June 2021 - Linux-stable-mirror

FAILED: patch "[PATCH] mm/hwpoison: do not lock page again when me_huge_page()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ea6d0630100b285f059d0a8d8e86f38a46407536 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Date: Thu, 24 Jun 2021 18:40:01 -0700 Subject: [PATCH] mm/hwpoison: do not lock page again when me_huge_page() successfully recovers Currently me_huge_page() temporary unlocks page to perform some actions then locks it again later. My testcase (which calls hard-offline on some tail page in a hugetlb, then accesses the address of the hugetlb range) showed that page allocation code detects this page lock on buddy page and printed out "BUG: Bad page state" message. check_new_page_bad() does not consider a page with __PG_HWPOISON as bad page, so this flag works as kind of filter, but this filtering doesn't work in this case because the "bad page" is not the actual hwpoisoned page. So stop locking page again. Actions to be taken depend on the page type of the error, so page unlocking should be done in ->action() callbacks. So let's make it assumed and change all existing callbacks that way. Link: https://lkml.kernel.org/r/20210609072029.74645-1-nao.horiguchi@gmail.com Fixes: commit 78bb920344b8 ("mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error") Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Tony Luck <tony.luck(a)intel.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f24105db7081..6f5f78885ab4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -658,6 +658,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, */ static int me_kernel(struct page *p, unsigned long pfn) { + unlock_page(p); return MF_IGNORED; } @@ -667,6 +668,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + unlock_page(p); return MF_FAILED; } @@ -675,6 +677,7 @@ static int me_unknown(struct page *p, unsigned long pfn) */ static int me_pagecache_clean(struct page *p, unsigned long pfn) { + int ret; struct address_space *mapping; delete_from_lru_cache(p); @@ -683,8 +686,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -698,7 +703,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + ret = MF_FAILED; + goto out; } /* @@ -706,7 +712,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, pfn, mapping); +out: + unlock_page(p); + return ret; } /* @@ -782,24 +791,26 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { + int ret; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + return ret; } static int me_swapcache_clean(struct page *p, unsigned long pfn) { + int ret; + delete_from_swap_cache(p); - if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + unlock_page(p); + return ret; } /* @@ -820,6 +831,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { res = truncate_error_page(hpage, pfn, mapping); + unlock_page(hpage); } else { res = MF_FAILED; unlock_page(hpage); @@ -834,7 +846,6 @@ static int me_huge_page(struct page *p, unsigned long pfn) page_ref_inc(p); res = MF_RECOVERED; } - lock_page(hpage); } return res; @@ -866,6 +877,8 @@ static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, @@ -929,6 +942,7 @@ static int page_action(struct page_state *ps, struct page *p, int result; int count; + /* page p should be unlocked after returning from ps->action(). */ result = ps->action(p, pfn); count = page_count(p) - 1; @@ -1313,7 +1327,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) goto out; } - res = identify_page_state(pfn, p, page_flags); + return identify_page_state(pfn, p, page_flags); out: unlock_page(head); return res; @@ -1596,6 +1610,8 @@ int memory_failure(unsigned long pfn, int flags) identify_page_state: res = identify_page_state(pfn, p, page_flags); + mutex_unlock(&mf_mutex); + return res; unlock_page: unlock_page(p); unlock_mutex:

3 years

1
0
0 0

FAILED: patch "[PATCH] mm/hwpoison: do not lock page again when me_huge_page()" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ea6d0630100b285f059d0a8d8e86f38a46407536 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Date: Thu, 24 Jun 2021 18:40:01 -0700 Subject: [PATCH] mm/hwpoison: do not lock page again when me_huge_page() successfully recovers Currently me_huge_page() temporary unlocks page to perform some actions then locks it again later. My testcase (which calls hard-offline on some tail page in a hugetlb, then accesses the address of the hugetlb range) showed that page allocation code detects this page lock on buddy page and printed out "BUG: Bad page state" message. check_new_page_bad() does not consider a page with __PG_HWPOISON as bad page, so this flag works as kind of filter, but this filtering doesn't work in this case because the "bad page" is not the actual hwpoisoned page. So stop locking page again. Actions to be taken depend on the page type of the error, so page unlocking should be done in ->action() callbacks. So let's make it assumed and change all existing callbacks that way. Link: https://lkml.kernel.org/r/20210609072029.74645-1-nao.horiguchi@gmail.com Fixes: commit 78bb920344b8 ("mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error") Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Tony Luck <tony.luck(a)intel.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f24105db7081..6f5f78885ab4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -658,6 +658,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, */ static int me_kernel(struct page *p, unsigned long pfn) { + unlock_page(p); return MF_IGNORED; } @@ -667,6 +668,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + unlock_page(p); return MF_FAILED; } @@ -675,6 +677,7 @@ static int me_unknown(struct page *p, unsigned long pfn) */ static int me_pagecache_clean(struct page *p, unsigned long pfn) { + int ret; struct address_space *mapping; delete_from_lru_cache(p); @@ -683,8 +686,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -698,7 +703,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + ret = MF_FAILED; + goto out; } /* @@ -706,7 +712,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, pfn, mapping); +out: + unlock_page(p); + return ret; } /* @@ -782,24 +791,26 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { + int ret; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + return ret; } static int me_swapcache_clean(struct page *p, unsigned long pfn) { + int ret; + delete_from_swap_cache(p); - if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + unlock_page(p); + return ret; } /* @@ -820,6 +831,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { res = truncate_error_page(hpage, pfn, mapping); + unlock_page(hpage); } else { res = MF_FAILED; unlock_page(hpage); @@ -834,7 +846,6 @@ static int me_huge_page(struct page *p, unsigned long pfn) page_ref_inc(p); res = MF_RECOVERED; } - lock_page(hpage); } return res; @@ -866,6 +877,8 @@ static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, @@ -929,6 +942,7 @@ static int page_action(struct page_state *ps, struct page *p, int result; int count; + /* page p should be unlocked after returning from ps->action(). */ result = ps->action(p, pfn); count = page_count(p) - 1; @@ -1313,7 +1327,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) goto out; } - res = identify_page_state(pfn, p, page_flags); + return identify_page_state(pfn, p, page_flags); out: unlock_page(head); return res; @@ -1596,6 +1610,8 @@ int memory_failure(unsigned long pfn, int flags) identify_page_state: res = identify_page_state(pfn, p, page_flags); + mutex_unlock(&mf_mutex); + return res; unlock_page: unlock_page(p); unlock_mutex:

