From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 39D3B3A9D84; Sat, 17 Oct 2026 16:34:05 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1792254846; cv=none; b=dMZEaNLEHScSDK09wlPeIywnyLGRuVW6reNhen3T8Ulwlo3S8ZBuPzWDmwgnJQIOH0jpZGRSyNXEQhgGOHVIdEZWyyE0X/HZdefYYsc1BJ3Vz/cFXuRdGCCRmQFm5v1C5C6cgZdlELh2AoccEjvsESoxpymCdlZvcjbYrxTXy6I= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1792254846; c=relaxed/simple; bh=lOQnWJ3n5oB49iLBSCyImTPJea0GgaB0E1XsbkniOqA=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=hhlFldiGFAZ9gkj/E9y14HAe6GtDO6/cPbhtuGvX1dczHugNpq18jm1maHhR1DiALR5djU1kpF6+FapKTPYspwNB+ueLb5b6XFNo0zX+KE2ZAsauWzSEuArOODBJB5LqAO45UdI99weH/8hSK1KT2hKeXJhTEsJoBk0K3Jx92Aw= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=MwZ/ytwr; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="MwZ/ytwr" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 8396B1F000C4; Sat, 17 Oct 2026 16:34:04 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linuxfoundation.org; s=korg; t=1792254845; bh=0b2O3XOFjLC5YFHZO5pds4+n/2s1CO1NX6SmR0RJLzc=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=MwZ/ytwrCcFLhmxjEWIRqWDl5MX43CPGzKxRdd5UP5cRTm3cvx02aHKRVUImKovg9 hGhVZlCg27cy6HxU/dK4qhgzZrv8Tttlt0462741aSZw+ThaqmCEN7FMLwX0bvkhbM quDDuiZXvHBlv0nrtxQqo0w7nUkZGGhaIsCAuiuc= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, James Zhu , Felix Kuehling , Alex Deucher , Sasha Levin Subject: [PATCH 6.12 581/869] drm/amdkfd: return migration pages from copy function Date: Sat, 17 Oct 2026 17:57:02 +0200 Message-ID: <20261017160051.956223765@linuxfoundation.org> X-Mailer: git-send-email 2.56.0 In-Reply-To: <20261017160036.979869304@linuxfoundation.org> References: <20261017160036.979869304@linuxfoundation.org> User-Agent: quilt/0.69 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: patches@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 6.12-stable review patch. If anyone has any objections, please let me know. ------------------ From: James Zhu [ Upstream commit bd6093e2f1601c0c83906f5115a2efb6b93050b1 ] dst MIGRATE_PFN_VALID bit and src MIGRATE_PFN_MIGRATE bit should always be set when migration success. cpage includes src MIGRATE_PFN_MIGRATE bit set and MIGRATE_PFN_VALID bit unset pages for both ram and vram when memory is only allocated without being populated before migration, those ram pages should be counted as migrate pages and those vram pages should not be counted as migrate pages. Here migration pages refer to how many vram pages involved. -v2 use dst to check MIGRATE_PFN_VALID bit (suggested-by Philip) -v3 add warning when vram pages is less than migration pages return migration pages directly from copy function -v4 correct comments and copy function return mpage (suggested-by Felix) Signed-off-by: James Zhu Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Stable-dep-of: 520e345ffe05 ("drm/amdkfd: Fix the case that vm range is hole at svm_migrate_copy_to_vram") Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 72 ++++++++++++------------ 1 file changed, 36 insertions(+), 36 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index c61b4ec4e141f..ee2adb41cb93f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -261,20 +261,7 @@ static void svm_migrate_put_sys_page(unsigned long addr) put_page(page); } -static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate) -{ - unsigned long upages = 0; - unsigned long i; - - for (i = 0; i < migrate->npages; i++) { - if (migrate->src[i] & MIGRATE_PFN_VALID && - !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) - upages++; - } - return upages; -} - -static int +static long svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, dma_addr_t *scratch, uint64_t ttm_res_offset) @@ -283,7 +270,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, struct amdgpu_device *adev = node->adev; struct device *dev = adev->dev; struct amdgpu_res_cursor cursor; - uint64_t mpages = 0; + long mpages; dma_addr_t *src; uint64_t *dst; uint64_t i, j; @@ -297,6 +284,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, amdgpu_res_first(prange->ttm_res, ttm_res_offset, npages << PAGE_SHIFT, &cursor); + mpages = 0; for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) { struct page *spage; @@ -357,13 +345,14 