- Kernel - mailweb.openeuler.org

[OLK-5.10 0/2] introduce handle_fasteoi_edge_irq
by Yipeng Zou 28 Aug '23

28 Aug '23

introduce handle_fasteoi_edge_irq Yipeng Zou (2): genirq: introduce handle_fasteoi_edge_irq flow handler genirq: introduce handle_fasteoi_edge_irq for phytium drivers/irqchip/irq-gic-phytium-2500.c | 2 +- drivers/irqchip/irq-gic-v3.c | 2 +- include/linux/irq.h | 1 + kernel/irq/chip.c | 67 ++++++++++++++++++++++++++ 4 files changed, 70 insertions(+), 2 deletions(-) -- 2.17.1

1 2

[PATCH openEuler-23.09 00/24] ILP32 for ARM64
by Chen Jiahao 28 Aug '23

28 Aug '23

backport ILP32 for ARM64 patches to openEuler-23.09 Andrew Pinski (3): arm64: rename COMPAT to AARCH32_EL0 arm64: uapi: set __BITS_PER_LONG correctly for ILP32 and LP64 arm64:ilp32: add ARM64_ILP32 to Kconfig Dave Martin (1): arm64: signal: Make parse_user_sigframe() independent of rt_sigframe layout James Morse (1): ptrace: Add compat PTRACE_{G,S}ETSIGMASK handlers Philipp Tomsich (1): arm64:ilp32: add vdso-ilp32 and use for signal return Xiongfeng Wang (4): arm64: rename functions that reference compat term arm64: secomp: fix the secure computing mode 1 syscall check for ilp32 ilp32: avoid clearing upper 32 bits of syscall return value for ilp32 ilp32: skip ARM erratum 1418040 for ilp32 application Yury Norov (14): thread: move thread bits accessors to separated file arm64: ilp32: add documentation on the ILP32 ABI for ARM64 arm64: introduce is_a32_compat_{task,thread} for AArch32 compat arm64: ilp32: add is_ilp32_compat_{task,thread} and TIF_32BIT_AARCH64 arm64: introduce AUDIT_ARCH_AARCH64ILP32 for ilp32 arm64: introduce binfmt_elf32.c arm64: change compat_elf_hwcap and compat_elf_hwcap2 prefix to a32 arm64: ilp32: introduce binfmt_ilp32.c arm64: ilp32: share aarch32 syscall handlers arm64: ilp32: introduce syscall table for ILP32 arm64: signal: share lp64 signal structures and routines to ilp32 arm64: signal32: move ilp32 and aarch32 common code to separated file arm64: ilp32: introduce ilp32-specific sigframe and ucontext arm64: ptrace: handle ptrace_request differently for aarch32 and ilp32 Documentation/arm64/ilp32.txt | 52 +++ arch/arm64/Kconfig | 19 +- arch/arm64/Makefile | 3 + arch/arm64/include/asm/arch_timer.h | 4 +- arch/arm64/include/asm/compat.h | 18 +- arch/arm64/include/asm/elf.h | 32 +- arch/arm64/include/asm/fpsimd.h | 2 +- arch/arm64/include/asm/ftrace.h | 2 +- arch/arm64/include/asm/hwcap.h | 8 +- arch/arm64/include/asm/is_compat.h | 78 ++++ arch/arm64/include/asm/processor.h | 15 +- arch/arm64/include/asm/ptrace.h | 12 +- arch/arm64/include/asm/seccomp.h | 32 +- arch/arm64/include/asm/signal32.h | 31 +- arch/arm64/include/asm/signal32_common.h | 13 + arch/arm64/include/asm/signal_common.h | 391 +++++++++++++++++ arch/arm64/include/asm/signal_ilp32.h | 23 + arch/arm64/include/asm/syscall.h | 17 +- arch/arm64/include/asm/thread_info.h | 4 +- arch/arm64/include/asm/unistd.h | 5 + arch/arm64/include/asm/vdso.h | 9 + arch/arm64/include/uapi/asm/bitsperlong.h | 9 +- arch/arm64/include/uapi/asm/unistd.h | 15 +- arch/arm64/kernel/Makefile | 8 +- arch/arm64/kernel/armv8_deprecated.c | 12 +- arch/arm64/kernel/asm-offsets.c | 13 +- arch/arm64/kernel/binfmt_elf32.c | 27 ++ arch/arm64/kernel/binfmt_ilp32.c | 89 ++++ arch/arm64/kernel/cpufeature.c | 36 +- arch/arm64/kernel/cpuinfo.c | 18 +- arch/arm64/kernel/debug-monitors.c | 4 +- arch/arm64/kernel/entry-common.c | 6 +- arch/arm64/kernel/hw_breakpoint.c | 8 +- arch/arm64/kernel/perf_callchain.c | 28 +- arch/arm64/kernel/perf_regs.c | 4 +- arch/arm64/kernel/process.c | 15 +- arch/arm64/kernel/proton-pack.c | 2 +- arch/arm64/kernel/ptrace.c | 38 +- arch/arm64/kernel/signal.c | 397 +++--------------- arch/arm64/kernel/signal32.c | 97 ++--- arch/arm64/kernel/signal32_common.c | 37 ++ arch/arm64/kernel/signal_ilp32.c | 67 +++ arch/arm64/kernel/sys32.c | 104 +---- arch/arm64/kernel/sys32_common.c | 106 +++++ arch/arm64/kernel/sys_compat.c | 12 +- arch/arm64/kernel/sys_ilp32.c | 82 ++++ arch/arm64/kernel/syscall.c | 37 +- arch/arm64/kernel/traps.c | 5 +- arch/arm64/kernel/vdso-ilp32/.gitignore | 2 + arch/arm64/kernel/vdso-ilp32/Makefile | 108 +++++ arch/arm64/kernel/vdso-ilp32/vdso-ilp32.S | 22 + arch/arm64/kernel/vdso-ilp32/vdso-ilp32.lds.S | 88 ++++ arch/arm64/kernel/vdso.c | 46 +- arch/arm64/mm/fault.c | 2 +- include/linux/sched.h | 1 + include/linux/thread_bits.h | 87 ++++ include/linux/thread_info.h | 73 +--- include/uapi/linux/audit.h | 1 + kernel/ptrace.c | 52 ++- 59 files changed, 1765 insertions(+), 763 deletions(-) create mode 100644 Documentation/arm64/ilp32.txt create mode 100644 arch/arm64/include/asm/is_compat.h create mode 100644 arch/arm64/include/asm/signal32_common.h create mode 100644 arch/arm64/include/asm/signal_common.h create mode 100644 arch/arm64/include/asm/signal_ilp32.h create mode 100644 arch/arm64/kernel/binfmt_elf32.c create mode 100644 arch/arm64/kernel/binfmt_ilp32.c create mode 100644 arch/arm64/kernel/signal32_common.c create mode 100644 arch/arm64/kernel/signal_ilp32.c create mode 100644 arch/arm64/kernel/sys32_common.c create mode 100644 arch/arm64/kernel/sys_ilp32.c create mode 100644 arch/arm64/kernel/vdso-ilp32/.gitignore create mode 100644 arch/arm64/kernel/vdso-ilp32/Makefile create mode 100644 arch/arm64/kernel/vdso-ilp32/vdso-ilp32.S create mode 100644 arch/arm64/kernel/vdso-ilp32/vdso-ilp32.lds.S create mode 100644 include/linux/thread_bits.h -- 2.34.1