3 years

1
0
0 0

FAILED: patch "[PATCH] mm/hwpoison: do not lock page again when me_huge_page()" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ea6d0630100b285f059d0a8d8e86f38a46407536 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Date: Thu, 24 Jun 2021 18:40:01 -0700 Subject: [PATCH] mm/hwpoison: do not lock page again when me_huge_page() successfully recovers Currently me_huge_page() temporary unlocks page to perform some actions then locks it again later. My testcase (which calls hard-offline on some tail page in a hugetlb, then accesses the address of the hugetlb range) showed that page allocation code detects this page lock on buddy page and printed out "BUG: Bad page state" message. check_new_page_bad() does not consider a page with __PG_HWPOISON as bad page, so this flag works as kind of filter, but this filtering doesn't work in this case because the "bad page" is not the actual hwpoisoned page. So stop locking page again. Actions to be taken depend on the page type of the error, so page unlocking should be done in ->action() callbacks. So let's make it assumed and change all existing callbacks that way. Link: https://lkml.kernel.org/r/20210609072029.74645-1-nao.horiguchi@gmail.com Fixes: commit 78bb920344b8 ("mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error") Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Tony Luck <tony.luck(a)intel.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)linux.vnet.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f24105db7081..6f5f78885ab4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -658,6 +658,7 @@ static int truncate_error_page(struct page *p, unsigned long pfn, */ static int me_kernel(struct page *p, unsigned long pfn) { + unlock_page(p); return MF_IGNORED; } @@ -667,6 +668,7 @@ static int me_kernel(struct page *p, unsigned long pfn) static int me_unknown(struct page *p, unsigned long pfn) { pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + unlock_page(p); return MF_FAILED; } @@ -675,6 +677,7 @@ static int me_unknown(struct page *p, unsigned long pfn) */ static int me_pagecache_clean(struct page *p, unsigned long pfn) { + int ret; struct address_space *mapping; delete_from_lru_cache(p); @@ -683,8 +686,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * For anonymous pages we're done the only reference left * should be the one m_f() holds. */ - if (PageAnon(p)) - return MF_RECOVERED; + if (PageAnon(p)) { + ret = MF_RECOVERED; + goto out; + } /* * Now truncate the page in the page cache. This is really @@ -698,7 +703,8 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) /* * Page has been teared down in the meanwhile */ - return MF_FAILED; + ret = MF_FAILED; + goto out; } /* @@ -706,7 +712,10 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - return truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, pfn, mapping); +out: + unlock_page(p); + return ret; } /* @@ -782,24 +791,26 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) */ static int me_swapcache_dirty(struct page *p, unsigned long pfn) { + int ret; + ClearPageDirty(p); /* Trigger EIO in shmem: */ ClearPageUptodate(p); - if (!delete_from_lru_cache(p)) - return MF_DELAYED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; + unlock_page(p); + return ret; } static int me_swapcache_clean(struct page *p, unsigned long pfn) { + int ret; + delete_from_swap_cache(p); - if (!delete_from_lru_cache(p)) - return MF_RECOVERED; - else - return MF_FAILED; + ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; + unlock_page(p); + return ret; } /* @@ -820,6 +831,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { res = truncate_error_page(hpage, pfn, mapping); + unlock_page(hpage); } else { res = MF_FAILED; unlock_page(hpage); @@ -834,7 +846,6 @@ static int me_huge_page(struct page *p, unsigned long pfn) page_ref_inc(p); res = MF_RECOVERED; } - lock_page(hpage); } return res; @@ -866,6 +877,8 @@ static struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page *p, unsigned long pfn); } error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, @@ -929,6 +942,7 @@ static int page_action(struct page_state *ps, struct page *p, int result; int count; + /* page p should be unlocked after returning from ps->action(). */ result = ps->action(p, pfn); count = page_count(p) - 1; @@ -1313,7 +1327,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) goto out; } - res = identify_page_state(pfn, p, page_flags); + return identify_page_state(pfn, p, page_flags); out: unlock_page(head); return res; @@ -1596,6 +1610,8 @@ int memory_failure(unsigned long pfn, int flags) identify_page_state: res = identify_page_state(pfn, p, page_flags); + mutex_unlock(&mf_mutex); + return res; unlock_page: unlock_page(p); unlock_mutex:

