- Kernel - mailweb.openeuler.org

[PATCH openEuler-5.10 001/129] ipvlan: Introduce l2e mode
by Zheng Zengkai 27 Dec '21

27 Dec '21

From: Keefe LIU <liuqifa(a)huawei.com> hulk inclusion category: feature bugzilla: 9511, https://gitee.com/openeuler/kernel/issues/I4IHL1 CVE: NA ------------------------------------------------- In a typical IPvlan L2 setup where master is in default-ns and each slave is into different (slave) ns. In this setup, if master and slaves in different net, egress packet processing for traffic originating from slave-ns can't be forwarded to master or other machine whose ip in the same net with master, and they can't be forwarded to other interface in default-ns. This patch introuce a new mode l2e for ipvlan to realize above goals, and it won't affect the original l2, l3, l3s mode. As the ip tool doesn't support l2e mode, We use module param "ipvlan_default_mode" to set the default work mode. 0 for l2 mode, 1 for l3, 2 for l2e, 3 for l3s, others invalid now. Attention, when we create ipvlan devices by "ip" commond, if we assign the mode, ipvlan will work in the mode we assigned other then the "ipvlan_default_mode". Signed-off-by: Keefe LIU <liuqifa(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Modified: when insmod the ipvlan module, the origin version(4.19) is 0 for l2, 1 for l3, 2 for l2e, 3 for l3s mode, but in 5.10 version is 0 for l2, 1 for l3, 2 for l3s, 3 for l2e mode. Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/net/ipvlan/ipvlan_core.c | 190 +++++++++++++++++++++++++++++++ drivers/net/ipvlan/ipvlan_main.c | 6 +- include/uapi/linux/if_link.h | 1 + 3 files changed, 196 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 8801d093135c..5b695ec5c650 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -532,6 +532,122 @@ static int ipvlan_process_outbound(struct sk_buff *skb) return ret; } +static int ipvlan_process_v4_forward(struct sk_buff *skb) +{ + const struct iphdr *ip4h = ip_hdr(skb); + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + struct rtable *rt; + int err, ret = NET_XMIT_DROP; + struct flowi4 fl4 = { + .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_flags = FLOWI_FLAG_ANYSRC, + .flowi4_mark = skb->mark, + .daddr = ip4h->daddr, + .saddr = ip4h->saddr, + }; + + rt = ip_route_output_flow(net, &fl4, NULL); + if (IS_ERR(rt)) + goto err; + + if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { + ip_rt_put(rt); + goto err; + } + skb_dst_set(skb, &rt->dst); + err = ip_local_out(net, skb->sk, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out; +err: + dev->stats.tx_errors++; + kfree_skb(skb); +out: + return ret; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int ipvlan_process_v6_forward(struct sk_buff *skb) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net_device *dev = skb->dev; + struct net *net = dev_net(dev); + struct dst_entry *dst; + int err, ret = NET_XMIT_DROP; + struct flowi6 fl6 = { + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + .flowi6_flags = FLOWI_FLAG_ANYSRC, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_mark = skb->mark, + .flowi6_proto = ip6h->nexthdr, + }; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + ret = dst->error; + dst_release(dst); + goto err; + } + skb_dst_set(skb, dst); + err = ip6_local_out(net, skb->sk, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out; +err: + dev->stats.tx_errors++; + kfree_skb(skb); +out: + return ret; +} +#else +static int ipvlan_process_v6_forward(struct sk_buff *skb) +{ + return NET_XMIT_DROP; +} +#endif + +static int ipvlan_process_forward(struct sk_buff *skb) +{ + struct ethhdr *ethh = eth_hdr(skb); + int ret = NET_XMIT_DROP; + + /* In this mode we dont care about multicast and broadcast traffic */ + if (is_multicast_ether_addr(ethh->h_dest)) { + pr_debug_ratelimited("Dropped {multi|broad}cast of type=[%x]\n", + ntohs(skb->protocol)); + kfree_skb(skb); + goto out; + } + + /* The ipvlan is a pseudo-L2 device, so the packets that we receive + * will have L2; which need to discarded and processed further + * in the net-ns of the main-device. + */ + if (skb_mac_header_was_set(skb)) { + skb_pull(skb, sizeof(*ethh)); + skb->mac_header = (typeof(skb->mac_header))~0U; + skb_reset_network_header(skb); + } + + if (skb->protocol == htons(ETH_P_IPV6)) { + ret = ipvlan_process_v6_forward(skb); + } else if (skb->protocol == htons(ETH_P_IP)) { + ret = ipvlan_process_v4_forward(skb); + } else { + pr_warn_ratelimited("Dropped outbound packet type=%x\n", + ntohs(skb->protocol)); + kfree_skb(skb); + } +out: + return ret; +} + static void ipvlan_multicast_enqueue(struct ipvl_port *port, struct sk_buff *skb, bool tx_pkt) { @@ -629,6 +745,46 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) return dev_queue_xmit(skb); } +static int ipvlan_xmit_mode_l2e(struct sk_buff *skb, struct net_device *dev) +{ + const struct ipvl_dev *ipvlan = netdev_priv(dev); + struct ethhdr *eth = eth_hdr(skb); + struct ipvl_addr *addr; + void *lyr3h; + int addr_type; + + if (!ipvlan_is_vepa(ipvlan->port) && + ether_addr_equal(eth->h_dest, eth->h_source)) { + lyr3h = ipvlan_get_L3_hdr(ipvlan->port, skb, &addr_type); + if (lyr3h) { + addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, + addr_type, true); + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } + return ipvlan_rcv_frame(addr, &skb, true); + } + } + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_XMIT_DROP; + + /* maybe the packet need been forward */ + skb->dev = ipvlan->phy_dev; + ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); + return ipvlan_process_forward(skb); + } else if (is_multicast_ether_addr(eth->h_dest)) { + ipvlan_skb_crossing_ns(skb, NULL); + ipvlan_multicast_enqueue(ipvlan->port, skb, true); + return NET_XMIT_SUCCESS; + } + + skb->dev = ipvlan->phy_dev; + return dev_queue_xmit(skb); +} + int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); @@ -648,6 +804,8 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) case IPVLAN_MODE_L3S: #endif return ipvlan_xmit_mode_l3(skb, dev); + case IPVLAN_MODE_L2E: + return ipvlan_xmit_mode_l2e(skb, dev); } /* Should not reach here */ @@ -729,6 +887,36 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb, return ret; } +static rx_handler_result_t ipvlan_handle_mode_l2e(struct sk_buff **pskb, + struct ipvl_port *port) +{ + struct sk_buff *skb = *pskb; + struct ethhdr *eth = eth_hdr(skb); + rx_handler_result_t ret = RX_HANDLER_PASS; + + if (is_multicast_ether_addr(eth->h_dest)) { + if (ipvlan_external_frame(skb, port)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + /* External frames are queued for device local + * distribution, but a copy is given to master + * straight away to avoid sending duplicates later + * when work-queue processes this frame. This is + * achieved by returning RX_HANDLER_PASS. + */ + if (nskb) { + ipvlan_skb_crossing_ns(nskb, NULL); + ipvlan_multicast_enqueue(port, nskb, false); + } + } + } else { + /* Perform like l3 mode for non-multicast packet */ + ret = ipvlan_handle_mode_l3(pskb, port); + } + + return ret; +} + rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; @@ -746,6 +934,8 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) case IPVLAN_MODE_L3S: return RX_HANDLER_PASS; #endif + case IPVLAN_MODE_L2E: + return ipvlan_handle_mode_l2e(pskb, port); } /* Should not reach here */ diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 60b7d93bb834..efd1452cd929 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -4,6 +4,10 @@ #include "ipvlan.h" +static int ipvlan_default_mode = IPVLAN_MODE_L3; +module_param(ipvlan_default_mode, int, 0400); +MODULE_PARM_DESC(ipvlan_default_mode, "set ipvlan default mode: 0 for l2, 1 for l3, 2 for l3s, 3 for l2e, others invalid now"); + static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { @@ -535,7 +539,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct ipvl_port *port; struct net_device *phy_dev; int err; - u16 mode = IPVLAN_MODE_L3; + u16 mode = ipvlan_default_mode; if (!tb[IFLA_LINK]) return -EINVAL; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c4b23f06f69e..50d4705e1cbc 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -690,6 +690,7 @@ enum ipvlan_mode { IPVLAN_MODE_L2 = 0, IPVLAN_MODE_L3, IPVLAN_MODE_L3S, + IPVLAN_MODE_L2E, IPVLAN_MODE_MAX }; -- 2.20.1

