- Linux-stable-mirror - lists.linaro.org

[PATCH v4 3/6] LoongArch: KVM: Disable update property num_cpu and feature

by Bibo Mao

Property num_cpu and feature is read-only once eiointc is created, which is set with KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL attr group before device creation. Attr group KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS is to update register and software state for migration and reset usage, property num_cpu and feature can not be update again if it is created already. Here discard write operation with property num_cpu and feature in attr group KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL. Cc: stable(a)vger.kernel.org Fixes: 1ad7efa552fd ("LoongArch: KVM: Add EIOINTC user mode read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index 0b648c56b0c3..b48511f903b5 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -910,9 +910,22 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev, data = (void __user *)attr->addr; switch (addr) { case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU: + /* + * Property num_cpu and feature is read-only once eiointc is + * created with KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL group API + * + * Disable writing with KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS + * group API + */ + if (is_write) + return ret; + p = &s->num_cpu; break; case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE: + if (is_write) + return ret; + p = &s->features; break; case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE: -- 2.39.3

6 days, 5 hours

1
0
0 0

[PATCH v4 2/6] LoongArch: KVM: Check interrupt route from physical cpu

by Bibo Mao

With eiointc interrupt controller, physical cpu id is set for irq route. However function kvm_get_vcpu() is used to get destination vCPU when delivering irq. With API kvm_get_vcpu(), logical cpu is used. With API kvm_get_vcpu_by_cpuid(), vCPU can be searched from physical cpu id. Cc: stable(a)vger.kernel.org Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index d2c521b0e923..0b648c56b0c3 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -9,7 +9,8 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) { - int ipnum, cpu, irq_index, irq_mask, irq; + int ipnum, cpu, irq_index, irq_mask, irq, cpuid; + struct kvm_vcpu *vcpu; for (irq = 0; irq < EIOINTC_IRQS; irq++) { ipnum = s->ipmap.reg_u8[irq / 32]; @@ -20,7 +21,12 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s) irq_index = irq / 32; irq_mask = BIT(irq & 0x1f); - cpu = s->coremap.reg_u8[irq]; + cpuid = s->coremap.reg_u8[irq]; + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (vcpu == NULL) + continue; + + cpu = vcpu->vcpu_id; if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask)) set_bit(irq, s->sw_coreisr[cpu][ipnum]); else @@ -68,17 +74,23 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, int irq, u64 val, u32 len, bool notify) { - int i, cpu; + int i, cpu, cpuid; + struct kvm_vcpu *vcpu; for (i = 0; i < len; i++) { - cpu = val & 0xff; + cpuid = val & 0xff; val = val >> 8; if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) { - cpu = ffs(cpu) - 1; - cpu = (cpu >= 4) ? 0 : cpu; + cpuid = ffs(cpuid) - 1; + cpuid = (cpuid >= 4) ? 0 : cpuid; } + vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid); + if (vcpu == NULL) + continue; + + cpu = vcpu->vcpu_id; if (s->sw_coremap[irq + i] == cpu) continue; -- 2.39.3

6 days, 5 hours

1
0
0 0

[PATCH v4 1/6] LoongArch: KVM: Fix interrupt route update with eiointc

by Bibo Mao

With function eiointc_update_sw_coremap(), there is forced assignment like val = *(u64 *)pvalue. Parameter pvalue may be pointer to char type or others, there is problem with forced assignment with u64 type. Here the detailed value is passed rather address pointer. Cc: stable(a)vger.kernel.org Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index f39929d7bf8a..d2c521b0e923 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -66,10 +66,9 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) } static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s, - int irq, void *pvalue, u32 len, bool notify) + int irq, u64 val, u32 len, bool notify) { int i, cpu; - u64 val = *(u64 *)pvalue; for (i = 0; i < len; i++) { cpu = val & 0xff; @@ -398,7 +397,7 @@ static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq; s->coremap.reg_u8[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -484,7 +483,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 1; s->coremap.reg_u16[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -570,7 +569,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 2; s->coremap.reg_u32[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -656,7 +655,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu, irq = offset - EIOINTC_COREMAP_START; index = irq >> 3; s->coremap.reg_u64[index] = data; - eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true); + eiointc_update_sw_coremap(s, irq, data, sizeof(data), true); break; default: ret = -EINVAL; @@ -809,7 +808,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, for (i = 0; i < (EIOINTC_IRQS / 4); i++) { start_irq = i * 4; eiointc_update_sw_coremap(s, start_irq, - (void *)&s->coremap.reg_u32[i], sizeof(u32), false); + s->coremap.reg_u32[i], sizeof(u32), false); } break; default: -- 2.39.3

