- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10 0/5] Fix CVE-2024-36939
by Wang Zhaolong 16 Jul '24

16 Jul '24

Josef Bacik (3): sunrpc: add a struct rpc_stats arg to rpc_create_args nfs: expose /proc/net/sunrpc/nfs in net namespaces nfs: make the rpc_stat per net namespace Kuniyuki Iwashima (1): nfs: Handle error of rpc_proc_register() in nfs_net_init(). Wang Zhaolong (1): sunrpc: fix KABI broken in struct rpc_create_args fs/nfs/client.c | 5 ++++- fs/nfs/inode.c | 13 +++++++++---- fs/nfs/internal.h | 2 -- fs/nfs/netns.h | 2 ++ include/linux/sunrpc/clnt.h | 2 +- net/sunrpc/clnt.c | 5 ++++- 6 files changed, 20 insertions(+), 9 deletions(-) -- 2.34.3

2 6

[PATCH OLK-6.6] ALSA: hda/cs_dsp_ctl: Use private_free for control cleanup
by Cui GaoSheng 16 Jul '24

16 Jul '24

From: Richard Fitzgerald <rf(a)opensource.cirrus.com> stable inclusion from stable-v6.6.33 commit 6e359be4975006ff72818e79dad8fe48293f2eb2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA7D1H CVE: CVE-2024-38388 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 172811e3a557d8681a5e2d0f871dc04a2d17eb13 ] Use the control private_free callback to free the associated data block. This ensures that the memory won't leak, whatever way the control gets destroyed. The original implementation didn't actually remove the ALSA controls in hda_cs_dsp_control_remove(). It only freed the internal tracking structure. This meant it was possible to remove/unload the amp driver while leaving its ALSA controls still present in the soundcard. Obviously attempting to access them could cause segfaults or at least dereferencing stale pointers. Signed-off-by: Richard Fitzgerald <rf(a)opensource.cirrus.com> Fixes: 3233b978af23 ("ALSA: hda: hda_cs_dsp_ctl: Add Library to support CS_DSP ALSA controls") Link: https://lore.kernel.org/r/20240508095627.44476-1-rf@opensource.cirrus.com Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- sound/pci/hda/hda_cs_dsp_ctl.c | 47 ++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 16 deletions(-) diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 463ca06036bf..9db45d7c17e5 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <sound/soc.h> +#include <linux/cleanup.h> #include <linux/firmware/cirrus/cs_dsp.h> #include <linux/firmware/cirrus/wmfw.h> #include "hda_cs_dsp_ctl.h" @@ -97,11 +98,23 @@ static unsigned int wmfw_convert_flags(unsigned int in) return out; } -static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) +static void hda_cs_dsp_free_kcontrol(struct snd_kcontrol *kctl) { + struct hda_cs_dsp_coeff_ctl *ctl = (struct hda_cs_dsp_coeff_ctl *)snd_kcontrol_chip(kctl); struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; + + /* NULL priv to prevent a double-free in hda_cs_dsp_control_remove() */ + cs_ctl->priv = NULL; + kfree(ctl); +} + +static void hda_cs_dsp_add_kcontrol(struct cs_dsp_coeff_ctl *cs_ctl, + const struct hda_cs_dsp_ctl_info *info, + const char *name) +{ struct snd_kcontrol_new kcontrol = {0}; struct snd_kcontrol *kctl; + struct hda_cs_dsp_coeff_ctl *ctl __free(kfree) = NULL; int ret = 0; if (cs_ctl->len > ADSP_MAX_STD_CTRL_SIZE) { @@ -110,6 +123,13 @@ static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char return; } + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return; + + ctl->cs_ctl = cs_ctl; + ctl->card = info->card; + kcontrol.name = name; kcontrol.info = hda_cs_dsp_coeff_info; kcontrol.iface = SNDRV_CTL_ELEM_IFACE_MIXER; @@ -117,20 +137,22 @@ static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char kcontrol.get = hda_cs_dsp_coeff_get; kcontrol.put = hda_cs_dsp_coeff_put; - /* Save ctl inside private_data, ctl is owned by cs_dsp, - * and will be freed when cs_dsp removes the control */ kctl = snd_ctl_new1(&kcontrol, (void *)ctl); if (!kctl) return; - ret = snd_ctl_add(ctl->card, kctl); + kctl->private_free = hda_cs_dsp_free_kcontrol; + ctl->kctl = kctl; + + /* snd_ctl_add() calls our private_free on error, which will kfree(ctl) */ + cs_ctl->priv = no_free_ptr(ctl); + ret = snd_ctl_add(info->card, kctl); if (ret) { dev_err(cs_ctl->dsp->dev, "Failed to add KControl %s = %d\n", kcontrol.name, ret); return; } dev_dbg(cs_ctl->dsp->dev, "Added KControl: %s\n", kcontrol.name); - ctl->kctl = kctl; } static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, @@ -138,7 +160,6 @@ static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, { struct cs_dsp *cs_dsp = cs_ctl->dsp; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - struct hda_cs_dsp_coeff_ctl *ctl; const char *region_name; int ret; @@ -163,15 +184,7 @@ static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, " %.*s", cs_ctl->subname_len - skip, cs_ctl->subname + skip); } - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); - if (!ctl) - return; - - ctl->cs_ctl = cs_ctl; - ctl->card = info->card; - cs_ctl->priv = ctl; - - hda_cs_dsp_add_kcontrol(ctl, name); + hda_cs_dsp_add_kcontrol(cs_ctl, info, name); } void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info) @@ -203,7 +216,9 @@ void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) { struct hda_cs_dsp_coeff_ctl *ctl = cs_ctl->priv; - kfree(ctl); + /* ctl and kctl may already have been removed by ALSA private_free */ + if (ctl && ctl->kctl) + snd_ctl_remove(ctl->card, ctl->kctl); } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_remove, SND_HDA_CS_DSP_CONTROLS); -- 2.34.1

2 1

[PATCH OLK-6.6] openrisc: traps: Don't send signals to kernel mode threads
by Cui GaoSheng 16 Jul '24

16 Jul '24

From: Stafford Horne <shorne(a)gmail.com> stable inclusion from stable-v6.6.33 commit c0ed9a711e3392d73e857faa031d8d349c0d70db category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6SH4 CVE: CVE-2024-38614 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit c88cfb5cea5f8f9868ef02cc9ce9183a26dcf20f ] OpenRISC exception handling sends signals to user processes on floating point exceptions and trap instructions (for debugging) among others. There is a bug where the trap handling logic may send signals to kernel threads, we should not send these signals to kernel threads, if that happens we treat it as an error. This patch adds conditions to die if the kernel receives these exceptions in kernel mode code. Fixes: 27267655c531 ("openrisc: Support floating point user api") Signed-off-by: Stafford Horne <shorne(a)gmail.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- arch/openrisc/kernel/traps.c | 48 ++++++++++++++++++++++-------------- 1 file changed, 29 insertions(+), 19 deletions(-) diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 9370888c9a7e..90554a5558fb 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -180,29 +180,39 @@ asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector) asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address) { - int code = FPE_FLTUNK; - unsigned long fpcsr = regs->fpcsr; - - if (fpcsr & SPR_FPCSR_IVF) - code = FPE_FLTINV; - else if (fpcsr & SPR_FPCSR_OVF) - code = FPE_FLTOVF; - else if (fpcsr & SPR_FPCSR_UNF) - code = FPE_FLTUND; - else if (fpcsr & SPR_FPCSR_DZF) - code = FPE_FLTDIV; - else if (fpcsr & SPR_FPCSR_IXF) - code = FPE_FLTRES; - - /* Clear all flags */ - regs->fpcsr &= ~SPR_FPCSR_ALLF; - - force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + if (user_mode(regs)) { + int code = FPE_FLTUNK; + unsigned long fpcsr = regs->fpcsr; + + if (fpcsr & SPR_FPCSR_IVF) + code = FPE_FLTINV; + else if (fpcsr & SPR_FPCSR_OVF) + code = FPE_FLTOVF; + else if (fpcsr & SPR_FPCSR_UNF) + code = FPE_FLTUND; + else if (fpcsr & SPR_FPCSR_DZF) + code = FPE_FLTDIV; + else if (fpcsr & SPR_FPCSR_IXF) + code = FPE_FLTRES; + + /* Clear all flags */ + regs->fpcsr &= ~SPR_FPCSR_ALLF; + + force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal fpe exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGFPE); + } } asmlinkage void do_trap(struct pt_regs *regs, unsigned long address) { - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + if (user_mode(regs)) { + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal trap exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGILL); + } } asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] netpoll: Fix race condition in netpoll_owner_active
by Zhengchao Shao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> mainline inclusion from mainline-v6.10-rc1 commit c2e6a872bde9912f1a7579639c5ca3adf1003916 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR1O CVE: CVE-2024-41005 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- KCSAN detected a race condition in netpoll: BUG: KCSAN: data-race in net_rx_action / netpoll_send_skb write (marked) to 0xffff8881164168b0 of 4 bytes by interrupt on cpu 10: net_rx_action (./include/linux/netpoll.h:90 net/core/dev.c:6712 net/core/dev.c:6822) <snip> read to 0xffff8881164168b0 of 4 bytes by task 1 on cpu 2: netpoll_send_skb (net/core/netpoll.c:319 net/core/netpoll.c:345 net/core/netpoll.c:393) netpoll_send_udp (net/core/netpoll.c:?) <snip> value changed: 0x0000000a -> 0xffffffff This happens because netpoll_owner_active() needs to check if the current CPU is the owner of the lock, touching napi->poll_owner non atomically. The ->poll_owner field contains the current CPU holding the lock. Use an atomic read to check if the poll owner is the current CPU. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240429100437.3487432-1-leitao@debian.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/core/netpoll.c [The conflict occurs because the commit 5251ef829932("net: make sure napi_list is safe for RCU traversal") is not merged] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/core/netpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index b23c32ed6773..f1a830550e0c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -315,7 +315,7 @@ static int netpoll_owner_active(struct net_device *dev) struct napi_struct *napi; list_for_each_entry(napi, &dev->napi_list, dev_list) { - if (napi->poll_owner == smp_processor_id()) + if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] Bluetooth: btusb: Add date->evt_skb is NULL check
by Yuan Can 16 Jul '24