1 128

[PATCH OLK-5.10 v2] arm64: Revert feature: Add memmap parameter and register pmem
by Zhuling 27 Dec '21

27 Dec '21

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4O31I?from=project-issue CVE: NA The reserve memory of PMEM conflicts with "add memmap interface to reserved memory for mremap syscall usage", need to rollback, resubmit after adaptation. Feature related commit： 1.PMEM function commit:94dc364f5eda10f49449ba573dc3322e1ea92280 2.PMEM feature config commit: 36d7a831e15ceb84e937122c87d01c14242dc377 Signed-off-by: Zhuling <zhuling8(a)huawei.com> --- arch/arm64/Kconfig | 21 -------- arch/arm64/configs/openeuler_defconfig | 3 -- arch/arm64/kernel/Makefile | 1 - arch/arm64/kernel/pmem.c | 35 ------------- arch/arm64/kernel/setup.c | 10 ---- arch/arm64/mm/init.c | 94 ---------------------------------- drivers/nvdimm/Kconfig | 5 -- drivers/nvdimm/Makefile | 1 - 8 files changed, 170 deletions(-) delete mode 100644 arch/arm64/kernel/pmem.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index df90a6e..2df4b31 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1321,27 +1321,6 @@ config RODATA_FULL_DEFAULT_ENABLED This requires the linear region to be mapped down to pages, which may adversely affect performance in some cases. -config ARM64_PMEM_RESERVE - bool "Reserve memory for persistent storage" - default n - help - Use memmap=nn[KMG]!ss[KMG](memmap=100K!0x1a0000000) reserve - memory for persistent storage. - - Say y here to enable this feature. - -config ARM64_PMEM_LEGACY_DEVICE - bool "Create persistent storage" - depends on BLK_DEV - depends on LIBNVDIMM - select ARM64_PMEM_RESERVE - help - Use reserved memory for persistent storage when the kernel - restart or update. the data in PMEM will not be lost and - can be loaded faster. - - Say y if unsure. - config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" help diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 17bc875..b5fc851 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -416,8 +416,6 @@ CONFIG_ARM64_CPU_PARK=y CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_UNMAP_KERNEL_AT_EL0=y CONFIG_RODATA_FULL_DEFAULT_ENABLED=y -CONFIG_ARM64_PMEM_RESERVE=y -CONFIG_ARM64_PMEM_LEGACY_DEVICE=y # CONFIG_ARM64_SW_TTBR0_PAN is not set CONFIG_ARM64_TAGGED_ADDR_ABI=y CONFIG_ARM64_ILP32=y @@ -6026,7 +6024,6 @@ CONFIG_ND_BTT=m CONFIG_BTT=y CONFIG_OF_PMEM=m CONFIG_NVDIMM_KEYS=y -CONFIG_PMEM_LEGACY=m CONFIG_DAX_DRIVER=y CONFIG_DAX=y CONFIG_DEV_DAX=m diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index f615325..169d90f 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -68,7 +68,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-$(CONFIG_MPAM) += mpam/ -obj-$(CONFIG_ARM64_PMEM_LEGACY_DEVICE) += pmem.o obj-y += vdso/ probes/ obj-$(CONFIG_COMPAT_VDSO) += vdso32/ diff --git a/arch/arm64/kernel/pmem.c b/arch/arm64/kernel/pmem.c deleted file mode 100644 index 16eaf70..0000000 --- a/arch/arm64/kernel/pmem.c +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright(c) 2021 Huawei Technologies Co., Ltd - * - * Derived from x86 and arm64 implement PMEM. - */ -#include <linux/platform_device.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/module.h> - -static int found(struct resource *res, void *data) -{ - return 1; -} - -static int __init register_e820_pmem(void) -{ - struct platform_device *pdev; - int rc; - - rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, - IORESOURCE_MEM, 0, -1, NULL, found); - if (rc <= 0) - return 0; - - /* - * See drivers/nvdimm/e820.c for the implementation, this is - * simply here to trigger the module to load on demand. - */ - pdev = platform_device_alloc("e820_pmem", -1); - - return platform_device_add(pdev); -} -device_initcall(register_e820_pmem); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 88ec495..7cd0425 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -70,10 +70,6 @@ static int __init arm64_enable_cpu0_hotplug(char *str) __setup("arm64_cpu0_hotplug", arm64_enable_cpu0_hotplug); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE -extern struct resource pmem_res; -#endif - phys_addr_t __fdt_pointer __initdata; /* @@ -288,12 +284,6 @@ static void __init request_standard_resources(void) request_resource(res, &pin_memory_resource); #endif } - -#ifdef CONFIG_ARM64_PMEM_RESERVE - if (pmem_res.end && pmem_res.start) - request_resource(&iomem_resource, &pmem_res); -#endif - } static int __init reserve_memblock_reserved_regions(void) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 3b9401e..e8d4461 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -55,7 +55,6 @@ */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -phys_addr_t start_at, mem_size; #ifdef CONFIG_PIN_MEMORY struct resource pin_memory_resource = { @@ -112,18 +111,6 @@ static void __init reserve_pin_memory_res(void) */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -static unsigned long long pmem_size, pmem_start; - -#ifdef CONFIG_ARM64_PMEM_RESERVE -struct resource pmem_res = { - .name = "Persistent Memory (legacy)", - .start = 0, - .end = 0, - .flags = IORESOURCE_MEM, - .desc = IORES_DESC_PERSISTENT_MEMORY_LEGACY -}; -#endif - #ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { @@ -417,83 +404,6 @@ static int __init reserve_park_mem(void) } #endif -static bool __init is_mem_valid(unsigned long long mem_size, unsigned long long mem_start) -{ - if (!memblock_is_region_memory(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region is not memory!\n"); - return false; - } - - if (memblock_is_region_reserved(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region overlaps reserved memory!\n"); - return false; - } - - if (!IS_ALIGNED(mem_start, SZ_2M)) { - pr_warn("cannot reserve mem: base address is not 2MB aligned!\n"); - return false; - } - - return true; -} - -static int __init parse_memmap_one(char *p) -{ - char *oldp; - - if (!p) - return -EINVAL; - - oldp = p; - mem_size = memparse(p, &p); - if (p == oldp) - return -EINVAL; - - if (!mem_size) - return -EINVAL; - - mem_size = PAGE_ALIGN(mem_size); - - if (*p == '!') { - start_at = memparse(p+1, &p); - - pmem_start = start_at; - pmem_size = mem_size; - } else - pr_info("Unrecognized memmap option, please check the parameter.\n"); - - return *p == '\0' ? 0 : -EINVAL; -} - -static int __init parse_memmap_opt(char *str) -{ - while (str) { - char *k = strchr(str, ','); - - if (k) - *k++ = 0; - parse_memmap_one(str); - str = k; - } - - return 0; -} -early_param("memmap", parse_memmap_opt); - -#ifdef CONFIG_ARM64_PMEM_RESERVE -static void __init reserve_pmem(void) -{ - if (!is_mem_valid(mem_size, start_at)) - return; - - memblock_remove(pmem_start, pmem_size); - pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - pmem_start, pmem_start + pmem_size, pmem_size >> 20); - pmem_res.start = pmem_start; - pmem_res.end = pmem_start + pmem_size - 1; -} -#endif - void __init arm64_memblock_init(void) { const s64 linear_region_size = BIT(vabits_actual - 1); @@ -668,10 +578,6 @@ void __init bootmem_init(void) reserve_quick_kexec(); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE - reserve_pmem(); -#endif - reserve_pin_memory_res(); memblock_dump_all(); diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index ce4de75..b7d1eb3 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -132,8 +132,3 @@ config NVDIMM_TEST_BUILD infrastructure. endif - -config PMEM_LEGACY - tristate "Pmem_legacy" - select X86_PMEM_LEGACY if X86 - select ARM64_PMEM_LEGACY_DEVICE if ARM64 diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 6f8dc92..0407753 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -3,7 +3,6 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o -obj-$(CONFIG_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_OF_PMEM) += of_pmem.o obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o -- 2.9.5

