Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: Bad rss-counter state from drm/ttm, drm/vmwgfx: Support huge TTM
 pagefaults
To:     "Alex Xu (Hello71)" <alex_y_xu@yahoo.ca>, linux-mm@kvack.org,
        dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org
Cc:     pv-drivers@vmware.com, linux-graphics-maintainer@vmware.com,
        Andrew Morton <akpm@linux-foundation.org>,
        Michal Hocko <mhocko@suse.com>,
        "Matthew Wilcox (Oracle)" <willy@infradead.org>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Ralph Campbell <rcampbell@nvidia.com>,
        =?UTF-8?B?SsOpcsO0bWUgR2xpc3Nl?= <jglisse@redhat.com>,
        =?UTF-8?Q?Christian_K=c3=b6nig?= <christian.koenig@amd.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Roland Scheidegger <sroland@vmware.com>
References: <1586138158.v5u7myprlp.none.ref@localhost>
 <1586138158.v5u7myprlp.none@localhost>
From:   =?UTF-8?Q?Thomas_Hellstr=c3=b6m_=28VMware=29?= 
        <thomas_os@shipmail.org>
Organization: VMware Inc.
Message-ID: <0b12b28c-5f42-b56b-ea79-6e3d1052b332@shipmail.org>
Date:   Mon, 6 Apr 2020 23:04:37 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
 Thunderbird/68.2.2
MIME-Version: 1.0
In-Reply-To: <1586138158.v5u7myprlp.none@localhost>
Content-Type: multipart/mixed;
 boundary="------------F0ED14F7B8417927F8CA67C2"
Content-Language: en-US
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This is a multi-part message in MIME format.
--------------F0ED14F7B8417927F8CA67C2
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit

Hi,

On 4/6/20 9:51 PM, Alex Xu (Hello71) wrote:
> Using 314b658 with amdgpu, starting sway and firefox causes "BUG: Bad
> rss-counter state" and "BUG: non-zero pgtables_bytes on freeing mm" to
> start filling dmesg, and then closing programs causes more BUGs and
> hangs, and then everything grinds to a halt (can't start more programs,
> can't even reboot through systemd).
>
> Using master and reverting that branch up to that point fixes the
> problem.
>
> I'm using a Ryzen 1600 and AMD Radeon RX 480 on an ASRock B450 Pro4
> board with IOMMU enabled.

If you could try the attached patch, that'd be great!

Thanks,

Thomas


--------------F0ED14F7B8417927F8CA67C2
Content-Type: text/x-patch; charset=UTF-8;
 name="0001-drm-ttm-Temporarily-disable-the-huge_fault-callback.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="0001-drm-ttm-Temporarily-disable-the-huge_fault-callback.pat";
 filename*1="ch"

From b630b9b4dcc1d01514d97a84cbb7f0cb85333154 Mon Sep 17 00:00:00 2001
From: "Thomas Hellstrom (VMware)" <thomas_os@shipmail.org>
Date: Mon, 6 Apr 2020 22:55:13 +0200
Subject: [PATCH] drm/ttm: Temporarily disable the huge_fault() callback

Signed-off-by: Thomas Hellstrom (VMware) <thomas_os@shipmail.org>
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 63 ---------------------------------
 1 file changed, 63 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 6ee3b96f0d13..0ad30b112982 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -442,66 +442,6 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(ttm_bo_vm_fault);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/**
- * ttm_pgprot_is_wrprotecting - Is a page protection value write-protecting?
- * @prot: The page protection value
- *
- * Return: true if @prot is write-protecting. false otherwise.
- */
-static bool ttm_pgprot_is_wrprotecting(pgprot_t prot)
-{
-	/*
-	 * This is meant to say "pgprot_wrprotect(prot) == prot" in a generic
-	 * way. Unfortunately there is no generic pgprot_wrprotect.
-	 */
-	return pte_val(pte_wrprotect(__pte(pgprot_val(prot)))) ==
-		pgprot_val(prot);
-}
-
-static vm_fault_t ttm_bo_vm_huge_fault(struct vm_fault *vmf,
-				       enum page_entry_size pe_size)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	pgprot_t prot;
-	struct ttm_buffer_object *bo = vma->vm_private_data;
-	vm_fault_t ret;
-	pgoff_t fault_page_size = 0;
-	bool write = vmf->flags & FAULT_FLAG_WRITE;
-
-	switch (pe_size) {
-	case PE_SIZE_PMD:
-		fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT;
-		break;
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-	case PE_SIZE_PUD:
-		fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT;
-		break;
-#endif
-	default:
-		WARN_ON_ONCE(1);
-		return VM_FAULT_FALLBACK;
-	}
-
-	/* Fallback on write dirty-tracking or COW */
-	if (write && ttm_pgprot_is_wrprotecting(vma->vm_page_prot))
-		return VM_FAULT_FALLBACK;
-
-	ret = ttm_bo_vm_reserve(bo, vmf);
-	if (ret)
-		return ret;
-
-	prot = vm_get_page_prot(vma->vm_flags);
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size);
-	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
-		return ret;
-
-	dma_resv_unlock(bo->base.resv);
-
-	return ret;
-}
-#endif
-
 void ttm_bo_vm_open(struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = vma->vm_private_data;
@@ -604,9 +544,6 @@ static const struct vm_operations_struct ttm_bo_vm_ops = {
 	.open = ttm_bo_vm_open,
 	.close = ttm_bo_vm_close,
 	.access = ttm_bo_vm_access,
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	.huge_fault = ttm_bo_vm_huge_fault,
-#endif
 };
 
 static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,
-- 
2.21.1


--------------F0ED14F7B8417927F8CA67C2--