16 Jul '24

From: youwan Wang <wangyouwan(a)126.com> mainline inclusion from mainline-v6.7-rc1 commit 624820f7c8826dd010e8b1963303c145f99816e9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9RFI9 CVE: CVE-2023-52833 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- [ Upstream commit 624820f7c8826dd010e8b1963303c145f99816e9 ] fix crash because of null pointers [ 6104.969662] BUG: kernel NULL pointer dereference, address: 00000000000000c8 [ 6104.969667] #PF: supervisor read access in kernel mode [ 6104.969668] #PF: error_code(0x0000) - not-present page [ 6104.969670] PGD 0 P4D 0 [ 6104.969673] Oops: 0000 [#1] SMP NOPTI [ 6104.969684] RIP: 0010:btusb_mtk_hci_wmt_sync+0x144/0x220 [btusb] [ 6104.969688] RSP: 0018:ffffb8d681533d48 EFLAGS: 00010246 [ 6104.969689] RAX: 0000000000000000 RBX: ffff8ad560bb2000 RCX: 0000000000000006 [ 6104.969691] RDX: 0000000000000000 RSI: ffffb8d681533d08 RDI: 0000000000000000 [ 6104.969692] RBP: ffffb8d681533d70 R08: 0000000000000001 R09: 0000000000000001 [ 6104.969694] R10: 0000000000000001 R11: 00000000fa83b2da R12: ffff8ad461d1d7c0 [ 6104.969695] R13: 0000000000000000 R14: ffff8ad459618c18 R15: ffffb8d681533d90 [ 6104.969697] FS: 00007f5a1cab9d40(0000) GS:ffff8ad578200000(0000) knlGS:00000 [ 6104.969699] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6104.969700] CR2: 00000000000000c8 CR3: 000000018620c001 CR4: 0000000000760ef0 [ 6104.969701] PKRU: 55555554 [ 6104.969702] Call Trace: [ 6104.969708] btusb_mtk_shutdown+0x44/0x80 [btusb] [ 6104.969732] hci_dev_do_close+0x470/0x5c0 [bluetooth] [ 6104.969748] hci_rfkill_set_block+0x56/0xa0 [bluetooth] [ 6104.969753] rfkill_set_block+0x92/0x160 [ 6104.969755] rfkill_fop_write+0x136/0x1e0 [ 6104.969759] __vfs_write+0x18/0x40 [ 6104.969761] vfs_write+0xdf/0x1c0 [ 6104.969763] ksys_write+0xb1/0xe0 [ 6104.969765] __x64_sys_write+0x1a/0x20 [ 6104.969769] do_syscall_64+0x51/0x180 [ 6104.969771] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 6104.969773] RIP: 0033:0x7f5a21f18fef [ 6104.9] RSP: 002b:00007ffeefe39010 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 [ 6104.969780] RAX: ffffffffffffffda RBX: 000055c10a7560a0 RCX: 00007f5a21f18fef [ 6104.969781] RDX: 0000000000000008 RSI: 00007ffeefe39060 RDI: 0000000000000012 [ 6104.969782] RBP: 00007ffeefe39060 R08: 0000000000000000 R09: 0000000000000017 [ 6104.969784] R10: 00007ffeefe38d97 R11: 0000000000000293 R12: 0000000000000002 [ 6104.969785] R13: 00007ffeefe39220 R14: 00007ffeefe391a0 R15: 000055c10a72acf0 Signed-off-by: youwan Wang <wangyouwan(a)126.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- drivers/bluetooth/btusb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 6efd981979bd..7e6c96b1dea5 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3083,6 +3083,9 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, goto err_free_wc; } + if (data->evt_skb == NULL) + goto err_free_wc; + /* Parse and handle the return WMT event */ wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data; if (wmt_evt->whdr.op != hdr->op) { -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] io_uring/io-wq: Use set_bit() and test_bit() at worker->flags
by Yifan Qiao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v6.6.35 commit ab702c3483db9046bab9f40306f1a28b22dbbdc0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR2Y CVE: CVE-2024-39508 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8a565304927fbd28c9f028c492b5c1714002cbab ] Utilize set_bit() and test_bit() on worker->flags within io_uring/io-wq to address potential data races. The structure io_worker->flags may be accessed through various data paths, leading to concurrency issues. When KCSAN is enabled, it reveals data races occurring in io_worker_handle_work and io_wq_activate_free_worker functions. BUG: KCSAN: data-race in io_worker_handle_work / io_wq_activate_free_worker write to 0xffff8885c4246404 of 4 bytes by task 49071 on cpu 28: io_worker_handle_work (io_uring/io-wq.c:434 io_uring/io-wq.c:569) io_wq_worker (io_uring/io-wq.c:?) <snip> read to 0xffff8885c4246404 of 4 bytes by task 49024 on cpu 5: io_wq_activate_free_worker (io_uring/io-wq.c:? io_uring/io-wq.c:285) io_wq_enqueue (io_uring/io-wq.c:947) io_queue_iowq (io_uring/io_uring.c:524) io_req_task_submit (io_uring/io_uring.c:1511) io_handle_tw_list (io_uring/io_uring.c:1198) <snip> Line numbers against commit 18daea77cca6 ("Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm"). These races involve writes and reads to the same memory location by different tasks running on different CPUs. To mitigate this, refactor the code to use atomic operations such as set_bit(), test_bit(), and clear_bit() instead of basic "and" and "or" operations. This ensures thread-safe manipulation of worker flags. Also, move `create_index` to avoid holes in the structure. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240507170002.2269003-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Stable-dep-of: 91215f70ea85 ("io_uring/io-wq: avoid garbage value of 'match' in io_wq_enqueue()") Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: io_uring/io-wq.c [The function names are different than cve commit. But their basic functions are same and they are using the io_worker in the same way.] Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- io_uring/io-wq.c | 47 ++++++++++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 6031fb319d87..cc31ebf3a1d5 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -21,10 +21,10 @@ #define WORKER_IDLE_TIMEOUT (5 * HZ) enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_BOUND = 8, /* is doing bounded work */ + IO_WORKER_F_UP = 0, /* up and active */ + IO_WORKER_F_RUNNING = 1, /* account as running */ + IO_WORKER_F_FREE = 2, /* worker on free list */ + IO_WORKER_F_BOUND = 3, /* is doing bounded work */ }; enum { @@ -40,7 +40,8 @@ enum { */ struct io_worker { refcount_t ref; - unsigned flags; + int create_index; + unsigned long flags; struct hlist_nulls_node nulls_node; struct list_head all_list; struct task_struct *task; @@ -53,7 +54,6 @@ struct io_worker { unsigned long create_state; struct callback_head create_work; - int create_index; union { struct rcu_head rcu; @@ -167,7 +167,7 @@ static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker) { - return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND); + return io_get_acct(worker->wqe, test_bit(IO_WORKER_F_BOUND, &worker->flags)); } static void io_worker_ref_put(struct io_wq *wq) @@ -220,7 +220,7 @@ static void io_worker_exit(struct io_worker *worker) wait_for_completion(&worker->ref_done); raw_spin_lock(&wqe->lock); - if (worker->flags & IO_WORKER_F_FREE) + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); preempt_disable(); @@ -389,7 +389,7 @@ static void io_wqe_dec_running(struct io_worker *worker) struct io_wqe_acct *acct = io_wqe_get_acct(worker); struct io_wqe *wqe = worker->wqe; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { @@ -409,8 +409,8 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, struct io_wq_work *work) __must_hold(wqe->lock) { - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) { + clear_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_del_init_rcu(&worker->nulls_node); } } @@ -425,8 +425,8 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) __must_hold(wqe->lock) { - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; + if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) { + set_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); } } @@ -615,7 +615,8 @@ static int io_wqe_worker(void *data) bool last_timeout = false; char buf[TASK_COMM_LEN]; - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + set_mask_bits(&worker->flags, 0, + BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); @@ -671,11 +672,11 @@ void io_wq_worker_running(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (worker->flags & IO_WORKER_F_RUNNING) + if (test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags |= IO_WORKER_F_RUNNING; + set_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wqe_inc_running(worker); } @@ -689,12 +690,12 @@ void io_wq_worker_sleeping(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) + if (!test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags &= ~IO_WORKER_F_RUNNING; + clear_bit(IO_WORKER_F_RUNNING, &worker->flags); raw_spin_lock(&worker->wqe->lock); io_wqe_dec_running(worker); @@ -712,7 +713,7 @@ static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, raw_spin_lock(&wqe->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); list_add_tail_rcu(&worker->all_list, &wqe->all_list); - worker->flags |= IO_WORKER_F_FREE; + set_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_unlock(&wqe->lock); wake_up_new_task(tsk); } @@ -816,7 +817,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) init_completion(&worker->ref_done); if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; + set_bit(IO_WORKER_F_BOUND, &worker->flags); tsk = create_io_thread(io_wqe_worker, worker, wqe->node); if (!IS_ERR(tsk)) { @@ -904,7 +905,7 @@ static bool io_wq_work_match_item(struct io_wq_work *work, void *data) static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) { struct io_wqe_acct *acct = io_work_get_acct(wqe, work); - unsigned work_flags = work->flags; + unsigned long work_flags = work->flags; bool do_create; /* -- 2.39.2