6 days, 5 hours

1
0
0 0

[PATCH v3 4/9] LoongArch: KVM: INTC: Check validation of num_cpu from user space

by Bibo Mao

The maximum supported cpu number is EIOINTC_ROUTE_MAX_VCPUS about irqchip eiointc, here add validation about cpu number to avoid array pointer overflow. Cc: stable(a)vger.kernel.org Fixes: 1ad7efa552fd ("LoongArch: KVM: Add EIOINTC user mode read and write functions") Signed-off-by: Bibo Mao <maobibo(a)loongson.cn> --- arch/loongarch/kvm/intc/eiointc.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index b48511f903b5..ed80bf290755 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -798,7 +798,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, int ret = 0; unsigned long flags; unsigned long type = (unsigned long)attr->attr; - u32 i, start_irq; + u32 i, start_irq, val; void __user *data; struct loongarch_eiointc *s = dev->kvm->arch.eiointc; @@ -806,7 +806,12 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev, spin_lock_irqsave(&s->lock, flags); switch (type) { case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU: - if (copy_from_user(&s->num_cpu, data, 4)) + if (copy_from_user(&val, data, 4) == 0) { + if (val < EIOINTC_ROUTE_MAX_VCPUS) + s->num_cpu = val; + else + ret = -EINVAL; + } else ret = -EFAULT; break; case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE: @@ -835,7 +840,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { - int addr, cpuid, offset, ret = 0; + int addr, cpu, offset, ret = 0; unsigned long flags; void *p = NULL; void __user *data; @@ -843,7 +848,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, s = dev->kvm->arch.eiointc; addr = attr->attr; - cpuid = addr >> 16; + cpu = addr >> 16; addr &= 0xffff; data = (void __user *)attr->addr; switch (addr) { @@ -868,8 +873,11 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev, p = &s->isr.reg_u32[offset]; break; case EIOINTC_COREISR_START ... EIOINTC_COREISR_END: + if (cpu >= s->num_cpu) + return -EINVAL; + offset = (addr - EIOINTC_COREISR_START) / 4; - p = &s->coreisr.reg_u32[cpuid][offset]; + p = &s->coreisr.reg_u32[cpu][offset]; break; case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END: offset = (addr - EIOINTC_COREMAP_START) / 4; -- 2.39.3