3 years

1
0
0 0

[PATCH][RESEND] ceph: fix test for whether we can skip read when writing beyond EOF

by Jeff Layton

It's not sufficient to skip reading when the pos is beyond the EOF. There may be data at the head of the page that we need to fill in before the write. Add a new helper function that corrects and clarifies the logic of when we can skip reads, and have it only zero out the part of the page that won't have data copied in for the write. [ Note: this fix is commit 827a746f405d in mainline kernels. The original bug was in ceph, but got lifted into the fs/netfs library for v5.13. This backport should apply to stable kernels v5.10 though v5.12. ] Cc: <stable(a)vger.kernel.org> # v5.10+ Fixes: 1cc1699070bd ("ceph: fold ceph_update_writeable_page into ceph_write_begin") Reported-by: Andrew W Elble <aweits(a)rit.edu> Signed-off-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: David Howells <dhowells(a)redhat.com> --- fs/ceph/addr.c | 54 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 41 insertions(+), 13 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 26e66436f005..c000fe338f7e 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1302,6 +1302,45 @@ ceph_find_incompatible(struct page *page) return NULL; } +/** + * prep_noread_page - prep a page for writing without reading first + * @page: page being prepared + * @pos: starting position for the write + * @len: length of write + * + * In some cases, write_begin doesn't need to read at all: + * - full page write + * - file is currently zero-length + * - write that lies in a page that is completely beyond EOF + * - write that covers the the page from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the page and return true. Otherwise, return false. + */ +static bool skip_page_read(struct page *page, loff_t pos, size_t len) +{ + struct inode *inode = page->mapping->host; + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_page(pos); + + /* Full page write */ + if (offset == 0 && len >= PAGE_SIZE) + return true; + + /* pos beyond last page in the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* write that covers the whole page from start to EOF or beyond it */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(page, 0, offset, offset + len, PAGE_SIZE); + return true; +} + /* * We are only allowed to write into/dirty the page if the page is * clean, or already dirty within the same snap context. @@ -1315,7 +1354,6 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, struct ceph_snap_context *snapc; struct page *page = NULL; pgoff_t index = pos >> PAGE_SHIFT; - int pos_in_page = pos & ~PAGE_MASK; int r = 0; dout("write_begin file %p inode %p page %p %d~%d\n", file, inode, page, (int)pos, (int)len); @@ -1350,19 +1388,9 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, break; } - /* - * In some cases we don't need to read at all: - * - full page write - * - write that lies completely beyond EOF - * - write that covers the the page from start to EOF or beyond it - */ - if ((pos_in_page == 0 && len == PAGE_SIZE) || - (pos >= i_size_read(inode)) || - (pos_in_page == 0 && (pos + len) >= i_size_read(inode))) { - zero_user_segments(page, 0, pos_in_page, - pos_in_page + len, PAGE_SIZE); + /* No need to read in some cases */ + if (skip_page_read(page, pos, len)) break; - } /* * We need to read it. If we get back -EINPROGRESS, then the page was -- 2.31.1