2 1

[PATCH OLK-5.10] io_uring/io-wq: Use set_bit() and test_bit() at worker->flags
by Yifan Qiao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v6.6.35 commit ab702c3483db9046bab9f40306f1a28b22dbbdc0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR2Y CVE: CVE-2024-39508 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8a565304927fbd28c9f028c492b5c1714002cbab ] Utilize set_bit() and test_bit() on worker->flags within io_uring/io-wq to address potential data races. The structure io_worker->flags may be accessed through various data paths, leading to concurrency issues. When KCSAN is enabled, it reveals data races occurring in io_worker_handle_work and io_wq_activate_free_worker functions. BUG: KCSAN: data-race in io_worker_handle_work / io_wq_activate_free_worker write to 0xffff8885c4246404 of 4 bytes by task 49071 on cpu 28: io_worker_handle_work (io_uring/io-wq.c:434 io_uring/io-wq.c:569) io_wq_worker (io_uring/io-wq.c:?) <snip> read to 0xffff8885c4246404 of 4 bytes by task 49024 on cpu 5: io_wq_activate_free_worker (io_uring/io-wq.c:? io_uring/io-wq.c:285) io_wq_enqueue (io_uring/io-wq.c:947) io_queue_iowq (io_uring/io_uring.c:524) io_req_task_submit (io_uring/io_uring.c:1511) io_handle_tw_list (io_uring/io_uring.c:1198) <snip> Line numbers against commit 18daea77cca6 ("Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm"). These races involve writes and reads to the same memory location by different tasks running on different CPUs. To mitigate this, refactor the code to use atomic operations such as set_bit(), test_bit(), and clear_bit() instead of basic "and" and "or" operations. This ensures thread-safe manipulation of worker flags. Also, move `create_index` to avoid holes in the structure. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240507170002.2269003-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Stable-dep-of: 91215f70ea85 ("io_uring/io-wq: avoid garbage value of 'match' in io_wq_enqueue()") Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: io_uring/io-wq.c [The function names are different than cve commit. But their basic functions are same and they are using the io_worker in the same way.] Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- io_uring/io-wq.c | 47 ++++++++++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index fe8594a0396c..066f9ab708c6 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -21,10 +21,10 @@ #define WORKER_IDLE_TIMEOUT (5 * HZ) enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_BOUND = 8, /* is doing bounded work */ + IO_WORKER_F_UP = 0, /* up and active */ + IO_WORKER_F_RUNNING = 1, /* account as running */ + IO_WORKER_F_FREE = 2, /* worker on free list */ + IO_WORKER_F_BOUND = 3, /* is doing bounded work */ }; enum { @@ -40,7 +40,8 @@ enum { */ struct io_worker { refcount_t ref; - unsigned flags; + int create_index; + unsigned long flags; struct hlist_nulls_node nulls_node; struct list_head all_list; struct task_struct *task; @@ -53,7 +54,6 @@ struct io_worker { unsigned long create_state; struct callback_head create_work; - int create_index; union { struct rcu_head rcu; @@ -167,7 +167,7 @@ static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe, static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker) { - return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND); + return io_get_acct(worker->wqe, test_bit(IO_WORKER_F_BOUND, &worker->flags)); } static void io_worker_ref_put(struct io_wq *wq) @@ -230,7 +230,7 @@ static void io_worker_exit(struct io_worker *worker) wait_for_completion(&worker->ref_done); raw_spin_lock(&wqe->lock); - if (worker->flags & IO_WORKER_F_FREE) + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); preempt_disable(); @@ -399,7 +399,7 @@ static void io_wqe_dec_running(struct io_worker *worker) struct io_wqe_acct *acct = io_wqe_get_acct(worker); struct io_wqe *wqe = worker->wqe; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { @@ -419,8 +419,8 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, struct io_wq_work *work) __must_hold(wqe->lock) { - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) { + clear_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_del_init_rcu(&worker->nulls_node); } } @@ -435,8 +435,8 @@ static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) __must_hold(wqe->lock) { - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; + if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) { + set_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); } } @@ -625,7 +625,8 @@ static int io_wqe_worker(void *data) bool last_timeout = false; char buf[TASK_COMM_LEN]; - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + set_mask_bits(&worker->flags, 0, + BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); @@ -681,11 +682,11 @@ void io_wq_worker_running(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (worker->flags & IO_WORKER_F_RUNNING) + if (test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags |= IO_WORKER_F_RUNNING; + set_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wqe_inc_running(worker); } @@ -699,12 +700,12 @@ void io_wq_worker_sleeping(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) + if (!test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags &= ~IO_WORKER_F_RUNNING; + clear_bit(IO_WORKER_F_RUNNING, &worker->flags); raw_spin_lock(&worker->wqe->lock); io_wqe_dec_running(worker); @@ -722,7 +723,7 @@ static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, raw_spin_lock(&wqe->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list); list_add_tail_rcu(&worker->all_list, &wqe->all_list); - worker->flags |= IO_WORKER_F_FREE; + set_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_unlock(&wqe->lock); wake_up_new_task(tsk); } @@ -826,7 +827,7 @@ static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) init_completion(&worker->ref_done); if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; + set_bit(IO_WORKER_F_BOUND, &worker->flags); tsk = create_io_thread(io_wqe_worker, worker, wqe->node); if (!IS_ERR(tsk)) { @@ -914,7 +915,7 @@ static bool io_wq_work_match_item(struct io_wq_work *work, void *data) static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) { struct io_wqe_acct *acct = io_work_get_acct(wqe, work); - unsigned work_flags = work->flags; + unsigned long work_flags = work->flags; bool do_create; /* -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] netpoll: Fix race condition in netpoll_owner_active
by Zhengchao Shao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v5.10.221 commit 43c0ca793a18578a0f5b305dd77fcf7ed99f1265 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR1O CVE: CVE-2024-41005 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit c2e6a872bde9912f1a7579639c5ca3adf1003916 ] KCSAN detected a race condition in netpoll: BUG: KCSAN: data-race in net_rx_action / netpoll_send_skb write (marked) to 0xffff8881164168b0 of 4 bytes by interrupt on cpu 10: net_rx_action (./include/linux/netpoll.h:90 net/core/dev.c:6712 net/core/dev.c:6822) <snip> read to 0xffff8881164168b0 of 4 bytes by task 1 on cpu 2: netpoll_send_skb (net/core/netpoll.c:319 net/core/netpoll.c:345 net/core/netpoll.c:393) netpoll_send_udp (net/core/netpoll.c:?) <snip> value changed: 0x0000000a -> 0xffffffff This happens because netpoll_owner_active() needs to check if the current CPU is the owner of the lock, touching napi->poll_owner non atomically. The ->poll_owner field contains the current CPU holding the lock. Use an atomic read to check if the poll owner is the current CPU. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240429100437.3487432-1-leitao@debian.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/core/netpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 960948290001..fd7375625dad 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -299,7 +299,7 @@ static int netpoll_owner_active(struct net_device *dev) struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { - if (napi->poll_owner == smp_processor_id()) + if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; -- 2.34.1

2 1

[PATCH OLK-5.10] netpoll: Fix race condition in netpoll_owner_active
by Zhengchao Shao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v5.10.221 commit 43c0ca793a18578a0f5b305dd77fcf7ed99f1265 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR1O CVE: CVE-2024-41005 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit c2e6a872bde9912f1a7579639c5ca3adf1003916 ] KCSAN detected a race condition in netpoll: BUG: KCSAN: data-race in net_rx_action / netpoll_send_skb write (marked) to 0xffff8881164168b0 of 4 bytes by interrupt on cpu 10: net_rx_action (./include/linux/netpoll.h:90 net/core/dev.c:6712 net/core/dev.c:6822) <snip> read to 0xffff8881164168b0 of 4 bytes by task 1 on cpu 2: netpoll_send_skb (net/core/netpoll.c:319 net/core/netpoll.c:345 net/core/netpoll.c:393) netpoll_send_udp (net/core/netpoll.c:?) <snip> value changed: 0x0000000a -> 0xffffffff This happens because netpoll_owner_active() needs to check if the current CPU is the owner of the lock, touching napi->poll_owner non atomically. The ->poll_owner field contains the current CPU holding the lock. Use an atomic read to check if the poll owner is the current CPU. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240429100437.3487432-1-leitao@debian.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/core/netpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2ad22511b9c6..f76afab9fd8b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -316,7 +316,7 @@ static int netpoll_owner_active(struct net_device *dev) struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { - if (napi->poll_owner == smp_processor_id()) + if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; -- 2.34.1

2 1

[PATCH OLK-6.6] io_uring/io-wq: Use set_bit() and test_bit() at worker->flags
by Yifan Qiao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v6.6.35 commit ab702c3483db9046bab9f40306f1a28b22dbbdc0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR2Y CVE: CVE-2024-39508 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 8a565304927fbd28c9f028c492b5c1714002cbab ] Utilize set_bit() and test_bit() on worker->flags within io_uring/io-wq to address potential data races. The structure io_worker->flags may be accessed through various data paths, leading to concurrency issues. When KCSAN is enabled, it reveals data races occurring in io_worker_handle_work and io_wq_activate_free_worker functions. BUG: KCSAN: data-race in io_worker_handle_work / io_wq_activate_free_worker write to 0xffff8885c4246404 of 4 bytes by task 49071 on cpu 28: io_worker_handle_work (io_uring/io-wq.c:434 io_uring/io-wq.c:569) io_wq_worker (io_uring/io-wq.c:?) <snip> read to 0xffff8885c4246404 of 4 bytes by task 49024 on cpu 5: io_wq_activate_free_worker (io_uring/io-wq.c:? io_uring/io-wq.c:285) io_wq_enqueue (io_uring/io-wq.c:947) io_queue_iowq (io_uring/io_uring.c:524) io_req_task_submit (io_uring/io_uring.c:1511) io_handle_tw_list (io_uring/io_uring.c:1198) <snip> Line numbers against commit 18daea77cca6 ("Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm"). These races involve writes and reads to the same memory location by different tasks running on different CPUs. To mitigate this, refactor the code to use atomic operations such as set_bit(), test_bit(), and clear_bit() instead of basic "and" and "or" operations. This ensures thread-safe manipulation of worker flags. Also, move `create_index` to avoid holes in the structure. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240507170002.2269003-1-leitao@debian.org Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Stable-dep-of: 91215f70ea85 ("io_uring/io-wq: avoid garbage value of 'match' in io_wq_enqueue()") Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- io_uring/io-wq.c | 47 ++++++++++++++++++++++++----------------------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 522196dfb0ff..606fc5b64c65 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -25,10 +25,10 @@ #define WORKER_IDLE_TIMEOUT (5 * HZ) enum { - IO_WORKER_F_UP = 1, /* up and active */ - IO_WORKER_F_RUNNING = 2, /* account as running */ - IO_WORKER_F_FREE = 4, /* worker on free list */ - IO_WORKER_F_BOUND = 8, /* is doing bounded work */ + IO_WORKER_F_UP = 0, /* up and active */ + IO_WORKER_F_RUNNING = 1, /* account as running */ + IO_WORKER_F_FREE = 2, /* worker on free list */ + IO_WORKER_F_BOUND = 3, /* is doing bounded work */ }; enum { @@ -44,7 +44,8 @@ enum { */ struct io_worker { refcount_t ref; - unsigned flags; + int create_index; + unsigned long flags; struct hlist_nulls_node nulls_node; struct list_head all_list; struct task_struct *task; @@ -58,7 +59,6 @@ struct io_worker { unsigned long create_state; struct callback_head create_work; - int create_index; union { struct rcu_head rcu; @@ -165,7 +165,7 @@ static inline struct io_wq_acct *io_work_get_acct(struct io_wq *wq, static inline struct io_wq_acct *io_wq_get_acct(struct io_worker *worker) { - return io_get_acct(worker->wq, worker->flags & IO_WORKER_F_BOUND); + return io_get_acct(worker->wq, test_bit(IO_WORKER_F_BOUND, &worker->flags)); } static void io_worker_ref_put(struct io_wq *wq) @@ -225,7 +225,7 @@ static void io_worker_exit(struct io_worker *worker) wait_for_completion(&worker->ref_done); raw_spin_lock(&wq->lock); - if (worker->flags & IO_WORKER_F_FREE) + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); raw_spin_unlock(&wq->lock); @@ -410,7 +410,7 @@ static void io_wq_dec_running(struct io_worker *worker) struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (!atomic_dec_and_test(&acct->nr_running)) @@ -430,8 +430,8 @@ static void io_wq_dec_running(struct io_worker *worker) */ static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker) { - if (worker->flags & IO_WORKER_F_FREE) { - worker->flags &= ~IO_WORKER_F_FREE; + if (test_bit(IO_WORKER_F_FREE, &worker->flags)) { + clear_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_lock(&wq->lock); hlist_nulls_del_init_rcu(&worker->nulls_node); raw_spin_unlock(&wq->lock); @@ -444,8 +444,8 @@ static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker) static void __io_worker_idle(struct io_wq *wq, struct io_worker *worker) __must_hold(wq->lock) { - if (!(worker->flags & IO_WORKER_F_FREE)) { - worker->flags |= IO_WORKER_F_FREE; + if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) { + set_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); } } @@ -631,7 +631,8 @@ static int io_wq_worker(void *data) bool exit_mask = false, last_timeout = false; char buf[TASK_COMM_LEN]; - worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + set_mask_bits(&worker->flags, 0, + BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); @@ -695,11 +696,11 @@ void io_wq_worker_running(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (worker->flags & IO_WORKER_F_RUNNING) + if (test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags |= IO_WORKER_F_RUNNING; + set_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_inc_running(worker); } @@ -713,12 +714,12 @@ void io_wq_worker_sleeping(struct task_struct *tsk) if (!worker) return; - if (!(worker->flags & IO_WORKER_F_UP)) + if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; - if (!(worker->flags & IO_WORKER_F_RUNNING)) + if (!test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; - worker->flags &= ~IO_WORKER_F_RUNNING; + clear_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_dec_running(worker); } @@ -732,7 +733,7 @@ static void io_init_new_worker(struct io_wq *wq, struct io_worker *worker, raw_spin_lock(&wq->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); list_add_tail_rcu(&worker->all_list, &wq->all_list); - worker->flags |= IO_WORKER_F_FREE; + set_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_unlock(&wq->lock); wake_up_new_task(tsk); } @@ -838,7 +839,7 @@ static bool create_io_worker(struct io_wq *wq, int index) init_completion(&worker->ref_done); if (index == IO_WQ_ACCT_BOUND) - worker->flags |= IO_WORKER_F_BOUND; + set_bit(IO_WORKER_F_BOUND, &worker->flags); tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE); if (!IS_ERR(tsk)) { @@ -924,8 +925,8 @@ static bool io_wq_work_match_item(struct io_wq_work *work, void *data) void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); + unsigned long work_flags = work->flags; struct io_cb_cancel_data match; - unsigned work_flags = work->flags; bool do_create; /* -- 2.39.2

