From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e9.ny.us.ibm.com (e9.ny.us.ibm.com [32.97.182.139]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 2ACD11A003C for ; Fri, 15 Aug 2014 17:26:32 +1000 (EST) Received: from /spool/local by e9.ny.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 15 Aug 2014 03:26:28 -0400 Received: from b01cxnp22035.gho.pok.ibm.com (b01cxnp22035.gho.pok.ibm.com [9.57.198.25]) by d01dlp01.pok.ibm.com (Postfix) with ESMTP id 048F338C8039 for ; Fri, 15 Aug 2014 03:26:27 -0400 (EDT) Received: from d01av01.pok.ibm.com (d01av01.pok.ibm.com [9.56.224.215]) by b01cxnp22035.gho.pok.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id s7F7QQ5r7471496 for ; Fri, 15 Aug 2014 07:26:26 GMT Received: from d01av01.pok.ibm.com (localhost [127.0.0.1]) by d01av01.pok.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id s7F7QPWH026945 for ; Fri, 15 Aug 2014 03:26:26 -0400 From: Sukadev Bhattiprolu To: Arnaldo Carvalho de Melo , ak@linux.intel.com, Jiri Olsa , peterz@infradead.org, eranian@google.com Subject: [PATCH v2 01/14] powerpc/perf/hv-24x7: use kmem_cache instead of aligned stack allocations Date: Fri, 15 Aug 2014 00:26:10 -0700 Message-Id: <1408087583-32239-2-git-send-email-sukadev@linux.vnet.ibm.com> In-Reply-To: <1408087583-32239-1-git-send-email-sukadev@linux.vnet.ibm.com> References: <1408087583-32239-1-git-send-email-sukadev@linux.vnet.ibm.com> Cc: linuxppc-dev@lists.ozlabs.org, dev@codyps.com, linux-kernel@vger.kernel.org, Michael Ellerman , Anshuman Khandual List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , From: Cody P Schafer Ian pointed out the use of __aligned(4096) caused rather large stack consumption in single_24x7_request(), so use the kmem_cache hv_page_cache (which we've already got set up for other allocations) insead of allocating locally. CC: Haren Myneni CC: Cody P Schafer Reported-by: Ian Munsie Signed-off-by: Cody P Schafer Signed-off-by: Sukadev Bhattiprolu --- arch/powerpc/perf/hv-24x7.c | 52 ++++++++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 66d0f17..13f3131 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -294,7 +294,7 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, u16 lpar, u64 *res, bool success_expected) { - unsigned long ret; + unsigned long ret = -ENOMEM; /* * request_buffer and result_buffer are not required to be 4k aligned, @@ -304,7 +304,27 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, struct reqb { struct hv_24x7_request_buffer buf; struct hv_24x7_request req; - } __packed __aligned(4096) request_buffer = { + } __packed *request_buffer; + struct resb { + struct hv_24x7_data_result_buffer buf; + struct hv_24x7_result res; + struct hv_24x7_result_element elem; + __be64 result; + } __packed *result_buffer; + + BUILD_BUG_ON(sizeof(*request_buffer) > 4096); + BUILD_BUG_ON(sizeof(*result_buffer) > 4096); + + request_buffer = kmem_cache_alloc(hv_page_cache, GFP_USER); + + if (!request_buffer) + goto out_reqb; + + result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER); + if (!result_buffer) + goto out_resb; + + *request_buffer = (struct reqb) { .buf = { .interface_version = HV_24X7_IF_VERSION_CURRENT, .num_requests = 1, @@ -320,28 +340,30 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, } }; - struct resb { - struct hv_24x7_data_result_buffer buf; - struct hv_24x7_result res; - struct hv_24x7_result_element elem; - __be64 result; - } __packed __aligned(4096) result_buffer = {}; - ret = plpar_hcall_norets(H_GET_24X7_DATA, - virt_to_phys(&request_buffer), sizeof(request_buffer), - virt_to_phys(&result_buffer), sizeof(result_buffer)); + virt_to_phys(request_buffer), sizeof(*request_buffer), + virt_to_phys(result_buffer), sizeof(*result_buffer)); if (ret) { if (success_expected) pr_err_ratelimited("hcall failed: %d %#x %#x %d => 0x%lx (%ld) detail=0x%x failing ix=%x\n", domain, offset, ix, lpar, ret, ret, - result_buffer.buf.detailed_rc, - result_buffer.buf.failing_request_ix); - return ret; + result_buffer->buf.detailed_rc, + result_buffer->buf.failing_request_ix); + goto out_hcall; } - *res = be64_to_cpu(result_buffer.result); + *res = be64_to_cpu(result_buffer->result); + kfree(result_buffer); + kfree(request_buffer); + return ret; + +out_hcall: + kfree(result_buffer); +out_resb: + kfree(request_buffer); +out_reqb: return ret; } -- 1.8.3.1