2 1

[PATCH openEuler-1.0-LTS 01/36] net: Prevent infinite while loop in skb_tx_hash()
by Yang Yingliang 27 Dec '21

27 Dec '21

From: Michael Chan <michael.chan(a)broadcom.com> stable inclusion from linux-4.19.215 commit 02302cbd52264337630a32848ac03648648e9685 -------------------------------- commit 0c57eeecc559ca6bc18b8c4e2808bc78dbe769b0 upstream. Drivers call netdev_set_num_tc() and then netdev_set_tc_queue() to set the queue count and offset for each TC. So the queue count and offset for the TCs may be zero for a short period after dev->num_tc has been set. If a TX packet is being transmitted at this time in the code path netdev_pick_tx() -> skb_tx_hash(), skb_tx_hash() may see nonzero dev->num_tc but zero qcount for the TC. The while loop that keeps looping while hash >= qcount will not end. Fix it by checking the TC's qcount to be nonzero before using it. Fixes: eadec877ce9c ("net: Add support for subordinate traffic classes to netdev_pick_tx") Reviewed-by: Andy Gospodarek <gospo(a)broadcom.com> Signed-off-by: Michael Chan <michael.chan(a)broadcom.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/core/dev.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 5d9800804d4a4..6ed7810ed7bd4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2846,6 +2846,12 @@ static u16 skb_tx_hash(const struct net_device *dev, qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; + if (unlikely(!qcount)) { + net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", + sb_dev->name, qoffset, tc); + qoffset = 0; + qcount = dev->real_num_tx_queues; + } } if (skb_rx_queue_recorded(skb)) { -- 2.25.1

1 35

[[PATCH OLK-5.10] Revert feature — arm64: Add memmap parameter and register pmem] revert feature — [arm64: Add memmap parameter and register pmem]
by Zhuling 27 Dec '21

