From: Yufeng Mo moyufeng@huawei.com

mainline inclusion from mainline-v5.15-rc2 commit 1dc839ec09d3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

Currently, affinity_mask is set to a single cpu. As a result, irqbalance becomes invalid in SUBSET or EXACT mode. To solve this problem, change affinity_mask to numa node range. In this way, irqbalance can be performed on the cpu of the numa node.

Fixes: 0812545487ec ("net: hns3: add interrupt affinity support for misc interrupt") Signed-off-by: Yufeng Mo moyufeng@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Reviewed-by: Yongxin Li liyongxin1@huawei.com Signed-off-by: Junxin Chen chenjunxin1@huawei.com --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e55ba2e511b1..aed97c934bfb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1528,9 +1528,10 @@ static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev) static int hclge_configure(struct hclge_dev *hdev) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + const struct cpumask *cpumask = cpu_online_mask; struct hclge_cfg cfg; unsigned int i; - int ret; + int node, ret;

ret = hclge_get_cfg(hdev, &cfg); if (ret) @@ -1595,11 +1596,12 @@ static int hclge_configure(struct hclge_dev *hdev)

hclge_init_kdump_kernel_config(hdev);

- /* Set the init affinity based on pci func number */ - i = cpumask_weight(cpumask_of_node(dev_to_node(&hdev->pdev->dev))); - i = i ? PCI_FUNC(hdev->pdev->devfn) % i : 0; - cpumask_set_cpu(cpumask_local_spread(i, dev_to_node(&hdev->pdev->dev)), - &hdev->affinity_mask); + /* Set the affinity based on numa node */ + node = dev_to_node(&hdev->pdev->dev); + if (node != NUMA_NO_NODE) + cpumask = cpumask_of_node(node); + + cpumask_copy(&hdev->affinity_mask, cpumask);

return ret; }

From: Jiaran Zhang zhangjiaran@huawei.com

mainline inclusion from mainline-v5.15-rc2 commit 472430a7b066 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

When the command for querying imp info is issued to the firmware, if the firmware does not support the command, the returned value of bd num is 0. Add protection mechanism before alloc memory to prevent apply for 0-length memory.

Fixes: 0b198b0d80ea ("net: hns3: refactor dump m7 info of debugfs") Signed-off-by: Jiaran Zhang zhangjiaran@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Reviewed-by: Yongxin Li liyongxin1@huawei.com Signed-off-by: Junxin Chen chenjunxin1@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 68ed1715ac52..87d96f82c318 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -1724,6 +1724,10 @@ hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len) }

bd_num = le32_to_cpu(req->bd_num); + if (!bd_num) { + dev_err(&hdev->pdev->dev, "imp statistics bd number is 0!\n"); + return -EINVAL; + }

desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); if (!desc_src)

From: Jian Shen shenjian15@huawei.com

mainline inclusion from mainline-v5.15-rc3 commit e184cec5e29d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

When user change rss 'hfunc' without set rss 'hkey' by ethtool -X command, the driver will ignore the 'hfunc' for the hkey is NULL. It's unreasonable. So fix it.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Fixes: 374ad291762a ("net: hns3: Add RSS general configuration support for VF") Signed-off-by: Jian Shen shenjian15@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Reviewed-by: Yongxin Li liyongxin1@huawei.com Signed-off-by: Junxin Chen chenjunxin1@huawei.com --- .../hisilicon/hns3/hns3pf/hclge_main.c | 45 ++++++++++------ .../hisilicon/hns3/hns3vf/hclgevf_main.c | 52 ++++++++++++------- 2 files changed, 64 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f1e46ba799f9..36c8741445e8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -4741,6 +4741,24 @@ static int hclge_get_rss(struct hnae3_handle *handle, u32 *indir, return 0; }

+static int hclge_parse_rss_hfunc(struct hclge_vport *vport, const u8 hfunc, + u8 *hash_algo) +{ + switch (hfunc) { + case ETH_RSS_HASH_TOP: + *hash_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; + return 0; + case ETH_RSS_HASH_XOR: + *hash_algo = HCLGE_RSS_HASH_ALGO_SIMPLE; + return 0; + case ETH_RSS_HASH_NO_CHANGE: + *hash_algo = vport->rss_algo; + return 0; + default: + return -EINVAL; + } +} + static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc) { @@ -4750,30 +4768,27 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, u8 hash_algo; int ret, i;

+ ret = hclge_parse_rss_hfunc(vport, hfunc, &hash_algo); + if (ret) { + dev_err(&hdev->pdev->dev, "invalid hfunc type %u\n", hfunc); + return ret; + } + /* Set the RSS Hash Key if specififed by the user */ if (key) { - switch (hfunc) { - case ETH_RSS_HASH_TOP: - hash_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; - break; - case ETH_RSS_HASH_XOR: - hash_algo = HCLGE_RSS_HASH_ALGO_SIMPLE; - break; - case ETH_RSS_HASH_NO_CHANGE: - hash_algo = vport->rss_algo; - break; - default: - return -EINVAL; - } - ret = hclge_set_rss_algo_key(hdev, hash_algo, key); if (ret) return ret;

/* Update the shadow RSS key with user specified qids */ memcpy(vport->rss_hash_key, key, HCLGE_RSS_KEY_SIZE); - vport->rss_algo = hash_algo; + } else { + ret = hclge_set_rss_algo_key(hdev, hash_algo, + vport->rss_hash_key); + if (ret) + return ret; } + vport->rss_algo = hash_algo;

