[patch added to 3.12-stable] drm/radeon: narrow asic_init for virtualization

[patch added to 3.12-stable] drm/radeon: narrow asic_init for virtualization

[Jiri Slaby]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 884031f0aacf57dad1575f96714efc80de9b19cc upstream.

Only needed on CIK+ due to the way pci reset is handled
by the GPU.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/gpu/drm/radeon/radeon_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b05ce8ac9bf4..dbfd435485fe 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -570,8 +570,9 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
-	/* for pass through, always force asic_init */
-	if (radeon_device_is_virtual())
+	/* for pass through, always force asic_init for CI */
+	if (rdev->family >= CHIP_BONAIRE &&
+	    radeon_device_is_virtual())
 		return false;
 
 	/* required for EFI mode on macbook2,1 which uses an r5xx asic */
-- 
2.10.1

[patch added to 3.12-stable] drm/radeon/si/dpm: fix phase shedding setup

[Jiri Slaby]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 427920292b00474d978d632bc03a8e4e50029af3 upstream.

Used the wrong index to setup the phase shedding mask.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/gpu/drm/radeon/si_dpm.c       | 2 +-
 drivers/gpu/drm/radeon/sislands_smc.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index db9c7d26ed16..c1281fc39040 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3968,7 +3968,7 @@ static int si_populate_smc_voltage_tables(struct radeon_device *rdev,
 						      &rdev->pm.dpm.dyn_state.phase_shedding_limits_table)) {
 			si_populate_smc_voltage_table(rdev, &si_pi->vddc_phase_shed_table, table);
 
-			table->phaseMaskTable.lowMask[SISLANDS_SMC_VOLTAGEMASK_VDDC] =
+			table->phaseMaskTable.lowMask[SISLANDS_SMC_VOLTAGEMASK_VDDC_PHASE_SHEDDING] =
 				cpu_to_be32(si_pi->vddc_phase_shed_table.mask_low);
 
 			si_write_smc_soft_register(rdev, SI_SMC_SOFT_REGISTER_phase_shedding_delay,
diff --git a/drivers/gpu/drm/radeon/sislands_smc.h b/drivers/gpu/drm/radeon/sislands_smc.h
index 5578e9837026..0c3f65dfa743 100644
--- a/drivers/gpu/drm/radeon/sislands_smc.h
+++ b/drivers/gpu/drm/radeon/sislands_smc.h
@@ -194,6 +194,7 @@ typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE;
 #define SISLANDS_SMC_VOLTAGEMASK_VDDC  0
 #define SISLANDS_SMC_VOLTAGEMASK_MVDD  1
 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2
+#define SISLANDS_SMC_VOLTAGEMASK_VDDC_PHASE_SHEDDING 3
 #define SISLANDS_SMC_VOLTAGEMASK_MAX   4
 
 struct SISLANDS_SMC_VOLTAGEMASKTABLE
-- 
2.10.1

[patch added to 3.12-stable] drm/radeon: change vblank_time's calculation method to reduce computational error.

[Jiri Slaby]

From: Alex Deucher <alexander.deucher@amd.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 02cfb5fccb0f9f968f0e208d89d9769aa16267bc upstream.

Ported from Rex's amdgpu change.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/gpu/drm/radeon/r600_dpm.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 729ad831886f..d52ab40369b6 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -155,19 +155,20 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
 	struct drm_device *dev = rdev->ddev;
 	struct drm_crtc *crtc;
 	struct radeon_crtc *radeon_crtc;
-	u32 line_time_us, vblank_lines;
+	u32 vblank_in_pixels;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
 	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
 			radeon_crtc = to_radeon_crtc(crtc);
 			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-				line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
-					radeon_crtc->hw_mode.clock;
-				vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
-					radeon_crtc->hw_mode.crtc_vdisplay +
-					(radeon_crtc->v_border * 2);
-				vblank_time_us = vblank_lines * line_time_us;
+				vblank_in_pixels =
+					radeon_crtc->hw_mode.crtc_htotal *
+					(radeon_crtc->hw_mode.crtc_vblank_end -
+					 radeon_crtc->hw_mode.crtc_vdisplay +
+					 (radeon_crtc->v_border * 2));
+
+				vblank_time_us = vblank_in_pixels * 1000 / radeon_crtc->hw_mode.clock;
 				break;
 			}
 		}
-- 
2.10.1

[patch added to 3.12-stable] mm/hugetlb: fix memory offline with hugepage size > memory block size

[Jiri Slaby]

From: Gerald Schaefer <gerald.schaefer@de.ibm.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 2247bb335ab9c40058484cac36ea74ee652f3b7b upstream.

Patch series "mm/hugetlb: memory offline issues with hugepages", v4.

This addresses several issues with hugepages and memory offline.  While
the first patch fixes a panic, and is therefore rather important, the
last patch is just a performance optimization.

The second patch fixes a theoretical issue with reserved hugepages,
while still leaving some ugly usability issue, see description.

This patch (of 3):

dissolve_free_huge_pages() will either run into the VM_BUG_ON() or a
list corruption and addressing exception when trying to set a memory
block offline that is part (but not the first part) of a "gigantic"
hugetlb page with a size > memory block size.

When no other smaller hugetlb page sizes are present, the VM_BUG_ON()
will trigger directly.  In the other case we will run into an addressing
exception later, because dissolve_free_huge_page() will not work on the
head page of the compound hugetlb page which will result in a NULL
hstate from page_hstate().