2 1

[PATCH OLK-6.6] netpoll: Fix race condition in netpoll_owner_active
by Zhengchao Shao 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v6.6.36 commit 3f1a155950a1685ffd0fd7175b3f671da8771f3d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR1O CVE: CVE-2024-41005 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit c2e6a872bde9912f1a7579639c5ca3adf1003916 ] KCSAN detected a race condition in netpoll: BUG: KCSAN: data-race in net_rx_action / netpoll_send_skb write (marked) to 0xffff8881164168b0 of 4 bytes by interrupt on cpu 10: net_rx_action (./include/linux/netpoll.h:90 net/core/dev.c:6712 net/core/dev.c:6822) <snip> read to 0xffff8881164168b0 of 4 bytes by task 1 on cpu 2: netpoll_send_skb (net/core/netpoll.c:319 net/core/netpoll.c:345 net/core/netpoll.c:393) netpoll_send_udp (net/core/netpoll.c:?) <snip> value changed: 0x0000000a -> 0xffffffff This happens because netpoll_owner_active() needs to check if the current CPU is the owner of the lock, touching napi->poll_owner non atomically. The ->poll_owner field contains the current CPU holding the lock. Use an atomic read to check if the poll owner is the current CPU. Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240429100437.3487432-1-leitao@debian.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/core/netpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 543007f159f9..55bcacf67df3 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -316,7 +316,7 @@ static int netpoll_owner_active(struct net_device *dev) struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { - if (napi->poll_owner == smp_processor_id()) + if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] usb: host: ohci-tmio: check return value after calling platform_get_resource()
by Zheng Zucheng 16 Jul '24

16 Jul '24

From: Yang Yingliang <yangyingliang(a)huawei.com> stable inclusion from stable-v5.10.82 commit 2474eb7fc3bfbce10f7b8ea431fcffe5dd5f5100 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9FNEW CVE: CVE-2021-47206 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 9eff2b2e59fda25051ab36cd1cb5014661df657b ] It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value. Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Link: https://lore.kernel.org/r/20211011134920.118477-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: drivers/usb/host/ohci-tmio.c [Some contexts different. No functional impact.] Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- drivers/usb/host/ohci-tmio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c index a631dbb369d7..b75f4ce642a2 100644 --- a/drivers/usb/host/ohci-tmio.c +++ b/drivers/usb/host/ohci-tmio.c @@ -196,7 +196,7 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev) if (usb_disabled()) return -ENODEV; - if (!cell) +: if (!cell || !regs || !config || !sram) return -EINVAL; hcd = usb_create_hcd(&ohci_tmio_hc_driver, &dev->dev, dev_name(&dev->dev)); -- 2.34.1

2 1

[PATCH OLK-6.6 0/1] kvm : add coda feature
by l00500167 16 Jul '24

16 Jul '24

From: JunBin Li <lijunbin4(a)huawei.com> virtCCA feature JunBin Li (1): kvm: add coda feature Signed-off-by: JunBin Li <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) -- 2.25.1

2 2

[PATCH OLK-6.6] btrfs: zoned: allocate dummy checksums for zoned NODATASUM writes
by Wang Zhaolong 16 Jul '24

16 Jul '24

From: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> stable inclusion from stable-v6.6.36 commit 082b3d4e788953a3ff42ecdb70c4210149076285 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACR20 CVE: CVE-2024-40962 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit cebae292e0c32a228e8f2219c270a7237be24a6a ] Shin'ichiro reported that when he's running fstests' test-case btrfs/167 on emulated zoned devices, he's seeing the following NULL pointer dereference in 'btrfs_zone_finish_endio()': Oops: general protection fault, probably for non-canonical address 0xdffffc0000000011: 0000 [#1] PREEMPT SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000088-0x000000000000008f] CPU: 4 PID: 2332440 Comm: kworker/u80:15 Tainted: G W 6.10.0-rc2-kts+ #4 Hardware name: Supermicro Super Server/X11SPi-TF, BIOS 3.3 02/21/2020 Workqueue: btrfs-endio-write btrfs_work_helper [btrfs] RIP: 0010:btrfs_zone_finish_endio.part.0+0x34/0x160 [btrfs] RSP: 0018:ffff88867f107a90 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff893e5534 RDX: 0000000000000011 RSI: 0000000000000004 RDI: 0000000000000088 RBP: 0000000000000002 R08: 0000000000000001 R09: ffffed1081696028 R10: ffff88840b4b0143 R11: ffff88834dfff600 R12: ffff88840b4b0000 R13: 0000000000020000 R14: 0000000000000000 R15: ffff888530ad5210 FS: 0000000000000000(0000) GS:ffff888e3f800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f87223fff38 CR3: 00000007a7c6a002 CR4: 00000000007706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> ? __die_body.cold+0x19/0x27 ? die_addr+0x46/0x70 ? exc_general_protection+0x14f/0x250 ? asm_exc_general_protection+0x26/0x30 ? do_raw_read_unlock+0x44/0x70 ? btrfs_zone_finish_endio.part.0+0x34/0x160 [btrfs] btrfs_finish_one_ordered+0x5d9/0x19a0 [btrfs] ? __pfx_lock_release+0x10/0x10 ? do_raw_write_lock+0x90/0x260 ? __pfx_do_raw_write_lock+0x10/0x10 ? __pfx_btrfs_finish_one_ordered+0x10/0x10 [btrfs] ? _raw_write_unlock+0x23/0x40 ? btrfs_finish_ordered_zoned+0x5a9/0x850 [btrfs] ? lock_acquire+0x435/0x500 btrfs_work_helper+0x1b1/0xa70 [btrfs] ? __schedule+0x10a8/0x60b0 ? __pfx___might_resched+0x10/0x10 process_one_work+0x862/0x1410 ? __pfx_lock_acquire+0x10/0x10 ? __pfx_process_one_work+0x10/0x10 ? assign_work+0x16c/0x240 worker_thread+0x5e6/0x1010 ? __pfx_worker_thread+0x10/0x10 kthread+0x2c3/0x3a0 ? trace_irq_enable.constprop.0+0xce/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Enabling CONFIG_BTRFS_ASSERT revealed the following assertion to trigger: assertion failed: !list_empty(&ordered->list), in fs/btrfs/zoned.c:1815 This indicates, that we're missing the checksums list on the ordered_extent. As btrfs/167 is doing a NOCOW write this is to be expected. Further analysis with drgn confirmed the assumption: >>> inode = prog.crashed_thread().stack_trace()[11]['ordered'].inode >>> btrfs_inode = drgn.container_of(inode, "struct btrfs_inode", \ "vfs_inode") >>> print(btrfs_inode.flags) (u32)1 As zoned emulation mode simulates conventional zones on regular devices, we cannot use zone-append for writing. But we're only attaching dummy checksums if we're doing a zone-append write. So for NOCOW zoned data writes on conventional zones, also attach a dummy checksum. Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki(a)wdc.com> Fixes: cbfce4c7fbde ("btrfs: optimize the logical to physical mapping for zoned writes") CC: Naohiro Aota <Naohiro.Aota(a)wdc.com> # 6.6+ Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki(a)wdc.com> Reviewed-by: Naohiro Aota <naohiro.aota(a)wdc.com> Signed-off-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Zhaolong <wangzhaolong1(a)huawei.com> --- fs/btrfs/bio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 12b12443efaa..e47eb248309f 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -705,7 +705,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) ret = btrfs_bio_csum(bbio); if (ret) goto fail_put_bio; - } else if (use_append) { + } else if (use_append || + (btrfs_is_zoned(fs_info) && inode && + inode->flags & BTRFS_INODE_NODATASUM)) { ret = btrfs_alloc_dummy_sum(bbio); if (ret) goto fail_put_bio; -- 2.34.3

2 1

[PATCH OLK-5.10] nilfs2: fix potential kernel bug due to lack of writeback flag waiting
by dinglongwei 16 Jul '24