1 24

[PATCH openEuler-1.0-LTS] ipvlan: Fix a reference count leak warning in ipvlan_ns_exit()
by Lu Wei 28 Aug '23

28 Aug '23

mainline inclusion from mainline-v6.4 commit 043d5f68d0ccdda91029b4b6dce7eeffdcfad281 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7WB3H Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- There are two network devices(veth1 and veth3) in ns1, and ipvlan1 with L3S mode and ipvlan2 with L2 mode are created based on them as figure (1). In this case, ipvlan_register_nf_hook() will be called to register nf hook which is needed by ipvlans in L3S mode in ns1 and value of ipvl_nf_hook_refcnt is set to 1. (1) ns1 ns2 ------------ ------------ veth1--ipvlan1 (L3S) veth3--ipvlan2 (L2) (2) ns1 ns2 ------------ ------------ veth1--ipvlan1 (L3S) ipvlan2 (L2) veth3 | | |------->-------->--------->-------- migrate When veth3 migrates from ns1 to ns2 as figure (2), veth3 will register in ns2 and calls call_netdevice_notifiers with NETDEV_REGISTER event: dev_change_net_namespace call_netdevice_notifiers ipvlan_device_event ipvlan_migrate_l3s_hook ipvlan_register_nf_hook(newnet) (I) ipvlan_unregister_nf_hook(oldnet) (II) In function ipvlan_migrate_l3s_hook(), ipvl_nf_hook_refcnt in ns1 is not 0 since veth1 with ipvlan1 still in ns1, (I) and (II) will be called to register nf_hook in ns2 and unregister nf_hook in ns1. As a result, ipvl_nf_hook_refcnt in ns1 is decreased incorrectly and this in ns2 is increased incorrectly. When the second net namespace is removed, a reference count leak warning in ipvlan_ns_exit() will be triggered. This patch add a check before ipvlan_migrate_l3s_hook() is called. The warning can be triggered as follows: $ ip netns add ns1 $ ip netns add ns2 $ ip netns exec ns1 ip link add veth1 type veth peer name veth2 $ ip netns exec ns1 ip link add veth3 type veth peer name veth4 $ ip netns exec ns1 ip link add ipv1 link veth1 type ipvlan mode l3s $ ip netns exec ns1 ip link add ipv2 link veth3 type ipvlan mode l2 $ ip netns exec ns1 ip link set veth3 netns ns2 $ ip net del ns2 Fixes: 3133822f5ac1 ("ipvlan: use pernet operations and restrict l3s hooks to master netns") Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Florian Westphal <fw(a)strlen.de> Link: https://lore.kernel.org/r/20230817145449.141827-1-luwei32@huawei.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> conflict: drivers/net/ipvlan/ipvlan_main.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- drivers/net/ipvlan/ipvlan_main.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 403852adaff5..9057cdf9b216 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -875,12 +875,14 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - old_vnet = net_generic(oldnet, ipvlan_netid); - if (!old_vnet->ipvl_nf_hook_refcnt) - break; + if (port->mode == IPVLAN_MODE_L3S) { + old_vnet = net_generic(oldnet, ipvlan_netid); + if (!old_vnet->ipvl_nf_hook_refcnt) + break; - ipvlan_register_nf_hook(newnet); - ipvlan_unregister_nf_hook(oldnet); + ipvlan_register_nf_hook(newnet); + ipvlan_unregister_nf_hook(oldnet); + } break; } case NETDEV_UNREGISTER: -- 2.34.1

2 1

[PATCH OLK-5.10] SUNRPC: don't pause on incomplete allocation
by ZhaoLong Wang 28 Aug '23

28 Aug '23

From: NeilBrown <neilb(a)suse.de> mainline inclusion from mainline-v5.15-rc1 commit e38b3f20059426a0adbde014ff71071739ab5226 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7RRY4 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- alloc_pages_bulk_array() attempts to allocate at least one page based on the provided pages, and then opportunistically allocates more if that can be done without dropping the spinlock. So if it returns fewer than requested, that could just mean that it needed to drop the lock. In that case, try again immediately. Only pause for a time if no progress could be made. Reported-and-tested-by: Mike Javorski <mike.javorski(a)gmail.com> Reported-and-tested-by: Lothar Paltins <lopa(a)mailbox.org> Fixes: f6e70aab9dfe ("SUNRPC: refresh rq_pages using a bulk page allocator") Signed-off-by: NeilBrown <neilb(a)suse.de> Acked-by: Mel Gorman <mgorman(a)suse.com> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Conflicts: net/sunrpc/svc_xprt.c --- net/sunrpc/svc_xprt.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 362487f3a6de..f56b4df6ce28 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -643,7 +643,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct xdr_buf *arg = &rqstp->rq_arg; - unsigned long pages, filled; + unsigned long pages, filled, ret; pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; if (pages > RPCSVC_MAXPAGES) { @@ -653,11 +653,12 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) pages = RPCSVC_MAXPAGES; } - for (;;) { - filled = alloc_pages_bulk_array(GFP_KERNEL, pages, - rqstp->rq_pages); - if (filled == pages) - break; + for (filled = 0; filled < pages; filled = ret) { + ret = alloc_pages_bulk_array(GFP_KERNEL, pages, + rqstp->rq_pages); + if (ret > filled) + /* Made progress, don't sleep yet */ + continue; set_current_state(TASK_INTERRUPTIBLE); if (signalled() || kthread_should_stop()) { -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] ip6mr: Fix skb_under_panic in ip6mr_cache_report()
by Yue Haibing 26 Aug '23

