5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Juergen Gross jgross@suse.com

commit afd30525a659ac0ae0904f0cb4a2ca75522c3123 upstream.

USERGS_SYSRET64 is used to return from a syscall via SYSRET, but a Xen PV guest will nevertheless use the IRET hypercall, as there is no sysret PV hypercall defined.

So instead of testing all the prerequisites for doing a sysret and then mangling the stack for Xen PV again for doing an iret just use the iret exit from the beginning.

This can easily be done via an ALTERNATIVE like it is done for the sysenter compat case already.

It should be noted that this drops the optimization in Xen for not restoring a few registers when returning to user mode, but it seems as if the saved instructions in the kernel more than compensate for this drop (a kernel build in a Xen PV guest was slightly faster with this patch applied).

While at it remove the stale sysret32 remnants.

[ pawan: Brad Spengler and Salvatore Bonaccorso carnil@debian.org reported a problem with the 5.10 backport commit edc702b4a820 ("x86/entry_64: Add VERW just before userspace transition").

When CONFIG_PARAVIRT_XXL=y, CLEAR_CPU_BUFFERS is not executed in syscall_return_via_sysret path as USERGS_SYSRET64 is runtime patched to:

.cpu_usergs_sysret64 = { 0x0f, 0x01, 0xf8, 0x48, 0x0f, 0x07 }, // swapgs; sysretq

which is missing CLEAR_CPU_BUFFERS. It turns out dropping USERGS_SYSRET64 simplifies the code, allowing CLEAR_CPU_BUFFERS to be explicitly added to syscall_return_via_sysret path. Below is with CONFIG_PARAVIRT_XXL=y and this patch applied:

syscall_return_via_sysret: ... <+342>: swapgs <+345>: xchg %ax,%ax <+347>: verw -0x1a2(%rip) <------ <+354>: sysretq ]

Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Link: https://lkml.kernel.org/r/20210120135555.32594-6-jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/entry/entry_64.S | 17 ++++++++--------- arch/x86/include/asm/irqflags.h | 7 ------- arch/x86/include/asm/paravirt.h | 5 ----- arch/x86/include/asm/paravirt_types.h | 8 -------- arch/x86/kernel/asm-offsets_64.c | 2 -- arch/x86/kernel/paravirt.c | 5 +---- arch/x86/kernel/paravirt_patch.c | 4 ---- arch/x86/xen/enlighten_pv.c | 1 - arch/x86/xen/xen-asm.S | 21 --------------------- arch/x86/xen/xen-ops.h | 2 -- 10 files changed, 9 insertions(+), 63 deletions(-)

--- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -46,14 +46,6 @@ .code64 .section .entry.text, "ax"

-#ifdef CONFIG_PARAVIRT_XXL -SYM_CODE_START(native_usergs_sysret64) - UNWIND_HINT_EMPTY - swapgs - sysretq -SYM_CODE_END(native_usergs_sysret64) -#endif /* CONFIG_PARAVIRT_XXL */ - /* * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. * @@ -128,7 +120,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_h * Try to use SYSRET instead of IRET if we're returning to * a completely clean 64-bit userspace context. If we're not, * go to the slow exit path. + * In the Xen PV case we must use iret anyway. */ + + ALTERNATIVE "", "jmp swapgs_restore_regs_and_return_to_usermode", \ + X86_FEATURE_XENPV + movq RCX(%rsp), %rcx movq RIP(%rsp), %r11

@@ -220,7 +217,9 @@ syscall_return_via_sysret:

popq %rdi popq %rsp - USERGS_SYSRET64 + swapgs + CLEAR_CPU_BUFFERS + sysretq SYM_CODE_END(entry_SYSCALL_64)

/* --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -132,13 +132,6 @@ static __always_inline unsigned long arc #endif

#define INTERRUPT_RETURN jmp native_iret -#define USERGS_SYSRET64 \ - swapgs; \ - CLEAR_CPU_BUFFERS; \ - sysretq; -#define USERGS_SYSRET32 \ - swapgs; \ - sysretl

