April 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] mm/mempolicy: fix use-after-free of VMA iterator" failed to apply to 6.2-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.2-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.2.y git checkout FETCH_HEAD git cherry-pick -x f4e9e0e69468583c2c6d9d5c7bfc975e292bf188 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023042437-profane-confidant-7987@gregkh' --subject-prefix 'PATCH 6.2.y' HEAD^.. Possible dependencies: f4e9e0e69468 ("mm/mempolicy: fix use-after-free of VMA iterator") 9760ebffbf55 ("mm: switch vma_merge(), split_vma(), and __split_vma to vma iterator") 47d9644de92c ("nommu: convert nommu to using the vma iterator") a27a11f92fe2 ("mm/mremap: use vmi version of vma_merge()") 076f16bf7698 ("mmap: use vmi version of vma_merge()") 0c0c5bffd0a2 ("mmap: pass through vmi iterator to __split_vma()") 178e22ac2078 ("madvise: use vmi iterator for __split_vma() and vma_merge()") f10c2abcdac4 ("mempolicy: convert to vma iterator") 37598f5a9d8b ("mlock: convert mlock to vma iterator") 2286a6914c77 ("mm: change mprotect_fixup to vma iterator") 11a9b90274f6 ("userfaultfd: use vma iterator") f2ebfe43ba6c ("mm: add temporary vma iterator versions of vma_merge(), split_vma(), and __split_vma()") 183654ce26a5 ("mmap: change do_mas_munmap and do_mas_aligned_munmap() to use vma iterator") 0378c0a0e9e4 ("mm/mmap: remove preallocation from do_mas_align_munmap()") 92fed82047d7 ("mm/mmap: convert brk to use vma iterator") baabcfc93d3b ("mm/mmap: fix typo in comment") c5d5546ea065 ("maple_tree: remove the parameter entry of mas_preallocate") 5ab0fc155dc0 ("Sync mm-stable with mm-hotfixes-stable to pick up dependent patches") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f4e9e0e69468583c2c6d9d5c7bfc975e292bf188 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" <Liam.Howlett(a)oracle.com> Date: Mon, 10 Apr 2023 11:22:05 -0400 Subject: [PATCH] mm/mempolicy: fix use-after-free of VMA iterator set_mempolicy_home_node() iterates over a list of VMAs and calls mbind_range() on each VMA, which also iterates over the singular list of the VMA passed in and potentially splits the VMA. Since the VMA iterator is not passed through, set_mempolicy_home_node() may now point to a stale node in the VMA tree. This can result in a UAF as reported by syzbot. Avoid the stale maple tree node by passing the VMA iterator through to the underlying call to split_vma(). mbind_range() is also overly complicated, since there are two calling functions and one already handles iterating over the VMAs. Simplify mbind_range() to only handle merging and splitting of the VMAs. Align the new loop in do_mbind() and existing loop in set_mempolicy_home_node() to use the reduced mbind_range() function. This allows for a single location of the range calculation and avoids constantly looking up the previous VMA (since this is a loop over the VMAs). Link: https://lore.kernel.org/linux-mm/000000000000c93feb05f87e24ad@google.com/ Fixes: 66850be55e8e ("mm/mempolicy: use vma iterator & maple state instead of vma linked list") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Reported-by: syzbot+a7c1ec5b1d71ceaa5186(a)syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/20230410152205.2294819-1-Liam.Howlett@oracle.com Tested-by: syzbot+a7c1ec5b1d71ceaa5186(a)syzkaller.appspotmail.com Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a256a241fd1d..2068b594dc88 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -790,61 +790,50 @@ static int vma_replace_policy(struct vm_area_struct *vma, return err; } -/* Step 2: apply policy to a range and do splits. */ -static int mbind_range(struct mm_struct *mm, unsigned long start, - unsigned long end, struct mempolicy *new_pol) +/* Split or merge the VMA (if required) and apply the new policy */ +static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, + unsigned long end, struct mempolicy *new_pol) { - VMA_ITERATOR(vmi, mm, start); - struct vm_area_struct *prev; - struct vm_area_struct *vma; - int err = 0; + struct vm_area_struct *merged; + unsigned long vmstart, vmend; pgoff_t pgoff; + int err; - prev = vma_prev(&vmi); - vma = vma_find(&vmi, end); - if (WARN_ON(!vma)) + vmend = min(end, vma->vm_end); + if (start > vma->vm_start) { + *prev = vma; + vmstart = start; + } else { + vmstart = vma->vm_start; + } + + if (mpol_equal(vma_policy(vma), new_pol)) return 0; - if (start > vma->vm_start) - prev = vma; - - do { - unsigned long vmstart = max(start, vma->vm_start); - unsigned long vmend = min(end, vma->vm_end); - - if (mpol_equal(vma_policy(vma), new_pol)) - goto next; - - pgoff = vma->vm_pgoff + - ((vmstart - vma->vm_start) >> PAGE_SHIFT); - prev = vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx, - anon_vma_name(vma)); - if (prev) { - vma = prev; - goto replace; - } - if (vma->vm_start != vmstart) { - err = split_vma(&vmi, vma, vmstart, 1); - if (err) - goto out; - } - if (vma->vm_end != vmend) { - err = split_vma(&vmi, vma, vmend, 0); - if (err) - goto out; - } -replace: - err = vma_replace_policy(vma, new_pol); + pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); + merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, new_pol, + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + if (merged) { + *prev = merged; + return vma_replace_policy(merged, new_pol); + } + + if (vma->vm_start != vmstart) { + err = split_vma(vmi, vma, vmstart, 1); if (err) - goto out; -next: - prev = vma; - } for_each_vma_range(vmi, vma, end); + return err; + } -out: - return err; + if (vma->vm_end != vmend) { + err = split_vma(vmi, vma, vmend, 0); + if (err) + return err; + } + + *prev = vma; + return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ @@ -1259,6 +1248,8 @@ static long do_mbind(unsigned long start, unsigned long len, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev; + struct vma_iterator vmi; struct mempolicy *new; unsigned long end; int err; @@ -1328,7 +1319,13 @@ static long do_mbind(unsigned long start, unsigned long len, goto up_out; } - err = mbind_range(mm, start, end, new); + vma_iter_init(&vmi, mm, start); + prev = vma_prev(&vmi); + for_each_vma_range(vmi, vma, end) { + err = mbind_range(&vmi, vma, &prev, start, end, new); + if (err) + break; + } if (!err) { int nr_failed = 0; @@ -1489,10 +1486,8 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; - unsigned long vmstart; - unsigned long vmend; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); @@ -1521,6 +1516,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le if (end == start) return 0; mmap_write_lock(mm); + prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND @@ -1541,9 +1537,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le } new->home_node = home_node; - vmstart = max(start, vma->vm_start); - vmend = min(end, vma->vm_end); - err = mbind_range(mm, vmstart, vmend, new); + err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break;

