- Linux-stable-mirror - lists.linaro.org

[PATCH 5.15.y] of: module: add buffer overflow check in of_modalias()

by Uwe Kleine-König

From: Sergey Shtylyov <s.shtylyov(a)omp.ru> commit cf7385cb26ac4f0ee6c7385960525ad534323252 upstream. In of_modalias(), if the buffer happens to be too small even for the 1st snprintf() call, the len parameter will become negative and str parameter (if not NULL initially) will point beyond the buffer's end. Add the buffer overflow check after the 1st snprintf() call and fix such check after the strlen() call (accounting for the terminating NUL char). Fixes: bc575064d688 ("of/device: use of_property_for_each_string to parse compatible strings") Signed-off-by: Sergey Shtylyov <s.shtylyov(a)omp.ru> Link: https://lore.kernel.org/r/bbfc6be0-c687-62b6-d015-5141b93f313e@omp.ru Signed-off-by: Rob Herring <robh(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Uwe Kleine-König <ukleinek(a)debian.org> --- drivers/of/device.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 19c42a9dcba9..f503bb10b10b 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -257,14 +257,15 @@ static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len csize = snprintf(str, len, "of:N%pOFn%c%s", dev->of_node, 'T', of_node_get_device_type(dev->of_node)); tsize = csize; + if (csize >= len) + csize = len > 0 ? len - 1 : 0; len -= csize; - if (str) - str += csize; + str += csize; of_property_for_each_string(dev->of_node, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; - if (csize > len) + if (csize >= len) continue; csize = snprintf(str, len, "C%s", compat); base-commit: 16fdf2c7111bd6927f16c3e811f5086fecebbf00 -- 2.47.2

4 months, 1 week

2
1
0 0

[PATCH 5.15.y] btrfs: do not clean up repair bio if submit fails

by bin.lan.cn＠windriver.com

From: Josef Bacik <josef(a)toxicpanda.com> [ Upstream commit 8cbc3001a3264d998d6b6db3e23f935c158abd4d ] The submit helper will always run bio_endio() on the bio if it fails to submit, so cleaning up the bio just leads to a variety of use-after-free and NULL pointer dereference bugs because we race with the endio function that is cleaning up the bio. Instead just return BLK_STS_OK as the repair function has to continue to process the rest of the pages, and the endio for the repair bio will do the appropriate cleanup for the page that it was given. Reviewed-by: Boris Burkov <boris(a)bur.io> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> [Minor context change fixed.] Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- fs/btrfs/extent_io.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 346fc46d019b..a1946d62911c 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2624,7 +2624,6 @@ int btrfs_repair_one_sector(struct inode *inode, const int icsum = bio_offset >> fs_info->sectorsize_bits; struct bio *repair_bio; struct btrfs_io_bio *repair_io_bio; - blk_status_t status; btrfs_debug(fs_info, "repair read error: read error at %llu", start); @@ -2664,13 +2663,13 @@ int btrfs_repair_one_sector(struct inode *inode, "repair read error: submitting new read to mirror %d", failrec->this_mirror); - status = submit_bio_hook(inode, repair_bio, failrec->this_mirror, - failrec->bio_flags); - if (status) { - free_io_failure(failure_tree, tree, failrec); - bio_put(repair_bio); - } - return blk_status_to_errno(status); + /* + * At this point we have a bio, so any errors from submit_bio_hook() + * will be handled by the endio on the repair_bio, so we can't return an + * error here. + */ + submit_bio_hook(inode, repair_bio, failrec->this_mirror, failrec->bio_flags); + return BLK_STS_OK; } static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) -- 2.34.1