6 days, 6 hours

2
5
0 0

[PATCH 5.15] bpf, sockmap: Fix skb refcnt race after locking changes

by Pranav Tyagi

From: John Fastabend <john.fastabend(a)gmail.com> [ Upstream commit a454d84ee20baf7bd7be90721b9821f73c7d23d9 ] There is a race where skb's from the sk_psock_backlog can be referenced after userspace side has already skb_consumed() the sk_buff and its refcnt dropped to zer0 causing use after free. The flow is the following: while ((skb = skb_peek(&psock->ingress_skb)) sk_psock_handle_Skb(psock, skb, ..., ingress) if (!ingress) ... sk_psock_skb_ingress sk_psock_skb_ingress_enqueue(skb) msg->skb = skb sk_psock_queue_msg(psock, msg) skb_dequeue(&psock->ingress_skb) The sk_psock_queue_msg() puts the msg on the ingress_msg queue. This is what the application reads when recvmsg() is called. An application can read this anytime after the msg is placed on the queue. The recvmsg hook will also read msg->skb and then after user space reads the msg will call consume_skb(skb) on it effectively free'ing it. But, the race is in above where backlog queue still has a reference to the skb and calls skb_dequeue(). If the skb_dequeue happens after the user reads and free's the skb we have a use after free. The !ingress case does not suffer from this problem because it uses sendmsg_*(sk, msg) which does not pass the sk_buff further down the stack. The following splat was observed with 'test_progs -t sockmap_listen': [ 1022.710250][ T2556] general protection fault, ... [...] [ 1022.712830][ T2556] Workqueue: events sk_psock_backlog [ 1022.713262][ T2556] RIP: 0010:skb_dequeue+0x4c/0x80 [ 1022.713653][ T2556] Code: ... [...] [ 1022.720699][ T2556] Call Trace: [ 1022.720984][ T2556] <TASK> [ 1022.721254][ T2556] ? die_addr+0x32/0x80^M [ 1022.721589][ T2556] ? exc_general_protection+0x25a/0x4b0 [ 1022.722026][ T2556] ? asm_exc_general_protection+0x22/0x30 [ 1022.722489][ T2556] ? skb_dequeue+0x4c/0x80 [ 1022.722854][ T2556] sk_psock_backlog+0x27a/0x300 [ 1022.723243][ T2556] process_one_work+0x2a7/0x5b0 [ 1022.723633][ T2556] worker_thread+0x4f/0x3a0 [ 1022.723998][ T2556] ? __pfx_worker_thread+0x10/0x10 [ 1022.724386][ T2556] kthread+0xfd/0x130 [ 1022.724709][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725066][ T2556] ret_from_fork+0x2d/0x50 [ 1022.725409][ T2556] ? __pfx_kthread+0x10/0x10 [ 1022.725799][ T2556] ret_from_fork_asm+0x1b/0x30 [ 1022.726201][ T2556] </TASK> To fix we add an skb_get() before passing the skb to be enqueued in the engress queue. This bumps the skb->users refcnt so that consume_skb() and kfree_skb will not immediately free the sk_buff. With this we can be sure the skb is still around when we do the dequeue. Then we just need to decrement the refcnt or free the skb in the backlog case which we do by calling kfree_skb() on the ingress case as well as the sendmsg case. Before locking change from fixes tag we had the sock locked so we couldn't race with user and there was no issue here. [ Backport to 5.15: context cleanly applied with no semantic changes. Build-tested. ] Fixes: 799aa7f98d53e ("skmsg: Avoid lock_sock() in sk_psock_backlog()") Reported-by: Jiri Olsa <jolsa(a)kernel.org> Signed-off-by: John Fastabend <john.fastabend(a)gmail.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Tested-by: Xu Kuohai <xukuohai(a)huawei.com> Tested-by: Jiri Olsa <jolsa(a)kernel.org> Link: https://lore.kernel.org/bpf/20230901202137.214666-1-john.fastabend@gmail.com Signed-off-by: Pranav Tyagi <pranav.tyagi03(a)gmail.com> --- net/core/skmsg.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a5947aa55983..a13ddb9976ad 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -608,12 +608,18 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { + int err = 0; + if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb, off, len); + skb_get(skb); + err = sk_psock_skb_ingress(psock, skb, off, len); + if (err < 0) + kfree_skb(skb); + return err; } static void sk_psock_skb_state(struct sk_psock *psock, @@ -681,9 +687,7 @@ static void sk_psock_backlog(struct work_struct *work) } while (len); skb = skb_dequeue(&psock->ingress_skb); - if (!ingress) { - kfree_skb(skb); - } + kfree_skb(skb); } end: mutex_unlock(&psock->work_mutex); -- 2.49.0