2 years, 2 months

1
0
0 0

[PATCH 5.4 00/92] 5.4.241-rc1 review

by Greg Kroah-Hartman

This is the start of the stable review cycle for the 5.4.241 release. There are 92 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Thu, 20 Apr 2023 12:02:44 +0000. Anything received after that time might be too late. The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.4.241-rc… or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.4.y and the diffstat can be found below. thanks, greg k-h ------------- Pseudo-Shortlog of commits: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Linux 5.4.241-rc1 Darrick J. Wong <djwong(a)kernel.org> xfs: force log and push AIL to clear pinned inodes when aborting mount Brian Foster <bfoster(a)redhat.com> xfs: don't reuse busy extents on extent trim Brian Foster <bfoster(a)redhat.com> xfs: consider shutdown in bmapbt cursor delete assert Darrick J. Wong <djwong(a)kernel.org> xfs: shut down the filesystem if we screw up quota reservation Darrick J. Wong <darrick.wong(a)oracle.com> xfs: report corruption only as a regular error Jeffrey Mitchell <jeffrey.mitchell(a)starlab.io> xfs: set inode size after creating symlink Christoph Hellwig <hch(a)lst.de> xfs: fix up non-directory creation in SGID directories Christoph Hellwig <hch(a)lst.de> xfs: remove the di_version field from struct icdinode Christoph Hellwig <hch(a)lst.de> xfs: simplify a check in xfs_ioctl_setattr_check_cowextsize Christoph Hellwig <hch(a)lst.de> xfs: simplify di_flags2 inheritance in xfs_ialloc Christoph Hellwig <hch(a)lst.de> xfs: only check the superblock version for dinode size calculation Christoph Hellwig <hch(a)lst.de> xfs: add a new xfs_sb_version_has_v3inode helper Christoph Hellwig <hch(a)lst.de> xfs: remove the kuid/kgid conversion wrappers Christoph Hellwig <hch(a)lst.de> xfs: remove the icdinode di_uid/di_gid members Christoph Hellwig <hch(a)lst.de> xfs: ensure that the inode uid/gid match values match the icdinode ones Christoph Hellwig <hch(a)lst.de> xfs: merge the projid fields in struct xfs_icdinode Kaixu Xia <kaixuxia(a)tencent.com> xfs: show the proper user quota options Steve Clevenger <scclevenger(a)os.amperecomputing.com> coresight-etm4: Fix for() loop drvdata->nr_addr_cmp range bug George Cherian <george.cherian(a)marvell.com> watchdog: sbsa_wdog: Make sure the timeout programming is within the limits Gregor Herburger <gregor.herburger(a)tq-group.com> i2c: ocores: generate stop condition after timeout in polling mode ZhaoLong Wang <wangzhaolong1(a)huawei.com> ubi: Fix deadlock caused by recursively holding work_sem Lee Jones <lee.jones(a)linaro.org> mtd: ubi: wl: Fix a couple of kernel-doc issues Zhihao Cheng <chengzhihao1(a)huawei.com> ubi: Fix failure attaching when vid_hdr offset equals to (sub)page size Robbie Harwood <rharwood(a)redhat.com> asymmetric_keys: log on fatal failures in PE/pkcs7 Robbie Harwood <rharwood(a)redhat.com> verify_pefile: relax wrapper length check Hans de Goede <hdegoede(a)redhat.com> drm: panel-orientation-quirks: Add quirk for Lenovo Yoga Book X90F Hans de Goede <hdegoede(a)redhat.com> efi: sysfb_efi: Add quirk for Lenovo Yoga Book X91F/L Alexander Stein <alexander.stein(a)ew.tq-group.com> i2c: imx-lpi2c: clean rx/tx buffers upon new message Grant Grundler <grundler(a)chromium.org> power: supply: cros_usbpd: reclassify "default case!" as debug Roman Gushchin <roman.gushchin(a)linux.dev> net: macb: fix a memory corruption in extended buffer descriptor mode Eric Dumazet <edumazet(a)google.com> udp6: fix potential access to stale information Saravanan Vajravel <saravanan.vajravel(a)broadcom.com> RDMA/core: Fix GID entry ref leak when create_ah fails Xin Long <lucien.xin(a)gmail.com> sctp: fix a potential overflow in sctp_ifwdtsn_skip Denis Plotnikov <den-plotnikov(a)yandex-team.ru> qlcnic: check pci_reset_function result Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com> niu: Fix missing unwind goto in niu_alloc_channels() Zheng Wang <zyytlz.wz(a)163.com> 9p/xen : Fix use after free bug in xen_9pfs_front_remove due to race condition Christophe Kerello <christophe.kerello(a)foss.st.com> mtd: rawnand: stm32_fmc2: remove unsupported EDO mode Arseniy Krasnov <avkrasnov(a)sberdevices.ru> mtd: rawnand: meson: fix bitmask for length in command word Bang Li <libang.linuxer(a)gmail.com> mtdblock: tolerate corrected bit-flips Christoph Hellwig <hch(a)lst.de> btrfs: fix fast csum implementation detection David Sterba <dsterba(a)suse.com> btrfs: print checksum type and implementation at mount time Min Li <lm0963hack(a)gmail.com> Bluetooth: Fix race condition in hidp_session_thread Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Bluetooth: L2CAP: Fix use-after-free in l2cap_disconnect_{req,rsp} Oswald Buddenhagen <oswald.buddenhagen(a)gmx.de> ALSA: hda/sigmatel: fix S/PDIF out on Intel D*45* motherboards Xu Biang <xubiang(a)hust.edu.cn> ALSA: firewire-tascam: add missing unwind goto in snd_tscm_stream_start_duplex() Oswald Buddenhagen <oswald.buddenhagen(a)gmx.de> ALSA: i2c/cs8427: fix iec958 mixer control deactivation Oswald Buddenhagen <oswald.buddenhagen(a)gmx.de> ALSA: hda/sigmatel: add pin overrides for Intel DP45SG motherboard Oswald Buddenhagen <oswald.buddenhagen(a)gmx.de> ALSA: emu10k1: fix capture interrupt handler unlinking Kornel Dulęba <korneld(a)chromium.org> Revert "pinctrl: amd: Disable and mask interrupts on resume" Johan Hovold <johan+linaro(a)kernel.org> irqdomain: Fix mapping-creation race Johan Hovold <johan+linaro(a)kernel.org> irqdomain: Refactor __irq_domain_alloc_irqs() Johan Hovold <johan+linaro(a)kernel.org> irqdomain: Look for existing mapping only once Rongwei Wang <rongwei.wang(a)linux.alibaba.com> mm/swap: fix swap_info_struct race between swapoff and get_swap_pages() Zheng Yejian <zhengyejian1(a)huawei.com> ring-buffer: Fix race while reader and writer are on the same page Boris Brezillon <boris.brezillon(a)collabora.com> drm/panfrost: Fix the panfrost_mmu_map_fault_addr() error path Pratyush Yadav <ptyadav(a)amazon.de> net_sched: prevent NULL dereference if default qdisc setup failed Steven Rostedt (Google) <rostedt(a)goodmis.org> tracing: Free error logs of tracing instances Oleksij Rempel <linux(a)rempel-privat.de> can: j1939: j1939_tp_tx_dat_new(): fix out-of-bounds memory access John Keeping <john(a)metanate.com> ftrace: Mark get_lock_parent_ip() __always_inline Kan Liang <kan.liang(a)linux.intel.com> perf/core: Fix the same task check in perf_event_set_output Jeremy Soller <jeremy(a)system76.com> ALSA: hda/realtek: Add quirk for Clevo X370SNW Ryusuke Konishi <konishi.ryusuke(a)gmail.com> nilfs2: fix sysfs interface lifetime Ryusuke Konishi <konishi.ryusuke(a)gmail.com> nilfs2: fix potential UAF of struct nilfs_sc_info in nilfs_segctor_thread() Sherry Sun <sherry.sun(a)nxp.com> tty: serial: fsl_lpuart: avoid checking for transfer complete when UARTCTRL_SBK is asserted in lpuart32_tx_empty Biju Das <biju.das.jz(a)bp.renesas.com> tty: serial: sh-sci: Fix Rx on RZ/G2L SCI Biju Das <biju.das.jz(a)bp.renesas.com> tty: serial: sh-sci: Fix transmit end interrupt handler William Breathitt Gray <william.gray(a)linaro.org> iio: dac: cio-dac: Fix max DAC write value check for 12-bit Lars-Peter Clausen <lars(a)metafoo.de> iio: adc: ti-ads7950: Set `can_sleep` flag for GPIO chip Bjørn Mork <bjorn(a)mork.no> USB: serial: option: add Quectel RM500U-CN modem Enrico Sau <enrico.sau(a)gmail.com> USB: serial: option: add Telit FE990 compositions RD Babiera <rdbabiera(a)google.com> usb: typec: altmodes/displayport: Fix configure initial pin assignment Kees Jan Koster <kjkoster(a)kjkoster.org> USB: serial: cp210x: add Silicon Labs IFS-USB-DATACABLE IDs D Scott Phillips <scott(a)os.amperecomputing.com> xhci: also avoid the XHCI_ZERO_64B_REGS quirk with a passthrough iommu Dai Ngo <dai.ngo(a)oracle.com> NFSD: callback request does not use correct credential for AUTH_SYS Jeff Layton <jlayton(a)kernel.org> sunrpc: only free unix grouplist after RCU settles Dhruva Gole <d-gole(a)ti.com> gpio: davinci: Add irq chip flag to skip set wake Ziyang Xuan <william.xuanziyang(a)huawei.com> ipv6: Fix an uninit variable access bug in __ip6_make_skb() Xin Long <lucien.xin(a)gmail.com> sctp: check send stream number after wait_for_sndbuf Jakub Kicinski <kuba(a)kernel.org> net: don't let netpoll invoke NAPI if in xmit context Eric Dumazet <edumazet(a)google.com> icmp: guard against too small mtu Felix Fietkau <nbd(a)nbd.name> wifi: mac80211: fix invalid drv_sta_pre_rcu_remove calls for non-uploaded sta Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> pwm: sprd: Explicitly set .polarity in .get_state() Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> pwm: cros-ec: Explicitly set .polarity in .get_state() Kornel Dulęba <korneld(a)chromium.org> pinctrl: amd: Disable