#else #define INTERRUPT_RETURN iret --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -776,11 +776,6 @@ extern void default_banner(void);

#ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL -#define USERGS_SYSRET64 \ - PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \ - ANNOTATE_RETPOLINE_SAFE; \ - jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);) - #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \ --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -157,14 +157,6 @@ struct pv_cpu_ops {

u64 (*read_pmc)(int counter);

- /* - * Switch to usermode gs and return to 64-bit usermode using - * sysret. Only used in 64-bit kernels to return to 64-bit - * processes. Usermode register state, including %rsp, must - * already be restored. - */ - void (*usergs_sysret64)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,8 +13,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT #ifdef CONFIG_PARAVIRT_XXL - OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template, - cpu.usergs_sysret64); #ifdef CONFIG_DEBUG_ENTRY OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl); #endif --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -124,8 +124,7 @@ unsigned paravirt_patch_default(u8 type, else if (opfunc == _paravirt_ident_64) ret = paravirt_patch_ident_64(insn_buff, len);

- else if (type == PARAVIRT_PATCH(cpu.iret) || - type == PARAVIRT_PATCH(cpu.usergs_sysret64)) + else if (type == PARAVIRT_PATCH(cpu.iret)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len); #endif @@ -159,7 +158,6 @@ static u64 native_steal_clock(int cpu)

/* These are in entry.S */ extern void native_iret(void); -extern void native_usergs_sysret64(void);

static struct resource reserve_ioports = { .start = 0, @@ -299,7 +297,6 @@ struct paravirt_patch_template pv_ops =

.cpu.load_sp0 = native_load_sp0,

- .cpu.usergs_sysret64 = native_usergs_sysret64, .cpu.iret = native_iret,

#ifdef CONFIG_X86_IOPL_IOPERM --- a/arch/x86/kernel/paravirt_patch.c +++ b/arch/x86/kernel/paravirt_patch.c @@ -27,7 +27,6 @@ struct patch_xxl { const unsigned char mmu_write_cr3[3]; const unsigned char irq_restore_fl[2]; const unsigned char cpu_wbinvd[2]; - const unsigned char cpu_usergs_sysret64[6]; const unsigned char mov64[3]; };

@@ -40,8 +39,6 @@ static const struct patch_xxl patch_data .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 .irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd - .cpu_usergs_sysret64 = { 0x0f, 0x01, 0xf8, - 0x48, 0x0f, 0x07 }, // swapgs; sysretq .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax };

@@ -83,7 +80,6 @@ unsigned int native_patch(u8 type, void PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len); PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);

- PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len); PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len); #endif

--- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1059,7 +1059,6 @@ static const struct pv_cpu_ops xen_cpu_o .read_pmc = xen_read_pmc,

.iret = xen_iret, - .usergs_sysret64 = xen_sysret64,

.load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -220,27 +220,6 @@ SYM_CODE_START(xen_iret) jmp hypercall_iret SYM_CODE_END(xen_iret)

-SYM_CODE_START(xen_sysret64) - UNWIND_HINT_EMPTY - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back. - * - * tss.sp2 is scratch space. - */ - movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER_DS - pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - pushq %r11 - pushq $__USER_CS - pushq %rcx - - pushq $VGCF_in_syscall - jmp hypercall_iret -SYM_CODE_END(xen_sysret64) - /* * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode() --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -138,8 +138,6 @@ __visible unsigned long xen_read_cr2_dir

/* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -__visible void xen_sysret32(void); -__visible void xen_sysret64(void);

extern int xen_panic_handler_init(void);

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Doug Berger opendmb@gmail.com

commit d85cf67a339685beae1d0aee27b7f61da95455be upstream.

The EXT_RGMII_OOB_CTRL register can be written from different contexts. It is predominantly written from the adjust_link handler which is synchronized by the phydev->lock, but can also be written from a different context when configuring the mii in bcmgenet_mii_config().