6 days, 6 hours

1
0
0 0

[PATCH] ipmi: fix underflow in ipmi_create_user()

by Yi Yang

Syzkaller reported this bug: ================================================================== BUG: KASAN: global-out-of-bounds in instrument_atomic_read_write include/linux/instrumented.h:96 [inline] BUG: KASAN: global-out-of-bounds in atomic_dec include/linux/atomic/atomic-instrumented.h:592 [inline] BUG: KASAN: global-out-of-bounds in ipmi_create_user.part.0+0x5e5/0x790 drivers/char/ipmi/ipmi_msghandler.c:1291 Write of size 4 at addr ffffffff8fc6a438 by task syz.5.1074/5888 CPU: 0 PID: 5888 Comm: syz.5.1074 Not tainted 6.6.0+ #60 ...... Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description.constprop.0+0x6b/0x3d0 mm/kasan/report.c:364 print_report+0xba/0x280 mm/kasan/report.c:475 kasan_report+0xa9/0xe0 mm/kasan/report.c:588 check_region_inline mm/kasan/generic.c:181 [inline] kasan_check_range+0x100/0x1c0 mm/kasan/generic.c:187 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_dec include/linux/atomic/atomic-instrumented.h:592 [inline] ipmi_create_user.part.0+0x5e5/0x790 drivers/char/ipmi/ipmi_msghandler.c:1291 ipmi_create_user+0x56/0x80 drivers/char/ipmi/ipmi_msghandler.c:1236 ipmi_open+0xac/0x2b0 drivers/char/ipmi/ipmi_devintf.c:97 chrdev_open+0x276/0x700 fs/char_dev.c:414 do_dentry_open+0x6a7/0x1410 fs/open.c:929 vfs_open+0xd1/0x440 fs/open.c:1060 do_open+0x957/0x10d0 fs/namei.c:3671 path_openat+0x258/0x770 fs/namei.c:3830 do_filp_open+0x1c7/0x410 fs/namei.c:3857 do_sys_openat2+0x5bd/0x6a0 fs/open.c:1428 do_sys_open fs/open.c:1443 [inline] __do_sys_openat fs/open.c:1459 [inline] __se_sys_openat fs/open.c:1454 [inline] __x64_sys_openat+0x17a/0x210 fs/open.c:1454 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x59/0x110 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x78/0xe2 RIP: 0033:0x54d2cd Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 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 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f4751920048 EFLAGS: 00000246 ORIG_RAX: 0000000000000101 RAX: ffffffffffffffda RBX: 0000000000796080 RCX: 000000000054d2cd RDX: 0000000000000000 RSI: 0000000020004280 RDI: ffffffffffffff9c RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000001e R11: 0000000000000246 R12: 000000000079608c R13: 0000000000000000 R14: 0000000000796080 R15: 00007f4751900000 </TASK> The buggy address belongs to the variable: ipmi_interfaces+0x38/0x40 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x45a6a flags: 0x3fffff00004000(reserved|node=0|zone=1|lastcpupid=0x1fffff) raw: 003fffff00004000 ffffea0001169a88 ffffea0001169a88 0000000000000000 raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffffffff8fc6a300: 00 00 00 00 f9 f9 f9 f9 00 00 00 00 f9 f9 f9 f9 ffffffff8fc6a380: 00 00 f9 f9 f9 f9 f9 f9 00 00 00 00 f9 f9 f9 f9 >ffffffff8fc6a400: 00 00 f9 f9 f9 f9 f9 f9 00 00 00 00 f9 f9 f9 f9 ^ ffffffff8fc6a480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffff8fc6a500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f9 f9 ================================================================== In the ipmi_create_user() function, the intf->nr_users variable has an underflow issue. Specifically, on the exception path (goto out_kfree;) before atomic_add_return(), calling atomic_dec() when intf->nr_users has not been incremented will result in an underflow. The relevant code has been completely rewritten in the next tree and has been fixed with commit 9e91f8a6c868 ("ipmi:msghandler: Remove srcu for the ipmi_interfaces list"). However, the issue still exists in the 5.19+ stable branches and needs to be fixed on those branches. Cc: stable(a)vger.kernel.org # 5.19+ Fixes: 8e76741c3d8b ("ipmi: Add a limit on the number of users that may use IPMI") Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/char/ipmi/ipmi_msghandler.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 186f1fee7534..0293fad2f4f2 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1246,18 +1246,18 @@ int ipmi_create_user(unsigned int if_num, found: if (atomic_add_return(1, &intf->nr_users) > max_users) { rv = -EBUSY; - goto out_kfree; + goto out_dec; } INIT_WORK(&new_user->remove_work, free_user_work); rv = init_srcu_struct(&new_user->release_barrier); if (rv) - goto out_kfree; + goto out_dec; if (!try_module_get(intf->owner)) { rv = -ENODEV; - goto out_kfree; + goto out_dec; } /* Note that each existing user holds a refcount to the interface. */ @@ -1281,8 +1281,9 @@ int ipmi_create_user(unsigned int if_num, *user = new_user; return 0; -out_kfree: +out_dec: atomic_dec(&intf->nr_users); +out_kfree: srcu_read_unlock(&ipmi_interfaces_srcu, index); vfree(new_user); return rv; -- 2.25.1