/* Update the shadow RSS table with user specified qids */ for (i = 0; i < ae_dev->dev_specs.rss_ind_tbl_size; i++) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a69e892277b3..5fdac8685f95 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -816,40 +816,56 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key, return 0; }

+static int hclgevf_parse_rss_hfunc(struct hclgevf_dev *hdev, const u8 hfunc, + u8 *hash_algo) +{ + switch (hfunc) { + case ETH_RSS_HASH_TOP: + *hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ; + return 0; + case ETH_RSS_HASH_XOR: + *hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE; + return 0; + case ETH_RSS_HASH_NO_CHANGE: + *hash_algo = hdev->rss_cfg.hash_algo; + return 0; + default: + return -EINVAL; + } +} + static int hclgevf_set_rss(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg; + u8 hash_algo; int ret, i;

if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) { + ret = hclgevf_parse_rss_hfunc(hdev, hfunc, &hash_algo); + if (ret) + return ret; + /* Set the RSS Hash Key if specififed by the user */ if (key) { - switch (hfunc) { - case ETH_RSS_HASH_TOP: - rss_cfg->hash_algo = - HCLGEVF_RSS_HASH_ALGO_TOEPLITZ; - break; - case ETH_RSS_HASH_XOR: - rss_cfg->hash_algo = - HCLGEVF_RSS_HASH_ALGO_SIMPLE; - break; - case ETH_RSS_HASH_NO_CHANGE: - break; - default: - return -EINVAL; - } - - ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo, - key); - if (ret) + ret = hclgevf_set_rss_algo_key(hdev, hash_algo, key); + if (ret) { + dev_err(&hdev->pdev->dev, + "invalid hfunc type %u\n", hfunc); return ret; + }

/* Update the shadow RSS key with user specified qids */ memcpy(rss_cfg->rss_hash_key, key, HCLGEVF_RSS_KEY_SIZE); + } else { + ret = hclgevf_set_rss_algo_key(hdev, hash_algo, + rss_cfg->rss_hash_key); + if (ret) + return ret; } + rss_cfg->hash_algo = hash_algo; }

/* update the shadow RSS table with user specified qids */

From: Jiaran Zhang zhangjiaran@huawei.com

mainline inclusion from mainline-v5.15-rc3 commit 311c0aaa9b4b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

vport_id include PF and VFs, vport_id = 0 means PF, other values mean VFs. So the actual vf id is equal to vport_id minus 1.

Some VF print logs are actually vport, and logs of vf id actually use vport id, so this patch fixes them.

Fixes: ac887be5b0fe ("net: hns3: change print level of RAS error log from warning to error") Fixes: adcf738b804b ("net: hns3: cleanup some print format warning") Signed-off-by: Jiaran Zhang zhangjiaran@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Reviewed-by: Yongxin Li liyongxin1@huawei.com Signed-off-by: Junxin Chen chenjunxin1@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 8 ++++---- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 10 ++++++---- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 718c16d686fa..bb9b026ae88e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -2445,12 +2445,12 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, return; }

- dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%u), queue_id(%u)\n", + dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vport(%u), queue_id(%u)\n", vf_id, q_id);

if (vf_id) { if (vf_id >= hdev->num_alloc_vport) { - dev_err(dev, "invalid vf id(%u)\n", vf_id); + dev_err(dev, "invalid vport(%u)\n", vf_id); return; }

@@ -2463,8 +2463,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev,

ret = hclge_inform_reset_assert_to_vf(&hdev->vport[vf_id]); if (ret) - dev_err(dev, "inform reset to vf(%u) failed %d!\n", - hdev->vport->vport_id, ret); + dev_err(dev, "inform reset to vport(%u) failed %d!\n", + vf_id, ret); } else { set_bit(HNAE3_FUNC_RESET, reset_requests); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c0f25ea043b0..afc88a41a89c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3661,7 +3661,8 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) if (ret) { dev_err(&hdev->pdev->dev, "set vf(%u) rst failed %d!\n", - vport->vport_id, ret); + vport->vport_id - HCLGE_VF_VPORT_START_NUM, + ret); return ret; }

@@ -3676,7 +3677,8 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) if (ret) dev_warn(&hdev->pdev->dev, "inform reset to vf(%u) failed %d!\n", - vport->vport_id, ret); + vport->vport_id - HCLGE_VF_VPORT_START_NUM, + ret); }

return 0; @@ -11467,11 +11469,11 @@ static void hclge_clear_resetting_state(struct hclge_dev *hdev) struct hclge_vport *vport = &hdev->vport[i]; int ret;

- /* Send cmd to clear VF's FUNC_RST_ING */ + /* Send cmd to clear vport's FUNC_RST_ING */ ret = hclge_set_vf_rst(hdev, vport->vport_id, false); if (ret) dev_warn(&hdev->pdev->dev, - "clear vf(%u) rst failed %d!\n", + "clear vport(%u) rst failed %d!\n", vport->vport_id, ret); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 2ce5302c5956..07aa6ada4fdb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -566,7 +566,7 @@ static int hclge_reset_vf(struct hclge_vport *vport) struct hclge_dev *hdev = vport->back;

dev_warn(&hdev->pdev->dev, "PF received VF reset request from VF %u!", - vport->vport_id); + vport->vport_id - HCLGE_VF_VPORT_START_NUM);

return hclge_func_reset_cmd(hdev, vport->vport_id); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 78d5bf1ea561..44618cc4cca1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -581,7 +581,7 @@ int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "vf%u, qs%u failed to set tx_rate:%d, ret=%d\n", + "vport%u, qs%u failed to set tx_rate:%d, ret=%d\n", vport->vport_id, shap_cfg_cmd->qs_id, max_tx_rate, ret); return ret;

From: liaoguojia liaoguojia@huawei.com

mainline inclusion from mainline-v5.15-rc3 commit ef39d632608e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4CVS3 CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

----------------------------------------------------------------------

The input parameters may not be reliable, so check the vlan id before using it, otherwise may set wrong vlan id into hardware.