and mask interrupts on resume Sachi King <nakato(a)nakato.io> pinctrl: amd: disable and mask interrupts on probe Linus Walleij <linus.walleij(a)linaro.org> pinctrl: amd: Use irqchip template Steve French <stfrench(a)microsoft.com> smb3: fix problem with null cifs super block with previous patch Kees Cook <keescook(a)chromium.org> treewide: Replace DECLARE_TASKLET() with DECLARE_TASKLET_OLD() Tom Saeger <tom.saeger(a)oracle.com> Revert "treewide: Replace DECLARE_TASKLET() with DECLARE_TASKLET_OLD()" Waiman Long <longman(a)redhat.com> cgroup/cpuset: Wake up cpuset_attach_wq tasks in cpuset_cancel_attach() Basavaraj Natikar <Basavaraj.Natikar(a)amd.com> x86/PCI: Add quirk for AMD XHCI controller that loses MSI-X state in D3hot Jiri Kosina <jkosina(a)suse.cz> scsi: ses: Handle enclosure with just a primary component gracefully ------------- Diffstat: Documentation/sound/hd-audio/models.rst | 2 +- Makefile | 4 +- arch/mips/lasat/picvue_proc.c | 2 +- arch/x86/kernel/sysfb_efi.c | 8 ++ arch/x86/pci/fixup.c | 21 +++ crypto/asymmetric_keys/pkcs7_verify.c | 10 +- crypto/asymmetric_keys/verify_pefile.c | 32 +++-- drivers/gpio/gpio-davinci.c | 2 +- drivers/gpu/drm/drm_panel_orientation_quirks.c | 13 +- drivers/gpu/drm/panfrost/panfrost_mmu.c | 1 + drivers/hwtracing/coresight/coresight-etm4x.c | 2 +- drivers/i2c/busses/i2c-imx-lpi2c.c | 2 + drivers/i2c/busses/i2c-ocores.c | 35 ++--- drivers/iio/adc/ti-ads7950.c | 1 + drivers/iio/dac/cio-dac.c | 4 +- drivers/infiniband/core/verbs.c | 2 + drivers/mtd/mtdblock.c | 12 +- drivers/mtd/nand/raw/meson_nand.c | 6 +- drivers/mtd/nand/raw/stm32_fmc2_nand.c | 3 + drivers/mtd/ubi/build.c | 21 ++- drivers/mtd/ubi/wl.c | 5 +- drivers/net/ethernet/cadence/macb_main.c | 4 + drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c | 8 +- drivers/net/ethernet/sun/niu.c | 2 +- drivers/pinctrl/pinctrl-amd.c | 52 +++++-- drivers/power/supply/cros_usbpd-charger.c | 2 +- drivers/pwm/pwm-cros-ec.c | 1 + drivers/pwm/pwm-sprd.c | 1 + drivers/scsi/ses.c | 20 ++- drivers/tty/serial/fsl_lpuart.c | 8 +- drivers/tty/serial/sh-sci.c | 9 +- drivers/usb/host/xhci.c | 6 +- drivers/usb/serial/cp210x.c | 1 + drivers/usb/serial/option.c | 10 ++ drivers/usb/typec/altmodes/displayport.c | 6 +- drivers/watchdog/sbsa_gwdt.c | 1 + fs/btrfs/disk-io.c | 17 +++ fs/btrfs/super.c | 2 - fs/cifs/cifsproto.h | 2 +- fs/cifs/smb2ops.c | 2 +- fs/nfsd/nfs4callback.c | 4 +- fs/nilfs2/segment.c | 3 +- fs/nilfs2/super.c | 2 + fs/nilfs2/the_nilfs.c | 12 +- fs/xfs/libxfs/xfs_attr_leaf.c | 5 +- fs/xfs/libxfs/xfs_bmap.c | 10 +- fs/xfs/libxfs/xfs_btree.c | 30 ++-- fs/xfs/libxfs/xfs_format.h | 33 +++-- fs/xfs/libxfs/xfs_ialloc.c | 6 +- fs/xfs/libxfs/xfs_inode_buf.c | 54 +++---- fs/xfs/libxfs/xfs_inode_buf.h | 8 +- fs/xfs/libxfs/xfs_inode_fork.c | 2 +- fs/xfs/libxfs/xfs_inode_fork.h | 9 +- fs/xfs/libxfs/xfs_log_format.h | 10 +- fs/xfs/libxfs/xfs_trans_resv.c | 2 +- fs/xfs/xfs_acl.c | 12 +- fs/xfs/xfs_bmap_util.c | 16 +-- fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_dquot.c | 6 +- fs/xfs/xfs_error.c | 2 +- fs/xfs/xfs_extent_busy.c | 14 -- fs/xfs/xfs_icache.c | 8 +- fs/xfs/xfs_inode.c | 61 +++----- fs/xfs/xfs_inode.h | 21 +-- fs/xfs/xfs_inode_item.c | 20 ++- fs/xfs/xfs_ioctl.c | 22 ++- fs/xfs/xfs_iops.c | 11 +- fs/xfs/xfs_itable.c | 8 +- fs/xfs/xfs_linux.h | 32 +---- fs/xfs/xfs_log_recover.c | 6 +- fs/xfs/xfs_mount.c | 90 ++++++------ fs/xfs/xfs_qm.c | 43 +++--- fs/xfs/xfs_qm_bhv.c | 2 +- fs/xfs/xfs_quota.h | 4 +- fs/xfs/xfs_super.c | 10 +- fs/xfs/xfs_symlink.c | 7 +- fs/xfs/xfs_trans_dquot.c | 16 ++- include/linux/ftrace.h | 2 +- kernel/cgroup/cpuset.c | 6 +- kernel/events/core.c | 2 +- kernel/irq/irqdomain.c | 182 +++++++++++++++--------- kernel/trace/ring_buffer.c | 13 +- kernel/trace/trace.c | 1 + mm/swapfile.c | 3 +- net/9p/trans_xen.c | 4 + net/bluetooth/hidp/core.c | 2 +- net/bluetooth/l2cap_core.c | 24 +--- net/can/j1939/transport.c | 5 +- net/core/netpoll.c | 19 ++- net/ipv4/icmp.c | 5 + net/ipv6/ip6_output.c | 7 +- net/ipv6/udp.c | 8 +- net/mac80211/sta_info.c | 3 +- net/sched/sch_generic.c | 1 + net/sctp/socket.c | 4 + net/sctp/stream_interleave.c | 3 +- net/sunrpc/svcauth_unix.c | 17 ++- sound/firewire/tascam/tascam-stream.c | 2 +- sound/i2c/cs8427.c | 7 +- sound/pci/emu10k1/emupcm.c | 4 +- sound/pci/hda/patch_realtek.c | 1 + sound/pci/hda/patch_sigmatel.c | 10 ++ 102 files changed, 731 insertions(+), 549 deletions(-)