27 Dec '21

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4O31I?from=project-issue CVE: NA The reserve memory of PMEM conflicts with "add memmap interface to reserved memory for mremap syscall usage", need to rollback, resubmit after adaptation. Feature related commit： 1.PMEM function commit:94dc364f5eda10f49449ba573dc3322e1ea92280 2.PMEM feature config commit: 36d7a831e15ceb84e937122c87d01c14242dc377 Signed-off-by: Zhuling <zhuling8(a)huawei.com> --- arch/arm64/Kconfig | 21 -------- arch/arm64/configs/openeuler_defconfig | 3 -- arch/arm64/kernel/Makefile | 1 - arch/arm64/kernel/pmem.c | 35 ------------- arch/arm64/kernel/setup.c | 10 ---- arch/arm64/mm/init.c | 94 ---------------------------------- drivers/nvdimm/Kconfig | 5 -- drivers/nvdimm/Makefile | 1 - 8 files changed, 170 deletions(-) delete mode 100644 arch/arm64/kernel/pmem.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index df90a6e..2df4b31 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1321,27 +1321,6 @@ config RODATA_FULL_DEFAULT_ENABLED This requires the linear region to be mapped down to pages, which may adversely affect performance in some cases. -config ARM64_PMEM_RESERVE - bool "Reserve memory for persistent storage" - default n - help - Use memmap=nn[KMG]!ss[KMG](memmap=100K!0x1a0000000) reserve - memory for persistent storage. - - Say y here to enable this feature. - -config ARM64_PMEM_LEGACY_DEVICE - bool "Create persistent storage" - depends on BLK_DEV - depends on LIBNVDIMM - select ARM64_PMEM_RESERVE - help - Use reserved memory for persistent storage when the kernel - restart or update. the data in PMEM will not be lost and - can be loaded faster. - - Say y if unsure. - config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" help diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 17bc875..b5fc851 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -416,8 +416,6 @@ CONFIG_ARM64_CPU_PARK=y CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_UNMAP_KERNEL_AT_EL0=y CONFIG_RODATA_FULL_DEFAULT_ENABLED=y -CONFIG_ARM64_PMEM_RESERVE=y -CONFIG_ARM64_PMEM_LEGACY_DEVICE=y # CONFIG_ARM64_SW_TTBR0_PAN is not set CONFIG_ARM64_TAGGED_ADDR_ABI=y CONFIG_ARM64_ILP32=y @@ -6026,7 +6024,6 @@ CONFIG_ND_BTT=m CONFIG_BTT=y CONFIG_OF_PMEM=m CONFIG_NVDIMM_KEYS=y -CONFIG_PMEM_LEGACY=m CONFIG_DAX_DRIVER=y CONFIG_DAX=y CONFIG_DEV_DAX=m diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index f615325..169d90f 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -68,7 +68,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-$(CONFIG_MPAM) += mpam/ -obj-$(CONFIG_ARM64_PMEM_LEGACY_DEVICE) += pmem.o obj-y += vdso/ probes/ obj-$(CONFIG_COMPAT_VDSO) += vdso32/ diff --git a/arch/arm64/kernel/pmem.c b/arch/arm64/kernel/pmem.c deleted file mode 100644 index 16eaf70..0000000 --- a/arch/arm64/kernel/pmem.c +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright(c) 2021 Huawei Technologies Co., Ltd - * - * Derived from x86 and arm64 implement PMEM. - */ -#include <linux/platform_device.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/module.h> - -static int found(struct resource *res, void *data) -{ - return 1; -} - -static int __init register_e820_pmem(void) -{ - struct platform_device *pdev; - int rc; - - rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, - IORESOURCE_MEM, 0, -1, NULL, found); - if (rc <= 0) - return 0; - - /* - * See drivers/nvdimm/e820.c for the implementation, this is - * simply here to trigger the module to load on demand. - */ - pdev = platform_device_alloc("e820_pmem", -1); - - return platform_device_add(pdev); -} -device_initcall(register_e820_pmem); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 88ec495..7cd0425 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -70,10 +70,6 @@ static int __init arm64_enable_cpu0_hotplug(char *str) __setup("arm64_cpu0_hotplug", arm64_enable_cpu0_hotplug); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE -extern struct resource pmem_res; -#endif - phys_addr_t __fdt_pointer __initdata; /* @@ -288,12 +284,6 @@ static void __init request_standard_resources(void) request_resource(res, &pin_memory_resource); #endif } - -#ifdef CONFIG_ARM64_PMEM_RESERVE - if (pmem_res.end && pmem_res.start) - request_resource(&iomem_resource, &pmem_res); -#endif - } static int __init reserve_memblock_reserved_regions(void) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 3b9401e..e8d4461 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -55,7 +55,6 @@ */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -phys_addr_t start_at, mem_size; #ifdef CONFIG_PIN_MEMORY struct resource pin_memory_resource = { @@ -112,18 +111,6 @@ static void __init reserve_pin_memory_res(void) */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -static unsigned long long pmem_size, pmem_start; - -#ifdef CONFIG_ARM64_PMEM_RESERVE -struct resource pmem_res = { - .name = "Persistent Memory (legacy)", - .start = 0, - .end = 0, - .flags = IORESOURCE_MEM, - .desc = IORES_DESC_PERSISTENT_MEMORY_LEGACY -}; -#endif - #ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { @@ -417,83 +404,6 @@ static int __init reserve_park_mem(void) } #endif -static bool __init is_mem_valid(unsigned long long mem_size, unsigned long long mem_start) -{ - if (!memblock_is_region_memory(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region is not memory!\n"); - return false; - } - - if (memblock_is_region_reserved(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region overlaps reserved memory!\n"); - return false; - } - - if (!IS_ALIGNED(mem_start, SZ_2M)) { - pr_warn("cannot reserve mem: base address is not 2MB aligned!\n"); - return false; - } - - return true; -} - -static int __init parse_memmap_one(char *p) -{ - char *oldp; - - if (!p) - return -EINVAL; - - oldp = p; - mem_size = memparse(p, &p); - if (p == oldp) - return -EINVAL; - - if (!mem_size) - return -EINVAL; - - mem_size = PAGE_ALIGN(mem_size); - - if (*p == '!') { - start_at = memparse(p+1, &p); - - pmem_start = start_at; - pmem_size = mem_size; - } else - pr_info("Unrecognized memmap option, please check the parameter.\n"); - - return *p == '\0' ? 0 : -EINVAL; -} - -static int __init parse_memmap_opt(char *str) -{ - while (str) { - char *k = strchr(str, ','); - - if (k) - *k++ = 0; - parse_memmap_one(str); - str = k; - } - - return 0; -} -early_param("memmap", parse_memmap_opt); - -#ifdef CONFIG_ARM64_PMEM_RESERVE -static void __init reserve_pmem(void) -{ - if (!is_mem_valid(mem_size, start_at)) - return; - - memblock_remove(pmem_start, pmem_size); - pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - pmem_start, pmem_start + pmem_size, pmem_size >> 20); - pmem_res.start = pmem_start; - pmem_res.end = pmem_start + pmem_size - 1; -} -#endif - void __init arm64_memblock_init(void) { const s64 linear_region_size = BIT(vabits_actual - 1); @@ -668,10 +578,6 @@ void __init bootmem_init(void) reserve_quick_kexec(); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE - reserve_pmem(); -#endif - reserve_pin_memory_res(); memblock_dump_all(); diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index ce4de75..b7d1eb3 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -132,8 +132,3 @@ config NVDIMM_TEST_BUILD infrastructure. endif - -config PMEM_LEGACY - tristate "Pmem_legacy" - select X86_PMEM_LEGACY if X86 - select ARM64_PMEM_LEGACY_DEVICE if ARM64 diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 6f8dc92..0407753 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -3,7 +3,6 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o -obj-$(CONFIG_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_OF_PMEM) += of_pmem.o obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o -- 2.9.5

4 4

[PATCH openEuler-1.0-LTS] watchdog: Fix check_preemption_disabled() error
by Yang Yingliang 27 Dec '21