The chances of contention are quite low, but it is conceivable that adjust_link could occur during resume when WoL is enabled so use the phydev->lock synchronizer in bcmgenet_mii_config() to be sure.

Fixes: afe3f907d20f ("net: bcmgenet: power on MII block for all MII modes") Cc: stable@vger.kernel.org Signed-off-by: Doug Berger opendmb@gmail.com Acked-by: Florian Fainelli florian.fainelli@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -264,6 +264,7 @@ int bcmgenet_mii_config(struct net_devic * block for the interface to work */ if (priv->ext_phy) { + mutex_lock(&phydev->lock); reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); reg &= ~ID_MODE_DIS; reg |= id_mode_dis; @@ -272,6 +273,7 @@ int bcmgenet_mii_config(struct net_devic else reg |= RGMII_MODE_EN; bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + mutex_unlock(&phydev->lock); }

if (init)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: liqiong liqiong@nfschina.com

commit eb0782bbdfd0d7c4786216659277c3fd585afc0e upstream.

The current IMA ruleset is identified by the variable "ima_rules" that default to "&ima_default_rules". When loading a custom policy for the first time, the variable is updated to "&ima_policy_rules" instead. That update isn't RCU-safe, and deadlocks are possible. Indeed, some functions like ima_match_policy() may loop indefinitely when traversing "ima_default_rules" with list_for_each_entry_rcu().

When iterating over the default ruleset back to head, if the list head is "ima_default_rules", and "ima_rules" have been updated to "&ima_policy_rules", the loop condition (&entry->list != ima_rules) stays always true, traversing won't terminate, causing a soft lockup and RCU stalls.

Introduce a temporary value for "ima_rules" when iterating over the ruleset to avoid the deadlocks.

Signed-off-by: liqiong liqiong@nfschina.com Reviewed-by: THOBY Simon Simon.THOBY@viveris.fr Fixes: 38d859f991f3 ("IMA: policy can now be updated multiple times") Reported-by: kernel test robot lkp@intel.com (Fix sparse: incompatible types in comparison expression.) Signed-off-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: GUO Zihua guozihua@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/integrity/ima/ima_policy.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-)

--- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -210,7 +210,7 @@ static struct ima_rule_entry *arch_polic static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); -static struct list_head *ima_rules = &ima_default_rules; +static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules);

static int ima_policy __initdata;

@@ -648,12 +648,14 @@ int ima_match_policy(struct inode *inode { struct ima_rule_entry *entry; int action = 0, actmask = flags | (flags << 1); + struct list_head *ima_rules_tmp;

if (template_desc) *template_desc = ima_template_desc_current();

rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) {

if (!(entry->action & actmask)) continue; @@ -701,11 +703,15 @@ int ima_match_policy(struct inode *inode void ima_update_policy_flag(void) { struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp;

- list_for_each_entry(entry, ima_rules, list) { + rcu_read_lock(); + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action & IMA_DO_MASK) ima_policy_flag |= entry->action; } + rcu_read_unlock();

ima_appraise |= (build_ima_appraise | temp_ima_appraise); if (!ima_appraise) @@ -898,10 +904,10 @@ void ima_update_policy(void)

list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu);

- if (ima_rules != policy) { + if (ima_rules != (struct list_head __rcu *)policy) { ima_policy_flag = 0; - ima_rules = policy;

+ rcu_assign_pointer(ima_rules, policy); /* * IMA architecture specific policy rules are specified * as strings and converted to an array of ima_entry_rules @@ -989,7 +995,7 @@ static int ima_lsm_rule_init(struct ima_ pr_warn("rule for LSM '%s' is undefined\n", entry->lsm[lsm_rule].args_p);

