Message-ID: <30d26b5c-7a5d-403e-a10b-381d09cae3b9@kernel.org>
Date: Tue, 16 Dec 2025 10:38:50 +0100
From: "Christophe Leroy (CS GROUP)" <chleroy@...nel.org>
To: Mukesh Kumar Chaurasiya <mkchauras@...ux.ibm.com>, maddy@...ux.ibm.com,
 mpe@...erman.id.au, npiggin@...il.com, oleg@...hat.com, kees@...nel.org,
 luto@...capital.net, wad@...omium.org, mchauras@...ux.ibm.com,
 thuth@...hat.com, sshegde@...ux.ibm.com, charlie@...osinc.com,
 macro@...am.me.uk, akpm@...ux-foundation.org, ldv@...ace.io, deller@....de,
 ankur.a.arora@...cle.com, segher@...nel.crashing.org, tglx@...utronix.de,
 thomas.weissschuh@...utronix.de, peterz@...radead.org,
 menglong8.dong@...il.com, bigeasy@...utronix.de, namcao@...utronix.de,
 kan.liang@...ux.intel.com, mingo@...nel.org, atrajeev@...ux.vnet.ibm.com,
 mark.barnett@....com, linuxppc-dev@...ts.ozlabs.org,
 linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 3/8] powerpc: introduce arch_enter_from_user_mode



Le 14/12/2025 à 14:02, Mukesh Kumar Chaurasiya a écrit :
> From: Mukesh Kumar Chaurasiya <mchauras@...ux.ibm.com>
> 
> Implement the arch_enter_from_user_mode() hook required by the generic
> entry/exit framework. This helper prepares the CPU state when entering
> the kernel from userspace, ensuring correct handling of KUAP/KUEP,
> transactional memory, and debug register state.
> 
> As part of this change, move booke_load_dbcr0() from interrupt.c to
> interrupt.h so it can be used by the new helper without introducing
> cross-file dependencies.
> 
> This patch contains no functional changes, it is purely preparatory for
> enabling the generic syscall and interrupt entry path on PowerPC.
> 
> Signed-off-by: Mukesh Kumar Chaurasiya <mchauras@...ux.ibm.com>
> ---
>   arch/powerpc/include/asm/entry-common.h | 97 +++++++++++++++++++++++++
>   arch/powerpc/include/asm/interrupt.h    | 22 ++++++
>   arch/powerpc/kernel/interrupt.c         | 22 ------
>   3 files changed, 119 insertions(+), 22 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/entry-common.h b/arch/powerpc/include/asm/entry-common.h
> index 3af16d821d07..093ece06ef79 100644
> --- a/arch/powerpc/include/asm/entry-common.h
> +++ b/arch/powerpc/include/asm/entry-common.h
> @@ -5,7 +5,104 @@
>   
>   #ifdef CONFIG_GENERIC_IRQ_ENTRY

This #ifdef is still unnecessary it seems.

>   
> +#include <asm/cputime.h>
> +#include <asm/interrupt.h>
>   #include <asm/stacktrace.h>
> +#include <asm/tm.h>
> +
> +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
> +{
> +	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
> +		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
> +
> +	BUG_ON(regs_is_unrecoverable(regs));
> +	BUG_ON(!user_mode(regs));
> +	BUG_ON(regs_irqs_disabled(regs));
> +
> +#ifdef CONFIG_PPC_PKEY
> +	if (mmu_has_feature(MMU_FTR_PKEY) && trap_is_syscall(regs)) {
> +		unsigned long amr, iamr;
> +		bool flush_needed = false;
> +		/*
> +		 * When entering from userspace we mostly have the AMR/IAMR
> +		 * different from kernel default values. Hence don't compare.
> +		 */
> +		amr = mfspr(SPRN_AMR);
> +		iamr = mfspr(SPRN_IAMR);
> +		regs->amr  = amr;
> +		regs->iamr = iamr;
> +		if (mmu_has_feature(MMU_FTR_KUAP)) {
> +			mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
> +			flush_needed = true;
> +		}
> +		if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
> +			mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
> +			flush_needed = true;
> +		}
> +		if (flush_needed)
> +			isync();
> +	} else
> +#endif
> +		kuap_assert_locked();

This construct is odd, can you do something about it ?