4 months, 1 week

2
1
0 0

[PATCH 5.4.y] of: module: add buffer overflow check in of_modalias()

by Uwe Kleine-König

From: Sergey Shtylyov <s.shtylyov(a)omp.ru> commit cf7385cb26ac4f0ee6c7385960525ad534323252 upstream. In of_modalias(), if the buffer happens to be too small even for the 1st snprintf() call, the len parameter will become negative and str parameter (if not NULL initially) will point beyond the buffer's end. Add the buffer overflow check after the 1st snprintf() call and fix such check after the strlen() call (accounting for the terminating NUL char). Fixes: bc575064d688 ("of/device: use of_property_for_each_string to parse compatible strings") Signed-off-by: Sergey Shtylyov <s.shtylyov(a)omp.ru> Link: https://lore.kernel.org/r/bbfc6be0-c687-62b6-d015-5141b93f313e@omp.ru Signed-off-by: Rob Herring <robh(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Uwe Kleine-König <ukleinek(a)debian.org> --- drivers/of/device.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 7fb870097a84..ee3467730dac 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -213,14 +213,15 @@ static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len csize = snprintf(str, len, "of:N%pOFn%c%s", dev->of_node, 'T', of_node_get_device_type(dev->of_node)); tsize = csize; + if (csize >= len) + csize = len > 0 ? len - 1 : 0; len -= csize; - if (str) - str += csize; + str += csize; of_property_for_each_string(dev->of_node, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; - if (csize > len) + if (csize >= len) continue; csize = snprintf(str, len, "C%s", compat); base-commit: 2c8115e4757809ffd537ed9108da115026d3581f -- 2.47.2

4 months, 1 week

2
1
0 0

+ mm-userfaultfd-correct-dirty-flags-set-for-both-present-and-swap-pte.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: userfaultfd: correct dirty flags set for both present and swap pte has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-userfaultfd-correct-dirty-flags-set-for-both-present-and-swap-pte.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Barry Song <v-songbaohua(a)oppo.com> Subject: mm: userfaultfd: correct dirty flags set for both present and swap pte Date: Fri, 9 May 2025 10:09:12 +1200 As David pointed out, what truly matters for mremap and userfaultfd move operations is the soft dirty bit. The current comment and implementation��which always sets the dirty bit for present PTEs and fails to set the soft dirty bit for swap PTEs��are incorrect. This could break features like Checkpoint-Restore in Userspace (CRIU). This patch updates the behavior to correctly set the soft dirty bit for both present and swap PTEs in accordance with mremap. Link: https://lkml.kernel.org/r/20250508220912.7275-1-21cnbao@gmail.com Fixes: adef440691bab ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Barry Song <v-songbaohua(a)oppo.com> Reported-by: David Hildenbrand <david(a)redhat.com> Closes: https://lore.kernel.org/linux-mm/02f14ee1-923f-47e3-a994-4950afb9afcc@redha… Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Suren Baghdasaryan <surenb(a)google.com> Cc: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/userfaultfd.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) --- a/mm/userfaultfd.c~mm-userfaultfd-correct-dirty-flags-set-for-both-present-and-swap-pte +++ a/mm/userfaultfd.c @@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_st src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); - /* Follow mremap() behavior and treat the entry dirty after the move */ - orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); + /* Set soft dirty bit so userspace can notice the pte was moved */ +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); +#endif + if (pte_dirty(orig_src_pte)) + orig_dst_pte = pte_mkdirty(orig_dst_pte); + orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma); set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); out: @@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struc } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); +#endif set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); _ Patches currently in -mm which might be from v-songbaohua(a)oppo.com are mm-userfaultfd-correct-dirty-flags-set-for-both-present-and-swap-pte.patch

4 months, 1 week

1
0
0 0

[PATCH v3] block, scsi: sd_zbc: Respect bio vector limits for report zones buffer