2 years, 2 months

11
102
0 0

[PATCH 1/2] cpufreq/schedutil: Add fast_switch callback check

by Wyes Karny

The set value of `fast_switch_enabled` flag doesn't guarantee that fast_switch callback is set. For some drivers such as amd_pstate, the adjust_perf callback is used but it still sets `fast_switch_possible` flag. This is not wrong because this flag doesn't imply fast_switch callback is set, it implies whether the driver can guarantee that frequency can be changed on any CPU sharing the policy and that the change will affect all of the policy CPUs without the need to send any IPIs or issue callbacks from the notifier chain. Therefore add an extra NULL check before calling fast_switch in sugov_update_single_freq function. Ideally `sugov_update_single_freq` function should not be called with amd_pstate. But in a corner case scenario, when aperf/mperf overflow occurs, kernel disables frequency invariance calculation which causes schedutil to fallback to sugov_update_single_freq which currently relies on the fast_switch callback. Normal flow: sugov_update_single_perf cpufreq_driver_adjust_perf cpufreq_driver->adjust_perf Error case flow: sugov_update_single_perf sugov_update_single_freq <-- This is chosen because the freq invariant is disabled due to aperf/mperf overflow cpufreq_driver_fast_switch cpufreq_driver->fast_switch <-- Here NULL pointer dereference is happening, because fast_switch is not set Fix this NULL pointer dereference issue by doing a NULL check. Fixes: a61dec744745 ("cpufreq: schedutil: Avoid missing updates for one-CPU policies") Signed-off-by: Wyes Karny <wyes.karny(a)amd.com> Cc: "Rafael J. Wysocki" <rafael(a)kernel.org> Cc: stable(a)vger.kernel.org --- drivers/cpufreq/cpufreq.c | 11 +++++++++++ include/linux/cpufreq.h | 1 + kernel/sched/cpufreq_schedutil.c | 2 +- 3 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6d8fd3b8dcb5..364d31b55380 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2138,6 +2138,17 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); +/** + * cpufreq_driver_has_fast_switch - Check "fast switch" callback. + * + * Return 'true' if the ->fast_switch callback is present for the + * current driver or 'false' otherwise. + */ +bool cpufreq_driver_has_fast_switch(void) +{ + return !!cpufreq_driver->fast_switch; +} + /** * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go. * @cpu: Target CPU. diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 65623233ab2f..8a9286fc718b 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -604,6 +604,7 @@ struct cpufreq_governor { /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); +bool cpufreq_driver_has_fast_switch(void); void cpufreq_driver_adjust_perf(unsigned int cpu, unsigned long min_perf, unsigned long target_perf, diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index e3211455b203..a1c449525ac2 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -364,7 +364,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, * concurrently on two different CPUs for the same target and it is not * necessary to acquire the lock in the fast switch case. */ - if (sg_policy->policy->fast_switch_enabled) { + if (sg_policy->policy->fast_switch_enabled && cpufreq_driver_has_fast_switch()) { cpufreq_driver_fast_switch(sg_policy->policy, next_f); } else { raw_spin_lock(&sg_policy->update_lock); -- 2.34.1