- if (ima_rules == &ima_default_rules) { + if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) { kfree(entry->lsm[lsm_rule].args_p); entry->lsm[lsm_rule].args_p = NULL; result = -EINVAL; @@ -1598,9 +1604,11 @@ void *ima_policy_start(struct seq_file * { loff_t l = *pos; struct ima_rule_entry *entry; + struct list_head *ima_rules_tmp;

rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (!l--) { rcu_read_unlock(); return entry; @@ -1619,7 +1627,8 @@ void *ima_policy_next(struct seq_file *m rcu_read_unlock(); (*pos)++;

- return (&entry->list == ima_rules) ? NULL : entry; + return (&entry->list == &ima_default_rules || + &entry->list == &ima_policy_rules) ? NULL : entry; }

void ima_policy_stop(struct seq_file *m, void *v) @@ -1823,6 +1832,7 @@ bool ima_appraise_signature(enum kernel_ struct ima_rule_entry *entry; bool found = false; enum ima_hooks func; + struct list_head *ima_rules_tmp;

if (id >= READING_MAX_ID) return false; @@ -1834,7 +1844,8 @@ bool ima_appraise_signature(enum kernel_ func = read_idmap[id] ?: FILE_CHECK;

rcu_read_lock(); - list_for_each_entry_rcu(entry, ima_rules, list) { + ima_rules_tmp = rcu_dereference(ima_rules); + list_for_each_entry_rcu(entry, ima_rules_tmp, list) { if (entry->action != APPRAISE) continue;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Sean Christopherson seanjc@google.com

commit 6c41468c7c12d74843bb414fc00307ea8a6318c3 upstream.

When injecting an exception into a vCPU in Real Mode, suppress the error code by clearing the flag that tracks whether the error code is valid, not by clearing the error code itself. The "typo" was introduced by recent fix for SVM's funky Paged Real Mode.

Opportunistically hoist the logic above the tracepoint so that the trace is coherent with respect to what is actually injected (this was also the behavior prior to the buggy commit).

Fixes: b97f07458373 ("KVM: x86: determine if an exception has an error code only when injecting it.") Cc: stable@vger.kernel.org Cc: Maxim Levitsky mlevitsk@redhat.com Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20230322143300.2209476-2-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com [nsaenz: backport to 5.10.y] Signed-off-by: Nicolas Saenz Julienne nsaenz@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Acked-by: Sean Christopherson seanjc@google.com --- arch/x86/kvm/x86.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8501,13 +8501,20 @@ static void update_cr8_intercept(struct

static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + /* + * Suppress the error code if the vCPU is in Real Mode, as Real Mode + * exceptions don't report error codes. The presence of an error code + * is carried with the exception and only stripped when the exception + * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do + * report an error code despite the CPU being in Real Mode. + */ + vcpu->arch.exception.has_error_code &= is_protmode(vcpu); + trace_kvm_inj_exception(vcpu->arch.exception.nr, vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code, vcpu->arch.exception.injected);

- if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) - vcpu->arch.exception.error_code = false; kvm_x86_ops.queue_exception(vcpu); }

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Paolo Abeni pabeni@redhat.com

commit fb7a0d334894206ae35f023a82cad5a290fd7386 upstream.

Christoph reported a splat hinting at a corrupted snd_una:

