-lldt-ltr-non-canonical-gp.patch
+kvm-x86-tag-kvm_mmu_x86_module_init-with-__init.patch
+riscv-set-default-pm_power_off-to-null.patch
+mm-add-kvrealloc.patch
+xfs-only-set-iomap_f_shared-when-providing-a-srcmap-to-a-write.patch
+xfs-fix-i_dontcache.patch
--- /dev/null
+From foo@baz Fri Aug 12 05:38:47 PM CEST 2022
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Wed, 10 Aug 2022 16:15:52 +0200
+Subject: xfs: fix I_DONTCACHE
+To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Cc: Sasha Levin <sashal@kernel.org>, "Darrick J . Wong" <djwong@kernel.org>, Leah Rumancik <leah.rumancik@gmail.com>, Chandan Babu R <chandan.babu@oracle.com>, Luis Chamberlain <mcgrof@kernel.org>, Adam Manzanares <a.manzanares@samsung.com>, linux-xfs@vger.kernel.org, stable@vger.kernel.org, Dave Chinner <dchinner@redhat.com>
+Message-ID: <20220810141552.168763-4-amir73il@gmail.com>
+
+From: Dave Chinner <dchinner@redhat.com>
+
+commit f38a032b165d812b0ba8378a5cd237c0888ff65f upstream.
+
+Yup, the VFS hoist broke it, and nobody noticed. Bulkstat workloads
+make it clear that it doesn't work as it should.
+
+Fixes: dae2f8ed7992 ("fs: Lift XFS_IDONTCACHE to the VFS layer")
+Signed-off-by: Dave Chinner <dchinner@redhat.com>
+Reviewed-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Acked-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/xfs/xfs_icache.c | 3 ++-
+ fs/xfs/xfs_iops.c | 2 +-
+ 2 files changed, 3 insertions(+), 2 deletions(-)
+
+--- a/fs/xfs/xfs_icache.c
++++ b/fs/xfs/xfs_icache.c
+@@ -47,8 +47,9 @@ xfs_inode_alloc(
+ return NULL;
+ }
+
+- /* VFS doesn't initialise i_mode! */
++ /* VFS doesn't initialise i_mode or i_state! */
+ VFS_I(ip)->i_mode = 0;
++ VFS_I(ip)->i_state = 0;
+
+ XFS_STATS_INC(mp, vn_active);
+ ASSERT(atomic_read(&ip->i_pincount) == 0);
+--- a/fs/xfs/xfs_iops.c
++++ b/fs/xfs/xfs_iops.c
+@@ -1328,7 +1328,7 @@ xfs_setup_inode(
+ gfp_t gfp_mask;
+
+ inode->i_ino = ip->i_ino;
+- inode->i_state = I_NEW;
++ inode->i_state |= I_NEW;
+
+ inode_sb_list_add(inode);
+ /* make the inode look hashed for the writeback code */
--- /dev/null
+From foo@baz Fri Aug 12 05:38:47 PM CEST 2022
+From: Amir Goldstein <amir73il@gmail.com>
+Date: Wed, 10 Aug 2022 16:15:51 +0200
+Subject: xfs: only set IOMAP_F_SHARED when providing a srcmap to a write
+To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+Cc: Sasha Levin <sashal@kernel.org>, "Darrick J . Wong" <djwong@kernel.org>, Leah Rumancik <leah.rumancik@gmail.com>, Chandan Babu R <chandan.babu@oracle.com>, Luis Chamberlain <mcgrof@kernel.org>, Adam Manzanares <a.manzanares@samsung.com>, linux-xfs@vger.kernel.org, stable@vger.kernel.org, Christoph Hellwig <hch@lst.de>, Chandan Babu R <chandanrlinux@gmail.com>
+Message-ID: <20220810141552.168763-3-amir73il@gmail.com>
+
+From: "Darrick J. Wong" <djwong@kernel.org>
+
+commit 72a048c1056a72e37ea2ee34cc73d8c6d6cb4290 upstream.