26 Aug '23

mainline inclusion from mainline-v6.5-rc3 commit 30e0191b16e8a58e4620fa3e2839ddc7b9d4281c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7W5X8 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- skbuff: skb_under_panic: text:ffffffff88771f69 len:56 put:-4 head:ffff88805f86a800 data:ffff887f5f86a850 tail:0x88 end:0x2c0 dev:pim6reg ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:192! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 22968 Comm: kworker/2:11 Not tainted 6.5.0-rc3-00044-g0a8db05b571a #236 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x152/0x1d0 Call Trace: <TASK> skb_push+0xc4/0xe0 ip6mr_cache_report+0xd69/0x19b0 reg_vif_xmit+0x406/0x690 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 vlan_dev_hard_start_xmit+0x3ab/0x5c0 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 neigh_connected_output+0x3ed/0x570 ip6_finish_output2+0x5b5/0x1950 ip6_finish_output+0x693/0x11c0 ip6_output+0x24b/0x880 NF_HOOK.constprop.0+0xfd/0x530 ndisc_send_skb+0x9db/0x1400 ndisc_send_rs+0x12a/0x6c0 addrconf_dad_completed+0x3c9/0xea0 addrconf_dad_work+0x849/0x1420 process_one_work+0xa22/0x16e0 worker_thread+0x679/0x10c0 ret_from_fork+0x28/0x60 ret_from_fork_asm+0x11/0x20 When setup a vlan device on dev pim6reg, DAD ns packet may sent on reg_vif_xmit(). reg_vif_xmit() ip6mr_cache_report() skb_push(skb, -skb_network_offset(pkt));//skb_network_offset(pkt) is 4 And skb_push declared as: void *skb_push(struct sk_buff *skb, unsigned int len); skb->data -= len; //0xffff88805f86a84c - 0xfffffffc = 0xffff887f5f86a850 skb->data is set to 0xffff887f5f86a850, which is invalid mem addr, lead to skb_push() fails. Fixes: 14fb64e1f449 ("[IPV6] MROUTE: Support PIM-SM (SSM).") Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> --- net/ipv6/ip6mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index d392a72cd784..c94a06b11141 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1070,7 +1070,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); -- 2.34.1

2 1

[PATCH OLK-5.10] SUNRPC: don't pause on incomplete allocation
by ZhaoLong Wang 26 Aug '23

26 Aug '23

From: NeilBrown <neilb(a)suse.de> mainline inclusion from mainline-5.15-rc1 commit e38b3f20059426a0adbde014ff71071739ab5226 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7RRY4 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------------- alloc_pages_bulk_array() attempts to allocate at least one page based on the provided pages, and then opportunistically allocates more if that can be done without dropping the spinlock. So if it returns fewer than requested, that could just mean that it needed to drop the lock. In that case, try again immediately. Only pause for a time if no progress could be made. Reported-and-tested-by: Mike Javorski <mike.javorski(a)gmail.com> Reported-and-tested-by: Lothar Paltins <lopa(a)mailbox.org> Fixes: f6e70aab9dfe ("SUNRPC: refresh rq_pages using a bulk page allocator") Signed-off-by: NeilBrown <neilb(a)suse.de> Acked-by: Mel Gorman <mgorman(a)suse.com> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Conflicts: net/sunrpc/svc_xprt.c --- net/sunrpc/svc_xprt.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 362487f3a6de..f56b4df6ce28 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -643,7 +643,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct xdr_buf *arg = &rqstp->rq_arg; - unsigned long pages, filled; + unsigned long pages, filled, ret; pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; if (pages > RPCSVC_MAXPAGES) { @@ -653,11 +653,12 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) pages = RPCSVC_MAXPAGES; } - for (;;) { - filled = alloc_pages_bulk_array(GFP_KERNEL, pages, - rqstp->rq_pages); - if (filled == pages) - break; + for (filled = 0; filled < pages; filled = ret) { + ret = alloc_pages_bulk_array(GFP_KERNEL, pages, + rqstp->rq_pages); + if (ret > filled) + /* Made progress, don't sleep yet */ + continue; set_current_state(TASK_INTERRUPTIBLE); if (signalled() || kthread_should_stop()) { -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] ip6mr: Fix skb_under_panic in ip6mr_cache_report()
by Yue Haibing 26 Aug '23