> +
> +	booke_restore_dbcr0();
> +
> +	account_cpu_user_entry();
> +
> +	account_stolen_time();
> +
> +	/*
> +	 * This is not required for the syscall exit path, but makes the
> +	 * stack frame look nicer. If this was initialised in the first stack
> +	 * frame, or if the unwinder was taught the first stack frame always
> +	 * returns to user with IRQS_ENABLED, this store could be avoided!
> +	 */
> +	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
> +
> +	/*
> +	 * If system call is called with TM active, set _TIF_RESTOREALL to
> +	 * prevent RFSCV being used to return to userspace, because POWER9
> +	 * TM implementation has problems with this instruction returning to
> +	 * transactional state. Final register values are not relevant because
> +	 * the transaction will be aborted upon return anyway. Or in the case
> +	 * of unsupported_scv SIGILL fault, the return state does not much
> +	 * matter because it's an edge case.
> +	 */
> +	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
> +	    unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
> +		set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
> +
> +	/*
> +	 * If the system call was made with a transaction active, doom it and
> +	 * return without performing the system call. Unless it was an
> +	 * unsupported scv vector, in which case it's treated like an illegal
> +	 * instruction.
> +	 */
> +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
> +	if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
> +	    !trap_is_unsupported_scv(regs)) {
> +		/* Enable TM in the kernel, and disable EE (for scv) */
> +		hard_irq_disable();
> +		mtmsr(mfmsr() | MSR_TM);
> +
> +		/* tabort, this dooms the transaction, nothing else */
> +		asm volatile(".long 0x7c00071d | ((%0) << 16)"
> +			     :: "r"(TM_CAUSE_SYSCALL | TM_CAUSE_PERSISTENT));
> +
> +		/*
> +		 * Userspace will never see the return value. Execution will
> +		 * resume after the tbegin. of the aborted transaction with the
> +		 * checkpointed register state. A context switch could occur
> +		 * or signal delivered to the process before resuming the
> +		 * doomed transaction context, but that should all be handled
> +		 * as expected.
> +		 */
> +		return;
> +	}
> +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
> +}
> +
> +#define arch_enter_from_user_mode arch_enter_from_user_mode
>   
>   #endif /* CONFIG_GENERIC_IRQ_ENTRY */
>   #endif /* _ASM_PPC_ENTRY_COMMON_H */
> diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
> index 0e2cddf8bd21..ca8a2cda9400 100644
> --- a/arch/powerpc/include/asm/interrupt.h
> +++ b/arch/powerpc/include/asm/interrupt.h
> @@ -138,6 +138,28 @@ static inline void nap_adjust_return(struct pt_regs *regs)
>   #endif
>   }
>   
> +static inline void booke_load_dbcr0(void)

It was a notrace function in interrupt.c
Should it be an __always_inline now ?

Christophe

> +{
> +#ifdef CONFIG_PPC_ADV_DEBUG_REGS
> +	unsigned long dbcr0 = current->thread.debug.dbcr0;
> +
> +	if (likely(!(dbcr0 & DBCR0_IDM)))
> +		return;
> +
> +	/*
> +	 * Check to see if the dbcr0 register is set up to debug.
> +	 * Use the internal debug mode bit to do this.
> +	 */
> +	mtmsr(mfmsr() & ~MSR_DE);
> +	if (IS_ENABLED(CONFIG_PPC32)) {
> +		isync();
> +		global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
> +	}
> +	mtspr(SPRN_DBCR0, dbcr0);
> +	mtspr(SPRN_DBSR, -1);
> +#endif
> +}
> +
>   static inline void booke_restore_dbcr0(void)
>   {
>   #ifdef CONFIG_PPC_ADV_DEBUG_REGS
> diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
> index 0d8fd47049a1..2a09ac5dabd6 100644
> --- a/arch/powerpc/kernel/interrupt.c
> +++ b/arch/powerpc/kernel/interrupt.c
> @@ -78,28 +78,6 @@ static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
>   	return true;
>   }
>   
> -static notrace void booke_load_dbcr0(void)
> -{
> -#ifdef CONFIG_PPC_ADV_DEBUG_REGS
> -	unsigned long dbcr0 = current->thread.debug.dbcr0;
> -
> -	if (likely(!(dbcr0 & DBCR0_IDM)))
> -		return;
> -
> -	/*
> -	 * Check to see if the dbcr0 register is set up to debug.
> -	 * Use the internal debug mode bit to do this.
> -	 */
> -	mtmsr(mfmsr() & ~MSR_DE);
> -	if (IS_ENABLED(CONFIG_PPC32)) {
> -		isync();
> -		global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
> -	}
> -	mtspr(SPRN_DBCR0, dbcr0);
> -	mtspr(SPRN_DBSR, -1);
> -#endif
> -}
> -
>   static notrace void check_return_regs_valid(struct pt_regs *regs)
>   {
>   #ifdef CONFIG_PPC_BOOK3S_64

Powered by blists - more mailing lists