linux-kernel - Re: [PATCH] powerpcs: perf: consolidate perf_callchain_user_64 and perf_callchain_user

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <8786906b-edd5-e4a3-8286-33a05f39668c@c-s.fr>
Date:   Tue, 7 Apr 2020 07:21:06 +0200
From:   Christophe Leroy <christophe.leroy@....fr>
To:     Michal Suchanek <msuchanek@...e.de>, linuxppc-dev@...ts.ozlabs.org,
        Nicholas Piggin <npiggin@...il.com>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        Michael Ellerman <mpe@...erman.id.au>,
        Benjamin Herrenschmidt <benh@...nel.crashing.org>,
        Paul Mackerras <paulus@...ba.org>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] powerpcs: perf: consolidate perf_callchain_user_64 and
 perf_callchain_user_32



Le 06/04/2020 à 23:00, Michal Suchanek a écrit :
> perf_callchain_user_64 and perf_callchain_user_32 are nearly identical.
> Consolidate into one function with thin wrappers.
> 
> Suggested-by: Nicholas Piggin <npiggin@...il.com>
> Signed-off-by: Michal Suchanek <msuchanek@...e.de>
> ---
>   arch/powerpc/perf/callchain.h    | 24 +++++++++++++++++++++++-
>   arch/powerpc/perf/callchain_32.c | 21 ++-------------------
>   arch/powerpc/perf/callchain_64.c | 14 ++++----------
>   3 files changed, 29 insertions(+), 30 deletions(-)
> 
> diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
> index 7a2cb9e1181a..7540bb71cb60 100644
> --- a/arch/powerpc/perf/callchain.h
> +++ b/arch/powerpc/perf/callchain.h
> @@ -2,7 +2,7 @@
>   #ifndef _POWERPC_PERF_CALLCHAIN_H
>   #define _POWERPC_PERF_CALLCHAIN_H
>   
> -int read_user_stack_slow(void __user *ptr, void *buf, int nb);
> +int read_user_stack_slow(const void __user *ptr, void *buf, int nb);

Does the constification of ptr has to be in this patch ?
Wouldn't it be better to have it as a separate patch ?

>   void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
>   			    struct pt_regs *regs);
>   void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> @@ -16,4 +16,26 @@ static inline bool invalid_user_sp(unsigned long sp)
>   	return (!sp || (sp & mask) || (sp > top));
>   }
>   
> +/*
> + * On 32-bit we just access the address and let hash_page create a
> + * HPTE if necessary, so there is no need to fall back to reading
> + * the page tables.  Since this is called at interrupt level,
> + * do_page_fault() won't treat a DSI as a page fault.
> + */
> +static inline int __read_user_stack(const void __user *ptr, void *ret,
> +				    size_t size)
> +{
> +	int rc;
> +
> +	if ((unsigned long)ptr > TASK_SIZE - size ||
> +			((unsigned long)ptr & (size - 1)))
> +		return -EFAULT;
> +	rc = probe_user_read(ret, ptr, size);
> +
> +	if (rc && IS_ENABLED(CONFIG_PPC64))

gcc is probably smart enough to deal with it efficiently, but it would
be more correct to test rc after checking CONFIG_PPC64.

> +		return read_user_stack_slow(ptr, ret, size);
> +
> +	return rc;
> +}
> +
>   #endif /* _POWERPC_PERF_CALLCHAIN_H */
> diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
> index 8aa951003141..1b4621f177e8 100644
> --- a/arch/powerpc/perf/callchain_32.c
> +++ b/arch/powerpc/perf/callchain_32.c
> @@ -31,26 +31,9 @@
>   
>   #endif /* CONFIG_PPC64 */
>   
> -/*
> - * On 32-bit we just access the address and let hash_page create a
> - * HPTE if necessary, so there is no need to fall back to reading
> - * the page tables.  Since this is called at interrupt level,
> - * do_page_fault() won't treat a DSI as a page fault.
> - */
> -static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
> +static int read_user_stack_32(const unsigned int __user *ptr, unsigned int *ret)
>   {
> -	int rc;
> -
> -	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
> -	    ((unsigned long)ptr & 3))
> -		return -EFAULT;
> -
> -	rc = probe_user_read(ret, ptr, sizeof(*ret));
> -
> -	if (IS_ENABLED(CONFIG_PPC64) && rc)
> -		return read_user_stack_slow(ptr, ret, 4);
> -
> -	return rc;
> +	return __read_user_stack(ptr, ret, sizeof(*ret);
>   }
>   
>   /*
> diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
> index df1ffd8b20f2..55bbc25a54ed 100644
> --- a/arch/powerpc/perf/callchain_64.c
> +++ b/arch/powerpc/perf/callchain_64.c
> @@ -24,7 +24,7 @@
>    * interrupt context, so if the access faults, we read the page tables
>    * to find which page (if any) is mapped and access it directly.
>    */
> -int read_user_stack_slow(void __user *ptr, void *buf, int nb)
> +int read_user_stack_slow(const void __user *ptr, void *buf, int nb)
>   {
>   	int ret = -EFAULT;
>   	pgd_t *pgdir;
> @@ -65,16 +65,10 @@ int read_user_stack_slow(void __user *ptr, void *buf, int nb)
>   	return ret;
>   }
>   
> -static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
> +static int read_user_stack_64(const unsigned long __user *ptr,
> +			      unsigned long *ret)
>   {
> -	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) ||
> -	    ((unsigned long)ptr & 7))
> -		return -EFAULT;
> -
> -	if (!probe_user_read(ret, ptr, sizeof(*ret)))
> -		return 0;
> -
> -	return read_user_stack_slow(ptr, ret, 8);
> +	return __read_user_stack(ptr, ret, sizeof(*ret));
>   }
>   
>   /*
> 

Christophe