6 days, 6 hours

1
1
0 0

[PATCH v2] iommu/rockchip: prevent iommus dead loop when two masters share one IOMMU

by Simon Xue

When two masters share an IOMMU, calling ops->of_xlate during the second master's driver init may overwrite iommu->domain set by the first. This causes the check if (iommu->domain == domain) in rk_iommu_attach_device() to fail, resulting in the same iommu->node being added twice to &rk_domain->iommus, which can lead to an infinite loop in subsequent &rk_domain->iommus operations. Fixes: 25c2325575cc ("iommu/rockchip: Add missing set_platform_dma_ops callback") Signed-off-by: Simon Xue <xxm(a)rock-chips.com> Reviewed-by: Robin Murphy <robin.murphy(a)arm.com> v2: No functional changes. --- drivers/iommu/rockchip-iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 22f74ba33a0e..e6bb3c784017 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1157,7 +1157,6 @@ static int rk_iommu_of_xlate(struct device *dev, return -ENOMEM; data->iommu = platform_get_drvdata(iommu_dev); - data->iommu->domain = &rk_identity_domain; dev_iommu_priv_set(dev, data); platform_device_put(iommu_dev); @@ -1195,6 +1194,8 @@ static int rk_iommu_probe(struct platform_device *pdev) if (!iommu) return -ENOMEM; + iommu->domain = &rk_identity_domain; + platform_set_drvdata(pdev, iommu); iommu->dev = dev; iommu->num_mmu = 0; -- 2.34.1