Fixes: dc8131d846d4 ("net: hns3: Fix for packet loss due wrong filter config in VLAN tbls") Signed-off-by: liaoguojia liaoguojia@huawei.com Signed-off-by: Guangbin Huang huangguangbin2@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Reviewed-by: Yongxin Li liyongxin1@huawei.com Signed-off-by: Junxin Chen chenjunxin1@huawei.com --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index afc88a41a89c..14e9daf09f8c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9817,6 +9817,9 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, if (is_kill && !vlan_id) return 0;

+ if (vlan_id >= VLAN_N_VID) + return -EINVAL; + ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id); if (ret) { dev_err(&hdev->pdev->dev,

From: Yang Li yang.lee@linux.alibaba.com

mainline inclusion from mainline-v5.13-rc1 commit 1406f0f3440265deec6932fd611549b07ac76e89 category: bugfix bugzilla: 106937 https://gitee.com/openeuler/kernel/issues/I4CZ0S CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-------------------------------------------------------------

In one of the error paths of the for_each_child_of_node() loop, add missing call to of_node_put().

Fix the following coccicheck warning: ./drivers/crypto/nx/nx-common-powernv.c:927:1-23: WARNING: Function "for_each_child_of_node" should have of_node_put() before return around line 936.

Reported-by: Abaci Robot abaci@linux.alibaba.com Signed-off-by: Yang Li yang.lee@linux.alibaba.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Cui GaoSheng cuigaosheng1@huawei.com Reviewed-by: Xiu Jianfeng xiujianfeng@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- drivers/crypto/nx/nx-common-powernv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/nx/nx-common-powernv.c b/drivers/crypto/nx/nx-common-powernv.c index 13c65deda8e9..446f611726df 100644 --- a/drivers/crypto/nx/nx-common-powernv.c +++ b/drivers/crypto/nx/nx-common-powernv.c @@ -932,8 +932,10 @@ static int __init nx_powernv_probe_vas(struct device_node *pn) ret = find_nx_device_tree(dn, chip_id, vasid, NX_CT_GZIP, "ibm,p9-nx-gzip", &ct_gzip);

- if (ret) + if (ret) { + of_node_put(dn); return ret; + } }

if (!ct_842 || !ct_gzip) {

From: "zhangyi (F)" yi.zhang@huawei.com

mainline inclusion from mainline-v5.14 commit 12e0613715e1cf305fffafaf0e89d810d9a85cc0 category: bugfix bugzilla: 172159 https://gitee.com/openeuler/kernel/issues/I4CZ4C CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

block_dump is an old debugging interface, one of it's functions is used to print the information about who write which file on disk. If we enable block_dump through /proc/sys/vm/block_dump and turn on debug log level, we can gather information about write process name, target file name and disk from kernel message. This feature is realized in block_dump___mark_inode_dirty(), it print above information into kernel message directly when marking inode dirty, so it is noisy and can easily trigger log storm. At the same time, get the dentry refcount is also not safe, we found it will lead to deadlock on ext4 file system with data=journal mode.

After tracepoints has been introduced into the kernel, we got a tracepoint in __mark_inode_dirty(), which is a better replacement of block_dump___mark_inode_dirty(). The only downside is that it only trace the inode number and not a file name, but it probably doesn't matter because the original printed file name in block_dump is not accurate in some cases, and we can still find it through the inode number and device id. So this patch delete the dirting inode part of block_dump feature.

Signed-off-by: zhangyi (F) yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20210313030146.2882027-2-yi.zhang@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk

conflicts: fs/fs-writeback.c

Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- fs/fs-writeback.c | 25 ------------------------- 1 file changed, 25 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 90dddb507e4a..0d0f014b09ec 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2196,28 +2196,6 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, return ret; }

-static noinline void block_dump___mark_inode_dirty(struct inode *inode) -{ - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; - - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } -} - /** * __mark_inode_dirty - internal function * @@ -2277,9 +2255,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) (dirtytime && (inode->i_state & I_DIRTY_INODE))) return;

- if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); - spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode;

From: "zhangyi (F)" yi.zhang@huawei.com

mainline inclusion from mainline-v5.14 commit 51fd43e2801054b1321b1d81b91dc37efdff5127 category: bugfix bugzilla: 172159 https://gitee.com/openeuler/kernel/issues/I4CZ4C CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Now block_dump feature is gone, remove all comments in docs.

Signed-off-by: zhangyi (F) yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20210313030146.2882027-4-yi.zhang@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- Documentation/admin-guide/laptops/laptop-mode.rst | 11 ----------- Documentation/admin-guide/sysctl/vm.rst | 8 -------- 2 files changed, 19 deletions(-)

diff --git a/Documentation/admin-guide/laptops/laptop-mode.rst b/Documentation/admin-guide/laptops/laptop-mode.rst index c984c4262f2e..b61cc601d298 100644 --- a/Documentation/admin-guide/laptops/laptop-mode.rst +++ b/Documentation/admin-guide/laptops/laptop-mode.rst @@ -101,17 +101,6 @@ this results in concentration of disk activity in a small time interval which occurs only once every 10 minutes, or whenever the disk is forced to spin up by a cache miss. The disk can then be spun down in the periods of inactivity.