WARNING: CPU: 1 PID: 38 at net/mptcp/protocol.c:1005 __mptcp_clean_una+0x4b3/0x620 net/mptcp/protocol.c:1005 Modules linked in: CPU: 1 PID: 38 Comm: kworker/1:1 Not tainted 6.9.0-rc1-gbbeac67456c9 #59 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 Workqueue: events mptcp_worker RIP: 0010:__mptcp_clean_una+0x4b3/0x620 net/mptcp/protocol.c:1005 Code: be 06 01 00 00 bf 06 01 00 00 e8 a8 12 e7 fe e9 00 fe ff ff e8 8e 1a e7 fe 0f b7 ab 3e 02 00 00 e9 d3 fd ff ff e8 7d 1a e7 fe <0f> 0b 4c 8b bb e0 05 00 00 e9 74 fc ff ff e8 6a 1a e7 fe 0f 0b e9 RSP: 0018:ffffc9000013fd48 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff8881029bd280 RCX: ffffffff82382fe4 RDX: ffff8881003cbd00 RSI: ffffffff823833c3 RDI: 0000000000000001 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: fefefefefefefeff R12: ffff888138ba8000 R13: 0000000000000106 R14: ffff8881029bd908 R15: ffff888126560000 FS: 0000000000000000(0000) GS:ffff88813bd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f604a5dae38 CR3: 0000000101dac002 CR4: 0000000000170ef0 Call Trace: <TASK> __mptcp_clean_una_wakeup net/mptcp/protocol.c:1055 [inline] mptcp_clean_una_wakeup net/mptcp/protocol.c:1062 [inline] __mptcp_retrans+0x7f/0x7e0 net/mptcp/protocol.c:2615 mptcp_worker+0x434/0x740 net/mptcp/protocol.c:2767 process_one_work+0x1e0/0x560 kernel/workqueue.c:3254 process_scheduled_works kernel/workqueue.c:3335 [inline] worker_thread+0x3c7/0x640 kernel/workqueue.c:3416 kthread+0x121/0x170 kernel/kthread.c:388 ret_from_fork+0x44/0x50 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:243 </TASK>

When fallback to TCP happens early on a client socket, snd_nxt is not yet initialized and any incoming ack will copy such value into snd_una. If the mptcp worker (dumbly) tries mptcp-level re-injection after such ack, that would unconditionally trigger a send buffer cleanup using 'bad' snd_una values.

We could easily disable re-injection for fallback sockets, but such dumb behavior already helped catching a few subtle issues and a very low to zero impact in practice.

Instead address the issue always initializing snd_nxt (and write_seq, for consistency) at connect time.

Fixes: 8fd738049ac3 ("mptcp: fallback in case of simultaneous connect") Cc: stable@vger.kernel.org Reported-by: Christoph Paasch cpaasch@apple.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/485 Tested-by: Christoph Paasch cpaasch@apple.com Signed-off-by: Paolo Abeni pabeni@redhat.com Reviewed-by: Mat Martineau martineau@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Link: https://lore.kernel.org/r/20240429-upstream-net-20240429-mptcp-snd_nxt-init-... Signed-off-by: Jakub Kicinski kuba@kernel.org [ snd_nxt field is not available in v5.10.y: before, only write_seq was used, see commit eaa2ffabfc35 ("mptcp: introduce MPTCP snd_nxt") for more details about that. ] Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/protocol.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2645,6 +2645,8 @@ static int mptcp_stream_connect(struct s if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) mptcp_subflow_early_fallback(msk, subflow);

+ WRITE_ONCE(msk->write_seq, subflow->idsn); + do_connect: err = ssock->ops->connect(ssock, uaddr, addr_len, flags); sock->state = ssock->state;

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Srinivasan Shanmugam srinivasan.shanmugam@amd.com

commit b8d55a90fd55b767c25687747e2b24abd1ef8680 upstream.

Return invalid error code -EINVAL for invalid block id.

Fixes the below:

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:1183 amdgpu_ras_query_error_status_helper() error: we previously assumed 'info' could be null (see line 1176)

Suggested-by: Hawking Zhang Hawking.Zhang@amd.com Cc: Tao Zhou tao.zhou1@amd.com Cc: Hawking Zhang Hawking.Zhang@amd.com Cc: Christian König christian.koenig@amd.com Cc: Alex Deucher alexander.deucher@amd.com Signed-off-by: Srinivasan Shanmugam srinivasan.shanmugam@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com [Ajay: applied AMDGPU_RAS_BLOCK_COUNT condition to amdgpu_ras_error_query() as amdgpu_ras_query_error_status_helper() not present in v5.10, v5.4 amdgpu_ras_query_error_status_helper() was introduced in 8cc0f5669eb6] Signed-off-by: Ajay Kaher ajay.kaher@broadcom.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -765,6 +765,9 @@ int amdgpu_ras_error_query(struct amdgpu if (!obj) return -EINVAL;

+ if (!info || info->head.block == AMDGPU_RAS_BLOCK_COUNT) + return -EINVAL; + switch (info->head.block) { case AMDGPU_RAS_BLOCK__UMC: if (adev->umc.funcs->query_ras_error_count)

5.10-stable review patch. If anyone has any objections, please let me know.