3 years

2
1
0 0

FAILED: patch "[PATCH] mm/memory-failure: use a mutex to avoid memory_failure()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 171936ddaf97e6f4e1264f4128bb5cf15691339c Mon Sep 17 00:00:00 2001 From: Tony Luck <tony.luck(a)intel.com> Date: Thu, 24 Jun 2021 18:39:55 -0700 Subject: [PATCH] mm/memory-failure: use a mutex to avoid memory_failure() races Patch series "mm,hwpoison: fix sending SIGBUS for Action Required MCE", v5. I wrote this patchset to materialize what I think is the current allowable solution mentioned by the previous discussion [1]. I simply borrowed Tony's mutex patch and Aili's return code patch, then I queued another one to find error virtual address in the best effort manner. I know that this is not a perfect solution, but should work for some typical case. [1]: https://lore.kernel.org/linux-mm/20210331192540.2141052f@alex-virtual-machi… This patch (of 2): There can be races when multiple CPUs consume poison from the same page. The first into memory_failure() atomically sets the HWPoison page flag and begins hunting for tasks that map this page. Eventually it invalidates those mappings and may send a SIGBUS to the affected tasks. But while all that work is going on, other CPUs see a "success" return code from memory_failure() and so they believe the error has been handled and continue executing. Fix by wrapping most of the internal parts of memory_failure() in a mutex. [akpm(a)linux-foundation.org: make mf_mutex local to memory_failure()] Link: https://lkml.kernel.org/r/20210521030156.2612074-1-nao.horiguchi@gmail.com Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@gmail.com Signed-off-by: Tony Luck <tony.luck(a)intel.com> Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Aili Yao <yaoaili(a)kingsoft.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jue Wang <juew(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0143d32bc666..a7fc1cd6765a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1429,9 +1429,10 @@ int memory_failure(unsigned long pfn, int flags) struct page *hpage; struct page *orig_head; struct dev_pagemap *pgmap; - int res; + int res = 0; unsigned long page_flags; bool retry = true; + static DEFINE_MUTEX(mf_mutex); if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1449,13 +1450,18 @@ int memory_failure(unsigned long pfn, int flags) return -ENXIO; } + mutex_lock(&mf_mutex); + try_again: - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); + if (PageHuge(p)) { + res = memory_failure_hugetlb(pfn, flags); + goto unlock_mutex; + } + if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return 0; + goto unlock_mutex; } orig_head = hpage = compound_head(p); @@ -1488,17 +1494,19 @@ int memory_failure(unsigned long pfn, int flags) res = MF_FAILED; } action_result(pfn, MF_MSG_BUDDY, res); - return res == MF_RECOVERED ? 0 : -EBUSY; + res = res == MF_RECOVERED ? 0 : -EBUSY; } else { action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); - return -EBUSY; + res = -EBUSY; } + goto unlock_mutex; } if (PageTransHuge(hpage)) { if (try_to_split_thp_page(p, "Memory Failure") < 0) { action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); - return -EBUSY; + res = -EBUSY; + goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); } @@ -1522,7 +1530,7 @@ int memory_failure(unsigned long pfn, int flags) if (PageCompound(p) && compound_head(p) != orig_head) { action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1542,14 +1550,14 @@ int memory_failure(unsigned long pfn, int flags) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } /* @@ -1573,7 +1581,7 @@ int memory_failure(unsigned long pfn, int flags) if (!hwpoison_user_mappings(p, pfn, flags, &p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1582,13 +1590,15 @@ int memory_failure(unsigned long pfn, int flags) if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: +unlock_page: unlock_page(p); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure);

3 years

1
0
0 0

FAILED: patch "[PATCH] mm/memory-failure: use a mutex to avoid memory_failure()" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 171936ddaf97e6f4e1264f4128bb5cf15691339c Mon Sep 17 00:00:00 2001 From: Tony Luck <tony.luck(a)intel.com> Date: Thu, 24 Jun 2021 18:39:55 -0700 Subject: [PATCH] mm/memory-failure: use a mutex to avoid memory_failure() races Patch series "mm,hwpoison: fix sending SIGBUS for Action Required MCE", v5. I wrote this patchset to materialize what I think is the current allowable solution mentioned by the previous discussion [1]. I simply borrowed Tony's mutex patch and Aili's return code patch, then I queued another one to find error virtual address in the best effort manner. I know that this is not a perfect solution, but should work for some typical case. [1]: https://lore.kernel.org/linux-mm/20210331192540.2141052f@alex-virtual-machi… This patch (of 2): There can be races when multiple CPUs consume poison from the same page. The first into memory_failure() atomically sets the HWPoison page flag and begins hunting for tasks that map this page. Eventually it invalidates those mappings and may send a SIGBUS to the affected tasks. But while all that work is going on, other CPUs see a "success" return code from memory_failure() and so they believe the error has been handled and continue executing. Fix by wrapping most of the internal parts of memory_failure() in a mutex. [akpm(a)linux-foundation.org: make mf_mutex local to memory_failure()] Link: https://lkml.kernel.org/r/20210521030156.2612074-1-nao.horiguchi@gmail.com Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@gmail.com Signed-off-by: Tony Luck <tony.luck(a)intel.com> Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: Aili Yao <yaoaili(a)kingsoft.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jue Wang <juew(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0143d32bc666..a7fc1cd6765a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1429,9 +1429,10 @@ int memory_failure(unsigned long pfn, int flags) struct page *hpage; struct page *orig_head; struct dev_pagemap *pgmap; - int res; + int res = 0; unsigned long page_flags; bool retry = true; + static DEFINE_MUTEX(mf_mutex); if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1449,13 +1450,18 @@ int memory_failure(unsigned long pfn, int flags) return -ENXIO; } + mutex_lock(&mf_mutex); + try_again: - if (PageHuge(p)) - return memory_failure_hugetlb(pfn, flags); + if (PageHuge(p)) { + res = memory_failure_hugetlb(pfn, flags); + goto unlock_mutex; + } + if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return 0; + goto unlock_mutex; } orig_head = hpage = compound_head(p); @@ -1488,17 +1494,19 @@ int memory_failure(unsigned long pfn, int flags) res = MF_FAILED; } action_result(pfn, MF_MSG_BUDDY, res); - return res == MF_RECOVERED ? 0 : -EBUSY; + res = res == MF_RECOVERED ? 0 : -EBUSY; } else { action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); - return -EBUSY; + res = -EBUSY; } + goto unlock_mutex; } if (PageTransHuge(hpage)) { if (try_to_split_thp_page(p, "Memory Failure") < 0) { action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); - return -EBUSY; + res = -EBUSY; + goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); } @@ -1522,7 +1530,7 @@ int memory_failure(unsigned long pfn, int flags) if (PageCompound(p) && compound_head(p) != orig_head) { action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1542,14 +1550,14 @@ int memory_failure(unsigned long pfn, int flags) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unlock_page(p); put_page(p); - return 0; + goto unlock_mutex; } /* @@ -1573,7 +1581,7 @@ int memory_failure(unsigned long pfn, int flags) if (!hwpoison_user_mappings(p, pfn, flags, &p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } /* @@ -1582,13 +1590,15 @@ int memory_failure(unsigned long pfn, int flags) if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); res = -EBUSY; - goto out; + goto unlock_page; } identify_page_state: res = identify_page_state(pfn, p, page_flags); -out: +unlock_page: unlock_page(p); +unlock_mutex: + mutex_unlock(&mf_mutex); return res; } EXPORT_SYMBOL_GPL(memory_failure);