-If you want to find out which process caused the disk to spin up, you can -gather information by setting the flag /proc/sys/vm/block_dump. When this flag -is set, Linux reports all disk read and write operations that take place, and -all block dirtyings done to files. This makes it possible to debug why a disk -needs to spin up, and to increase battery life even more. The output of -block_dump is written to the kernel output, and it can be retrieved using -"dmesg". When you use block_dump and your kernel logging level also includes -kernel debugging messages, you probably want to turn off klogd, otherwise -the output of block_dump will be logged, causing disk activity that is not -normally there. -

Configuration ------------- diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 06027c6a233a..a5fbef4740c2 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -25,7 +25,6 @@ files can be found in mm/swap.c. Currently, these files are in /proc/sys/vm:

- admin_reserve_kbytes -- block_dump - compact_memory - compaction_proactiveness - compact_unevictable_allowed @@ -106,13 +105,6 @@ On x86_64 this is about 128MB. Changing this takes effect whenever an application requests memory.

-block_dump -========== - -block_dump enables block I/O debugging when set to a nonzero value. More -information on block I/O debugging is in Documentation/admin-guide/laptops/laptop-mode.rst. - - compact_memory ==============

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.12-rc1 commit d13c613f136c category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Add a macro cond_yield that branches to a specified label when called if the TIF_NEED_RESCHED flag is set and decreasing the preempt count would make the task preemptible again, resulting in a schedule to occur. This can be used by kernel mode SIMD code that keeps a lot of state in SIMD registers, which would make chunking the input in order to perform the cond_resched() check from C code disproportionately costly.

Signed-off-by: Ard Biesheuvel ardb@kernel.org Link: https://lore.kernel.org/r/20210203113626.220151-2-ardb@kernel.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/include/asm/assembler.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index ddbe6bf00e33..f1838bd93a40 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -745,6 +745,22 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .Lyield_out_@ : .endm

+ /* + * Check whether preempt-disabled code should yield as soon as it + * is able. This is the case if re-enabling preemption a single + * time results in a preempt count of zero, and the TIF_NEED_RESCHED + * flag is set. (Note that the latter is stored negated in the + * top word of the thread_info::preempt_count field) + */ + .macro cond_yield, lbl:req, tmp:req +#ifdef CONFIG_PREEMPTION + get_current_task \tmp + ldr \tmp, [\tmp, #TSK_TI_PREEMPT] + sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET + cbz \tmp, \lbl +#endif + .endm + /* * This macro emits a program property note section identifying * architecture features which require special handling, mainly for

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.12-rc1 commit b2eadbf40e8f category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Instead of calling into kernel_neon_end() and kernel_neon_begin() (and potentially into schedule()) from the assembler code when running in task mode and a reschedule is pending, perform only the preempt count check in assembler, but simply return early in this case, and let the C code deal with the consequences.

This reverts commit d82f37ab5e2426287013eba38b1212e8b71e5be3.

Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/crypto/sha2-ce-core.S | 38 +++++++++++--------------------- arch/arm64/crypto/sha2-ce-glue.c | 22 +++++++++--------- 2 files changed, 25 insertions(+), 35 deletions(-)

diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S index 3f9d0f326987..6cdea7d56059 100644 --- a/arch/arm64/crypto/sha2-ce-core.S +++ b/arch/arm64/crypto/sha2-ce-core.S @@ -76,36 +76,30 @@ */ .text SYM_FUNC_START(sha2_ce_transform) - frame_push 3 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - /* load round constants */ -0: adr_l x8, .Lsha2_rcon + adr_l x8, .Lsha2_rcon ld1 { v0.4s- v3.4s}, [x8], #64 ld1 { v4.4s- v7.4s}, [x8], #64 ld1 { v8.4s-v11.4s}, [x8], #64 ld1 {v12.4s-v15.4s}, [x8]

/* load state */ - ld1 {dgav.4s, dgbv.4s}, [x19] + ld1 {dgav.4s, dgbv.4s}, [x0]

/* load sha256_ce_state::finalize */ ldr_l w4, sha256_ce_offsetof_finalize, x4 - ldr w4, [x19, x4] + ldr w4, [x0, x4]

/* load input */ -1: ld1 {v16.4s-v19.4s}, [x20], #64 - sub w21, w21, #1 +0: ld1 {v16.4s-v19.4s}, [x1], #64 + sub w2, w2, #1

CPU_LE( rev32 v16.16b, v16.16b ) CPU_LE( rev32 v17.16b, v17.16b ) CPU_LE( rev32 v18.16b, v18.16b ) CPU_LE( rev32 v19.16b, v19.16b )

-2: add t0.4s, v16.4s, v0.4s +1: add t0.4s, v16.4s, v0.4s mov dg0v.16b, dgav.16b mov dg1v.16b, dgbv.16b

@@ -134,24 +128,18 @@ CPU_LE( rev32 v19.16b, v19.16b ) add dgbv.4s, dgbv.4s, dg1v.4s

/* handled all input blocks? */ - cbz w21, 3f - - if_will_cond_yield_neon - st1 {dgav.4s, dgbv.4s}, [x19] - do_cond_yield_neon + cbz w2, 2f + cond_yield 3f, x5 b 0b - endif_yield_neon - - b 1b