27 Dec '21

From: Wei Li <liwei391(a)huawei.com> hulk inclusion category: bugfix bugzilla: 173968, https://gitee.com/openeuler/kernel/issues/I3J87Y CVE: NA ------------------------------------------------- When enabling CONFIG_DEBUG_PREEMPT and CONFIG_PREEMPT, it triggers a 'BUG' in the pmu based nmi_watchdog initializaion: [ 3.341853] BUG: using smp_processor_id() in preemptible [00000000] code: swapper/0/1 [ 3.344392] caller is debug_smp_processor_id+0x17/0x20 [ 3.344395] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.10.0+ #398 [ 3.344397] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014 [ 3.344399] Call Trace: [ 3.344410] dump_stack+0x60/0x76 [ 3.344412] check_preemption_disabled+0xba/0xc0 [ 3.344415] debug_smp_processor_id+0x17/0x20 [ 3.344422] hardlockup_detector_event_create+0xf/0x60 [ 3.344427] hardlockup_detector_perf_init+0xf/0x41 [ 3.344430] watchdog_nmi_probe+0xe/0x10 [ 3.344432] lockup_detector_init+0x22/0x5b [ 3.344437] kernel_init_freeable+0x20c/0x245 [ 3.344439] ? rest_init+0xd0/0xd0 [ 3.344441] kernel_init+0xe/0x110 [ 3.344446] ret_from_fork+0x22/0x30 This issue was introduced by commit 141482cb4b01, which move down lockup_detector_init() after do_basic_setup(), after sched_init_smp() too. hardlockup_detector_event_create |- hardlockup_detector_perf_init (unsafe) |- watchdog_nmi_probe |- lockup_detector_init |- hardlockup_detector_perf_enable |- watchdog_nmi_enable |- watchdog_enable |- lockup_detector_online_cpu |- softlockup_start_fn |- softlockup_start_all |- lockup_detector_reconfigure |- lockup_detector_setup |- lockup_detector_init After analysing the calling context, it's only unsafe to use smp_processor_id() in hardlockup_detector_perf_init() as the thread 'kernel_init' is preemptible after sched_init_smp(). While it is just a test if we can enable the pmu based nmi_watchdog, the real enabling process is in softlockup_start_fn() later which ensures that watchdog_enable() is called on all cores. So it's free to disable preempt to fix this 'BUG'. Fixes: 141482cb4b01 ("lockup_detector: init lockup detector after all the init_calls") Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/watchdog_hld.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 43832b1023693..a5aff8ffa48ce 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -508,14 +508,17 @@ void __init hardlockup_detector_perf_restart(void) */ int __init hardlockup_detector_perf_init(void) { - int ret = hardlockup_detector_event_create(); + int ret; + preempt_disable(); + ret = hardlockup_detector_event_create(); if (ret) { pr_info("Perf NMI watchdog permanently disabled\n"); } else { perf_event_release_kernel(this_cpu_read(watchdog_ev)); this_cpu_write(watchdog_ev, NULL); } + preempt_enable(); return ret; } #endif /* CONFIG_HARDLOCKUP_DETECTOR_PERF */ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] btrfs: unlock newly allocated extent buffer after error
by Yang Yingliang 27 Dec '21

27 Dec '21

From: Qu Wenruo <wqu(a)suse.com> mainline inclusion from mainline-v5.15-rc6 commit 19ea40dddf1833db868533958ca066f368862211 category: bugfix bugzilla: NA CVE: CVE-2021-4149 -------------------------------- [BUG] There is a bug report that injected ENOMEM error could leave a tree block locked while we return to user-space: BTRFS info (device loop0): enabling ssd optimizations FAULT_INJECTION: forcing a failure. name failslab, interval 1, probability 0, space 0, times 0 CPU: 0 PID: 7579 Comm: syz-executor Not tainted 5.15.0-rc1 #16 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x8d/0xcf lib/dump_stack.c:106 fail_dump lib/fault-inject.c:52 [inline] should_fail+0x13c/0x160 lib/fault-inject.c:146 should_failslab+0x5/0x10 mm/slab_common.c:1328 slab_pre_alloc_hook.constprop.99+0x4e/0xc0 mm/slab.h:494 slab_alloc_node mm/slub.c:3120 [inline] slab_alloc mm/slub.c:3214 [inline] kmem_cache_alloc+0x44/0x280 mm/slub.c:3219 btrfs_alloc_delayed_extent_op fs/btrfs/delayed-ref.h:299 [inline] btrfs_alloc_tree_block+0x38c/0x670 fs/btrfs/extent-tree.c:4833 __btrfs_cow_block+0x16f/0x7d0 fs/btrfs/ctree.c:415 btrfs_cow_block+0x12a/0x300 fs/btrfs/ctree.c:570 btrfs_search_slot+0x6b0/0xee0 fs/btrfs/ctree.c:1768 btrfs_insert_empty_items+0x80/0xf0 fs/btrfs/ctree.c:3905 btrfs_new_inode+0x311/0xa60 fs/btrfs/inode.c:6530 btrfs_create+0x12b/0x270 fs/btrfs/inode.c:6783 lookup_open+0x660/0x780 fs/namei.c:3282 open_last_lookups fs/namei.c:3352 [inline] path_openat+0x465/0xe20 fs/namei.c:3557 do_filp_open+0xe3/0x170 fs/namei.c:3588 do_sys_openat2+0x357/0x4a0 fs/open.c:1200 do_sys_open+0x87/0xd0 fs/open.c:1216 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x34/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x46ae99 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f46711b9c48 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 000000000078c0a0 RCX: 000000000046ae99 RDX: 0000000000000000 RSI: 00000000000000a1 RDI: 0000000020005800 RBP: 00007f46711b9c80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000017 R13: 0000000000000000 R14: 000000000078c0a0 R15: 00007ffc129da6e0 ================================================ WARNING: lock held when returning to user space! 5.15.0-rc1 #16 Not tainted ------------------------------------------------ syz-executor/7579 is leaving the kernel with locks still held! 1 lock held by syz-executor/7579: #0: ffff888104b73da8 (btrfs-tree-01/1){+.+.}-{3:3}, at: __btrfs_tree_lock+0x2e/0x1a0 fs/btrfs/locking.c:112 [CAUSE] In btrfs_alloc_tree_block(), after btrfs_init_new_buffer(), the new extent buffer @buf is locked, but if later operations like adding delayed tree ref fail, we just free @buf without unlocking it, resulting above warning. [FIX] Unlock @buf in out_free_buf: label. Reported-by: Hao Sun <sunhao.th(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CACkBjsZ9O6Zr0KK1yGn=1rQi6Crh1yeCRdTSBx… CC: stable(a)vger.kernel.org # 5.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/btrfs/extent-tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4bf93184362ec..dcbb76b62a0b0 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8324,6 +8324,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, out_free_delayed: btrfs_free_delayed_extent_op(extent_op); out_free_buf: + btrfs_tree_unlock(buf); free_extent_buffer(buf); out_free_reserved: btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 0); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] ext4: Fix null-ptr-deref in '__ext4_journal_ensure_credits'
by Yang Yingliang 25 Dec '21