6 days, 7 hours

3
3
0 0

[PATCH v2] x86/sev: Use TSC_FACTOR for Secure TSC frequency calculation

by Nikunj A Dadhania

When using Secure TSC, the GUEST_TSC_FREQ MSR reports a frequency based on the nominal P0 frequency, which deviates slightly (typically ~0.2%) from the actual mean TSC frequency due to clocking parameters. Over extended VM uptime, this discrepancy accumulates, causing clock skew between the hypervisor and SEV-SNP VM, leading to early timer interrupts as perceived by the guest. The guest kernel relies on the reported nominal frequency for TSC-based timekeeping, while the actual frequency set during SNP_LAUNCH_START may differ. This mismatch results in inaccurate time calculations, causing the guest to perceive hrtimers as firing earlier than expected. Utilize the TSC_FACTOR from the SEV firmware's secrets page (see "Secrets Page Format" in the SNP Firmware ABI Specification) to calculate the mean TSC frequency, ensuring accurate timekeeping and mitigating clock skew in SEV-SNP VMs. Use early_ioremap_encrypted() to map the secrets page as ioremap_encrypted() uses kmalloc() which is not available during early TSC initialization and causes a panic. Fixes: 73bbf3b0fbba ("x86/tsc: Init the TSC for Secure TSC guests") Cc: stable(a)vger.kernel.org Signed-off-by: Nikunj A Dadhania <nikunj(a)amd.com> --- v2: * Move the SNP TSC scaling constant to the header (Dionna) * Drop the unsigned long cast and add in securetsc_get_tsc_khz (Tom) * Drop the RB from Tom as the code has changed --- arch/x86/include/asm/sev.h | 18 +++++++++++++++++- arch/x86/coco/sev/core.c | 16 ++++++++++++++-- 2 files changed, 31 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index fbb616fcbfb8..869355367210 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -223,6 +223,19 @@ struct snp_tsc_info_resp { u8 rsvd2[100]; } __packed; + +/* + * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with + * TSC_FACTOR as documented in the SNP Firmware ABI specification: + * + * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001)) + * + * which is equivalent to: + * + * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000; + */ +#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - ((freq) * (factor)) / 100000) + struct snp_guest_req { void *req_buf; size_t req_sz; @@ -283,8 +296,11 @@ struct snp_secrets_page { u8 svsm_guest_vmpl; u8 rsvd3[3]; + /* The percentage decrease from nominal to mean TSC frequency. */ + u32 tsc_factor; + /* Remainder of page */ - u8 rsvd4[3744]; + u8 rsvd4[3740]; } __packed; struct snp_msg_desc { diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index 8375ca7fbd8a..36f419ff25d4 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -2156,20 +2156,32 @@ void __init snp_secure_tsc_prepare(void) static unsigned long securetsc_get_tsc_khz(void) { - return snp_tsc_freq_khz; + return (unsigned long)snp_tsc_freq_khz; } void __init snp_secure_tsc_init(void) { + struct snp_secrets_page *secrets; unsigned long long tsc_freq_mhz; + void *mem; if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) return; + mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE); + if (!mem) { + pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n"); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC); + } + + secrets = (__force struct snp_secrets_page *)mem; + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz); - snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000); + snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor); x86_platform.calibrate_cpu = securetsc_get_tsc_khz; x86_platform.calibrate_tsc = securetsc_get_tsc_khz; + + early_memunmap(mem, PAGE_SIZE); } base-commit: 49151ac6671fe0372261054daf5e4da3567b8271 -- 2.43.0

6 days, 11 hours

4
4
0 0

[PATCH v3 0/6] media: ti, cdns: Multiple pixel support and misc fixes

by Jai Luthra

Hi, The first four patches in this series are miscellaneous fixes and improvements in the Cadence and TI CSI-RX drivers around probing, fwnode and link creation. The last two patches add support for transmitting multiple pixels per clock on the internal bus between Cadence CSI-RX bridge and TI CSI-RX wrapper. As this internal bus is 32-bit wide, the maximum number of pixels that can be transmitted per cycle depend upon the format's bit width. Secondly, the downstream element must support unpacking of multiple pixels. Thus we export a module function that can be used by the downstream driver to negotiate the pixels per cycle on the output pixel stream of the Cadence bridge. Signed-off-by: Jai Luthra <jai.luthra(a)ideasonboard.com> --- Changes in v3: - Move cdns-csi2rx header to include/media - Export symbol from cdns-csi2rx.c to be used only through the j721e-csi2rx.c module namespace - Other minor fixes suggested by Sakari - Add Abhilash's T-by tags - Link to v2: https://lore.kernel.org/r/20250410-probe_fixes-v2-0-801bc6eebdea@ideasonboa… Changes in v2: - Rebase on v6.15-rc1 - Fix lkp warnings in PATCH 5/6 missing header for FIELD_PREP - Add R-By tags from Devarsh and Changhuang - Link to v1: https://lore.kernel.org/r/20250324-probe_fixes-v1-0-5cd5b9e1cfac@ideasonboa… --- Jai Luthra (6): media: ti: j721e-csi2rx: Use devm_of_platform_populate media: ti: j721e-csi2rx: Use fwnode_get_named_child_node media: ti: j721e-csi2rx: Fix source subdev link creation media: cadence: csi2rx: Implement get_fwnode_pad op media: cadence: cdns-csi2rx: Support multiple pixels per clock cycle media: ti: j721e-csi2rx: Support multiple pixels per clock MAINTAINERS | 1 + drivers/media/platform/cadence/cdns-csi2rx.c | 74 ++++++++++++++++------ drivers/media/platform/ti/Kconfig | 3 +- .../media/platform/ti/j721e-csi2rx/j721e-csi2rx.c | 65 ++++++++++++++----- include/media/cadence/cdns-csi2rx.h | 19 ++++++ 5 files changed, 127 insertions(+), 35 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250314-probe_fixes-7e0ec33c7fee Best regards, -- Jai Luthra <jai.luthra(a)ideasonboard.com>