/* * Final block: add padding and total bit count. * Skip if the input size was not a round multiple of the block size, * the padding is handled by the C code in that case. */ -3: cbz x4, 4f +2: cbz x4, 3f ldr_l w4, sha256_ce_offsetof_count, x4 - ldr x4, [x19, x4] + ldr x4, [x0, x4] movi v17.2d, #0 mov x8, #0x80000000 movi v18.2d, #0 @@ -160,10 +148,10 @@ CPU_LE( rev32 v19.16b, v19.16b ) mov x4, #0 mov v19.d[0], xzr mov v19.d[1], x7 - b 2b + b 1b

/* store new state */ -4: st1 {dgav.4s, dgbv.4s}, [x19] - frame_pop +3: st1 {dgav.4s, dgbv.4s}, [x0] + mov w0, w2 ret SYM_FUNC_END(sha2_ce_transform) diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index ded3a6488f81..c57a6119fefc 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -30,14 +30,22 @@ struct sha256_ce_state { extern const u32 sha256_ce_offsetof_count; extern const u32 sha256_ce_offsetof_finalize;

-asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src, - int blocks); +asmlinkage int sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src, + int blocks);

static void __sha2_ce_transform(struct sha256_state *sst, u8 const *src, int blocks) { - sha2_ce_transform(container_of(sst, struct sha256_ce_state, sst), src, - blocks); + while (blocks) { + int rem; + + kernel_neon_begin(); + rem = sha2_ce_transform(container_of(sst, struct sha256_ce_state, + sst), src, blocks); + kernel_neon_end(); + src += (blocks - rem) * SHA256_BLOCK_SIZE; + blocks = rem; + } }

const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state, @@ -63,9 +71,7 @@ static int sha256_ce_update(struct shash_desc *desc, const u8 *data, __sha256_block_data_order);

sctx->finalize = 0; - kernel_neon_begin(); sha256_base_do_update(desc, data, len, __sha2_ce_transform); - kernel_neon_end();

return 0; } @@ -90,11 +96,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, */ sctx->finalize = finalize;

- kernel_neon_begin(); sha256_base_do_update(desc, data, len, __sha2_ce_transform); if (!finalize) sha256_base_do_finalize(desc, __sha2_ce_transform); - kernel_neon_end(); return sha256_base_finish(desc, out); }

@@ -108,9 +112,7 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out) }

sctx->finalize = 0; - kernel_neon_begin(); sha256_base_do_finalize(desc, __sha2_ce_transform); - kernel_neon_end(); return sha256_base_finish(desc, out); }

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.12-rc1 commit 5f6cb2e61768 category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Instead of calling into kernel_neon_end() and kernel_neon_begin() (and potentially into schedule()) from the assembler code when running in task mode and a reschedule is pending, perform only the preempt count check in assembler, but simply return early in this case, and let the C code deal with the consequences.

This reverts commit 6caf7adc5e458f77f550b6c6ca8effa152d61b4a.

Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/crypto/sha512-ce-core.S | 29 +++++----------- arch/arm64/crypto/sha512-ce-glue.c | 53 +++++++++++++++--------------- 2 files changed, 34 insertions(+), 48 deletions(-)

diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S index cde606c0323e..d6e7f6c95fa6 100644 --- a/arch/arm64/crypto/sha512-ce-core.S +++ b/arch/arm64/crypto/sha512-ce-core.S @@ -107,23 +107,17 @@ */ .text SYM_FUNC_START(sha512_ce_transform) - frame_push 3 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - /* load state */ -0: ld1 {v8.2d-v11.2d}, [x19] + ld1 {v8.2d-v11.2d}, [x0]

/* load first 4 round constants */ adr_l x3, .Lsha512_rcon ld1 {v20.2d-v23.2d}, [x3], #64

/* load input */ -1: ld1 {v12.2d-v15.2d}, [x20], #64 - ld1 {v16.2d-v19.2d}, [x20], #64 - sub w21, w21, #1 +0: ld1 {v12.2d-v15.2d}, [x1], #64 + ld1 {v16.2d-v19.2d}, [x1], #64 + sub w2, w2, #1

CPU_LE( rev64 v12.16b, v12.16b ) CPU_LE( rev64 v13.16b, v13.16b ) @@ -201,19 +195,12 @@ CPU_LE( rev64 v19.16b, v19.16b ) add v10.2d, v10.2d, v2.2d add v11.2d, v11.2d, v3.2d

+ cond_yield 3f, x4 /* handled all input blocks? */ - cbz w21, 3f - - if_will_cond_yield_neon - st1 {v8.2d-v11.2d}, [x19] - do_cond_yield_neon - b 0b - endif_yield_neon - - b 1b + cbnz w2, 0b

/* store new state */ -3: st1 {v8.2d-v11.2d}, [x19] - frame_pop +3: st1 {v8.2d-v11.2d}, [x0] + mov w0, w2 ret SYM_FUNC_END(sha512_ce_transform) diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c index a6b1adf31c56..e62a094a9d52 100644 --- a/arch/arm64/crypto/sha512-ce-glue.c +++ b/arch/arm64/crypto/sha512-ce-glue.c @@ -26,11 +26,25 @@ MODULE_LICENSE("GPL v2"); MODULE_ALIAS_CRYPTO("sha384"); MODULE_ALIAS_CRYPTO("sha512");

-asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src, - int blocks); +asmlinkage int sha512_ce_transform(struct sha512_state *sst, u8 const *src, + int blocks);

asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);