25 Dec '21

From: Ye Bin <yebin10(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185945, https://gitee.com/openeuler/kernel/issues/I4O33F CVE: NA ----------------------------------------------- We got issue as follows when run syzkaller test: [ 1901.130043] EXT4-fs error (device vda): ext4_remount:5624: comm syz-executor.5: Abort forced by user [ 1901.130901] Aborting journal on device vda-8. [ 1901.131437] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.16: Detected aborted journal [ 1901.131566] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.11: Detected aborted journal [ 1901.132586] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.18: Detected aborted journal [ 1901.132751] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.9: Detected aborted journal [ 1901.136149] EXT4-fs error (device vda) in ext4_reserve_inode_write:6035: Journal has aborted [ 1901.136837] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-fuzzer: Detected aborted journal [ 1901.136915] ================================================================== [ 1901.138175] BUG: KASAN: null-ptr-deref in __ext4_journal_ensure_credits+0x74/0x140 [ext4] [ 1901.138343] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.13: Detected aborted journal [ 1901.138398] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.1: Detected aborted journal [ 1901.138808] Read of size 8 at addr 0000000000000000 by task syz-executor.17/968 [ 1901.138817] [ 1901.138852] EXT4-fs error (device vda): ext4_journal_check_start:61: comm syz-executor.30: Detected aborted journal [ 1901.144779] CPU: 1 PID: 968 Comm: syz-executor.17 Not tainted 4.19.90-vhulk2111.1.0.h893.eulerosv2r10.aarch64+ #1 [ 1901.146479] Hardware name: linux,dummy-virt (DT) [ 1901.147317] Call trace: [ 1901.147552] dump_backtrace+0x0/0x2d8 [ 1901.147898] show_stack+0x28/0x38 [ 1901.148215] dump_stack+0xec/0x15c [ 1901.148746] kasan_report+0x108/0x338 [ 1901.149207] __asan_load8+0x58/0xb0 [ 1901.149753] __ext4_journal_ensure_credits+0x74/0x140 [ext4] [ 1901.150579] ext4_xattr_delete_inode+0xe4/0x700 [ext4] [ 1901.151316] ext4_evict_inode+0x524/0xba8 [ext4] [ 1901.151985] evict+0x1a4/0x378 [ 1901.152353] iput+0x310/0x428 [ 1901.152733] do_unlinkat+0x260/0x428 [ 1901.153056] __arm64_sys_unlinkat+0x6c/0xc0 [ 1901.153455] el0_svc_common+0xc8/0x320 [ 1901.153799] el0_svc_handler+0xf8/0x160 [ 1901.154265] el0_svc+0x10/0x218 [ 1901.154682] ================================================================== This issue may happens like this: Process1 Process2 ext4_evict_inode ext4_journal_start ext4_truncate ext4_ind_truncate ext4_free_branches ext4_ind_truncate_ensure_credits ext4_journal_ensure_credits_fn ext4_journal_restart handle->h_transaction = NULL; mount -o remount,abort /mnt -> trigger JBD abort start_this_handle -> will return failed ext4_xattr_delete_inode ext4_journal_ensure_credits ext4_journal_ensure_credits_fn __ext4_journal_ensure_credits jbd2_handle_buffer_credits journal = handle->h_transaction->t_journal; ->null-ptr-deref Now, indirect truncate process didn't handle error. To solve this issue maybe simply add check handle is abort in '__ext4_journal_ensure_credits' is enough, and i also think this is necessary. Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/ext4_jbd2.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 022ab8afd9499..2c6dc99292fdc 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -140,6 +140,8 @@ int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, { if (!ext4_handle_valid(handle)) return 0; + if (is_handle_aborted(handle)) + return -EROFS; if (jbd2_handle_buffer_credits(handle) >= check_cred && handle->h_revoke_credits >= revoke_cred) return 0; -- 2.25.1

1 0

[[PATCH OLK-5.10] Revert feature — [arm64: Add memmap parameter and register pmem]] revert feature — [arm64: Add memmap parameter and register pmem]
by Zhuling 25 Dec '21