26 Aug '23

mainline inclusion from mainline-v6.5-rc3 commit 30e0191b16e8a58e4620fa3e2839ddc7b9d4281c category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- skbuff: skb_under_panic: text:ffffffff88771f69 len:56 put:-4 head:ffff88805f86a800 data:ffff887f5f86a850 tail:0x88 end:0x2c0 dev:pim6reg ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:192! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 22968 Comm: kworker/2:11 Not tainted 6.5.0-rc3-00044-g0a8db05b571a #236 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:skb_panic+0x152/0x1d0 Call Trace: <TASK> skb_push+0xc4/0xe0 ip6mr_cache_report+0xd69/0x19b0 reg_vif_xmit+0x406/0x690 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 vlan_dev_hard_start_xmit+0x3ab/0x5c0 dev_hard_start_xmit+0x17e/0x6e0 __dev_queue_xmit+0x2d6a/0x3d20 neigh_connected_output+0x3ed/0x570 ip6_finish_output2+0x5b5/0x1950 ip6_finish_output+0x693/0x11c0 ip6_output+0x24b/0x880 NF_HOOK.constprop.0+0xfd/0x530 ndisc_send_skb+0x9db/0x1400 ndisc_send_rs+0x12a/0x6c0 addrconf_dad_completed+0x3c9/0xea0 addrconf_dad_work+0x849/0x1420 process_one_work+0xa22/0x16e0 worker_thread+0x679/0x10c0 ret_from_fork+0x28/0x60 ret_from_fork_asm+0x11/0x20 When setup a vlan device on dev pim6reg, DAD ns packet may sent on reg_vif_xmit(). reg_vif_xmit() ip6mr_cache_report() skb_push(skb, -skb_network_offset(pkt));//skb_network_offset(pkt) is 4 And skb_push declared as: void *skb_push(struct sk_buff *skb, unsigned int len); skb->data -= len; //0xffff88805f86a84c - 0xfffffffc = 0xffff887f5f86a850 skb->data is set to 0xffff887f5f86a850, which is invalid mem addr, lead to skb_push() fails. Fixes: 14fb64e1f449 ("[IPV6] MROUTE: Support PIM-SM (SSM).") Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> --- net/ipv6/ip6mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index d392a72cd784..c94a06b11141 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1070,7 +1070,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); -- 2.34.1

2 1

[PATCH openEuler-23.09 v2 0/8] enable files_cgroup
by Lu Jialin 26 Aug '23

26 Aug '23

v2->v1: enable CONFIG_CGROUP_FILES in openeuler_defconfig for x86 and arm64 Binder Makin (1): cgroups: Resource controller for open files Hou Tao (1): cgroup/files: use task_get_css() to get a valid css during dup_fd() Lu Jialin (3): fs: fix files.usage bug when move tasks fs/filescontrol.c: fix warning:large integer implicitly truncated to unsigned type openeuler_defconfig: enable CONFIG_CGROUP_FILES in openeuler_defconfig for x86 and arm64 Yu Kuai (1): fs/filescontrol: add a switch to enable / disable accounting of open fds Zhang Xiaoxu (1): files_cgroup: fix error pointer when kvm_vm_worker_thread yangerkun (1): fs/dcache.c: avoid panic while lockref of dentry overflow arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/Makefile | 1 + fs/dcache.c | 32 ++- fs/file.c | 53 ++++- fs/filescontrol.c | 312 +++++++++++++++++++++++++ include/linux/cgroup-defs.h | 8 +- include/linux/cgroup_subsys.h | 6 + include/linux/fdtable.h | 1 + include/linux/filescontrol.h | 34 +++ include/linux/fs.h | 3 + init/Kconfig | 10 + 12 files changed, 453 insertions(+), 9 deletions(-) create mode 100644 fs/filescontrol.c create mode 100644 include/linux/filescontrol.h -- 2.34.1

2 9

[PATCH v2 OLK-5.10 0/4] Synchronizing mainline HiSilicon uncore PMU patches
by Junhao He 25 Aug '23