+static void __sha512_ce_transform(struct sha512_state *sst, u8 const *src, + int blocks) +{ + while (blocks) { + int rem; + + kernel_neon_begin(); + rem = sha512_ce_transform(sst, src, blocks); + kernel_neon_end(); + src += (blocks - rem) * SHA512_BLOCK_SIZE; + blocks = rem; + } +} + static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src, int blocks) { @@ -40,45 +54,30 @@ static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src, static int sha512_ce_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - if (!crypto_simd_usable()) - return sha512_base_do_update(desc, data, len, - __sha512_block_data_order); - - kernel_neon_begin(); - sha512_base_do_update(desc, data, len, sha512_ce_transform); - kernel_neon_end(); + sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform + : __sha512_block_data_order;

+ sha512_base_do_update(desc, data, len, fn); return 0; }

static int sha512_ce_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - if (!crypto_simd_usable()) { - if (len) - sha512_base_do_update(desc, data, len, - __sha512_block_data_order); - sha512_base_do_finalize(desc, __sha512_block_data_order); - return sha512_base_finish(desc, out); - } + sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform + : __sha512_block_data_order;

- kernel_neon_begin(); - sha512_base_do_update(desc, data, len, sha512_ce_transform); - sha512_base_do_finalize(desc, sha512_ce_transform); - kernel_neon_end(); + sha512_base_do_update(desc, data, len, fn); + sha512_base_do_finalize(desc, fn); return sha512_base_finish(desc, out); }

static int sha512_ce_final(struct shash_desc *desc, u8 *out) { - if (!crypto_simd_usable()) { - sha512_base_do_finalize(desc, __sha512_block_data_order); - return sha512_base_finish(desc, out); - } + sha512_block_fn *fn = crypto_simd_usable() ? __sha512_ce_transform + : __sha512_block_data_order;

- kernel_neon_begin(); - sha512_base_do_finalize(desc, sha512_ce_transform); - kernel_neon_end(); + sha512_base_do_finalize(desc, fn); return sha512_base_finish(desc, out); }

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.12-rc1 commit f0070f4a7934 category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/crypto/aes-glue.c | 21 +++++++++----- arch/arm64/crypto/aes-modes.S | 52 +++++++++++++---------------------- 2 files changed, 33 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index cafb5b96be0e..3de1dc918ad4 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -103,9 +103,9 @@ asmlinkage void aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[], int rounds, int blocks, u8 iv[], u32 const rk2[]);

-asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds, - int blocks, u8 dg[], int enc_before, - int enc_after); +asmlinkage int aes_mac_update(u8 const in[], u32 const rk[], int rounds, + int blocks, u8 dg[], int enc_before, + int enc_after);

struct crypto_aes_xts_ctx { struct crypto_aes_ctx key1; @@ -852,10 +852,17 @@ static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks, int rounds = 6 + ctx->key_length / 4;

if (crypto_simd_usable()) { - kernel_neon_begin(); - aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before, - enc_after); - kernel_neon_end(); + int rem; + + do { + kernel_neon_begin(); + rem = aes_mac_update(in, ctx->key_enc, rounds, blocks, + dg, enc_before, enc_after); + kernel_neon_end(); + in += (blocks - rem) * AES_BLOCK_SIZE; + blocks = rem; + enc_before = 0; + } while (blocks); } else { if (enc_before) aes_encrypt(ctx, dg, dg); diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index cf618d8f6cec..ab570aa86a5c 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -619,61 +619,47 @@ AES_FUNC_END(aes_xts_decrypt) * int blocks, u8 dg[], int enc_before, int enc_after) */ AES_FUNC_START(aes_mac_update) - frame_push 6 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x6 - - ld1 {v0.16b}, [x23] /* get dg */ + ld1 {v0.16b}, [x4] /* get dg */ enc_prepare w2, x1, x7 cbz w5, .Lmacloop4x

encrypt_block v0, w2, x1, x7, w8

.Lmacloop4x: - subs w22, w22, #4 + subs w3, w3, #4 bmi .Lmac1x - ld1 {v1.16b-v4.16b}, [x19], #64 /* get next pt block */ + ld1 {v1.16b-v4.16b}, [x0], #64 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */ - encrypt_block v0, w21, x20, x7, w8 + encrypt_block v0, w2, x1, x7, w8 eor v0.16b, v0.16b, v2.16b - encrypt_block v0, w21, x20, x7, w8 + encrypt_block v0, w2, x1, x7, w8 eor v0.16b, v0.16b, v3.16b - encrypt_block v0, w21, x20, x7, w8 + encrypt_block v0, w2, x1, x7, w8 eor v0.16b, v0.16b, v4.16b - cmp w22, wzr - csinv x5, x24, xzr, eq + cmp w3, wzr + csinv x5, x6, xzr, eq cbz w5, .Lmacout - encrypt_block v0, w21, x20, x7, w8 - st1 {v0.16b}, [x23] /* return dg */ - cond_yield_neon .Lmacrestart + encrypt_block v0, w2, x1, x7, w8 + st1 {v0.16b}, [x4] /* return dg */ + cond_yield .Lmacout, x7 b .Lmacloop4x .Lmac1x: - add w22, w22, #4 + add w3, w3, #4 .Lmacloop: - cbz w22, .Lmacout - ld1 {v1.16b}, [x19], #16 /* get next pt block */ + cbz w3, .Lmacout + ld1 {v1.16b}, [x0], #16 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */

- subs w22, w22, #1 - csinv x5, x24, xzr, eq + subs w3, w3, #1 + csinv x5, x6, xzr, eq cbz w5, .Lmacout

.Lmacenc: - encrypt_block v0, w21, x20, x7, w8 + encrypt_block v0, w2, x1, x7, w8 b .Lmacloop

.Lmacout: - st1 {v0.16b}, [x23] /* return dg */ - frame_pop + st1 {v0.16b}, [x4] /* return dg */ + mov w0, w3 ret - -.Lmacrestart: - ld1 {v0.16b}, [x23] /* get dg */ - enc_prepare w21, x20, x0 - b .Lmacloop4x AES_FUNC_END(aes_mac_update)

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.13-rc1 commit 27248fe1abb2 category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

The users of the conditional NEON yield macros have all been switched to the simplified cond_yield macro, and so the NEON specific ones can be removed.