3 years

1
0
0 0

FAILED: patch "[PATCH] swiotlb: manipulate orig_addr when tlb_addr has offset" failed to apply to 5.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 5f89468e2f060031cd89fd4287298e0eaf246bf6 Mon Sep 17 00:00:00 2001 From: Bumyong Lee <bumyong.lee(a)samsung.com> Date: Mon, 10 May 2021 18:10:04 +0900 Subject: [PATCH] swiotlb: manipulate orig_addr when tlb_addr has offset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit in case of driver wants to sync part of ranges with offset, swiotlb_tbl_sync_single() copies from orig_addr base to tlb_addr with offset and ends up with data mismatch. It was removed from "swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single", but said logic has to be added back in. >From Linus's email: "That commit which the removed the offset calculation entirely, because the old (unsigned long)tlb_addr & (IO_TLB_SIZE - 1) was wrong, but instead of removing it, I think it should have just fixed it to be (tlb_addr - mem->start) & (IO_TLB_SIZE - 1); instead. That way the slot offset always matches the slot index calculation." (Unfortunatly that broke NVMe). The use-case that drivers are hitting is as follow: 1. Get dma_addr_t from dma_map_single() dma_addr_t tlb_addr = dma_map_single(dev, vaddr, vsize, DMA_TO_DEVICE); |<---------------vsize------------->| +-----------------------------------+ | | original buffer +-----------------------------------+ vaddr swiotlb_align_offset |<----->|<---------------vsize------------->| +-------+-----------------------------------+ | | | swiotlb buffer +-------+-----------------------------------+ tlb_addr 2. Do something 3. Sync dma_addr_t through dma_sync_single_for_device(..) dma_sync_single_for_device(dev, tlb_addr + offset, size, DMA_TO_DEVICE); Error case. Copy data to original buffer but it is from base addr (instead of base addr + offset) in original buffer: swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr |<- size ->| +-----------------------------------+ |##########| | original buffer +-----------------------------------+ vaddr The fix is to copy the data to the original buffer and take into account the offset, like so: swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr |<- offset ->|<- size ->| +-----------------------------------+ | |##########| | original buffer +-----------------------------------+ vaddr [One fix which was Linus's that made more sense to as it created a symmetry would break NVMe. The reason for that is the: unsigned int offset = (tlb_addr - mem->start) & (IO_TLB_SIZE - 1); would come up with the proper offset, but it would lose the alignment (which this patch contains).] Fixes: 16fc3cef33a0 ("swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single") Signed-off-by: Bumyong Lee <bumyong.lee(a)samsung.com> Signed-off-by: Chanho Park <chanho61.park(a)samsung.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reported-by: Dominique MARTINET <dominique.martinet(a)atmark-techno.com> Reported-by: Horia Geantă <horia.geanta(a)nxp.com> Tested-by: Horia Geantă <horia.geanta(a)nxp.com> CC: stable(a)vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8ca7d505d61c..e50df8d8f87e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -334,6 +334,14 @@ void __init swiotlb_exit(void) io_tlb_default_mem = NULL; } +/* + * Return the offset into a iotlb slot required to keep the device happy. + */ +static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +{ + return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); +} + /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ @@ -346,10 +354,17 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = phys_to_virt(tlb_addr); + unsigned int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; + tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(dev, orig_addr); + + orig_addr += tlb_offset; + alloc_size -= tlb_offset; + if (size > alloc_size) { dev_WARN_ONCE(dev, 1, "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", @@ -390,14 +405,6 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size #define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT)) -/* - * Return the offset into a iotlb slot required to keep the device happy. - */ -static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) -{ - return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); -} - /* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. */