16 Jul '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v6.1.95 commit 271dcd977ccda8c7a26e360425ae7b4db7d2ecc0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA8AE5 CVE: CVE-2024-37078 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit a4ca369ca221bb7e06c725792ac107f0e48e82e7 upstream. Destructive writes to a block device on which nilfs2 is mounted can cause a kernel bug in the folio/page writeback start routine or writeback end routine (__folio_start_writeback in the log below): kernel BUG at mm/page-writeback.c:3070! Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI ... RIP: 0010:__folio_start_writeback+0xbaa/0x10e0 Code: 25 ff 0f 00 00 0f 84 18 01 00 00 e8 40 ca c6 ff e9 17 f6 ff ff e8 36 ca c6 ff 4c 89 f7 48 c7 c6 80 c0 12 84 e8 e7 b3 0f 00 90 <0f> 0b e8 1f ca c6 ff 4c 89 f7 48 c7 c6 a0 c6 12 84 e8 d0 b3 0f 00 ... Call Trace: <TASK> nilfs_segctor_do_construct+0x4654/0x69d0 [nilfs2] nilfs_segctor_construct+0x181/0x6b0 [nilfs2] nilfs_segctor_thread+0x548/0x11c0 [nilfs2] kthread+0x2f0/0x390 ret_from_fork+0x4b/0x80 ret_from_fork_asm+0x1a/0x30 </TASK> This is because when the log writer starts a writeback for segment summary blocks or a super root block that use the backing device's page cache, it does not wait for the ongoing folio/page writeback, resulting in an inconsistent writeback state. Fix this issue by waiting for ongoing writebacks when putting folios/pages on the backing device into writeback state. Link: https://lkml.kernel.org/r/20240530141556.4411-1-konishi.ryusuke@gmail.com Fixes: 9ff05123e3bf ("nilfs2: segment constructor") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: dinglongwei <dinglongwei1(a)huawei.com> --- fs/nilfs2/segment.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 2eeae67ad298..02407c524382 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1697,6 +1697,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh->b_page != bd_page) { if (bd_page) { lock_page(bd_page); + wait_on_page_writeback(bd_page); clear_page_dirty_for_io(bd_page); set_page_writeback(bd_page); unlock_page(bd_page); @@ -1710,6 +1711,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); + wait_on_page_writeback(bd_page); clear_page_dirty_for_io(bd_page); set_page_writeback(bd_page); unlock_page(bd_page); @@ -1726,6 +1728,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } if (bd_page) { lock_page(bd_page); + wait_on_page_writeback(bd_page); clear_page_dirty_for_io(bd_page); set_page_writeback(bd_page); unlock_page(bd_page); -- 2.17.1

2 1

[PATCH OLK-6.6 0/2] bpf: Fix null-pointer-deref in resolve_prog_type()
by Tengda Wu 16 Jul '24

16 Jul '24

Hi, This patchset is going to fix null-pointer-deref in resolve_prog_type() for BPF_PROG_TYPE_EXT. `prog->aux->dst_prog` in resolve_prog_type() is assigned by `attach_prog_fd`, and would be NULL if `attach_prog_fd` is not provided. Loading EXT prog with bpf_dynptr_from_skb() kfunc call in this way will lead to null-pointer-deref. In last version we fix it by forcing `attach_prog_fd` non-empty at load time, which leads to libbpf_probe_prog_types() api broken. Currently, we fix it by just adding null check for EXT prog in resolve_prog_type() as the old way did. For the sake of safety, we compared the full test logs of selftest before and after applying these changes, and the results show that the two test logs were consistent. Best regards, Tengda Tengda Wu (2): bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT selftests/bpf: Test for null-pointer-deref bugfix in resolve_prog_type() include/linux/bpf_verifier.h | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/1] kvm : add coda feature
by l00500167 16 Jul '24

16 Jul '24

virtCCA feature l00500167 (1): kvm: add coda feature Signed-off-by: l00500167 <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) -- 2.25.1

2 2

[PATCH openEuler-22.03-LTS-SP1 0/3] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock Ritesh Harjani (1): ext4: remove duplicate definition of ext4_xattr_ibody_inline_set() fs/ext4/xattr.h | 6 +- fs/ext4/inline.c | 11 ++- fs/ext4/xattr.c | 175 +++++++++++++++++++---------------------------- 3 files changed, 79 insertions(+), 113 deletions(-) -- 2.39.2

2 4

[PATCH openEuler-22.03-LTS-SP1 0/2] Fix CVE-2023-52781
by Wang Wensheng 16 Jul '24

16 Jul '24

Alan Stern (1): USB: core: Change configuration warnings to notices Niklas Neronin (1): usb: config: fix iteration issue in 'usb_get_bos_descriptor()' drivers/usb/core/config.c | 85 ++++++++++++++++++++------------------- 1 file changed, 43 insertions(+), 42 deletions(-) -- 2.17.1

2 3

[PATCH OLK-6.6 0/2] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 155 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 82 deletions(-) -- 2.39.2

2 3

[PATCH openEuler-1.0-LTS] usb: host: ohci-tmio: check return value after calling platform_get_resource()
by Zheng Zucheng 16 Jul '24

16 Jul '24

From: Yang Yingliang <yangyingliang(a)huawei.com> stable inclusion form stable-v5.10.82 commit 2474eb7fc3bfbce10f7b8ea431fcffe5dd5f5100 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9FNEW CVE: CVE-2021-47206 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 9eff2b2e59fda25051ab36cd1cb5014661df657b ] It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value. Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Link: https://lore.kernel.org/r/20211011134920.118477-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: drivers/usb/host/ohci-tmio.c [Some contexts different. No functional impact.] Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- drivers/usb/host/ohci-tmio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c index a631dbb369d7..b75f4ce642a2 100644 --- a/drivers/usb/host/ohci-tmio.c +++ b/drivers/usb/host/ohci-tmio.c @@ -196,7 +196,7 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev) if (usb_disabled()) return -ENODEV; - if (!cell) +: if (!cell || !regs || !config || !sram) return -EINVAL; hcd = usb_create_hcd(&ohci_tmio_hc_driver, &dev->dev, dev_name(&dev->dev)); -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] bpf: Fix null-pointer-deref in resolve_prog_type()
by Tengda Wu 16 Jul '24

16 Jul '24

Hi, This patchset is going to fix null-pointer-deref in resolve_prog_type() for BPF_PROG_TYPE_EXT. `prog->aux->dst_prog` in resolve_prog_type() is assigned by `attach_prog_fd`, and would be NULL if `attach_prog_fd` is not provided. Loading EXT prog with bpf_dynptr_from_skb() kfunc call in this way will lead to null-pointer-deref. In last version we fix it by forcing `attach_prog_fd` non-empty at load time, which leads to libbpf_probe_prog_types() api broken. Currently, we fix it by just adding null check for EXT prog in resolve_prog_type() as the old way did. For the sake of safety, we compared the full test logs of selftest before and after applying these changes, and the results show that the two test logs were consistent. Best regards, Tengda Tengda Wu (2): bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT selftests/bpf: Test for null-pointer-deref bugfix in resolve_prog_type() include/linux/bpf_verifier.h | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) -- 2.34.1

2 3

[PATCH OLK-5.10] KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin()
by felix 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> mainline inclusion from mainline-v6.10-rc5 commit 49f683b41f28918df3e51ddc0d928cb2e934ccdb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACT6J CVE: CVE-2024-40953 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the loads and stores are atomic. In the extremely unlikely scenario the compiler tears the stores, it's theoretically possible for KVM to attempt to get a vCPU using an out-of-bounds index, e.g. if the write is split into multiple 8-bit stores, and is paired with a 32-bit load on a VM with 257 vCPUs: CPU0 CPU1 last_boosted_vcpu = 0xff; (last_boosted_vcpu = 0x100) last_boosted_vcpu[15:8] = 0x01; i = (last_boosted_vcpu = 0x1ff) last_boosted_vcpu[7:0] = 0x00; vcpu = kvm->vcpu_array[0x1ff]; As detected by KCSAN: BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm] write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x00000012 -> 0x00000000 Fixes: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin") Cc: stable(a)vger.kernel.org Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Conflicts: virt/kvm/kvm_main.c [Fix context because of 46808a4cb89708c2e5b264eb9d1035762581921b not merged] Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- virt/kvm/kvm_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 53c83483653f..2b28fcb35641 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2503,12 +2503,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; int yielded = 0; int try = 3; int pass; int i; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -2538,7 +2539,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin()
by felix 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> mainline inclusion from mainline-v6.10-rc5 commit 49f683b41f28918df3e51ddc0d928cb2e934ccdb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACT6J CVE: CVE-2024-40953 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the loads and stores are atomic. In the extremely unlikely scenario the compiler tears the stores, it's theoretically possible for KVM to attempt to get a vCPU using an out-of-bounds index, e.g. if the write is split into multiple 8-bit stores, and is paired with a 32-bit load on a VM with 257 vCPUs: CPU0 CPU1 last_boosted_vcpu = 0xff; (last_boosted_vcpu = 0x100) last_boosted_vcpu[15:8] = 0x01; i = (last_boosted_vcpu = 0x1ff) last_boosted_vcpu[7:0] = 0x00; vcpu = kvm->vcpu_array[0x1ff]; As detected by KCSAN: BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm] write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x00000012 -> 0x00000000 Fixes: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin") Cc: stable(a)vger.kernel.org Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Conflicts: virt/kvm/kvm_main.c [Fix context because of 46808a4cb89708c2e5b264eb9d1035762581921b not merged] Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- virt/kvm/kvm_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 53c83483653f..2b28fcb35641 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2503,12 +2503,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; int yielded = 0; int try = 3; int pass; int i; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -2538,7 +2539,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] usb: host: ohci-tmio: check return value after calling platform_get_resource()
by Zheng Zucheng 16 Jul '24

16 Jul '24

From: Yang Yingliang <yangyingliang(a)huawei.com> stable inclusion form stable-v5.10.82 commit 2474eb7fc3bfbce10f7b8ea431fcffe5dd5f5100 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9FNEW CVE: CVE-2021-47206 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 9eff2b2e59fda25051ab36cd1cb5014661df657b ] It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value. Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Link: https://lore.kernel.org/r/20211011134920.118477-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Zheng Zucheng <zhengzucheng(a)huawei.com> --- drivers/usb/host/ohci-tmio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c index a631dbb369d7..b75f4ce642a2 100644 --- a/drivers/usb/host/ohci-tmio.c +++ b/drivers/usb/host/ohci-tmio.c @@ -196,7 +196,7 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev) if (usb_disabled()) return -ENODEV; - if (!cell) +: if (!cell || !regs || !config || !sram) return -EINVAL; hcd = usb_create_hcd(&ohci_tmio_hc_driver, &dev->dev, dev_name(&dev->dev)); -- 2.34.1