To fix this, first remove the VM_BUG_ON() because it is wrong, and then
use the compound head page in dissolve_free_huge_page().  This means
that an unused pre-allocated gigantic page that has any part of itself
inside the memory block that is going offline will be dissolved
completely.  Losing an unused gigantic hugepage is preferable to failing
the memory offline, for example in the situation where a (possibly
faulty) memory DIMM needs to go offline.

Changes for v4.4 stable:
  - make it apply w/o commit c1470b33 "mm/hugetlb: fix incorrect
    hugepages count during mem hotplug"

Fixes: c8721bbb ("mm: memory-hotplug: enable memory hotplug to handle hugepage")
Link: http://lkml.kernel.org/r/20160926172811.94033-2-gerald.schaefer@de.ibm.com
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Rui Teng <rui.teng@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 mm/hugetlb.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a3a9676c65cf..2aaf11bdfb17 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -899,12 +899,13 @@ static void dissolve_free_huge_page(struct page *page)
 {
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
-		struct hstate *h = page_hstate(page);
-		int nid = page_to_nid(page);
-		list_del(&page->lru);
+		struct page *head = compound_head(page);
+		struct hstate *h = page_hstate(head);
+		int nid = page_to_nid(head);
+		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
-		update_and_free_page(h, page);
+		update_and_free_page(h, head);
 	}
 	spin_unlock(&hugetlb_lock);
 }
@@ -912,7 +913,8 @@ static void dissolve_free_huge_page(struct page *page)
 /*
  * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
  * make specified memory blocks removable from the system.
- * Note that start_pfn should aligned with (minimum) hugepage size.
+ * Note that this will dissolve a free gigantic hugepage completely, if any
+ * part of it lies within the given range.
  */
 void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -924,7 +926,6 @@ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	for_each_hstate(h)
 		if (order > huge_page_order(h))
 			order = huge_page_order(h);
-	VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << order));
 	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order)
 		dissolve_free_huge_page(pfn_to_page(pfn));
 }
-- 
2.10.1

[patch added to 3.12-stable] tunnels: Remove encapsulation offloads on decap.

[Jiri Slaby]

From: Jesse Gross <jesse@kernel.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit a09a4c8dd1ec7f830e1fb9e59eb72bddc965d168 upstream.

If a packet is either locally encapsulated or processed through GRO
it is marked with the offloads that it requires. However, when it is
decapsulated these tunnel offload indications are not removed. This
means that if we receive an encapsulated TCP packet, aggregate it with
GRO, decapsulate, and retransmit the resulting frame on a NIC that does
not support encapsulation, we won't be able to take advantage of hardware
offloads even though it is just a simple TCP packet at this point.

This fixes the problem by stripping off encapsulation offload indications
when packets are decapsulated.

The performance impacts of this bug are significant. In a test where a
Geneve encapsulated TCP stream is sent to a hypervisor, GRO'ed, decapsulated,
and bridged to a VM performance is improved by 60% (5Gbps->8Gbps) as a
result of avoiding unnecessary segmentation at the VM tap interface.

[js] no fou in 3.12 yet

Reported-by: Ramu Ramamurthy <sramamur@linux.vnet.ibm.com>
Fixes: 68c33163 ("v4 GRE: Add TCP segmentation offload for GRE")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
(backported from commit a09a4c8dd1ec7f830e1fb9e59eb72bddc965d168)
[adapt iptunnel_pull_header arguments, avoid 7f290c9]
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Juerg Haefliger <juerg.haefliger@hpe.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 include/net/ip_tunnels.h  | 16 ++++++++++++++++
 net/ipv4/ip_tunnel_core.c |  3 ++-
 net/ipv6/sit.c            |  5 +++--
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a0a4a100f5c9..df661ab4aa23 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -150,6 +150,22 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 		  __be32 src, __be32 dst, __u8 proto,
 		  __u8 tos, __u8 ttl, __be16 df, bool xnet);
 
+static inline int iptunnel_pull_offloads(struct sk_buff *skb)
+{
+	if (skb_is_gso(skb)) {
+		int err;
+
+		err = skb_unclone(skb, GFP_ATOMIC);
+		if (unlikely(err))
+			return err;
+		skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >>
+					       NETIF_F_GSO_SHIFT);
+	}
+
+	skb->encapsulation = 0;
+	return 0;
+}
+
 static inline void iptunnel_xmit_stats(int err,
 				       struct net_device_stats *err_stats,
 				       struct pcpu_tstats __percpu *stats)
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index ff3f84f38e6d..792dd807c635 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -114,6 +114,7 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
 	skb->pkt_type = PACKET_HOST;
-	return 0;
+
+	return iptunnel_pull_offloads(skb);
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a883776bcec8..a28d8d2bbd8f 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -647,14 +647,15 @@ static int ipip6_rcv(struct sk_buff *skb)
 		skb->mac_header = skb->network_header;
 		skb_reset_network_header(skb);
 		IPCB(skb)->flags = 0;
-		skb->protocol = htons(ETH_P_IPV6);
+		skb->dev = tunnel->dev;
 
 		if (packet_is_spoofed(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
 			goto out;
 		}
 
-		__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
+		if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6)))
+			goto out;
 
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
-- 
2.10.1