25 Dec '21

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4O31I?from=project-issue CVE: NA The reserve memory of PMEM conflicts with "add memmap interface to reserved memory for mremap syscall usage", need to rollback, resubmit after adaptation. Feature related commit： 1.PMEM function commit:94dc364f5eda10f49449ba573dc3322e1ea92280 2.PMEM feature config commit: 36d7a831e15ceb84e937122c87d01c14242dc377 Signed-off-by: Zhuling <zhuling8(a)huawei.com> --- arch/arm64/Kconfig | 21 -------- arch/arm64/configs/openeuler_defconfig | 3 -- arch/arm64/kernel/Makefile | 1 - arch/arm64/kernel/pmem.c | 35 ------------- arch/arm64/kernel/setup.c | 10 ---- arch/arm64/mm/init.c | 94 ---------------------------------- drivers/nvdimm/Kconfig | 5 -- drivers/nvdimm/Makefile | 1 - 8 files changed, 170 deletions(-) delete mode 100644 arch/arm64/kernel/pmem.c diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index df90a6e..2df4b31 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1321,27 +1321,6 @@ config RODATA_FULL_DEFAULT_ENABLED This requires the linear region to be mapped down to pages, which may adversely affect performance in some cases. -config ARM64_PMEM_RESERVE - bool "Reserve memory for persistent storage" - default n - help - Use memmap=nn[KMG]!ss[KMG](memmap=100K!0x1a0000000) reserve - memory for persistent storage. - - Say y here to enable this feature. - -config ARM64_PMEM_LEGACY_DEVICE - bool "Create persistent storage" - depends on BLK_DEV - depends on LIBNVDIMM - select ARM64_PMEM_RESERVE - help - Use reserved memory for persistent storage when the kernel - restart or update. the data in PMEM will not be lost and - can be loaded faster. - - Say y if unsure. - config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" help diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 17bc875..b5fc851 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -416,8 +416,6 @@ CONFIG_ARM64_CPU_PARK=y CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_UNMAP_KERNEL_AT_EL0=y CONFIG_RODATA_FULL_DEFAULT_ENABLED=y -CONFIG_ARM64_PMEM_RESERVE=y -CONFIG_ARM64_PMEM_LEGACY_DEVICE=y # CONFIG_ARM64_SW_TTBR0_PAN is not set CONFIG_ARM64_TAGGED_ADDR_ABI=y CONFIG_ARM64_ILP32=y @@ -6026,7 +6024,6 @@ CONFIG_ND_BTT=m CONFIG_BTT=y CONFIG_OF_PMEM=m CONFIG_NVDIMM_KEYS=y -CONFIG_PMEM_LEGACY=m CONFIG_DAX_DRIVER=y CONFIG_DAX=y CONFIG_DEV_DAX=m diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index f615325..169d90f 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -68,7 +68,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-$(CONFIG_MPAM) += mpam/ -obj-$(CONFIG_ARM64_PMEM_LEGACY_DEVICE) += pmem.o obj-y += vdso/ probes/ obj-$(CONFIG_COMPAT_VDSO) += vdso32/ diff --git a/arch/arm64/kernel/pmem.c b/arch/arm64/kernel/pmem.c deleted file mode 100644 index 16eaf70..0000000 --- a/arch/arm64/kernel/pmem.c +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright(c) 2021 Huawei Technologies Co., Ltd - * - * Derived from x86 and arm64 implement PMEM. - */ -#include <linux/platform_device.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/module.h> - -static int found(struct resource *res, void *data) -{ - return 1; -} - -static int __init register_e820_pmem(void) -{ - struct platform_device *pdev; - int rc; - - rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, - IORESOURCE_MEM, 0, -1, NULL, found); - if (rc <= 0) - return 0; - - /* - * See drivers/nvdimm/e820.c for the implementation, this is - * simply here to trigger the module to load on demand. - */ - pdev = platform_device_alloc("e820_pmem", -1); - - return platform_device_add(pdev); -} -device_initcall(register_e820_pmem); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 88ec495..7cd0425 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -70,10 +70,6 @@ static int __init arm64_enable_cpu0_hotplug(char *str) __setup("arm64_cpu0_hotplug", arm64_enable_cpu0_hotplug); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE -extern struct resource pmem_res; -#endif - phys_addr_t __fdt_pointer __initdata; /* @@ -288,12 +284,6 @@ static void __init request_standard_resources(void) request_resource(res, &pin_memory_resource); #endif } - -#ifdef CONFIG_ARM64_PMEM_RESERVE - if (pmem_res.end && pmem_res.start) - request_resource(&iomem_resource, &pmem_res); -#endif - } static int __init reserve_memblock_reserved_regions(void) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 3b9401e..e8d4461 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -55,7 +55,6 @@ */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); -phys_addr_t start_at, mem_size; #ifdef CONFIG_PIN_MEMORY struct resource pin_memory_resource = { @@ -112,18 +111,6 @@ static void __init reserve_pin_memory_res(void) */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -static unsigned long long pmem_size, pmem_start; - -#ifdef CONFIG_ARM64_PMEM_RESERVE -struct resource pmem_res = { - .name = "Persistent Memory (legacy)", - .start = 0, - .end = 0, - .flags = IORESOURCE_MEM, - .desc = IORES_DESC_PERSISTENT_MEMORY_LEGACY -}; -#endif - #ifndef CONFIG_KEXEC_CORE static void __init reserve_crashkernel(void) { @@ -417,83 +404,6 @@ static int __init reserve_park_mem(void) } #endif -static bool __init is_mem_valid(unsigned long long mem_size, unsigned long long mem_start) -{ - if (!memblock_is_region_memory(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region is not memory!\n"); - return false; - } - - if (memblock_is_region_reserved(mem_start, mem_size)) { - pr_warn("cannot reserve mem: region overlaps reserved memory!\n"); - return false; - } - - if (!IS_ALIGNED(mem_start, SZ_2M)) { - pr_warn("cannot reserve mem: base address is not 2MB aligned!\n"); - return false; - } - - return true; -} - -static int __init parse_memmap_one(char *p) -{ - char *oldp; - - if (!p) - return -EINVAL; - - oldp = p; - mem_size = memparse(p, &p); - if (p == oldp) - return -EINVAL; - - if (!mem_size) - return -EINVAL; - - mem_size = PAGE_ALIGN(mem_size); - - if (*p == '!') { - start_at = memparse(p+1, &p); - - pmem_start = start_at; - pmem_size = mem_size; - } else - pr_info("Unrecognized memmap option, please check the parameter.\n"); - - return *p == '\0' ? 0 : -EINVAL; -} - -static int __init parse_memmap_opt(char *str) -{ - while (str) { - char *k = strchr(str, ','); - - if (k) - *k++ = 0; - parse_memmap_one(str); - str = k; - } - - return 0; -} -early_param("memmap", parse_memmap_opt); - -#ifdef CONFIG_ARM64_PMEM_RESERVE -static void __init reserve_pmem(void) -{ - if (!is_mem_valid(mem_size, start_at)) - return; - - memblock_remove(pmem_start, pmem_size); - pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - pmem_start, pmem_start + pmem_size, pmem_size >> 20); - pmem_res.start = pmem_start; - pmem_res.end = pmem_start + pmem_size - 1; -} -#endif - void __init arm64_memblock_init(void) { const s64 linear_region_size = BIT(vabits_actual - 1); @@ -668,10 +578,6 @@ void __init bootmem_init(void) reserve_quick_kexec(); #endif -#ifdef CONFIG_ARM64_PMEM_RESERVE - reserve_pmem(); -#endif - reserve_pin_memory_res(); memblock_dump_all(); diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index ce4de75..b7d1eb3 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -132,8 +132,3 @@ config NVDIMM_TEST_BUILD infrastructure. endif - -config PMEM_LEGACY - tristate "Pmem_legacy" - select X86_PMEM_LEGACY if X86 - select ARM64_PMEM_LEGACY_DEVICE if ARM64 diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 6f8dc92..0407753 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -3,7 +3,6 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o -obj-$(CONFIG_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_OF_PMEM) += of_pmem.o obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o -- 2.9.5

1 0

[PATCH openEuler-1.0-LTS] net/hinic: Fix call trace when the rx_buff module parameter is grater than 2
by Yang Yingliang 25 Dec '21

25 Dec '21

From: Chiqijun <chiqijun(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4O2ZZ ----------------------------------------------------------------------- When rx_buff is greater than 2, the driver will alloc for more than 1 page of memory for network rx, but the __GFP_COMP gfp flag is not set, resulting in the following call trace: CPU: 3 PID: 494041 Comm: ping Kdump: loaded Tainted: G W OE 4.19.90-2106.3.0.0095.oe1.x86_64 #1 Hardware name: Huawei Technologies Co., Ltd. RH2288H V3/BC11HGSA0, BIOS 5.15 05/21/2019 RIP: 0010:copy_page_to_iter+0x154/0x310 Code: 31 b8 00 10 00 00 f7 c6 00 80 00 00 74 07 0f b6 49 51 48 d3 e0 48 39 c2 0f 86 ed fe ff ff 48 c7 c7 30 RSP: 0018:ffffbd6907d03bd8 EFLAGS: 00010286 RAX: 0000000000000024 RBX: ffffe0ffee5b3000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff9edbbfcd6858 RDI: ffff9edbbfcd6858 RBP: 0000000000000001 R08: 000000000001574a R09: 0000000000000004 R10: 000000000000004e R11: 0000000000000001 R12: ffffbd6907d03ed0 R13: 0000000000002100 R14: 0000000000000030 R15: 0000000000000000 FS: 00007f9d37244dc0(0000) GS:ffff9edbbfcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffe0e715f80 CR3: 000000203c018005 CR4: 00000000001606e0 Call Trace: skb_copy_datagram_iter+0x16c/0x2a0 raw_recvmsg+0xd0/0x1f0 inet_recvmsg+0x5b/0xd0 ____sys_recvmsg+0x95/0x160 ? import_iovec+0x37/0xd0 ? copy_msghdr_from_user+0x5c/0x90 ___sys_recvmsg+0x8c/0xd0 ? __audit_syscall_exit+0x228/0x290 ? kretprobe_trampoline+0x25/0x50 ? __sys_recvmsg+0x5b/0xa0 __sys_recvmsg+0x5b/0xa0 do_syscall_64+0x5f/0x240 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Use 'dev_alloc_pages' instead of calling ’alloc_pages_node‘ directly. Signed-off-by: Chiqijun <chiqijun(a)huawei.com> Reviewed-by: Wangxiaoyun <cloud.wangxiaoyun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/huawei/hinic/hinic_rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index a9047432f3053..019cd439ce696 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -67,7 +67,7 @@ static bool rx_alloc_mapped_page(struct hinic_rxq *rxq, return true; /* alloc new page for storage */ - page = alloc_pages_node(NUMA_NO_NODE, GFP_ATOMIC, nic_dev->page_order); + page = dev_alloc_pages(nic_dev->page_order); if (unlikely(!page)) { RXQ_STATS_INC(rxq, alloc_rx_buf_err); return false; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS 1/3] arm64/mpam: remove __init macro to support driver probe
by Yang Yingliang 24 Dec '21