6 days, 13 hours

1
2
0 0

[PATCH v2 1/1] iommu/vt-d: Assign devtlb cache tag on ATS enablement

by Lu Baolu

Commit <4f1492efb495> ("iommu/vt-d: Revert ATS timing change to fix boot failure") placed the enabling of ATS in the probe_finalize callback. This occurs after the default domain attachment, which is when the ATS cache tag is assigned. Consequently, the device TLB cache tag is missed when the domain is attached, leading to the device TLB not being invalidated in the iommu_unmap paths. Fix this by assigning the CACHE_TAG_DEVTLB cache tag when ATS is enabled. Fixes: 4f1492efb495 ("iommu/vt-d: Revert ATS timing change to fix boot failure") Cc: stable(a)vger.kernel.org Suggested-by: Kevin Tian <kevin.tian(a)intel.com> Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> Tested-by: Shuicheng Lin <shuicheng.lin(a)intel.com> --- drivers/iommu/intel/cache.c | 5 ++--- drivers/iommu/intel/iommu.c | 11 ++++++++++- drivers/iommu/intel/iommu.h | 2 ++ 3 files changed, 14 insertions(+), 4 deletions(-) Change log: v2: - The v1 solution has a flaw: ATS will never be enabled for drivers with driver_managed_dma enabled, as their devices are not expected to be automatically attached to the default domain. v1: https://lore.kernel.org/linux-iommu/20250620060802.3036137-1-baolu.lu@linux… diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index fc35cba59145..47692cbfaabd 100644 --- a/drivers/iommu/intel/cache.c +++ b/drivers/iommu/intel/cache.c @@ -40,9 +40,8 @@ static bool cache_tage_match(struct cache_tag *tag, u16 domain_id, } /* Assign a cache tag with specified type to domain. */ -static int cache_tag_assign(struct dmar_domain *domain, u16 did, - struct device *dev, ioasid_t pasid, - enum cache_tag_type type) +int cache_tag_assign(struct dmar_domain *domain, u16 did, struct device *dev, + ioasid_t pasid, enum cache_tag_type type) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7aa3932251b2..148b944143b8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3780,8 +3780,17 @@ static void intel_iommu_probe_finalize(struct device *dev) !pci_enable_pasid(to_pci_dev(dev), info->pasid_supported & ~1)) info->pasid_enabled = 1; - if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) + if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { iommu_enable_pci_ats(info); + /* Assign a DEVTLB cache tag to the default domain. */ + if (info->ats_enabled && info->domain) { + u16 did = domain_id_iommu(info->domain, iommu); + + if (cache_tag_assign(info->domain, did, dev, + IOMMU_NO_PASID, CACHE_TAG_DEVTLB)) + iommu_disable_pci_ats(info); + } + } iommu_enable_pci_pri(info); } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 3ddbcc603de2..2d1afab5eedc 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -1289,6 +1289,8 @@ struct cache_tag { unsigned int users; }; +int cache_tag_assign(struct dmar_domain *domain, u16 did, struct device *dev, + ioasid_t pasid, enum cache_tag_type type); int cache_tag_assign_domain(struct dmar_domain *domain, struct device *dev, ioasid_t pasid); void cache_tag_unassign_domain(struct dmar_domain *domain, -- 2.43.0

6 days, 15 hours

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror