--- /dev/null
+From 87a7ae75d7383afa998f57656d1d14e2a730cc47 Mon Sep 17 00:00:00 2001
+From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
+Date: Tue, 11 Apr 2023 19:52:13 +0530
+Subject: mm/vmemmap/devdax: fix kernel crash when probing devdax devices
+
+From: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+
+commit 87a7ae75d7383afa998f57656d1d14e2a730cc47 upstream.
+
+commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for
+compound devmaps") added support for using optimized vmmemap for devdax
+devices. But how vmemmap mappings are created are architecture specific.
+For example, powerpc with hash translation doesn't have vmemmap mappings
+in init_mm page table instead they are bolted table entries in the
+hardware page table
+
+vmemmap_populate_compound_pages() used by vmemmap optimization code is not
+aware of these architecture-specific mapping. Hence allow architecture to
+opt for this feature. I selected architectures supporting
+HUGETLB_PAGE_OPTIMIZE_VMEMMAP option as also supporting this feature.
+
+This patch fixes the below crash on ppc64.
+
+BUG: Unable to handle kernel data access on write at 0xc00c000100400038
+Faulting instruction address: 0xc000000001269d90
+Oops: Kernel access of bad area, sig: 11 [#1]
+LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
+Modules linked in:
+CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a
+Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries
+NIP: c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000
+REGS: c000000003632c30 TRAP: 0300 Not tainted (6.3.0-rc5-150500.34-default+)
+MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24842228 XER: 00000000
+CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0
+....
+NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c
+LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0
+Call Trace:
+[c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable)
+[c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250
+[c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0
+[c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0
+[c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0
+[c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140
+[c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520
+[c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230
+[c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120
+[c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0
+[c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130
+[c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250
+[c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110
+[c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10
+[c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530
+[c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270
+[c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70
+[c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0
+[c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520
+[c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230
+[c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120
+[c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240
+[c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130
+[c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50
+[c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300
+[c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0
+[c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100
+[c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48
+[c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320
+[c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400
+[c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0
+[c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64
+
+Link: https://lkml.kernel.org/r/20230411142214.64464-1-aneesh.kumar@linux.ibm.com
+Fixes: 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps")
+Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
+Reported-by: Tarun Sahu <tsahu@linux.ibm.com>
+Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
+Cc: Muchun Song <songmuchun@bytedance.com>
+Cc: Dan Williams <dan.j.williams@intel.com>
+Cc: Mike Kravetz <mike.kravetz@oracle.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Piyush Sachdeva <piyushs@linux.ibm.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/linux/mm.h | 16 ++++++++++++++++
+ mm/page_alloc.c | 10 ++++++----
+ mm/sparse-vmemmap.c | 3 +--
+ 3 files changed, 23 insertions(+), 6 deletions(-)
+
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -3425,6 +3425,22 @@ void vmemmap_populate_print_last(void);
+ void vmemmap_free(unsigned long start, unsigned long end,
+ struct vmem_altmap *altmap);
+ #endif
++
++#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
++static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
++ struct dev_pagemap *pgmap)
++{
++ return is_power_of_2(sizeof(struct page)) &&
++ pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
++}
++#else
++static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
++ struct dev_pagemap *pgmap)
++{
++ return false;
++}
++#endif
++
+ void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
+ unsigned long nr_pages);
+
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -6905,10 +6905,12 @@ static void __ref __init_zone_device_pag
+ * of an altmap. See vmemmap_populate_compound_pages().
+ */
+ static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
+- unsigned long nr_pages)
++ struct dev_pagemap *pgmap)
+ {
+- return is_power_of_2(sizeof(struct page)) &&
+- !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages;
++ if (!vmemmap_can_optimize(altmap, pgmap))
++ return pgmap_vmemmap_nr(pgmap);
++
++ return 2 * (PAGE_SIZE / sizeof(struct page));
+ }
+
+ static void __ref memmap_init_compound(struct page *head,
+@@ -6973,7 +6975,7 @@ void __ref memmap_init_zone_device(struc
+ continue;
+
+ memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
+- compound_nr_pages(altmap, pfns_per_compound));
++ compound_nr_pages(altmap, pgmap));
+ }
+
+ pr_info("%s initialised %lu pages in %ums\n", __func__,
+--- a/mm/sparse-vmemmap.c
++++ b/mm/sparse-vmemmap.c
+@@ -458,8 +458,7 @@ struct page * __meminit __populate_secti
+ !IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
+ return NULL;
+
+- if (is_power_of_2(sizeof(struct page)) &&
+- pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
++ if (vmemmap_can_optimize(altmap, pgmap))
+ r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
+ else
+ r = vmemmap_populate(start, end, nid, altmap);
--- /dev/null
+From de3004c874e740304cc4f4a83d6200acb511bbda Mon Sep 17 00:00:00 2001
+From: Roberto Sassu <roberto.sassu@huawei.com>
+Date: Tue, 14 Mar 2023 09:17:16 +0100
+Subject: ocfs2: Switch to security_inode_init_security()
+
+From: Roberto Sassu <roberto.sassu@huawei.com>
+
+commit de3004c874e740304cc4f4a83d6200acb511bbda upstream.