Signed-off-by: Ard Biesheuvel ardb@kernel.org Acked-by: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20210302090118.30666-2-ardb@kernel.org Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/include/asm/assembler.h | 70 ------------------------------ 1 file changed, 70 deletions(-)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index f1838bd93a40..2746aaa61438 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -675,76 +675,6 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .endif .endm

-/* - * Check whether to yield to another runnable task from kernel mode NEON code - * (which runs with preemption disabled). - * - * if_will_cond_yield_neon - * // pre-yield patchup code - * do_cond_yield_neon - * // post-yield patchup code - * endif_yield_neon <label> - * - * where <label> is optional, and marks the point where execution will resume - * after a yield has been performed. If omitted, execution resumes right after - * the endif_yield_neon invocation. Note that the entire sequence, including - * the provided patchup code, will be omitted from the image if - * CONFIG_PREEMPTION is not defined. - * - * As a convenience, in the case where no patchup code is required, the above - * sequence may be abbreviated to - * - * cond_yield_neon <label> - * - * Note that the patchup code does not support assembler directives that change - * the output section, any use of such directives is undefined. - * - * The yield itself consists of the following: - * - Check whether the preempt count is exactly 1 and a reschedule is also - * needed. If so, calling of preempt_enable() in kernel_neon_end() will - * trigger a reschedule. If it is not the case, yielding is pointless. - * - Disable and re-enable kernel mode NEON, and branch to the yield fixup - * code. - * - * This macro sequence may clobber all CPU state that is not guaranteed by the - * AAPCS to be preserved across an ordinary function call. - */ - - .macro cond_yield_neon, lbl - if_will_cond_yield_neon - do_cond_yield_neon - endif_yield_neon \lbl - .endm - - .macro if_will_cond_yield_neon -#ifdef CONFIG_PREEMPTION - get_current_task x0 - ldr x0, [x0, #TSK_TI_PREEMPT] - sub x0, x0, #PREEMPT_DISABLE_OFFSET - cbz x0, .Lyield_@ - /* fall through to endif_yield_neon */ - .subsection 1 -.Lyield_@ : -#else - .section ".discard.cond_yield_neon", "ax" -#endif - .endm - - .macro do_cond_yield_neon - bl kernel_neon_end - bl kernel_neon_begin - .endm - - .macro endif_yield_neon, lbl - .ifnb \lbl - b \lbl - .else - b .Lyield_out_@ - .endif - .previous -.Lyield_out_@ : - .endm - /* * Check whether preempt-disabled code should yield as soon as it * is able. This is the case if re-enabling preemption a single

From: Ard Biesheuvel ardb@kernel.org

mainline inclusion from mainline-v5.13-rc1 commit 13150149aa6d category: bugfix bugzilla: 172149 https://gitee.com/openeuler/kernel/issues/I4CZ7H CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

-----------------------------------------------

Kernel mode NEON can be used in task or softirq context, but only in a non-nesting manner, i.e., softirq context is only permitted if the interrupt was not taken at a point where the kernel was using the NEON in task context.

This means all users of kernel mode NEON have to be aware of this limitation, and either need to provide scalar fallbacks that may be much slower (up to 20x for AES instructions) and potentially less safe, or use an asynchronous interface that defers processing to a later time when the NEON is guaranteed to be available.

Given that grabbing and releasing the NEON is cheap, we can relax this restriction, by increasing the granularity of kernel mode NEON code, and always disabling softirq processing while the NEON is being used in task context.

Signed-off-by: Ard Biesheuvel ardb@kernel.org Acked-by: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20210302090118.30666-4-ardb@kernel.org Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Wei Li liwei391@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Reviewed-by: Hanjun Guo guohanjun@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- arch/arm64/crypto/aes-modes.S | 2 +- arch/arm64/crypto/sha1-ce-core.S | 2 +- arch/arm64/crypto/sha2-ce-core.S | 2 +- arch/arm64/crypto/sha3-ce-core.S | 4 ++-- arch/arm64/crypto/sha512-ce-core.S | 2 +- arch/arm64/include/asm/assembler.h | 28 +++++++++++++++++++++------- arch/arm64/kernel/asm-offsets.c | 2 ++ arch/arm64/kernel/fpsimd.c | 4 ++-- 8 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index ab570aa86a5c..503d9b31795c 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -641,7 +641,7 @@ AES_FUNC_START(aes_mac_update) cbz w5, .Lmacout encrypt_block v0, w2, x1, x7, w8 st1 {v0.16b}, [x4] /* return dg */ - cond_yield .Lmacout, x7 + cond_yield .Lmacout, x7, x8 b .Lmacloop4x .Lmac1x: add w3, w3, #4 diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S index 8c02bbc2684e..889ca0f8972b 100644 --- a/arch/arm64/crypto/sha1-ce-core.S +++ b/arch/arm64/crypto/sha1-ce-core.S @@ -121,7 +121,7 @@ CPU_LE( rev32 v11.16b, v11.16b ) add dgav.4s, dgav.4s, dg0v.4s

cbz w2, 2f - cond_yield 3f, x5 + cond_yield 3f, x5, x6 b 0b

/* diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S index 6cdea7d56059..491179922f49 100644 --- a/arch/arm64/crypto/sha2-ce-core.S +++ b/arch/arm64/crypto/sha2-ce-core.S @@ -129,7 +129,7 @@ CPU_LE( rev32 v19.16b, v19.16b )