25 Aug '23

Synchronizing mainline HiSilicon uncore PMU patches The HISI uncore UC PMU and uncore H60PA/PAv3 PMU drivers have been integrated into the main line. Compared with OLK-5.10, some modifications are made. Add support for HiSilicon UC/H60PA/PAv3 PMU driver. PAv3 PMU: Compared with the PAv2 PMU, the PAv3 PMU has different event. The PAv3 PMU removed some events which are supported by PAv2 PMU. The older PA PMU driver will probe v3 as v2. Add the HISI0275 HID for PAv3 PMU to distinguish different. H60PA PMU: The H60PA PMU and PA are two different devices. The H60PA PMU supports higher bandwidth, and the PA PMU delay is relatively low. Different HIDs are used to distinguish the delay. UC PMU: Each cluster is integrated with a unified cache (UC) PMU, which provides consistency between NUMA and UMA domains. It sits between L2 and the memory system. Junhao He (4): Revert "drivers/perf: hisi: Add support for HiSilicon UC PMU driver" Revert "drivers/perf: hisi: Add support for HiSilicon H60PA and PAv3 PMU driver" drivers/perf: hisi: Add support for HiSilicon H60PA and PAv3 PMU driver drivers/perf: hisi: Add support for HiSilicon UC PMU driver drivers/perf/hisilicon/hisi_uncore_pa_pmu.c | 107 +++++++++----------- drivers/perf/hisilicon/hisi_uncore_pmu.c | 5 +- drivers/perf/hisilicon/hisi_uncore_pmu.h | 32 +----- drivers/perf/hisilicon/hisi_uncore_uc_pmu.c | 35 +++---- 4 files changed, 72 insertions(+), 107 deletions(-) -- 2.33.0

2 5

[PATCH v2 openEuler-22.03-LTS-SP2] mm: add preferred_swap ability
by liubo 25 Aug '23