2 1

openEuler Kernel SIG双周例会
by openEuler conference 16 Jul '24

16 Jul '24

您好！ Kernel 邀请您参加 2024-07-19 14:00 召开的WeLink会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中（新增议题可直接回复本邮件申请，或填报至会议纪要看板）会议链接：https://meeting.huaweicloud.com:36443/#/j/961167952 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 更多资讯尽在：https://www.openeuler.org/zh/ Hello! Kernel invites you to attend the WeLink conference(auto recording) will be held at 2024-07-19 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中（新增议题可直接回复本邮件申请，或填报至会议纪要看板） You can join the meeting at https://meeting.huaweicloud.com:36443/#/j/961167952. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. More information: https://www.openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin()
by felix 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> mainline inclusion from mainline-v6.10-rc5 commit 49f683b41f28918df3e51ddc0d928cb2e934ccdb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACT6J CVE: CVE-2024-40953 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the loads and stores are atomic. In the extremely unlikely scenario the compiler tears the stores, it's theoretically possible for KVM to attempt to get a vCPU using an out-of-bounds index, e.g. if the write is split into multiple 8-bit stores, and is paired with a 32-bit load on a VM with 257 vCPUs: CPU0 CPU1 last_boosted_vcpu = 0xff; (last_boosted_vcpu = 0x100) last_boosted_vcpu[15:8] = 0x01; i = (last_boosted_vcpu = 0x1ff) last_boosted_vcpu[7:0] = 0x00; vcpu = kvm->vcpu_array[0x1ff]; As detected by KCSAN: BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm] write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x00000012 -> 0x00000000 Fixes: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin") Cc: stable(a)vger.kernel.org Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Conflicts: virt/kvm/kvm_main.c [Fix context because of 46808a4cb89708c2e5b264eb9d1035762581921b not merged] Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- virt/kvm/kvm_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 53c83483653f..2b28fcb35641 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2503,12 +2503,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; int yielded = 0; int try = 3; int pass; int i; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -2538,7 +2539,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; -- 2.34.1

2 1

[openeuler:openEuler-1.0-LTS] BUILD SUCCESS WITH WARNING 55dbcf2f32ff417a82aec66a24e6a9ac00bf759c
by kernel test robot 16 Jul '24

16 Jul '24

tree/branch: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS branch HEAD: 55dbcf2f32ff417a82aec66a24e6a9ac00bf759c !9830 mmc: davinci: Don't strip remove function when driver is builtin Warning: (recently discovered and may have been fixed) kernel/livepatch/core.c:75:16: warning: no previous prototype for function 'klp_check_patch_kprobed' [-Wmissing-prototypes] Unverified Warning (likely false positive, please contact us if interested): drivers/block/loop.c:1338 loop_set_status() warn: inconsistent returns '&loop_ctl_mutex'. Warning ids grouped by kconfigs: recent_errors |-- x86_64-randconfig-073-20240521 | `-- kernel-livepatch-core.c:warning:no-previous-prototype-for-function-klp_check_patch_kprobed `-- x86_64-randconfig-161-20240430 `-- drivers-block-loop.c-loop_set_status()-warn:inconsistent-returns-loop_ctl_mutex-. elapsed time: 723m configs tested: 26 configs skipped: 139 tested configs: arm64 allmodconfig gcc-14.1.0 arm64 allnoconfig gcc-14.1.0 arm64 defconfig gcc-14.1.0 arm64 randconfig-001-20240716 gcc-14.1.0 arm64 randconfig-002-20240716 gcc-14.1.0 arm64 randconfig-003-20240716 gcc-14.1.0 arm64 randconfig-004-20240716 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240716 gcc-13 x86_64 buildonly-randconfig-002-20240716 clang-18 x86_64 buildonly-randconfig-003-20240716 clang-18 x86_64 buildonly-randconfig-004-20240716 clang-18 x86_64 buildonly-randconfig-005-20240716 clang-18 x86_64 buildonly-randconfig-006-20240716 clang-18 x86_64 defconfig gcc-13 x86_64 randconfig-001-20240716 gcc-13 x86_64 randconfig-002-20240716 gcc-8 x86_64 randconfig-003-20240716 gcc-8 x86_64 randconfig-004-20240716 clang-18 x86_64 randconfig-005-20240716 gcc-12 x86_64 randconfig-006-20240716 clang-18 x86_64 randconfig-011-20240716 clang-18 x86_64 randconfig-012-20240716 gcc-9 x86_64 randconfig-015-20240716 gcc-7 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-22.03-LTS-SP1 0/3] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock Ritesh Harjani (1): ext4: remove duplicate definition of ext4_xattr_ibody_inline_set() send-patches.sh | 96 ++++++++++++++++++++++++++ fs/ext4/xattr.h | 6 +- fs/ext4/inline.c | 11 ++- fs/ext4/xattr.c | 175 +++++++++++++++++++---------------------------- 4 files changed, 175 insertions(+), 113 deletions(-) create mode 100644 send-patches.sh -- 2.39.2

2 4

[PATCH OLK-6.6] KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin()
by felix 16 Jul '24

16 Jul '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v6.6.36 commit a937ef951bba72f48d2402451419d725d70dba20 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACT6J CVE: CVE-2024-40953 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 49f683b41f28918df3e51ddc0d928cb2e934ccdb upstream. Use {READ,WRITE}_ONCE() to access kvm->last_boosted_vcpu to ensure the loads and stores are atomic. In the extremely unlikely scenario the compiler tears the stores, it's theoretically possible for KVM to attempt to get a vCPU using an out-of-bounds index, e.g. if the write is split into multiple 8-bit stores, and is paired with a 32-bit load on a VM with 257 vCPUs: CPU0 CPU1 last_boosted_vcpu = 0xff; (last_boosted_vcpu = 0x100) last_boosted_vcpu[15:8] = 0x01; i = (last_boosted_vcpu = 0x1ff) last_boosted_vcpu[7:0] = 0x00; vcpu = kvm->vcpu_array[0x1ff]; As detected by KCSAN: BUG: KCSAN: data-race in kvm_vcpu_on_spin [kvm] / kvm_vcpu_on_spin [kvm] write to 0xffffc90025a92344 of 4 bytes by task 4340 on cpu 16: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4112) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffffc90025a92344 of 4 bytes by task 4342 on cpu 4: kvm_vcpu_on_spin (arch/x86/kvm/../../../virt/kvm/kvm_main.c:4069) kvm handle_pause (arch/x86/kvm/vmx/vmx.c:5929) kvm_intel vmx_handle_exit (arch/x86/kvm/vmx/vmx.c:? arch/x86/kvm/vmx/vmx.c:6606) kvm_intel vcpu_run (arch/x86/kvm/x86.c:11107 arch/x86/kvm/x86.c:11211) kvm kvm_arch_vcpu_ioctl_run (arch/x86/kvm/x86.c:?) kvm kvm_vcpu_ioctl (arch/x86/kvm/../../../virt/kvm/kvm_main.c:?) kvm __se_sys_ioctl (fs/ioctl.c:52 fs/ioctl.c:904 fs/ioctl.c:890) __x64_sys_ioctl (fs/ioctl.c:890) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x00000012 -> 0x00000000 Fixes: 217ece6129f2 ("KVM: use yield_to instead of sleep in kvm_vcpu_on_spin") Cc: stable(a)vger.kernel.org Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240510092353.2261824-1-leitao@debian.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- virt/kvm/kvm_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5877ba2f0056..62f19b4b9605 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3788,12 +3788,13 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; - int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; + last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not @@ -3824,7 +3825,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { - kvm->last_boosted_vcpu = i; + WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; -- 2.34.1

2 1

[PATCH OLK-6.6 0/3] CVE-2024-39503
by Liu Jian 16 Jul '24

16 Jul '24

CVE-2024-39503 Alexander Maltsev (1): netfilter: ipset: Add list flush to cancel_gc Jozsef Kadlecsik (2): netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type netfilter: ipset: Fix suspicious rcu_dereference_protected() net/netfilter/ipset/ip_set_core.c | 92 +++++++++++++++------------ net/netfilter/ipset/ip_set_list_set.c | 33 +++++----- 2 files changed, 69 insertions(+), 56 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/2] bpf: Fix null-pointer-deref in resolve_prog_type()
by Tengda Wu 16 Jul '24

16 Jul '24

From: Tengda Wu <wutengda(a)huaweicloud.com> Hi, This patchset is going to fix null-pointer-deref in resolve_prog_type() for BPF_PROG_TYPE_EXT. `prog->aux->dst_prog` in resolve_prog_type() is assigned by `attach_prog_fd`, and would be NULL if `attach_prog_fd` is not provided. Loading EXT prog with bpf_dynptr_from_skb() kfunc call in this way will lead to null-pointer-deref. In last version we fix it by forcing `attach_prog_fd` non-empty at load time, which leads to libbpf_probe_prog_types() api broken. Currently, we fix it by just adding null check for EXT prog in resolve_prog_type() as the old way did. For the sake of safety, we compared the full test logs of selftest before and after applying these changes, and the results show that the two test logs were consistent. Best regards, Tengda Change list: v4: - Fix by add null check in resolve_prog_type() which can avoid libbpf_probe_prog_types api breaking. v3: - Add a small selftest for the BPF CI, and split 1-patch into 3-patch series as recommended by Daniel. https://lore.kernel.org/all/d16b4f29-8966-464f-b530-35e39fda3f46@huaweiclou… v2: - Fix libbpf_probe_prog_types test failure reported by CI by adapting libbpf code. (thanks for jirka's reminder) v1: https://lore.kernel.org/all/20240620060701.1465291-1-wutengda@huaweicloud.c… Tengda Wu (2): bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT selftests/bpf: Test for null-pointer-deref bugfix in resolve_prog_type() include/linux/bpf_verifier.h | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) -- 2.34.1

1 0

[PATCH openEuler-22.03-LTS-SP1 v2] netfilter: nft_set_pipapo: do not free live element
by Wei Li 16 Jul '24