2 years, 2 months

2
3
0 0

[PATCH v5.10.x 1/2] pwm: iqs620a: Explicitly set .polarity in .get_state()

by Uwe Kleine-König

[ Upstream commit b20b097128d9145fadcea1cbb45c4d186cb57466 ] The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. Fixes: 6f0841a8197b ("pwm: Add support for Azoteq IQS620A PWM generator") Reviewed-by: Jeff LaBundy <jeff(a)labundy.com> Link: https://lore.kernel.org/r/20230228135508.1798428-4-u.kleine-koenig@pengutro… Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> Signed-off-by: Thierry Reding <thierry.reding(a)gmail.com> Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> --- drivers/pwm/pwm-iqs620a.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c index 3e967a12458c..a2aef006cb71 100644 --- a/drivers/pwm/pwm-iqs620a.c +++ b/drivers/pwm/pwm-iqs620a.c @@ -132,6 +132,7 @@ static void iqs620_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, mutex_unlock(&iqs620_pwm->lock); state->period = IQS620_PWM_PERIOD_NS; + state->polarity = PWM_POLARITY_NORMAL; } static int iqs620_pwm_notifier(struct notifier_block *notifier, -- 2.39.2

2 years, 2 months

1
1
0 0

FAILED: patch "[PATCH] pwm: meson: Explicitly set .polarity in .get_state()" 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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 8caa81eb950cb2e9d2d6959b37d853162d197f57 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023042242-unsaved-sanded-d4c1@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 8caa81eb950c ("pwm: meson: Explicitly set .polarity in .get_state()") 6c452cff79f8 ("pwm: Make .get_state() callback return an error code") 8eca6b0a647a ("Merge tag 'pwm/for-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8caa81eb950cb2e9d2d6959b37d853162d197f57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de> Date: Wed, 22 Mar 2023 22:45:44 +0100 Subject: [PATCH] pwm: meson: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. This fixes a regression that was possible since commit c73a3107624d ("pwm: Handle .get_state() failures") which stopped to zero-initialize the state passed to the .get_state() callback. This was reported at https://forum.odroid.com/viewtopic.php?f=177&t=46360 . While this was an unintended side effect, the real issue is the driver's callback not setting the polarity. There is a complicating fact, that the .apply() callback fakes support for inversed polarity. This is not (and cannot) be matched by .get_state(). As fixing this isn't easy, only point it out in a comment to prevent authors of other drivers from copying that approach. Fixes: c375bcbaabdb ("pwm: meson: Read the full hardware state in meson_pwm_get_state()") Reported-by: Munehisa Kamata <kamatam(a)amazon.com> Acked-by: Martin Blumenstingl <martin.blumenstingl(a)googlemail.com> Link: https://lore.kernel.org/r/20230310191405.2606296-1-u.kleine-koenig@pengutro… Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> Signed-off-by: Thierry Reding <thierry.reding(a)gmail.com> diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 16d79ca5d8f5..5cd7b90872c6 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -162,6 +162,12 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, duty = state->duty_cycle; period = state->period; + /* + * Note this is wrong. The result is an output wave that isn't really + * inverted and so is wrongly identified by .get_state as normal. + * Fixing this needs some care however as some machines might rely on + * this. + */ if (state->polarity == PWM_POLARITY_INVERSED) duty = period - duty; @@ -358,6 +364,8 @@ static int meson_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->duty_cycle = 0; } + state->polarity = PWM_POLARITY_NORMAL; + return 0; }

2 years, 2 months

2
1
0 0

[PATCH v5.15.x 1/2] pwm: iqs620a: Explicitly set .polarity in .get_state()

by Uwe Kleine-König

[ Upstream commit b20b097128d9145fadcea1cbb45c4d186cb57466 ] The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. Fixes: 6f0841a8197b ("pwm: Add support for Azoteq IQS620A PWM generator") Reviewed-by: Jeff LaBundy <jeff(a)labundy.com> Link: https://lore.kernel.org/r/20230228135508.1798428-4-u.kleine-koenig@pengutro… Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> Signed-off-by: Thierry Reding <thierry.reding(a)gmail.com> Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> --- drivers/pwm/pwm-iqs620a.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c index 54bd95a5cab0..8cee8f626d4e 100644 --- a/drivers/pwm/pwm-iqs620a.c +++ b/drivers/pwm/pwm-iqs620a.c @@ -126,6 +126,7 @@ static void iqs620_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, mutex_unlock(&iqs620_pwm->lock); state->period = IQS620_PWM_PERIOD_NS; + state->polarity = PWM_POLARITY_NORMAL; } static int iqs620_pwm_notifier(struct notifier_block *notifier, -- 2.39.2