by Steve Siwinski

The report zones buffer size is currently limited by the HBA's maximum segment count to ensure the buffer can be mapped. However, the block layer further limits the number of iovec entries to 1024 when allocating a bio. To avoid allocation of buffers too large to be mapped, further restrict the maximum buffer size to BIO_MAX_INLINE_VECS. Replace the UIO_MAXIOV symbolic name with the more contextually appropriate BIO_MAX_INLINE_VECS. Fixes: b091ac616846 ("sd_zbc: Fix report zones buffer allocation") Cc: stable(a)vger.kernel.org Signed-off-by: Steve Siwinski <ssiwinski(a)atto.com> --- block/bio.c | 2 +- drivers/scsi/sd_zbc.c | 6 +++++- include/linux/bio.h | 1 + 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/block/bio.c b/block/bio.c index 4e6c85a33d74..4be592d37fb6 100644 --- a/block/bio.c +++ b/block/bio.c @@ -611,7 +611,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_vecs > UIO_MAXIOV) + if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 7a447ff600d2..a8db66428f80 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, unsigned int nr_zones, size_t *buflen) { struct request_queue *q = sdkp->disk->queue; + unsigned int max_segments; size_t bufsize; void *buf; @@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * Furthermore, since the report zone command cannot be split, make * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. + * Since max segments can be larger than the max inline bio vectors, + * further limit the allocated buffer to BIO_MAX_INLINE_VECS. */ nr_zones = min(nr_zones, sdkp->zone_info.nr_zones); bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); - bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); + max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q)); + bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT); while (bufsize >= SECTOR_SIZE) { buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); diff --git a/include/linux/bio.h b/include/linux/bio.h index cafc7c215de8..b786ec5bcc81 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -11,6 +11,7 @@ #include <linux/uio.h> #define BIO_MAX_VECS 256U +#define BIO_MAX_INLINE_VECS UIO_MAXIOV struct queue_limits; -- 2.43.5

4 months, 1 week

2
1
0 0

[PATCH v2] mm: userfaultfd: correct dirty flags set for both present and swap pte

by Barry Song

From: Barry Song <v-songbaohua(a)oppo.com> As David pointed out, what truly matters for mremap and userfaultfd move operations is the soft dirty bit. The current comment and implementation—which always sets the dirty bit for present PTEs and fails to set the soft dirty bit for swap PTEs—are incorrect. This could break features like Checkpoint-Restore in Userspace (CRIU). This patch updates the behavior to correctly set the soft dirty bit for both present and swap PTEs in accordance with mremap. Reported-by: David Hildenbrand <david(a)redhat.com> Closes: https://lore.kernel.org/linux-mm/02f14ee1-923f-47e3-a994-4950afb9afcc@redha… Acked-by: Peter Xu <peterx(a)redhat.com> Reviewed-by: Suren Baghdasaryan <surenb(a)google.com> Cc: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Fixes: adef440691bab ("userfaultfd: UFFDIO_MOVE uABI") Cc: stable(a)vger.kernel.org Signed-off-by: Barry Song <v-songbaohua(a)oppo.com> --- mm/userfaultfd.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e8ce92dc105f..bc473ad21202 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm, src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = folio_mk_pte(src_folio, dst_vma->vm_page_prot); - /* Follow mremap() behavior and treat the entry dirty after the move */ - orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); + /* Set soft dirty bit so userspace can notice the pte was moved */ +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); +#endif + if (pte_dirty(orig_src_pte)) + orig_dst_pte = pte_mkdirty(orig_dst_pte); + orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma); set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); out: @@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); +#endif set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); -- 2.39.3 (Apple Git-146)

4 months, 1 week

1
0
0 0

[PATCH v2] wifi: mt76: mt7925: fix missing hdr_trans_tlv command for broadcast wtbl

by Mingyen Hsieh

From: Ming Yen Hsieh <mingyen.hsieh(a)mediatek.com> The hdr_trans_tlv function call has been moved inside the conditional block to ensure it is executed when info->enable is true. Cc: stable(a)vger.kernel.org Fixes: cb1353ef3473 ("wifi: mt76: mt7925: integrate *mlo_sta_cmd and *sta_cmd") Signed-off-by: Ming Yen Hsieh <mingyen.hsieh(a)mediatek.com> Tested-by: Niklas Schnelle <niks(a)kernel.org> --- v2: add tested-by tag --- drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index a42b584634ab..fd756f0d18f8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -2183,14 +2183,14 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, mt7925_mcu_sta_mld_tlv(skb, info->vif, info->link_sta->sta); mt7925_mcu_sta_eht_mld_tlv(skb, info->vif, info->link_sta->sta); } - - mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta); } if (!info->enable) { mt7925_mcu_sta_remove_tlv(skb); mt76_connac_mcu_add_tlv(skb, STA_REC_MLD_OFF, sizeof(struct tlv)); + } else { + mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta); } return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); -- 2.34.1

4 months, 1 week

2
1
0 0

[PATCH] clk: s2mps11: initialise clk_hw_onecell_data::num before accessing ::hws[] in probe()

by André Draszik

With UBSAN enabled, we're getting the following trace: UBSAN: array-index-out-of-bounds in .../drivers/clk/clk-s2mps11.c:186:3 index 0 is out of range for type 'struct clk_hw *[] __counted_by(num)' (aka 'struct clk_hw *[]') This is because commit f316cdff8d67 ("clk: Annotate struct clk_hw_onecell_data with __counted_by") annotated the hws member of that struct with __counted_by, which informs the bounds sanitizer about the number of elements in hws, so that it can warn when hws is accessed out of bounds. As noted in that change, the __counted_by member must be initialised with the number of elements before the first array access happens, otherwise there will be a warning from each access prior to the initialisation because the number of elements is zero. This occurs in s2mps11_clk_probe() due to ::num being assigned after ::hws access. Move the assignment to satisfy the requirement of assign-before-access. Cc: stable(a)vger.kernel.org Fixes: f316cdff8d67 ("clk: Annotate struct clk_hw_onecell_data with __counted_by") Signed-off-by: André Draszik <andre.draszik(a)linaro.org> --- drivers/clk/clk-s2mps11.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index 014db6386624071e173b5b940466301d2596400a..8ddf3a9a53dfd5bb52a05a3e02788a357ea77ad3 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -137,6 +137,8 @@ static int s2mps11_clk_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; + clk_data->num = S2MPS11_CLKS_NUM; + switch (hwid) { case S2MPS11X: s2mps11_reg = S2MPS11_REG_RTC_CTRL; @@ -186,7 +188,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev) clk_data->hws[i] = &s2mps11_clks[i].hw; } - clk_data->num = S2MPS11_CLKS_NUM; of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get, clk_data); --- base-commit: 9388ec571cb1adba59d1cded2300eeb11827679c change-id: 20250326-s2mps11-ubsan-c90978e7bc04 Best regards, -- André Draszik <andre.draszik(a)linaro.org>

4 months, 1 week

3
2
0 0

perf r5101c4 counter regression

by Salvatore Bonaccorso

Hi, Pasi Kallinen reported in Debian a regression with perf r5101c4 counter, initially it was found in https://github.com/rr-debugger/rr/issues/3949 but said to be a kernel problem. On Tue, May 06, 2025 at 07:18:39PM +0300, Pasi Kallinen wrote: > Package: src:linux > Version: 6.12.25-1 > Severity: normal > X-Debbugs-Cc: debian-amd64(a)lists.debian.org, paxed(a)alt.org > User: debian-amd64(a)lists.debian.org > Usertags: amd64 > > Dear Maintainer, > > perf stat -e r5101c4 true > > reports "not supported". > > The counters worked in kernel 6.11.10. > > I first noticed this not working when updating to 6.12.22. > Booting back to 6.11.10, the counters work correctly. Does this ring a bell? Would you be able to bisect the changes to identify where the behaviour changed? Regards, Salvatore