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, out_free_vram_pages: if (r) { pr_debug("failed %d to copy memory to vram\n", r); - for (i = 0; i < npages && mpages; i++) { + while (i-- && mpages) { if (!dst[i]) continue; svm_migrate_put_vram_page(adev, dst[i]); migrate->dst[i] = 0; mpages--; } + mpages = r; } #ifdef DEBUG_FORCE_MIXED_DOMAINS @@ -381,7 +370,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, } #endif - return r; + return mpages; } static long @@ -396,7 +385,7 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, struct dma_fence *mfence = NULL; struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; - unsigned long mpages = 0; + long mpages = 0; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -442,15 +431,17 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, else pr_debug("0x%lx pages collected\n", cpages); - r = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset); + mpages = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset); migrate_vma_pages(&migrate); svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); - mpages = cpages - svm_migrate_unsuccessful_pages(&migrate); - pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n", + if (mpages >= 0) + pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", mpages, cpages, migrate.npages); + else + r = mpages; kfd_smi_event_migration_end(node, p->lead_thread->pid, start >> PAGE_SHIFT, end >> PAGE_SHIFT, @@ -461,14 +452,13 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, out_free: kvfree(buf); out: - if (!r && mpages) { + if (!r && mpages > 0) { pdd = svm_range_get_pdd_by_node(prange, node); if (pdd) WRITE_ONCE(pdd->page_in, pdd->page_in + mpages); - - return mpages; } - return r; + + return r ? r : mpages; } /** @@ -579,7 +569,7 @@ static void svm_migrate_page_free(struct page *page) } } -static int +static long svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, dma_addr_t *scratch, uint64_t npages) @@ -588,6 +578,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t *src; dma_addr_t *dst; struct page *dpage; + long mpages; uint64_t i = 0, j; uint64_t addr; int r = 0; @@ -600,6 +591,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, src = (uint64_t *)(scratch + npages); dst = scratch; + mpages = 0; for (i = 0, j = 0; i < npages; i++, addr += PAGE_SIZE) { struct page *spage; @@ -648,6 +640,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); + mpages++; j++; } @@ -657,13 +650,17 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, out_oom: if (r) { pr_debug("failed %d copy to ram\n", r); - while (i--) { + while (i-- && mpages) { + if (!migrate->dst[i]) + continue; svm_migrate_put_sys_page(dst[i]); migrate->dst[i] = 0; + mpages--; } + mpages = r; } - return r; + return mpages; } /** @@ -690,9 +687,8 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; - unsigned long upages = npages; unsigned long cpages = 0; - unsigned long mpages = 0; + long mpages = 0; struct amdgpu_device *adev = node->adev; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; @@ -747,13 +743,15 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, else pr_debug("0x%lx pages collected\n", cpages); - r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, + mpages = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, scratch, npages); migrate_vma_pages(&migrate); - upages = svm_migrate_unsuccessful_pages(&migrate); - pr_debug("unsuccessful/cpages/npages 0x%lx/0x%lx/0x%lx\n", - upages, cpages, migrate.npages); + if (mpages >= 0) + pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n", + mpages, cpages, migrate.npages); + else + r = mpages; svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); @@ -767,8 +765,7 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, out_free: kvfree(buf); out: - if (!r && cpages) { - mpages = cpages - upages; + if (!r && mpages > 0) { pdd = svm_range_get_pdd_by_node(prange, node); if (pdd) WRITE_ONCE(pdd->page_out, pdd->page_out + mpages); @@ -851,6 +848,9 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, } if (r >= 0) { + WARN_ONCE(prange->vram_pages < mpages, + "Recorded vram pages(0x%llx) should not be less than migration pages(0x%lx).", + prange->vram_pages, mpages); prange->vram_pages -= mpages; /* prange does not have vram page set its actual_loc to system -- 2.53.0