3 years

4
6
0 0

Projects

by Jotham Masuku

Hello there, I hope this message finds you in good spirits especially during this challenging time of coronavirus pandemic. I hope you and your family are well and keeping safe. Anyway, I am Jotham Masuku, a broker working with Flippiebecker Wealth. I got your contact through an online business directory and I thought I should contact you to see if you are interested in this opportunity. I am contacting you because one of my high profile clients is interested in investing abroad and has asked me to look for individuals and companies in your country with interesting business ideas and projects that he can invest in. He wants to invest a substantial amount of asset abroad. I have decided to keep this brief for now but please kindly respond back to this email if you are interested in this opportunity. Once I receive your response, I will give you more details and we can plan a strategy that will be beneficial to all parties. Best regards J Masuku Flippiebecker Wealth

3 years

1
0
0 0

FAILED: patch "[PATCH] swiotlb: manipulate orig_addr when tlb_addr has offset" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 5f89468e2f060031cd89fd4287298e0eaf246bf6 Mon Sep 17 00:00:00 2001 From: Bumyong Lee <bumyong.lee(a)samsung.com> Date: Mon, 10 May 2021 18:10:04 +0900 Subject: [PATCH] swiotlb: manipulate orig_addr when tlb_addr has offset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit in case of driver wants to sync part of ranges with offset, swiotlb_tbl_sync_single() copies from orig_addr base to tlb_addr with offset and ends up with data mismatch. It was removed from "swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single", but said logic has to be added back in. >From Linus's email: "That commit which the removed the offset calculation entirely, because the old (unsigned long)tlb_addr & (IO_TLB_SIZE - 1) was wrong, but instead of removing it, I think it should have just fixed it to be (tlb_addr - mem->start) & (IO_TLB_SIZE - 1); instead. That way the slot offset always matches the slot index calculation." (Unfortunatly that broke NVMe). The use-case that drivers are hitting is as follow: 1. Get dma_addr_t from dma_map_single() dma_addr_t tlb_addr = dma_map_single(dev, vaddr, vsize, DMA_TO_DEVICE); |<---------------vsize------------->| +-----------------------------------+ | | original buffer +-----------------------------------+ vaddr swiotlb_align_offset |<----->|<---------------vsize------------->| +-------+-----------------------------------+ | | | swiotlb buffer +-------+-----------------------------------+ tlb_addr 2. Do something 3. Sync dma_addr_t through dma_sync_single_for_device(..) dma_sync_single_for_device(dev, tlb_addr + offset, size, DMA_TO_DEVICE); Error case. Copy data to original buffer but it is from base addr (instead of base addr + offset) in original buffer: swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr |<- size ->| +-----------------------------------+ |##########| | original buffer +-----------------------------------+ vaddr The fix is to copy the data to the original buffer and take into account the offset, like so: swiotlb_align_offset |<----->|<- offset ->|<- size ->| +-------+-----------------------------------+ | | |##########| | swiotlb buffer +-------+-----------------------------------+ tlb_addr |<- offset ->|<- size ->| +-----------------------------------+ | |##########| | original buffer +-----------------------------------+ vaddr [One fix which was Linus's that made more sense to as it created a symmetry would break NVMe. The reason for that is the: unsigned int offset = (tlb_addr - mem->start) & (IO_TLB_SIZE - 1); would come up with the proper offset, but it would lose the alignment (which this patch contains).] Fixes: 16fc3cef33a0 ("swiotlb: don't modify orig_addr in swiotlb_tbl_sync_single") Signed-off-by: Bumyong Lee <bumyong.lee(a)samsung.com> Signed-off-by: Chanho Park <chanho61.park(a)samsung.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reported-by: Dominique MARTINET <dominique.martinet(a)atmark-techno.com> Reported-by: Horia Geantă <horia.geanta(a)nxp.com> Tested-by: Horia Geantă <horia.geanta(a)nxp.com> CC: stable(a)vger.kernel.org Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8ca7d505d61c..e50df8d8f87e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -334,6 +334,14 @@ void __init swiotlb_exit(void) io_tlb_default_mem = NULL; } +/* + * Return the offset into a iotlb slot required to keep the device happy. + */ +static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +{ + return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); +} + /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ @@ -346,10 +354,17 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = phys_to_virt(tlb_addr); + unsigned int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; + tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(dev, orig_addr); + + orig_addr += tlb_offset; + alloc_size -= tlb_offset; + if (size > alloc_size) { dev_WARN_ONCE(dev, 1, "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", @@ -390,14 +405,6 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size #define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT)) -/* - * Return the offset into a iotlb slot required to keep the device happy. - */ -static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) -{ - return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); -} - /* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. */