16 Jul '24

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v6.9-rc5 commit 3cfc9ec039af60dbd8965ae085b2c2ccdcfbe1cc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9JFG2 CVE: CVE-2024-26924 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?i… -------------------------------- Pablo reports a crash with large batches of elements with a back-to-back add/remove pattern. Quoting Pablo: add_elem("00000000") timeout 100 ms ... add_elem("0000000X") timeout 100 ms del_elem("0000000X") <---------------- delete one that was just added ... add_elem("00005000") timeout 100 ms 1) nft_pipapo_remove() removes element 0000000X Then, KASAN shows a splat. Looking at the remove function there is a chance that we will drop a rule that maps to a non-deactivated element. Removal happens in two steps, first we do a lookup for key k and return the to-be-removed element and mark it as inactive in the next generation. Then, in a second step, the element gets removed from the set/map. The _remove function does not work correctly if we have more than one element that share the same key. This can happen if we insert an element into a set when the set already holds an element with same key, but the element mapping to the existing key has timed out or is not active in the next generation. In such case its possible that removal will unmap the wrong element. If this happens, we will leak the non-deactivated element, it becomes unreachable. The element that got deactivated (and will be freed later) will remain reachable in the set data structure, this can result in a crash when such an element is retrieved during lookup (stale pointer). Add a check that the fully matching key does in fact map to the element that we have marked as inactive in the deactivation step. If not, we need to continue searching. Add a bug/warn trap at the end of the function as well, the remove function must not ever be called with an invisible/unreachable/non-existent element. v2: avoid uneeded temporary variable (Stefano) Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Reported-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Reviewed-by: Stefano Brivio <sbrivio(a)redhat.com> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nft_set_pipapo.c [lw: fix context conflict due to lack of commit f8bf7706151a ("netfilter: nf_tables: integrate pipapo into commit protocol")] Signed-off-by: Wei Li <liwei391(a)huawei.com> --- net/netfilter/nft_set_pipapo.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9ca18f4c4eaf7..9b9505f31733f 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1932,6 +1932,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1944,17 +1946,19 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - pipapo_commit(set); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + pipapo_commit(set); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** -- 2.25.1

2 1

[PATCH OLK-5.10 0/2] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 154 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 81 deletions(-) -- 2.39.2

2 3

[PATCH OLK-6.6 0/2] CVE-2024-40955
by Yifan Qiao 16 Jul '24

16 Jul '24

Baokun Li (2): ext4: avoid overflow when setting values via sysfs ext4: fix slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists() fs/ext4/mballoc.c | 4 ++++ fs/ext4/sysfs.c | 26 ++++++++++++++++++++------ 2 files changed, 24 insertions(+), 6 deletions(-) -- 2.39.2

2 3

[PATCH OLK-5.10 0/2] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 154 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 81 deletions(-) -- 2.39.2

2 3

[PATCH OLK-6.6 0/2] CVE-2024-40955
by Yifan Qiao 16 Jul '24

16 Jul '24

Baokun Li (2): ext4: avoid overflow when setting values via sysfs ext4: fix slab-out-of-bounds in ext4_mb_find_good_group_avg_frag_lists() fs/ext4/mballoc.c | 4 ++++ fs/ext4/sysfs.c | 26 ++++++++++++++++++++------ 2 files changed, 24 insertions(+), 6 deletions(-) -- 2.39.2

2 3

[openeuler:OLK-5.10] BUILD SUCCESS 9bb937dc2a0a27c10c505388c7a3665f5e5f23d2
by kernel test robot 16 Jul '24

16 Jul '24

tree/branch: https://gitee.com/openeuler/kernel.git OLK-5.10 branch HEAD: 9bb937dc2a0a27c10c505388c7a3665f5e5f23d2 !9871 cifs: Fix deadlock in cifs_writepages during reconnect elapsed time: 725m configs tested: 35 configs skipped: 139 The following configs have been built successfully. More configs may be tested in the coming days. tested configs: arm64 allmodconfig clang-19 arm64 allnoconfig gcc-14.1.0 arm64 defconfig gcc-14.1.0 arm64 randconfig-001-20240716 gcc-14.1.0 arm64 randconfig-002-20240716 clang-19 arm64 randconfig-003-20240716 gcc-14.1.0 arm64 randconfig-004-20240716 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240716 gcc-13 x86_64 buildonly-randconfig-002-20240716 clang-18 x86_64 buildonly-randconfig-003-20240716 clang-18 x86_64 buildonly-randconfig-004-20240716 clang-18 x86_64 buildonly-randconfig-005-20240716 clang-18 x86_64 buildonly-randconfig-006-20240716 clang-18 x86_64 defconfig gcc-13 x86_64 randconfig-001-20240716 gcc-13 x86_64 randconfig-002-20240716 gcc-8 x86_64 randconfig-003-20240716 gcc-8 x86_64 randconfig-004-20240716 clang-18 x86_64 randconfig-005-20240716 gcc-12 x86_64 randconfig-006-20240716 clang-18 x86_64 randconfig-011-20240716 clang-18 x86_64 randconfig-012-20240716 gcc-9 x86_64 randconfig-013-20240716 gcc-13 x86_64 randconfig-014-20240716 gcc-13 x86_64 randconfig-015-20240716 gcc-7 x86_64 randconfig-016-20240716 clang-18 x86_64 randconfig-071-20240716 clang-18 x86_64 randconfig-072-20240716 clang-18 x86_64 randconfig-073-20240716 clang-18 x86_64 randconfig-074-20240716 clang-18 x86_64 randconfig-075-20240716 clang-18 x86_64 randconfig-076-20240716 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] Bluetooth: qca: fix info leak when fetching board id
by felix 16 Jul '24

16 Jul '24

From: Johan Hovold <johan+linaro(a)kernel.org> stable inclusion from stable-v6.6.31 commit ba307abed5e09759845c735ba036f8c12f55b209 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TN2K CVE: CVE-2024-36033 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0adcf6be1445ed50bfd4a451a7a782568f270197 upstream. Add the missing sanity check when fetching the board id to avoid leaking slab data when later requesting the firmware. Fixes: a7f8dedb4be2 ("Bluetooth: qca: add support for QCA2066") Cc: stable(a)vger.kernel.org # 6.7 Cc: Tim Jiang <quic_tjiang(a)quicinc.com> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- drivers/bluetooth/btqca.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 35fb26cbf229..47ea1e909476 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -259,6 +259,11 @@ static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) goto out; } + if (skb->len < 3) { + err = -EILSEQ; + goto out; + } + *bid = (edl->data[1] << 8) + edl->data[2]; bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); -- 2.34.1

2 1

[PATCH OLK-6.6] Bluetooth: qca: fix info leak when fetching board id
by felix 16 Jul '24

16 Jul '24

From: Johan Hovold <johan+linaro(a)kernel.org> stable inclusion from stable-v6.6.31 commit ba307abed5e09759845c735ba036f8c12f55b209 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9TN2K CVE: CVE-2024-36033 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0adcf6be1445ed50bfd4a451a7a782568f270197 upstream. Add the missing sanity check when fetching the board id to avoid leaking slab data when later requesting the firmware. Fixes: a7f8dedb4be2 ("Bluetooth: qca: add support for QCA2066") Cc: stable(a)vger.kernel.org # 6.7 Cc: Tim Jiang <quic_tjiang(a)quicinc.com> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Felix Fu <fuzhen5(a)huawei.com> --- drivers/bluetooth/btqca.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 35fb26cbf229..47ea1e909476 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -259,6 +259,11 @@ static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) goto out; } + if (skb->len < 3) { + err = -EILSEQ; + goto out; + } + *bid = (edl->data[1] << 8) + edl->data[2]; bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); -- 2.34.1

2 2

[PATCH OLK-5.10 0/2] CVE-2024-40972
by Yifan Qiao 16 Jul '24

16 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 154 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 81 deletions(-) -- 2.39.2

2 3

[PATCH OLK-6.6] iommu/arm-smmu-v3: Change the style to identify the the hisi_platform
by Zhang Zekun 16 Jul '24

16 Jul '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IACKUP ---------------------------------------------- The code is isolated by CONFIG_ARCH_HISI which could also be opened in other platforms . Change the style to identify the hisi platform to minimize the code influence scope. Fixes: 0b84ef37d4f8 ("iommu/arm-smmu-v3: Enable iotlb_sync_map according to SMMU_IIDR") Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 22 +++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 87f9bed391ec..16217647fd67 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -141,6 +141,7 @@ struct arm_smmu_ctx_desc quiet_cd = { 0 }; static struct arm_smmu_option_prop arm_smmu_options[] = { { ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" }, { ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"}, + { ARM_SMMU_OPT_SYNC_MAP, "hisilicon,broken-prefetch-pgtbl"}, { 0, NULL}, }; @@ -4493,6 +4494,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) } #ifdef CONFIG_ACPI +static struct acpi_platform_list arm_smmu_v3_plat_info[] __initdata = { + /* HiSilicon Hip09 Platform */ + {"HISI ", "HIP09 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, + {"HISI ", "HIP10 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, + {"HISI ", "HIP11 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162100602", 0}, + { } +}; + +static void acpi_get_hisi_options(struct arm_smmu_device *smmu) +{ + if (acpi_match_platform_list(arm_smmu_v3_plat_info) < 0) + return; + + smmu->options |= ARM_SMMU_OPT_SYNC_MAP; +} + static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu) { switch (model) { @@ -4504,6 +4524,8 @@ static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu) break; } + acpi_get_hisi_options(smmu); + dev_notice(smmu->dev, "option mask 0x%x\n", smmu->options); } -- 2.17.1

2 1

[PATCH OLK-6.6 0/1] kvm : add coda feature
by l00500167 16 Jul '24

16 Jul '24

virtCCA feature l00500167 (1): kvm: add coda feature Signed-off-by: l00500167 <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) -- 2.25.1

2 2

[PATCH OLK-6.6 0/1] kvm : add coda feature
by l00500167 16 Jul '24

16 Jul '24

virtCCA feature l00500167 (1): kvm: add coda feature Signed-off-by: l00500167 <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ include/linux/iommu.h | 10 ++++++++++ 2 files changed, 24 insertions(+) -- 2.25.1

2 2

[openeuler:OLK-6.6] BUILD SUCCESS 46ad6f1c27febfee76dfe034d20c531348ebb487
by kernel test robot 16 Jul '24