25 Aug '23

From: Ni Cunshu <nicunshu(a)huawei.com> euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I7U78A CVE: NA ------------------------------------------------ add a new attribute preferred_swap for each process, which indicates the swapfile or swap device that can be used by the process. Each process can only have one preferred_swap. Signed-off-by: Ni Cunshu <nicunshu(a)huawei.com> --- fs/proc/base.c | 113 +++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 4 ++ include/linux/swap.h | 13 +++++ kernel/fork.c | 4 ++ mm/Kconfig | 7 +++ mm/swap_slots.c | 68 ++++++++++++++++++++++- mm/swapfile.c | 86 ++++++++++++++++++++++++++++- 7 files changed, 292 insertions(+), 3 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 24c70ff923b8..34537572db57 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3330,6 +3330,116 @@ static const struct file_operations proc_preferred_cpuset_operations = { }; #endif +#ifdef CONFIG_PREFERRED_SWAP +static ssize_t proc_preferred_swap_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + struct mm_struct *mm; + int ret; + int err = 0; + size_t len; + char *buffer; + char *path; + + if (!task) + return -ESRCH; + + ret = 0; + mm = get_task_mm(task); + if (!mm) + goto out_no_mm; + + if (mm->preferred_swap) { + buffer = (char *)kmalloc(PATH_MAX + 1, GFP_KERNEL); + if (buffer == NULL) { + err = -ENOMEM; + goto out; + } + + path = d_path(&mm->preferred_swap->swap_file->f_path, + buffer, PATH_MAX); + + if (IS_ERR(path)) { + err = PTR_ERR(path); + kfree(buffer); + goto out; + } + + len = snprintf(buffer, strlen(path) + 2, "%s\n", path); + ret = simple_read_from_buffer(buf, count, ppos, buffer, len); + kfree(buffer); + } +out: + mmput(mm); +out_no_mm: + put_task_struct(task); + if (err < 0) + return err; + return ret; +} + +static ssize_t proc_preferred_swap_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + struct task_struct *task; + struct mm_struct *mm; + char *buffer; + int err = 0; + + if (count >= PATH_MAX) + return -EINVAL; + + buffer = (char *)kmalloc(PATH_MAX, GFP_KERNEL); + if (buffer == NULL) { + err = -ENOMEM; + goto out_no_buffer; + } + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out_no_task; + } + buffer[count] = '\0'; + strreplace(buffer, '\n', '\0'); + task = get_proc_task(file_inode(file)); + if (!task) { + err = -ESRCH; + goto out_no_task; + } + mm = get_task_mm(task); + if (!mm) { + err = -ESRCH; + goto out_no_mm; + } + if (strlen(buffer) == 0) { + mm->preferred_swap = NULL; + goto out; + } + err = find_swap_info(buffer, mm); + if (err) { + pr_info("%s failed to be found as swap\n", buffer); + goto out; + } + + preferred_swap_used = 1; +out: + mmput(mm); +out_no_mm: + put_task_struct(task); +out_no_task: + kfree(buffer); +out_no_buffer: + if (err < 0) + return err; + return count; +} +static const struct file_operations proc_preferred_swap_operations = { + .write = proc_preferred_swap_write, + .read = proc_preferred_swap_read, + .llseek = generic_file_llseek, +}; +#endif /* CONFIG_PREFERRED_SWAP */ + static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -3526,6 +3636,9 @@ static const struct pid_entry tgid_base_stuff[] = { ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat), #endif +#ifdef CONFIG_PREFERRED_SWAP + REG("preferred_swap", S_IRUGO|S_IWUSR, proc_preferred_swap_operations), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e3eaf458787a..2edd816fba7f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -638,7 +638,11 @@ struct mm_struct { KABI_RESERVE(2) KABI_RESERVE(3) #endif +#ifdef CONFIG_PREFERRED_SWAP + KABI_USE(4, struct swap_info_struct *preferred_swap) +#else KABI_RESERVE(4) +#endif KABI_RESERVE(5) KABI_RESERVE(6) KABI_RESERVE(7) diff --git a/include/linux/swap.h b/include/linux/swap.h index 7f49964f27d2..998f10e97601 