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

From: Daniel Thompson daniel.thompson@linaro.org

commit b2aba15ad6f908d1a620fd97f6af5620c3639742 upstream.

Currently, when kdb is compiled with keyboard support, then we will use schedule_work() to provoke reset of the keyboard status. Unfortunately schedule_work() gets called from the kgdboc post-debug-exception handler. That risks deadlock since schedule_work() is not NMI-safe and, even on platforms where the NMI is not directly used for debugging, the debug trap can have NMI-like behaviour depending on where breakpoints are placed.

Fix this by using the irq work system, which is NMI-safe, to defer the call to schedule_work() to a point when it is safe to call.

Reported-by: Liuye liu.yeC@h3c.com Closes: https://lore.kernel.org/all/20240228025602.3087748-1-liu.yeC@h3c.com/ Cc: stable@vger.kernel.org Reviewed-by: Douglas Anderson dianders@chromium.org Acked-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Link: https://lore.kernel.org/r/20240424-kgdboc_fix_schedule_work-v2-1-50f5a490aec... Signed-off-by: Daniel Thompson daniel.thompson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/kgdboc.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-)

--- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -19,6 +19,7 @@ #include <linux/console.h> #include <linux/vt_kern.h> #include <linux/input.h> +#include <linux/irq_work.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/serial_core.h> @@ -48,6 +49,25 @@ static struct kgdb_io kgdboc_earlycon_i static int (*earlycon_orig_exit)(struct console *con); #endif /* IS_BUILTIN(CONFIG_KGDB_SERIAL_CONSOLE) */

+/* + * When we leave the debug trap handler we need to reset the keyboard status + * (since the original keyboard state gets partially clobbered by kdb use of + * the keyboard). + * + * The path to deliver the reset is somewhat circuitous. + * + * To deliver the reset we register an input handler, reset the keyboard and + * then deregister the input handler. However, to get this done right, we do + * have to carefully manage the calling context because we can only register + * input handlers from task context. + * + * In particular we need to trigger the action from the debug trap handler with + * all its NMI and/or NMI-like oddities. To solve this the kgdboc trap exit code + * (the "post_exception" callback) uses irq_work_queue(), which is NMI-safe, to + * schedule a callback from a hardirq context. From there we have to defer the + * work again, this time using schedule_work(), to get a callback using the + * system workqueue, which runs in task context. + */ #ifdef CONFIG_KDB_KEYBOARD static int kgdboc_reset_connect(struct input_handler *handler, struct input_dev *dev, @@ -99,10 +119,17 @@ static void kgdboc_restore_input_helper(

static DECLARE_WORK(kgdboc_restore_input_work, kgdboc_restore_input_helper);

+static void kgdboc_queue_restore_input_helper(struct irq_work *unused) +{ + schedule_work(&kgdboc_restore_input_work); +} + +static DEFINE_IRQ_WORK(kgdboc_restore_input_irq_work, kgdboc_queue_restore_input_helper); + static void kgdboc_restore_input(void) { if (likely(system_state == SYSTEM_RUNNING)) - schedule_work(&kgdboc_restore_input_work); + irq_work_queue(&kgdboc_restore_input_irq_work); }

static int kgdboc_register_kbd(char **cptr) @@ -133,6 +160,7 @@ static void kgdboc_unregister_kbd(void) i--; } } + irq_work_sync(&kgdboc_restore_input_irq_work); flush_work(&kgdboc_restore_input_work); } #else /* ! CONFIG_KDB_KEYBOARD */