16 Jul '24

tree/branch: https://gitee.com/openeuler/kernel.git OLK-6.6 branch HEAD: 46ad6f1c27febfee76dfe034d20c531348ebb487 !9899 ionic: fix use after netif_napi_del() Warning ids grouped by kconfigs: recent_errors |-- arm64-allmodconfig | `-- clang:warning:no-such-include-directory:drivers-infiniband-hw-hiroce3-include-mag |-- arm64-defconfig | `-- drivers-char-virtio_console.c:warning:u-directive-output-may-be-truncated-writing-between-and-bytes-into-a-region-of-size-between-and |-- loongarch-allmodconfig | `-- arch-loongarch-kvm-..-..-..-virt-kvm-kvm_main.c:warning:kvmalloc_array-sizes-specified-with-sizeof-in-the-earlier-argument-and-not-in-the-later-argument |-- loongarch-defconfig | |-- arch-loongarch-kvm-..-..-..-virt-kvm-kvm_main.c:warning:kvmalloc_array-sizes-specified-with-sizeof-in-the-earlier-argument-and-not-in-the-later-argument | `-- drivers-char-virtio_console.c:warning:u-directive-output-may-be-truncated-writing-between-and-bytes-into-a-region-of-size-between-and |-- loongarch-randconfig-001-20240715 | |-- arch-loongarch-kvm-..-..-..-virt-kvm-kvm_main.c:warning:kvmalloc_array-sizes-specified-with-sizeof-in-the-earlier-argument-and-not-in-the-later-argument | `-- drivers-char-virtio_console.c:warning:u-directive-output-may-be-truncated-writing-between-and-bytes-into-a-region-of-size-between-and `-- x86_64-allyesconfig `-- drivers-gpu-drm-amd-amdgpu-..-amdkfd-kfd_topology.c:warning:stack-frame-size-()-exceeds-limit-()-in-kfd_topology_add_device elapsed time: 720m configs tested: 40 configs skipped: 134 The following configs have been built successfully. More configs may be tested in the coming days. tested configs: arm64 allmodconfig clang-19 arm64 allnoconfig gcc-14.1.0 arm64 defconfig gcc-14.1.0 arm64 randconfig-001-20240715 clang-19 arm64 randconfig-002-20240715 clang-19 arm64 randconfig-003-20240715 clang-19 arm64 randconfig-004-20240715 clang-19 loongarch allmodconfig gcc-14.1.0 loongarch allnoconfig gcc-14.1.0 loongarch defconfig gcc-14.1.0 loongarch randconfig-001-20240715 gcc-14.1.0 loongarch randconfig-002-20240715 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240715 clang-18 x86_64 buildonly-randconfig-002-20240715 gcc-13 x86_64 buildonly-randconfig-003-20240715 clang-18 x86_64 buildonly-randconfig-004-20240715 gcc-13 x86_64 buildonly-randconfig-005-20240715 gcc-13 x86_64 buildonly-randconfig-006-20240715 gcc-8 x86_64 defconfig gcc-13 x86_64 randconfig-001-20240715 gcc-9 x86_64 randconfig-002-20240715 gcc-7 x86_64 randconfig-003-20240715 clang-18 x86_64 randconfig-004-20240715 clang-18 x86_64 randconfig-005-20240715 gcc-11 x86_64 randconfig-006-20240715 clang-18 x86_64 randconfig-011-20240715 gcc-12 x86_64 randconfig-012-20240715 clang-18 x86_64 randconfig-013-20240715 clang-18 x86_64 randconfig-014-20240715 gcc-12 x86_64 randconfig-015-20240715 gcc-10 x86_64 randconfig-016-20240715 gcc-10 x86_64 randconfig-071-20240715 gcc-13 x86_64 randconfig-072-20240715 gcc-13 x86_64 randconfig-073-20240715 gcc-13 x86_64 randconfig-074-20240715 gcc-12 x86_64 randconfig-075-20240715 clang-18 x86_64 randconfig-076-20240715 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6 0/1] kvm: add coda feature
by l00500167 16 Jul '24

16 Jul '24

virtCCA feature l00500167 (1): kvm: add coda feature Signed-off-by: l00500167 <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ include/linux/iommu.h | 9 +++++++++ 2 files changed, 23 insertions(+) -- 2.25.1

2 2

[PATCH OLK-6.6] parisc: Try to fix random segmentation faults in package builds
by Tengda Wu 16 Jul '24

16 Jul '24

From: John David Anglin <dave(a)parisc-linux.org> stable inclusion from stable-v6.6.35 commit 5bf196f1936bf93df31112fbdfb78c03537c07b0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAD05C CVE: CVE-2024-40918 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 72d95924ee35c8cd16ef52f912483ee938a34d49 upstream. PA-RISC systems with PA8800 and PA8900 processors have had problems with random segmentation faults for many years. Systems with earlier processors are much more stable. Systems with PA8800 and PA8900 processors have a large L2 cache which needs per page flushing for decent performance when a large range is flushed. The combined cache in these systems is also more sensitive to non-equivalent aliases than the caches in earlier systems. The majority of random segmentation faults that I have looked at appear to be memory corruption in memory allocated using mmap and malloc. My first attempt at fixing the random faults didn't work. On reviewing the cache code, I realized that there were two issues which the existing code didn't handle correctly. Both relate to cache move-in. Another issue is that the present bit in PTEs is racy. 1) PA-RISC caches have a mind of their own and they can speculatively load data and instructions for a page as long as there is a entry in the TLB for the page which allows move-in. TLBs are local to each CPU. Thus, the TLB entry for a page must be purged before flushing the page. This is particularly important on SMP systems. In some of the flush routines, the flush routine would be called and then the TLB entry would be purged. This was because the flush routine needed the TLB entry to do the flush. 2) My initial approach to trying the fix the random faults was to try and use flush_cache_page_if_present for all flush operations. This actually made things worse and led to a couple of hardware lockups. It finally dawned on me that some lines weren't being flushed because the pte check code was racy. This resulted in random inequivalent mappings to physical pages. The __flush_cache_page tmpalias flush sets up its own TLB entry and it doesn't need the existing TLB entry. As long as we can find the pte pointer for the vm page, we can get the pfn and physical address of the page. We can also purge the TLB entry for the page before doing the flush. Further, __flush_cache_page uses a special TLB entry that inhibits cache move-in. When switching page mappings, we need to ensure that lines are removed from the cache. It is not sufficient to just flush the lines to memory as they may come back. This made it clear that we needed to implement all the required flush operations using tmpalias routines. This includes flushes for user and kernel pages. After modifying the code to use tmpalias flushes, it became clear that the random segmentation faults were not fully resolved. The frequency of faults was worse on systems with a 64 MB L2 (PA8900) and systems with more CPUs (rp4440). The warning that I added to flush_cache_page_if_present to detect pages that couldn't be flushed triggered frequently on some systems. Helge and I looked at the pages that couldn't be flushed and found that the PTE was either cleared or for a swap page. Ignoring pages that were swapped out seemed okay but pages with cleared PTEs seemed problematic. I looked at routines related to pte_clear and noticed ptep_clear_flush. The default implementation just flushes the TLB entry. However, it was obvious that on parisc we need to flush the cache page as well. If we don't flush the cache page, stale lines will be left in the cache and cause random corruption. Once a PTE is cleared, there is no way to find the physical address associated with the PTE and flush the associated page at a later time. I implemented an updated change with a parisc specific version of ptep_clear_flush. It fixed the random data corruption on Helge's rp4440 and rp3440, as well as on my c8000. At this point, I realized that I could restore the code where we only flush in flush_cache_page_if_present if the page has been accessed. However, for this, we also need to flush the cache when the accessed bit is cleared in ptep_clear_flush_young to keep things synchronized. The default implementation only flushes the TLB entry. Other changes in this version are: 1) Implement parisc specific version of ptep_get. It's identical to default but needed in arch/parisc/include/asm/pgtable.h. 2) Revise parisc implementation of ptep_test_and_clear_young to use ptep_get (READ_ONCE). 3) Drop parisc implementation of ptep_get_and_clear. We can use default. 4) Revise flush_kernel_vmap_range and invalidate_kernel_vmap_range to use full data cache flush. 5) Move flush_cache_vmap and flush_cache_vunmap to cache.c. Handle VM_IOREMAP case in flush_cache_vmap. At this time, I don't know whether it is better to always flush when the PTE present bit is set or when both the accessed and present bits are set. The later saves flushing pages that haven't been accessed, but we need to flush in ptep_clear_flush_young. It also needs a page table lookup to find the PTE pointer. The lpa instruction only needs a page table lookup when the PTE entry isn't in the TLB. We don't atomically handle setting and clearing the _PAGE_ACCESSED bit. If we miss an update, we may miss a flush and the cache may get corrupted. Whether the current code is effectively atomic depends on process control. When CONFIG_FLUSH_PAGE_ACCESSED is set to zero, the page will eventually be flushed when the PTE is cleared or in flush_cache_page_if_present. The _PAGE_ACCESSED bit is not used, so the problem is avoided. The flush method can be selected using the CONFIG_FLUSH_PAGE_ACCESSED define in cache.c. The default is 0. I didn't see a large difference in performance. Signed-off-by: John David Anglin <dave.anglin(a)bell.net> Cc: <stable(a)vger.kernel.org> # v6.6+ Signed-off-by: Helge Deller <deller(a)gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Tengda Wu <wutengda2(a)huawei.com> --- arch/parisc/include/asm/cacheflush.h | 15 +- arch/parisc/include/asm/pgtable.h | 27 +- arch/parisc/kernel/cache.c | 413 +++++++++++++++++---------- 3 files changed, 275 insertions(+), 180 deletions(-) diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index ba4c05bc24d6..8394718870e1 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,18 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); #define flush_cache_vmap_early(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd..babf65751e81 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 393822f16727..f7953b0391cf 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/syscalls.h> +#include <linux/vmalloc.h> #include <asm/pdc.h> #include <asm/cache.h> #include <asm/cacheflush.h> @@ -31,20 +32,31 @@ #include <asm/mmu_context.h> #include <asm/cachectl.h> +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -317,6 +329,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -324,46 +348,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -371,13 +393,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -406,6 +431,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -454,50 +514,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -587,35 +620,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -625,7 +651,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -634,16 +660,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -677,32 +704,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -753,21 +758,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -775,34 +778,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -814,15 +916,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); -- 2.34.1

2 1

[PATCH OLK-6.6 0/1] kvm: add coda feature
by l00500167 15 Jul '24

15 Jul '24

virtCCA feature l00500167 (1): kvm: add coda feature Signed-off-by: l00500167 <lijunbin4(a)huawei.com> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 14 ++++++++++++++ include/linux/iommu.h | 9 +++++++++ 2 files changed, 23 insertions(+) -- 2.25.1

2 2

[PATCH OLK-5.10 0/2] CVE-2024-40972
by Yifan Qiao 15 Jul '24

15 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 154 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 81 deletions(-) -- 2.39.2

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] CVE-2024-40972
by Yifan Qiao 15 Jul '24

15 Jul '24

Jan Kara (2): ext4: fold quota accounting into ext4_xattr_inode_lookup_create() ext4: do not create EA inode under buffer lock fs/ext4/xattr.c | 154 +++++++++++++++++++++++------------------------- 1 file changed, 73 insertions(+), 81 deletions(-) -- 2.39.2

2 3

2024

2023

2022

2021

2020

2019

Kernel