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -389,6 +389,10 @@ extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long reclaim_pages(struct list_head *page_list); +#ifdef CONFIG_PREFERRED_SWAP +extern int find_swap_info(char *filename, struct mm_struct *mm); +extern void clear_tasks_mm_preferred_swap(struct swap_info_struct *p); +#endif #ifdef CONFIG_ETMEM enum etmem_swapcache_watermark_en { ETMEM_SWAPCACHE_WMARK_LOW, @@ -496,6 +500,10 @@ extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +#ifdef CONFIG_PREFERRED_SWAP +extern int preferred_swap_used; +#endif + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { @@ -511,7 +519,12 @@ extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(struct page *page); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); +#ifdef CONFIG_PREFERRED_SWAP +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size, + struct swap_info_struct *preferred_swap); +#else extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); +#endif extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); diff --git a/kernel/fork.c b/kernel/fork.c index 2547c6a6e5b1..734882ed98c6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1072,6 +1072,10 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_uprobes_state(mm); hugetlb_count_init(mm); +#ifdef CONFIG_PREFERRED_SWAP + mm->preferred_swap = NULL; +#endif + if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; diff --git a/mm/Kconfig b/mm/Kconfig index f66457168de9..48c37c3bda8c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -999,6 +999,13 @@ config EXTEND_HUGEPAGE_MAPPING help Introduce vmalloc/vmap/remap interfaces that handle only hugepages. +config PREFERRED_SWAP + bool "make task only swapping memory to assigned swap" + depends on SYSFS + default y + help + Say Y here to enable kernel to limit tasks only swapping memory to assigned swap. + source "mm/damon/Kconfig" endmenu diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 0357fbe70645..79a3164bf393 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -33,6 +33,9 @@ #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> +#ifdef CONFIG_PREFERRED_SWAP +#include <linux/rmap.h> +#endif static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots); static bool swap_slot_cache_active; @@ -265,8 +268,13 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache) cache->cur = 0; if (swap_slot_cache_active) +#ifdef CONFIG_PREFERRED_SWAP + cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, + cache->slots, 1, NULL); +#else cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, cache->slots, 1); +#endif return cache->nr; } @@ -303,16 +311,66 @@ int free_swap_slot(swp_entry_t entry) return 0; } +#ifdef CONFIG_PREFERRED_SWAP +static bool has_preferred_swap(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct swap_info_struct **si = (struct swap_info_struct **)arg; + + if (*si) { + *si = ERR_PTR(-EPERM); + return false; + } + if (vma->vm_file) { + *si = ERR_PTR(-EPERM); + return false; + } + if (vma->vm_mm->preferred_swap) { + *si = vma->vm_mm->preferred_swap; + } else { + *si = ERR_PTR(-EPERM); + return false; + } + return true; +} + +static struct swap_info_struct *page_preferred_swap(struct page *page) +{ + struct swap_info_struct *preferred_swap = NULL; + struct rmap_walk_control rwc = { + .rmap_one = has_preferred_swap, + .arg = (void *)&preferred_swap, + .anon_lock = page_lock_anon_vma_read, + }; + rmap_walk(page, &rwc); + if (IS_ERR_OR_NULL(preferred_swap)) + preferred_swap = NULL; + + return preferred_swap; +} +#endif /* CONFIG_PREFERRED_SWAP */ + swp_entry_t get_swap_page(struct page *page) { swp_entry_t entry; struct swap_slots_cache *cache; +#ifdef CONFIG_PREFERRED_SWAP + struct swap_info_struct *preferred_swap = NULL; + + if (!page_mapping(page)) + preferred_swap = page_preferred_swap(page); +#endif + entry.val = 0; if (PageTransHuge(page)) { if (IS_ENABLED(CONFIG_THP_SWAP)) +#ifdef CONFIG_PREFERRED_SWAP + get_swap_pages(1, &entry, HPAGE_PMD_NR, preferred_swap); +#else get_swap_pages(1, &entry, HPAGE_PMD_NR); +#endif goto out; } @@ -327,7 +385,11 @@ swp_entry_t get_swap_page(struct page *page) */ cache = raw_cpu_ptr(&swp_slots); - if (likely(check_cache_active() && cache->slots)) { +#ifdef CONFIG_PREFERRED_SWAP + if (likely(check_cache_active() && cache->slots && !preferred_swap)) { +#else + if (likely(check_cache_active() && cache->slots &&)) { +#endif mutex_lock(&cache->alloc_lock); if (cache->slots) { repeat: @@ -344,7 +406,11 @@ swp_entry_t get_swap_page(struct page *page) goto out; } +#ifdef CONFIG_PREFERRED_SWAP + get_swap_pages(1, &entry, 1, preferred_swap); +#else get_swap_pages(1, &entry, 1); +#endif out: if (mem_cgroup_try_charge_swap(page, entry)) { put_swap_page(page, entry); diff --git a/mm/swapfile.c b/mm/swapfile.c index 14e2396fa8a3..835f8a8913b6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -62,7 +62,10 @@ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; - +#ifdef CONFIG_PREFERRED_SWAP +DEFINE_SPINLOCK(preferred_swap_lock); +int preferred_swap_used; +#endif static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; @@ -1056,7 +1059,13 @@ static unsigned long scan_swap_map(struct swap_info_struct *si, } -int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) +#ifdef CONFIG_PREFERRED_SWAP +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], + int entry_size, struct swap_info_struct *preferred_swap) +#else +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], + int entry_size) +#endif { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; @@ -1082,6 +1091,10 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { +#ifdef CONFIG_PREFERRED_SWAP + if (preferred_swap && preferred_swap != si) + goto nextsi; +#endif /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); @@ -2643,6 +2656,10 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); +#ifdef CONFIG_PREFERRED_SWAP + if (preferred_swap_used) + clear_tasks_mm_preferred_swap(p); +#endif disable_swap_slots_cache_lock(); @@ -3878,6 +3895,71 @@ void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) } #endif +#ifdef CONFIG_PREFERRED_SWAP +int find_swap_info(char *filename, struct mm_struct *mm) +{ + struct file *chosen_file; + unsigned int type; + struct path path; + int err = 0; + struct swap_info_struct *found_swap = NULL; + + err = kern_path(filename, LOOKUP_FOLLOW, &path); + if (err) + goto out_no_path; + chosen_file = dentry_open(&path, O_RDWR|O_LARGEFILE, current_cred()); + if (IS_ERR(chosen_file)) { + err = PTR_ERR(chosen_file); + goto out_no_file; + } + spin_lock(&preferred_swap_lock); + spin_lock(&swap_lock); + for (type = 0; type < nr_swapfiles; type++) { + if ((swap_info[type]->flags & SWP_USED) && + (swap_info[type]->flags & SWP_WRITEOK)) { + if (swap_info[type]->swap_file->f_mapping == + chosen_file->f_mapping) { + found_swap = swap_info[type]; + break; + } + } + } + + spin_unlock(&swap_lock); + if (type >= nr_swapfiles) { + err = -EINVAL; + goto out; + } + + mm->preferred_swap = found_swap; +out: + spin_unlock(&preferred_swap_lock); + filp_close(chosen_file, NULL); +out_no_file: + path_put(&path); +out_no_path: + return err; +} + +void clear_tasks_mm_preferred_swap(struct swap_info_struct *p) +{ + struct task_struct *task; + struct mm_struct *mm; + + spin_lock(&preferred_swap_lock); + read_lock(&tasklist_lock); + for_each_process(task) { + mm = get_task_mm(task); + if (mm) { + if (mm->preferred_swap == p) + mm->preferred_swap = NULL; + mmput(mm); + } + } + read_unlock(&tasklist_lock); + spin_unlock(&preferred_swap_lock); +} +#endif static int __init swapfile_init(void) { int nid; -- 2.27.0

2 1