3 years

2
1
0 0

[PATCHv3 1/4] clk: agilex/stratix10: remove noc_clk

by Dinh Nguyen

Early documentation had a noc_clk, but in reality, it's just the noc_free_clk. Remove the noc_clk clock and just use the noc_free_clk. Fixes: 80c6b7a0894f ("clk: socfpga: agilex: add clock driver for the Agilex platform") Cc: stable(a)vger.kernel.org Signed-off-by: Dinh Nguyen <dinguyen(a)kernel.org> --- v3: no change v2: add linux-stable to cc --- drivers/clk/socfpga/clk-agilex.c | 32 +++++++++++++++----------------- drivers/clk/socfpga/clk-s10.c | 32 +++++++++++++++----------------- 2 files changed, 30 insertions(+), 34 deletions(-) diff --git a/drivers/clk/socfpga/clk-agilex.c b/drivers/clk/socfpga/clk-agilex.c index 92a6d740a799..5b8131542218 100644 --- a/drivers/clk/socfpga/clk-agilex.c +++ b/drivers/clk/socfpga/clk-agilex.c @@ -222,11 +222,9 @@ static const struct stratix10_perip_cnt_clock agilex_main_perip_cnt_clks[] = { { AGILEX_MPU_FREE_CLK, "mpu_free_clk", NULL, mpu_free_mux, ARRAY_SIZE(mpu_free_mux), 0, 0x3C, 0, 0, 0}, { AGILEX_NOC_FREE_CLK, "noc_free_clk", NULL, noc_free_mux, ARRAY_SIZE(noc_free_mux), - 0, 0x40, 0, 0, 1}, - { AGILEX_L4_SYS_FREE_CLK, "l4_sys_free_clk", "noc_free_clk", NULL, 1, 0, - 0, 4, 0, 0}, - { AGILEX_NOC_CLK, "noc_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), - 0, 0, 0, 0x30, 1}, + 0, 0x40, 0, 0, 0}, + { AGILEX_L4_SYS_FREE_CLK, "l4_sys_free_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, + 0, 4, 0x30, 1}, { AGILEX_EMAC_A_FREE_CLK, "emaca_free_clk", NULL, emaca_free_mux, ARRAY_SIZE(emaca_free_mux), 0, 0xD4, 0, 0x88, 0}, { AGILEX_EMAC_B_FREE_CLK, "emacb_free_clk", NULL, emacb_free_mux, ARRAY_SIZE(emacb_free_mux), @@ -252,24 +250,24 @@ static const struct stratix10_gate_clock agilex_gate_clks[] = { 0, 0, 0, 0, 0, 0, 4}, { AGILEX_MPU_CCU_CLK, "mpu_ccu_clk", "mpu_clk", NULL, 1, 0, 0x24, 0, 0, 0, 0, 0, 0, 2}, - { AGILEX_L4_MAIN_CLK, "l4_main_clk", "noc_clk", NULL, 1, 0, 0x24, - 1, 0x44, 0, 2, 0, 0, 0}, - { AGILEX_L4_MP_CLK, "l4_mp_clk", "noc_clk", NULL, 1, 0, 0x24, - 2, 0x44, 8, 2, 0, 0, 0}, + { AGILEX_L4_MAIN_CLK, "l4_main_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x24, + 1, 0x44, 0, 2, 0x30, 1, 0}, + { AGILEX_L4_MP_CLK, "l4_mp_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x24, + 2, 0x44, 8, 2, 0x30, 1, 0}, /* * The l4_sp_clk feeds a 100 MHz clock to various peripherals, one of them * being the SP timers, thus cannot get gated. */ - { AGILEX_L4_SP_CLK, "l4_sp_clk", "noc_clk", NULL, 1, CLK_IS_CRITICAL, 0x24, - 3, 0x44, 16, 2, 0, 0, 0}, - { AGILEX_CS_AT_CLK, "cs_at_clk", "noc_clk", NULL, 1, 0, 0x24, - 4, 0x44, 24, 2, 0, 0, 0}, - { AGILEX_CS_TRACE_CLK, "cs_trace_clk", "noc_clk", NULL, 1, 0, 0x24, - 4, 0x44, 26, 2, 0, 0, 0}, + { AGILEX_L4_SP_CLK, "l4_sp_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), CLK_IS_CRITICAL, 0x24, + 3, 0x44, 16, 2, 0x30, 1, 0}, + { AGILEX_CS_AT_CLK, "cs_at_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x24, + 4, 0x44, 24, 2, 0x30, 1, 0}, + { AGILEX_CS_TRACE_CLK, "cs_trace_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x24, + 4, 0x44, 26, 2, 0x30, 1, 0}, { AGILEX_CS_PDBG_CLK, "cs_pdbg_clk", "cs_at_clk", NULL, 1, 0, 0x24, 4, 0x44, 28, 1, 0, 0, 0}, - { AGILEX_CS_TIMER_CLK, "cs_timer_clk", "noc_clk", NULL, 1, 0, 0x24, - 5, 0, 0, 0, 0, 0, 0}, + { AGILEX_CS_TIMER_CLK, "cs_timer_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x24, + 5, 0, 0, 0, 0x30, 1, 0}, { AGILEX_S2F_USER0_CLK, "s2f_user0_clk", NULL, s2f_usr0_mux, ARRAY_SIZE(s2f_usr0_mux), 