+
+In preparation for removing security_old_inode_init_security(), switch to
+security_inode_init_security().
+
+Extend the existing ocfs2_initxattrs() to take the
+ocfs2_security_xattr_info structure from fs_info, and populate the
+name/value/len triple with the first xattr provided by LSMs.
+
+As fs_info was not used before, ocfs2_initxattrs() can now handle the case
+of replicating the behavior of security_old_inode_init_security(), i.e.
+just obtaining the xattr, in addition to setting all xattrs provided by
+LSMs.
+
+Supporting multiple xattrs is not currently supported where
+security_old_inode_init_security() was called (mknod, symlink), as it
+requires non-trivial changes that can be done at a later time. Like for
+reiserfs, even if EVM is invoked, it will not provide an xattr (if it is
+not the first to set it, its xattr will be discarded; if it is the first,
+it does not have xattrs to calculate the HMAC on).
+
+Finally, since security_inode_init_security(), unlike
+security_old_inode_init_security(), returns zero instead of -EOPNOTSUPP if
+no xattrs were provided by LSMs or if inodes are private, additionally
+check in ocfs2_init_security_get() if the xattr name is set.
+
+If not, act as if security_old_inode_init_security() returned -EOPNOTSUPP,
+and set si->enable to zero to notify to the functions following
+ocfs2_init_security_get() that no xattrs are available.
+
+Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
+Reviewed-by: Casey Schaufler <casey@schaufler-ca.com>
+Acked-by: Joseph Qi <joseph.qi@linux.alibaba.com>
+Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
+Signed-off-by: Paul Moore <paul@paul-moore.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ fs/ocfs2/namei.c | 2 ++
+ fs/ocfs2/xattr.c | 30 ++++++++++++++++++++++++++----
+ 2 files changed, 28 insertions(+), 4 deletions(-)
+
+--- a/fs/ocfs2/namei.c
++++ b/fs/ocfs2/namei.c
+@@ -242,6 +242,7 @@ static int ocfs2_mknod(struct mnt_idmap
+ int want_meta = 0;
+ int xattr_credits = 0;
+ struct ocfs2_security_xattr_info si = {
++ .name = NULL,
+ .enable = 1,
+ };
+ int did_quota_inode = 0;
+@@ -1805,6 +1806,7 @@ static int ocfs2_symlink(struct mnt_idma
+ int want_clusters = 0;
+ int xattr_credits = 0;
+ struct ocfs2_security_xattr_info si = {
++ .name = NULL,
+ .enable = 1,
+ };
+ int did_quota = 0, did_quota_inode = 0;
+--- a/fs/ocfs2/xattr.c
++++ b/fs/ocfs2/xattr.c
+@@ -7259,9 +7259,21 @@ static int ocfs2_xattr_security_set(cons
+ static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *fs_info)
+ {
++ struct ocfs2_security_xattr_info *si = fs_info;
+ const struct xattr *xattr;
+ int err = 0;
+
++ if (si) {
++ si->value = kmemdup(xattr_array->value, xattr_array->value_len,
++ GFP_KERNEL);
++ if (!si->value)
++ return -ENOMEM;
++
++ si->name = xattr_array->name;
++ si->value_len = xattr_array->value_len;
++ return 0;
++ }
++
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ err = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY,
+ xattr->name, xattr->value,
+@@ -7277,13 +7289,23 @@ int ocfs2_init_security_get(struct inode
+ const struct qstr *qstr,
+ struct ocfs2_security_xattr_info *si)
+ {
++ int ret;
++
+ /* check whether ocfs2 support feature xattr */
+ if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb)))
+ return -EOPNOTSUPP;
+- if (si)
+- return security_old_inode_init_security(inode, dir, qstr,
+- &si->name, &si->value,
+- &si->value_len);
++ if (si) {
++ ret = security_inode_init_security(inode, dir, qstr,
++ &ocfs2_initxattrs, si);
++ /*
++ * security_inode_init_security() does not return -EOPNOTSUPP,
++ * we have to check the xattr ourselves.
++ */
++ if (!ret && !si->name)
++ si->enable = 0;
++
++ return ret;
++ }
+
+ return security_inode_init_security(inode, dir, qstr,
+ &ocfs2_initxattrs, NULL);
projects / thirdparty / kernel / stable-queue.git / commitdiff