/* handled all input blocks? */ cbz w2, 2f - cond_yield 3f, x5 + cond_yield 3f, x5, x6 b 0b

/* diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S index 6f5208414fe3..9c77313f5a60 100644 --- a/arch/arm64/crypto/sha3-ce-core.S +++ b/arch/arm64/crypto/sha3-ce-core.S @@ -184,11 +184,11 @@ SYM_FUNC_START(sha3_ce_transform) eor v0.16b, v0.16b, v31.16b

cbnz w8, 3b - cond_yield 3f, x8 + cond_yield 4f, x8, x9 cbnz w2, 0b

/* save state */ -3: st1 { v0.1d- v3.1d}, [x0], #32 +4: st1 { v0.1d- v3.1d}, [x0], #32 st1 { v4.1d- v7.1d}, [x0], #32 st1 { v8.1d-v11.1d}, [x0], #32 st1 {v12.1d-v15.1d}, [x0], #32 diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S index d6e7f6c95fa6..b6a3a36e15f5 100644 --- a/arch/arm64/crypto/sha512-ce-core.S +++ b/arch/arm64/crypto/sha512-ce-core.S @@ -195,7 +195,7 @@ CPU_LE( rev64 v19.16b, v19.16b ) add v10.2d, v10.2d, v2.2d add v11.2d, v11.2d, v3.2d

- cond_yield 3f, x4 + cond_yield 3f, x4, x5 /* handled all input blocks? */ cbnz w2, 0b

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 21d679bf1e55..c7b9b859a860 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -15,6 +15,7 @@ #include <asm-generic/export.h>

#include <asm/asm-offsets.h> +#include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/debug-monitors.h> @@ -684,19 +685,32 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .endm

/* - * Check whether preempt-disabled code should yield as soon as it - * is able. This is the case if re-enabling preemption a single - * time results in a preempt count of zero, and the TIF_NEED_RESCHED - * flag is set. (Note that the latter is stored negated in the - * top word of the thread_info::preempt_count field) + * Check whether preempt/bh-disabled asm code should yield as soon as + * it is able. This is the case if we are currently running in task + * context, and either a softirq is pending, or the TIF_NEED_RESCHED + * flag is set and re-enabling preemption a single time would result in + * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is + * stored negated in the top word of the thread_info::preempt_count + * field) */ - .macro cond_yield, lbl:req, tmp:req -#ifdef CONFIG_PREEMPTION + .macro cond_yield, lbl:req, tmp:req, tmp2:req get_current_task \tmp ldr \tmp, [\tmp, #TSK_TI_PREEMPT] + /* + * If we are serving a softirq, there is no point in yielding: the + * softirq will not be preempted no matter what we do, so we should + * run to completion as quickly as we can. + */ + tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_@ +#ifdef CONFIG_PREEMPTION sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET cbz \tmp, \lbl #endif + adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING + this_cpu_offset \tmp2 + ldr w\tmp, [\tmp, \tmp2] + cbnz w\tmp, \lbl // yield on pending softirq in task context +.Lnoyield_@: .endm

/* diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 13b66005077f..4ed1fec68907 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -93,6 +93,8 @@ int main(void) DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE); BLANK(); DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET); + DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT); + DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_TVAL_TV_SEC, offsetof(struct old_timeval32, tv_sec)); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 062b21f30f94..823e3a8a8871 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -180,7 +180,7 @@ static void __get_cpu_fpsimd_context(void) */ static void get_cpu_fpsimd_context(void) { - preempt_disable(); + local_bh_disable(); __get_cpu_fpsimd_context(); }

@@ -201,7 +201,7 @@ static void __put_cpu_fpsimd_context(void) static void put_cpu_fpsimd_context(void) { __put_cpu_fpsimd_context(); - preempt_enable(); + local_bh_enable(); }

static bool have_cpu_fpsimd_context(void)

From: Zhang Yi yi.zhang@huawei.com

mainline inclusion from mainline-v5.14-rc1 commit 76a8040817b4b9c69b53f9b326987fa891b4082a category: bugfix bugzilla: 109296 https://gitee.com/openeuler/kernel/issues/I4D2TX CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

---------------------------

After commit a79050434b45 ("blk-rq-qos: refactor out common elements of blk-wbt"), if throttle was disabled by wbt_disable_default(), we could not enable again, fix this by set enable_state back to WBT_STATE_ON_DEFAULT.

Fixes: a79050434b45 ("blk-rq-qos: refactor out common elements of blk-wbt") Signed-off-by: Zhang Yi yi.zhang@huawei.com Link: https://lore.kernel.org/r/20210619093700.920393-3-yi.zhang@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com --- block/blk-wbt.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-wbt.c b/block/blk-wbt.c index d90082c6b41f..35d81b5deae1 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -637,9 +637,13 @@ void wbt_set_write_cache(struct request_queue *q, bool write_cache_on) void wbt_enable_default(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); + /* Throttling already enabled? */ - if (rqos) + if (rqos) { + if (RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) + RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; + }

/* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q))