2 years, 2 months

1
1
0 0

FAILED: patch "[PATCH] pwm: meson: Explicitly set .polarity in .get_state()" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 8caa81eb950cb2e9d2d6959b37d853162d197f57 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023042244-audience-anemic-4b09@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 8caa81eb950c ("pwm: meson: Explicitly set .polarity in .get_state()") 6c452cff79f8 ("pwm: Make .get_state() callback return an error code") 8eca6b0a647a ("Merge tag 'pwm/for-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8caa81eb950cb2e9d2d6959b37d853162d197f57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig(a)pengutronix.de> Date: Wed, 22 Mar 2023 22:45:44 +0100 Subject: [PATCH] pwm: meson: Explicitly set .polarity in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver only supports normal polarity. Complete the implementation of .get_state() by setting .polarity accordingly. This fixes a regression that was possible since commit c73a3107624d ("pwm: Handle .get_state() failures") which stopped to zero-initialize the state passed to the .get_state() callback. This was reported at https://forum.odroid.com/viewtopic.php?f=177&t=46360 . While this was an unintended side effect, the real issue is the driver's callback not setting the polarity. There is a complicating fact, that the .apply() callback fakes support for inversed polarity. This is not (and cannot) be matched by .get_state(). As fixing this isn't easy, only point it out in a comment to prevent authors of other drivers from copying that approach. Fixes: c375bcbaabdb ("pwm: meson: Read the full hardware state in meson_pwm_get_state()") Reported-by: Munehisa Kamata <kamatam(a)amazon.com> Acked-by: Martin Blumenstingl <martin.blumenstingl(a)googlemail.com> Link: https://lore.kernel.org/r/20230310191405.2606296-1-u.kleine-koenig@pengutro… Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)pengutronix.de> Signed-off-by: Thierry Reding <thierry.reding(a)gmail.com> diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 16d79ca5d8f5..5cd7b90872c6 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -162,6 +162,12 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm, duty = state->duty_cycle; period = state->period; + /* + * Note this is wrong. The result is an output wave that isn't really + * inverted and so is wrongly identified by .get_state as normal. + * Fixing this needs some care however as some machines might rely on + * this. + */ if (state->polarity == PWM_POLARITY_INVERSED) duty = period - duty; @@ -358,6 +364,8 @@ static int meson_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, state->duty_cycle = 0; } + state->polarity = PWM_POLARITY_NORMAL; + return 0; }

2 years, 2 months

2
1
0 0

[PATCH 5.4] xfs: fix forkoff miscalculation related to XFS_LITINO(mp)

by Chandan Babu R

From: Gao Xiang <hsiangkao(a)redhat.com> commit ada49d64fb3538144192181db05de17e2ffc3551 upstream. Currently, commit e9e2eae89ddb dropped a (int) decoration from XFS_LITINO(mp), and since sizeof() expression is also involved, the result of XFS_LITINO(mp) is simply as the size_t type (commonly unsigned long). Considering the expression in xfs_attr_shortform_bytesfit(): offset = (XFS_LITINO(mp) - bytes) >> 3; let "bytes" be (int)340, and "XFS_LITINO(mp)" be (unsigned long)336. on 64-bit platform, the expression is offset = ((unsigned long)336 - (int)340) >> 3 = (int)(0xfffffffffffffffcUL >> 3) = -1 but on 32-bit platform, the expression is offset = ((unsigned long)336 - (int)340) >> 3 = (int)(0xfffffffcUL >> 3) = 0x1fffffff instead. so offset becomes a large positive number on 32-bit platform, and cause xfs_attr_shortform_bytesfit() returns maxforkoff rather than 0. Therefore, one result is "ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));" assertion failure in xfs_idata_realloc(), which was also the root cause of the original bugreport from Dennis, see: https://bugzilla.redhat.com/show_bug.cgi?id=1894177 And it can also be manually triggered with the following commands: $ touch a; $ setfattr -n user.0 -v "`seq 0 80`" a; $ setfattr -n user.1 -v "`seq 0 80`" a on 32-bit platform. Fix the case in xfs_attr_shortform_bytesfit() by bailing out "XFS_LITINO(mp) < bytes" in advance suggested by Eric and a misleading comment together with this bugfix suggested by Darrick. It seems the other users of XFS_LITINO(mp) are not impacted. Fixes: e9e2eae89ddb ("xfs: only check the superblock version for dinode size calculation") Cc: <stable(a)vger.kernel.org> # 5.7+ Reported-and-tested-by: Dennis Gilmore <dgilmore(a)redhat.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Gao Xiang <hsiangkao(a)redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Signed-off-by: Chandan Babu R <chandan.babu(a)oracle.com> Acked-by: Darrick J. Wong <djwong(a)kernel.org> --- Hi Greg, I had missed this commit when backporting fixes for 5.4.y from v5.11 & v5.12. The commit has been acked by Darrick. fs/xfs/libxfs/xfs_attr_leaf.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index f5b16120c64d..2b74b6e9a354 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -435,7 +435,7 @@ xfs_attr_copy_value( *========================================================================*/ /* - * Query whether the requested number of additional bytes of extended + * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the di_forkoff fork offset to be used in the @@ -455,6 +455,12 @@ xfs_attr_shortform_bytesfit( int maxforkoff; int offset; + /* + * Check if the new size could fit at all first: + */ + if (bytes > XFS_LITINO(mp)) + return 0; + /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; -- 2.39.1

