drm/ttm: don't attempt to use hugepages if dma32 requested (v2)

The commit below introduced thp support for ttm allocations, however it didn't
take into account the case where dma32 was requested. Some drivers always request
dma32, and the bochs driver is one of those.

This fixes an oops:

[   30.108507] ------------[ cut here ]------------
[   30.108920] kernel BUG at ./include/linux/gfp.h:408!
[   30.109356] invalid opcode: 0000 [#1] SMP
[   30.109700] Modules linked in: fuse nf_conntrack_netbios_ns nf_conntrack_broadcast xt_CT ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack devlink ip_set nfnetlink ebtable_nat ebtable_broute bridge ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_raw ip6table_security iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack libcrc32c iptable_mangle iptable_raw iptable_security ebtable_filter ebtables ip6table_filter ip6_tables snd_hda_codec_generic kvm_intel kvm snd_hda_intel snd_hda_codec irqbypass ppdev snd_hda_core snd_hwdep snd_seq snd_seq_device snd_pcm bochs_drm ttm joydev drm_kms_helper virtio_balloon snd_timer snd parport_pc drm soundcore parport i2c_piix4 nls_utf8 isofs squashfs zstd_decompress xxhash 8021q garp mrp stp llc virtio_net
[   30.115605]  virtio_console virtio_scsi crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel serio_raw virtio_pci virtio_ring virtio ata_generic pata_acpi qemu_fw_cfg sunrpc scsi_transport_iscsi loop
[   30.117425] CPU: 0 PID: 1347 Comm: gnome-shell Not tainted 4.15.0-0.rc0.git6.1.fc28.x86_64 #1
[   30.118141] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014
[   30.118866] task: ffff923a77e03380 task.stack: ffffa78182228000
[   30.119366] RIP: 0010:__alloc_pages_nodemask+0x35e/0x430
[   30.119810] RSP: 0000:ffffa7818222bba8 EFLAGS: 00010202
[   30.120250] RAX: 0000000000000001 RBX: 00000000014382c6 RCX: 0000000000000006
[   30.120840] RDX: 0000000000000000 RSI: 0000000000000009 RDI: 0000000000000000
[   30.121443] RBP: ffff923a760d6000 R08: 0000000000000000 R09: 0000000000000006
[   30.122039] R10: 0000000000000040 R11: 0000000000000300 R12: ffff923a729273c0
[   30.122629] R13: 0000000000000000 R14: 0000000000000000 R15: ffff923a7483d400
[   30.123223] FS:  00007fe48da7dac0(0000) GS:ffff923a7cc00000(0000) knlGS:0000000000000000
[   30.123896] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   30.124373] CR2: 00007fe457b73000 CR3: 0000000078313000 CR4: 00000000000006f0
[   30.124968] Call Trace:
[   30.125186]  ttm_pool_populate+0x19b/0x400 [ttm]
[   30.125578]  ttm_bo_vm_fault+0x325/0x570 [ttm]
[   30.125964]  __do_fault+0x19/0x11e
[   30.126255]  __handle_mm_fault+0xcd3/0x1260
[   30.126609]  handle_mm_fault+0x14c/0x310
[   30.126947]  __do_page_fault+0x28c/0x530
[   30.127282]  do_page_fault+0x32/0x270
[   30.127593]  async_page_fault+0x22/0x30
[   30.127922] RIP: 0033:0x7fe48aae39a8
[   30.128225] RSP: 002b:00007ffc21c4d928 EFLAGS: 00010206
[   30.128664] RAX: 00007fe457b73000 RBX: 000055cd4c1041a0 RCX: 00007fe457b73040
[   30.129259] RDX: 0000000000300000 RSI: 0000000000000000 RDI: 00007fe457b73000
[   30.129855] RBP: 0000000000000300 R08: 000000000000000c R09: 0000000100000000
[   30.130457] R10: 0000000000000001 R11: 0000000000000246 R12: 000055cd4c1041a0
[   30.131054] R13: 000055cd4bdfe990 R14: 000055cd4c104110 R15: 0000000000000400
[   30.131648] Code: 11 01 00 0f 84 a9 00 00 00 65 ff 0d 6d cc dd 44 e9 0f ff ff ff 40 80 cd 80 e9 99 fe ff ff 48 89 c7 e8 e7 f6 01 00 e9 b7 fe ff ff <0f> 0b 0f ff e9 40 fd ff ff 65 48 8b 04 25 80 d5 00 00 8b 40 4c
[   30.133245] RIP: __alloc_pages_nodemask+0x35e/0x430 RSP: ffffa7818222bba8
[   30.133836] ---[ end trace d4f1deb60784f40a ]---

v2: handle free path as well.

Reported-by: Laura Abbott <labbott@redhat.com>
Reported-by: Adam Williamson <awilliam@redhat.com>
Fixes: 0284f1ead87463bc17cf5e81a24fc65c052486f3 (drm/ttm: add transparent huge page support for cached allocations v2)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 316f831ad5f044d99be8bcfc40db59da8e3fdc7a..b0551aa677b82fcb3ca5e26c72e6d612bee9447a 100644 (file)
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -744,12 +744,14 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
                        }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-                       for (j = 0; j < HPAGE_PMD_NR; ++j)
-                               if (p++ != pages[i + j])
-                                   break;
+                       if (!(flags & TTM_PAGE_FLAG_DMA32)) {
+                               for (j = 0; j < HPAGE_PMD_NR; ++j)
+                                       if (p++ != pages[i + j])
+                                           break;
 
-                       if (j == HPAGE_PMD_NR)
-                               order = HPAGE_PMD_ORDER;
+                               if (j == HPAGE_PMD_NR)
+                                       order = HPAGE_PMD_ORDER;
+                       }
 #endif
 
                        if (page_count(pages[i]) != 1)
@@ -865,20 +867,22 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
 
                i = 0;
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-               while (npages >= HPAGE_PMD_NR) {
-                       gfp_t huge_flags = gfp_flags;
+               if (!(gfp_flags & GFP_DMA32)) {
+                       while (npages >= HPAGE_PMD_NR) {
+                               gfp_t huge_flags = gfp_flags;
 
-                       huge_flags |= GFP_TRANSHUGE;
-                       huge_flags &= ~__GFP_MOVABLE;
-                       huge_flags &= ~__GFP_COMP;
-                       p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
-                       if (!p)
-                               break;
+                               huge_flags |= GFP_TRANSHUGE;
+                               huge_flags &= ~__GFP_MOVABLE;
+                               huge_flags &= ~__GFP_COMP;
+                               p = alloc_pages(huge_flags, HPAGE_PMD_ORDER);
+                               if (!p)
+                                       break;
 
-                       for (j = 0; j < HPAGE_PMD_NR; ++j)
-                               pages[i++] = p++;
+                               for (j = 0; j < HPAGE_PMD_NR; ++j)
+                                       pages[i++] = p++;
 
-                       npages -= HPAGE_PMD_NR;
+                               npages -= HPAGE_PMD_NR;
+                       }
                }
 #endif