+
+While prototyping a free space defragmentation tool, I observed an
+unexpected IO error while running a sequence of commands that can be
+recreated by the following sequence of commands:
+
+$ xfs_io -f -c "pwrite -S 0x58 -b 10m 0 10m" file1
+$ cp --reflink=always file1 file2
+$ punch-alternating -o 1 file2
+$ xfs_io -c "funshare 0 10m" file2
+fallocate: Input/output error
+
+I then scraped this (abbreviated) stack trace from dmesg:
+
+WARNING: CPU: 0 PID: 30788 at fs/iomap/buffered-io.c:577 iomap_write_begin+0x376/0x450
+CPU: 0 PID: 30788 Comm: xfs_io Not tainted 5.14.0-rc6-xfsx #rc6 5ef57b62a900814b3e4d885c755e9014541c8732
+Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014
+RIP: 0010:iomap_write_begin+0x376/0x450
+RSP: 0018:ffffc90000c0fc20 EFLAGS: 00010297
+RAX: 0000000000000001 RBX: ffffc90000c0fd10 RCX: 0000000000001000
+RDX: ffffc90000c0fc54 RSI: 000000000000000c RDI: 000000000000000c
+RBP: ffff888005d5dbd8 R08: 0000000000102000 R09: ffffc90000c0fc50
+R10: 0000000000b00000 R11: 0000000000101000 R12: ffffea0000336c40
+R13: 0000000000001000 R14: ffffc90000c0fd10 R15: 0000000000101000
+FS: 00007f4b8f62fe40(0000) GS:ffff88803ec00000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 000056361c554108 CR3: 000000000524e004 CR4: 00000000001706f0
+Call Trace:
+ iomap_unshare_actor+0x95/0x140
+ iomap_apply+0xfa/0x300
+ iomap_file_unshare+0x44/0x60
+ xfs_reflink_unshare+0x50/0x140 [xfs 61947ea9b3a73e79d747dbc1b90205e7987e4195]
+ xfs_file_fallocate+0x27c/0x610 [xfs 61947ea9b3a73e79d747dbc1b90205e7987e4195]
+ vfs_fallocate+0x133/0x330
+ __x64_sys_fallocate+0x3e/0x70
+ do_syscall_64+0x35/0x80
+ entry_SYSCALL_64_after_hwframe+0x44/0xae
+RIP: 0033:0x7f4b8f79140a
+
+Looking at the iomap tracepoints, I saw this:
+
+iomap_iter: dev 8:64 ino 0x100 pos 0 length 0 flags WRITE|0x80 (0x81) ops xfs_buffered_write_iomap_ops caller iomap_file_unshare
+iomap_iter_dstmap: dev 8:64 ino 0x100 bdev 8:64 addr -1 offset 0 length 131072 type DELALLOC flags SHARED
+iomap_iter_srcmap: dev 8:64 ino 0x100 bdev 8:64 addr 147456 offset 0 length 4096 type MAPPED flags
+iomap_iter: dev 8:64 ino 0x100 pos 0 length 4096 flags WRITE|0x80 (0x81) ops xfs_buffered_write_iomap_ops caller iomap_file_unshare
+iomap_iter_dstmap: dev 8:64 ino 0x100 bdev 8:64 addr -1 offset 4096 length 4096 type DELALLOC flags SHARED
+console: WARNING: CPU: 0 PID: 30788 at fs/iomap/buffered-io.c:577 iomap_write_begin+0x376/0x450
+
+The first time funshare calls ->iomap_begin, xfs sees that the first
+block is shared and creates a 128k delalloc reservation in the COW fork.
+The delalloc reservation is returned as dstmap, and the shared block is
+returned as srcmap. So far so good.
+
+funshare calls ->iomap_begin to try the second block. This time there's
+no srcmap (punch-alternating punched it out!) but we still have the
+delalloc reservation in the COW fork. Therefore, we again return the
+reservation as dstmap and the hole as srcmap. iomap_unshare_iter
+incorrectly tries to unshare the hole, which __iomap_write_begin rejects
+because shared regions must be fully written and therefore cannot
+require zeroing.
+
+Therefore, change the buffered write iomap_begin function not to set
+IOMAP_F_SHARED when there isn't a source mapping to read from for the
+unsharing.
+
+Signed-off-by: Darrick J. Wong <djwong@kernel.org>
+Reviewed-by: Christoph Hellwig <hch@lst.de>
+Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com>
+Signed-off-by: Amir Goldstein <amir73il@gmail.com>
+Acked-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/xfs/xfs_iomap.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+--- a/fs/xfs/xfs_iomap.c
++++ b/fs/xfs/xfs_iomap.c
+@@ -1062,11 +1062,11 @@ found_cow:
+ error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
+ if (error)
+ return error;
+- } else {
+- xfs_trim_extent(&cmap, offset_fsb,
+- imap.br_startoff - offset_fsb);
++ return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+ }
+- return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
++
++ xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
++ return xfs_bmbt_to_iomap(ip, iomap, &cmap, 0);
+
+ out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
projects / thirdparty / kernel / stable-queue.git / commitdiff