24 Dec '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA --------------------------------------------------- To support device tree boot for arm64 mpam, the __init macro might be used by the dts driver. This remove the necessary __init macro for the related functions. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Reviewed-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/include/asm/resctrl.h | 2 +- arch/arm64/kernel/mpam/mpam_device.c | 14 +++++++------- arch/arm64/kernel/mpam/mpam_internal.h | 2 +- arch/arm64/kernel/mpam/mpam_resctrl.c | 2 +- fs/resctrlfs.c | 2 +- include/linux/arm_mpam.h | 14 +++++++------- 6 files changed, 18 insertions(+), 18 deletions(-) diff --git a/arch/arm64/include/asm/resctrl.h b/arch/arm64/include/asm/resctrl.h index ff4ce56430d1f..3fceaa482e5a3 100644 --- a/arch/arm64/include/asm/resctrl.h +++ b/arch/arm64/include/asm/resctrl.h @@ -424,7 +424,7 @@ int resctrl_update_groups_config(struct rdtgroup *rdtgrp); #define RESCTRL_MAX_CLOSID 32 -int __init resctrl_group_init(void); +int resctrl_group_init(void); void post_resctrl_mount(void); diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index c0615f6947a1f..4139b4476a836 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -534,7 +534,7 @@ static void mpam_disable_irqs(void) * Scheduled by mpam_discovery_complete() once all devices have been created. * Also scheduled when new devices are probed when new CPUs come online. */ -static void __init mpam_enable(struct work_struct *work) +static void mpam_enable(struct work_struct *work) { int err; unsigned long flags; @@ -761,7 +761,7 @@ static struct mpam_class * __init mpam_class_get(u8 level_idx, * class/component structures may be allocated. * Returns the new device, or an ERR_PTR(). */ -struct mpam_device * __init +struct mpam_device * __mpam_device_create(u8 level_idx, enum mpam_class_types type, int component_id, const struct cpumask *fw_affinity, phys_addr_t hwpage_address) @@ -810,7 +810,7 @@ __mpam_device_create(u8 level_idx, enum mpam_class_types type, return dev; } -void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, u32 flags) { unsigned long irq_save_flags; @@ -821,7 +821,7 @@ void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, spin_unlock_irqrestore(&dev->lock, irq_save_flags); } -void __init mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, u32 flags) { unsigned long irq_save_flags; @@ -864,7 +864,7 @@ static inline u16 mpam_cpu_max_pmg(void) /* * prepare for initializing devices. */ -int __init mpam_discovery_start(void) +int mpam_discovery_start(void) { if (!mpam_cpus_have_feature()) return -EOPNOTSUPP; @@ -1104,7 +1104,7 @@ static int mpam_cpu_offline(unsigned int cpu) return 0; } -int __init mpam_discovery_complete(void) +int mpam_discovery_complete(void) { int ret = 0; @@ -1121,7 +1121,7 @@ int __init mpam_discovery_complete(void) return ret; } -void __init mpam_discovery_failed(void) +void mpam_discovery_failed(void) { struct mpam_class *class, *tmp; diff --git a/arch/arm64/kernel/mpam/mpam_internal.h b/arch/arm64/kernel/mpam/mpam_internal.h index cfaef82428aa5..7b84ea54975aa 100644 --- a/arch/arm64/kernel/mpam/mpam_internal.h +++ b/arch/arm64/kernel/mpam/mpam_internal.h @@ -329,7 +329,7 @@ int mpam_resctrl_setup(void); struct raw_resctrl_resource * mpam_get_raw_resctrl_resource(u32 level); -int __init mpam_resctrl_init(void); +int mpam_resctrl_init(void); int mpam_resctrl_set_default_cpu(unsigned int cpu); void mpam_resctrl_clear_default_cpu(unsigned int cpu); diff --git a/arch/arm64/kernel/mpam/mpam_resctrl.c b/arch/arm64/kernel/mpam/mpam_resctrl.c index 51cdefebaeba8..1ad4cd49762a3 100644 --- a/arch/arm64/kernel/mpam/mpam_resctrl.c +++ b/arch/arm64/kernel/mpam/mpam_resctrl.c @@ -2209,7 +2209,7 @@ static int __init mpam_setup(char *str) } __setup("mpam", mpam_setup); -int __init mpam_resctrl_init(void) +int mpam_resctrl_init(void) { mpam_init_padding(); diff --git a/fs/resctrlfs.c b/fs/resctrlfs.c index 11741c87eb0af..ea9df7d77b95a 100644 --- a/fs/resctrlfs.c +++ b/fs/resctrlfs.c @@ -1029,7 +1029,7 @@ static int __init resctrl_group_setup_root(void) * * Return: 0 on success or -errno */ -int __init resctrl_group_init(void) +int resctrl_group_init(void) { int ret = 0; diff --git a/include/linux/arm_mpam.h b/include/linux/arm_mpam.h index 44d0690ae8c4b..a242d4fdff8b3 100644 --- a/include/linux/arm_mpam.h +++ b/include/linux/arm_mpam.h @@ -16,7 +16,7 @@ enum mpam_class_types { MPAM_CLASS_UNKNOWN, /* Everything else, e.g. TLBs etc */ }; -struct mpam_device * __init +struct mpam_device * __mpam_device_create(u8 level_idx, enum mpam_class_types type, int component_id, const struct cpumask *fw_affinity, phys_addr_t hwpage_address); @@ -54,9 +54,9 @@ mpam_device_create_memory(int nid, phys_addr_t hwpage_address) return __mpam_device_create(~0, MPAM_CLASS_MEMORY, nid, &dev_affinity, hwpage_address); } -int __init mpam_discovery_start(void); -int __init mpam_discovery_complete(void); -void __init mpam_discovery_failed(void); +int mpam_discovery_start(void); +int mpam_discovery_complete(void); +void mpam_discovery_failed(void); enum mpam_enable_type { MPAM_ENABLE_DENIED = 0, @@ -71,12 +71,12 @@ extern enum mpam_enable_type mpam_enabled; #define mpam_irq_flags_to_acpi(x) ((x & MPAM_IRQ_MODE_LEVEL) ? \ ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE) -void __init mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_error_irq(struct mpam_device *dev, u32 irq, u32 flags); -void __init mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, +void mpam_device_set_overflow_irq(struct mpam_device *dev, u32 irq, u32 flags); -static inline int __init mpam_register_device_irq(struct mpam_device *dev, +static inline int mpam_register_device_irq(struct mpam_device *dev, u32 overflow_interrupt, u32 overflow_flags, u32 error_interrupt, u32 error_flags) { -- 2.25.1

1 2