0, 0x24, 6, 0, 0, 0, 0, 0, 0}, { AGILEX_EMAC0_CLK, "emac0_clk", NULL, emac_mux, ARRAY_SIZE(emac_mux), 0, 0x7C, diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c index f0bd77138ecb..0199cffe4d77 100644 --- a/drivers/clk/socfpga/clk-s10.c +++ b/drivers/clk/socfpga/clk-s10.c @@ -167,7 +167,7 @@ static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = { { STRATIX10_MPU_FREE_CLK, "mpu_free_clk", NULL, mpu_free_mux, ARRAY_SIZE(mpu_free_mux), 0, 0x48, 0, 0, 0}, { STRATIX10_NOC_FREE_CLK, "noc_free_clk", NULL, noc_free_mux, ARRAY_SIZE(noc_free_mux), - 0, 0x4C, 0, 0, 0}, + 0, 0x4C, 0, 0x3C, 1}, { STRATIX10_MAIN_EMACA_CLK, "main_emaca_clk", "main_noc_base_clk", NULL, 1, 0, 0x50, 0, 0, 0}, { STRATIX10_MAIN_EMACB_CLK, "main_emacb_clk", "main_noc_base_clk", NULL, 1, 0, @@ -200,10 +200,8 @@ static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = { 0, 0xD4, 0, 0, 0}, { STRATIX10_PERI_PSI_REF_CLK, "peri_psi_ref_clk", "peri_noc_base_clk", NULL, 1, 0, 0xD8, 0, 0, 0}, - { STRATIX10_L4_SYS_FREE_CLK, "l4_sys_free_clk", "noc_free_clk", NULL, 1, 0, - 0, 4, 0, 0}, - { STRATIX10_NOC_CLK, "noc_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), - 0, 0, 0, 0x3C, 1}, + { STRATIX10_L4_SYS_FREE_CLK, "l4_sys_free_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, + 0, 4, 0x3C, 1}, { STRATIX10_EMAC_A_FREE_CLK, "emaca_free_clk", NULL, emaca_free_mux, ARRAY_SIZE(emaca_free_mux), 0, 0, 2, 0xB0, 0}, { STRATIX10_EMAC_B_FREE_CLK, "emacb_free_clk", NULL, emacb_free_mux, ARRAY_SIZE(emacb_free_mux), @@ -227,20 +225,20 @@ static const struct stratix10_gate_clock s10_gate_clks[] = { 0, 0, 0, 0, 0, 0, 4}, { STRATIX10_MPU_L2RAM_CLK, "mpu_l2ram_clk", "mpu_clk", NULL, 1, 0, 0x30, 0, 0, 0, 0, 0, 0, 2}, - { STRATIX10_L4_MAIN_CLK, "l4_main_clk", "noc_clk", NULL, 1, 0, 0x30, - 1, 0x70, 0, 2, 0, 0, 0}, - { STRATIX10_L4_MP_CLK, "l4_mp_clk", "noc_clk", NULL, 1, 0, 0x30, - 2, 0x70, 8, 2, 0, 0, 0}, - { STRATIX10_L4_SP_CLK, "l4_sp_clk", "noc_clk", NULL, 1, CLK_IS_CRITICAL, 0x30, - 3, 0x70, 16, 2, 0, 0, 0}, - { STRATIX10_CS_AT_CLK, "cs_at_clk", "noc_clk", NULL, 1, 0, 0x30, - 4, 0x70, 24, 2, 0, 0, 0}, - { STRATIX10_CS_TRACE_CLK, "cs_trace_clk", "noc_clk", NULL, 1, 0, 0x30, - 4, 0x70, 26, 2, 0, 0, 0}, + { STRATIX10_L4_MAIN_CLK, "l4_main_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x30, + 1, 0x70, 0, 2, 0x3C, 1, 0}, + { STRATIX10_L4_MP_CLK, "l4_mp_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x30, + 2, 0x70, 8, 2, 0x3C, 1, 0}, + { STRATIX10_L4_SP_CLK, "l4_sp_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), CLK_IS_CRITICAL, 0x30, + 3, 0x70, 16, 2, 0x3C, 1, 0}, + { STRATIX10_CS_AT_CLK, "cs_at_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x30, + 4, 0x70, 24, 2, 0x3C, 1, 0}, + { STRATIX10_CS_TRACE_CLK, "cs_trace_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x30, + 4, 0x70, 26, 2, 0x3C, 1, 0}, { STRATIX10_CS_PDBG_CLK, "cs_pdbg_clk", "cs_at_clk", NULL, 1, 0, 0x30, 4, 0x70, 28, 1, 0, 0, 0}, - { STRATIX10_CS_TIMER_CLK, "cs_timer_clk", "noc_clk", NULL, 1, 0, 0x30, - 5, 0, 0, 0, 0, 0, 0}, + { STRATIX10_CS_TIMER_CLK, "cs_timer_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0x30, + 5, 0, 0, 0, 0x3C, 1, 0}, { STRATIX10_S2F_USER0_CLK, "s2f_user0_clk", NULL, s2f_usr0_mux, ARRAY_SIZE(s2f_usr0_mux), 0, 0x30, 6, 0, 0, 0, 0, 0, 0}, { STRATIX10_EMAC0_CLK, "emac0_clk", NULL, emac_mux, ARRAY_SIZE(emac_mux), 0, 0xA4, -- 2.25.1

3 years

2
8
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2021