2 years, 2 months

1
0
0 0

[PATCH v3] vhost_vdpa: fix unmap process in no-batch mode

by Cindy Lu

While using the vdpa device with vIOMMU enabled in the guest VM, when the vdpa device bind to vfio-pci and run testpmd then system will fail to unmap. The test process is Load guest VM --> attach to virtio driver--> bind to vfio-pci driver So the mapping process is 1)batched mode map to normal MR 2)batched mode unmapped the normal MR 3)unmapped all the memory 4)mapped to iommu MR This error happened in step 3). The iotlb was freed in step 2) and the function vhost_vdpa_process_iotlb_msg will return fail Which causes failure. To fix this, we will not remove the AS while the iotlb->nmaps is 0. This will free in the vhost_vdpa_clean Cc: stable(a)vger.kernel.org Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API") Signed-off-by: Cindy Lu <lulu(a)redhat.com> --- drivers/vhost/vdpa.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 7be9d9d8f01c..74c7d1f978b7 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -851,11 +851,7 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, if (!v->in_batch) ops->set_map(vdpa, asid, iotlb); } - /* If we are in the middle of batch processing, delay the free - * of AS until BATCH_END. - */ - if (!v->in_batch && !iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); + } static int vhost_vdpa_va_map(struct vhost_vdpa *v, @@ -1112,8 +1108,6 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, if (v->in_batch && ops->set_map) ops->set_map(vdpa, asid, iotlb); v->in_batch = false; - if (!iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); break; default: r = -EINVAL; -- 2.34.3

2 years, 2 months

2
1
0 0

[PATCH v2 1/2] x86/cacheinfo: Delete global num_cache_leaves

by Ricardo Neri

Linux remembers cpu_cachinfo::num_leaves per CPU, but x86 initializes all CPUs from the same global "num_cache_leaves". This is erroneous on systems like Meteor Lake, which has different num_leaves per CPU. Delete the global "num_cache_leaves" and initialize num_leaves accurately on each CPU. Cc: Andreas Herrmann <aherrmann(a)suse.com> Cc: Chen Yu <yu.c.chen(a)intel.com> Cc: Len Brown <len.brown(a)intel.com> Cc: Pu Wen <puwen(a)hygon.cn> Cc: "Rafael J. Wysocki" <rafael.j.wysocki(a)intel.com> Cc: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Cc: Zhang Rui <rui.zhang(a)intel.com> Cc: stable(a)vger.kernel.org Reviewed-by: Len Brown <len.brown(a)intel.com> Signed-off-by: Ricardo Neri <ricardo.neri-calderon(a)linux.intel.com> --- After this change, all CPUs will traverse CPUID leaf 0x4 when booted for the first time. On systems with asymmetric cache topologies this is useless work. Creating a list of processor models that have asymmetric cache topologies was considered. The burden of maintaining such list would outweigh the performance benefit of skipping this extra step. --- Changes since v1: * Do not make num_cache_leaves a per-CPU variable. Instead, reuse the existing per-CPU ci_cpu_cacheinfo variable. (Dave Hansen) --- arch/x86/kernel/cpu/cacheinfo.c | 45 ++++++++++++++++++--------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 4063e8991211..45c4e9daf3f1 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -176,7 +176,16 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -static unsigned short num_cache_leaves; +static inline unsigned int get_num_cache_leaves(unsigned int cpu) +{ + return get_cpu_cacheinfo(cpu)->num_leaves; +} + +static inline void +set_num_cache_leaves(unsigned int nr_leaves, unsigned int cpu) +{ + get_cpu_cacheinfo(cpu)->num_leaves = nr_leaves; +} /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: @@ -716,19 +725,21 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { + unsigned int cpu = c->cpu_index; + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - num_cache_leaves = find_num_cache_leaves(c); + set_num_cache_leaves(find_num_cache_leaves(c), cpu); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) - num_cache_leaves = 4; + set_num_cache_leaves(4, cpu); else - num_cache_leaves = 3; + set_num_cache_leaves(3, cpu); } } void init_hygon_cacheinfo(struct cpuinfo_x86 *c) { - num_cache_leaves = find_num_cache_leaves(c); + set_num_cache_leaves(find_num_cache_leaves(c), c->cpu_index); } void init_intel_cacheinfo(struct cpuinfo_x86 *c) @@ -738,24 +749,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_SMP unsigned int cpu = c->cpu_index; -#endif if (c->cpuid_level > 3) { - static int is_initialized; - - if (is_initialized == 0) { - /* Init num_cache_leaves from boot CPU */ - num_cache_leaves = find_num_cache_leaves(c); - is_initialized++; - } + /* + * There should be at least one leaf. A non-zero value means + * that the number of leaves has been initialized. + */ + if (!get_num_cache_leaves(cpu)) + set_num_cache_leaves(find_num_cache_leaves(c), cpu); /* * Whenever possible use cpuid(4), deterministic cache * parameters cpuid leaf to find the cache details */ - for (i = 0; i < num_cache_leaves; i++) { + for (i = 0; i < get_num_cache_leaves(cpu); i++) { struct _cpuid4_info_regs this_leaf = {}; int retval; @@ -791,14 +799,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for * trace cache */ - if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) { + if ((!get_num_cache_leaves(cpu) || c->x86 == 15) && c->cpuid_level > 1) { /* supports eax=2 call */ int j, n; unsigned int regs[4]; unsigned char *dp = (unsigned char *)regs; int only_trace = 0; - if (num_cache_leaves != 0 && c->x86 == 15) + if (get_num_cache_leaves(cpu) && c->x86 == 15) only_trace = 1; /* Number of times to iterate */ @@ -1000,12 +1008,9 @@ int init_cache_level(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - if (!num_cache_leaves) - return -ENOENT; if (!this_cpu_ci) return -EINVAL; this_cpu_ci->num_levels = 3; - this_cpu_ci->num_leaves = num_cache_leaves; return 0; } -- 2.25.1

2 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2023