4 months, 1 week

2
1
0 0

[PATCH] xenbus: Use kref to track req lifetime

by Jason Andryuk

Marek reported seeing a NULL pointer fault in the xenbus_thread callstack: BUG: kernel NULL pointer dereference, address: 0000000000000000 RIP: e030:__wake_up_common+0x4c/0x180 Call Trace: <TASK> __wake_up_common_lock+0x82/0xd0 process_msg+0x18e/0x2f0 xenbus_thread+0x165/0x1c0 process_msg+0x18e is req->cb(req). req->cb is set to xs_wake_up(), a thin wrapper around wake_up(), or xenbus_dev_queue_reply(). It seems like it was xs_wake_up() in this case. It seems like req may have woken up the xs_wait_for_reply(), which kfree()ed the req. When xenbus_thread resumes, it faults on the zero-ed data. Linux Device Drivers 2nd edition states: "Normally, a wake_up call can cause an immediate reschedule to happen, meaning that other processes might run before wake_up returns." ... which would match the behaviour observed. Change to keeping two krefs on each request. One for the caller, and one for xenbus_thread. Each will kref_put() when finished, and the last will free it. This use of kref matches the description in Documentation/core-api/kref.rst Link: https://lore.kernel.org/xen-devel/ZO0WrR5J0xuwDIxW@mail-itl/ Reported-by: "Marek Marczykowski-Górecki" <marmarek(a)invisiblethingslab.com> Fixes: fd8aa9095a95 ("xen: optimize xenbus driver for multiple concurrent xenstore accesses") Cc: stable(a)vger.kernel.org Signed-off-by: Jason Andryuk <jason.andryuk(a)amd.com> --- Kinda RFC-ish as I don't know if it fixes Marek's issue. This does seem like the correct approach if we are seeing req free()ed out from under xenbus_thread. drivers/xen/xenbus/xenbus.h | 2 ++ drivers/xen/xenbus/xenbus_comms.c | 9 ++++----- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 +- drivers/xen/xenbus/xenbus_xs.c | 18 ++++++++++++++++-- 4 files changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 13821e7e825e..9ac0427724a3 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -77,6 +77,7 @@ enum xb_req_state { struct xb_req_data { struct list_head list; wait_queue_head_t wq; + struct kref kref; struct xsd_sockmsg msg; uint32_t caller_req_id; enum xsd_sockmsg_type type; @@ -103,6 +104,7 @@ int xb_init_comms(void); void xb_deinit_comms(void); int xs_watch_msg(struct xs_watch_event *event); void xs_request_exit(struct xb_req_data *req); +void xs_free_req(struct kref *kref); int xenbus_match(struct device *_dev, const struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index e5fda0256feb..82df2da1b880 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,8 +309,8 @@ static int process_msg(void) virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); - } else - kfree(req); + } + kref_put(&req->kref, xs_free_req); } mutex_unlock(&xs_response_mutex); @@ -386,14 +386,13 @@ static int process_writes(void) state.req->msg.type = XS_ERROR; state.req->err = err; list_del(&state.req->list); - if (state.req->state == xb_req_state_aborted) - kfree(state.req); - else { + if (state.req->state != xb_req_state_aborted) { /* write err, then update state */ virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } + kref_put(&state.req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 46f8916597e5..f5c21ba64df5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) mutex_unlock(&u->reply_mutex); kfree(req->body); - kfree(req); + kref_put(&req->kref, xs_free_req); kref_put(&u->kref, xenbus_file_free); diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index d32c726f7a12..dcf9182c8451 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -112,6 +112,12 @@ static void xs_suspend_exit(void) wake_up_all(&xs_state_enter_wq); } +void xs_free_req(struct kref *kref) +{ + struct xb_req_data *req = container_of(kref, struct xb_req_data, kref); + kfree(req); +} + static uint32_t xs_request_enter(struct xb_req_data *req) { uint32_t rq_id; @@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); + /* + * Take 2nd ref. One for this thread, and the second for the + * xenbus_thread. + */ + kref_get(&req->kref); + mutex_lock(&xb_write_mutex); list_add_tail(&req->list, &xb_write_list); notify = list_is_singular(&xb_write_list); @@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg) if (req->state == xb_req_state_queued || req->state == xb_req_state_wait_reply) req->state = xb_req_state_aborted; - else - kfree(req); + + kref_put(&req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); return ret; @@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->cb = xenbus_dev_queue_reply; req->par = par; req->user_req = true; + kref_init(&req->kref); xs_send(req, msg); @@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; req->user_req = false; + kref_init(&req->kref); msg.req_id = 0; msg.tx_id = t.id; -- 2.34.1

4 months, 1 week

3
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror