[Skiboot] [PATCH] hw/phb4: Tune GPU direct performance on witherspoon in PCI mode
Frederic Barrat
fbarrat at linux.ibm.com
Thu Mar 12 02:28:05 AEDT 2020
Good GPU direct performance on witherspoon, with a Mellanox adapter
on the shared slot, requires to reallocate some dma engines within
PEC2, "stealing" some from PHB4&5 and giving extras to PHB3. It's
currently done when using CAPI mode. But the same is true if the
adapter stays in PCI mode.
In preparation for upcoming versions of MOFED, which may not use CAPI
mode, this patch reallocates dma engines even in PCI mode for a series
of Mellanox adapters that can be used with GPU direct, on witherspoon
and on the shared slot only.
The loss of dma engines for PHB4&5 on witherspoon has not shown
problems in testing, as well as in current deployments where CAPI mode
is used.
Here is a comparison of the bandwidth numbers seen with the PHB in
PCI mode (no CAPI) with and without this patch:
# OSU MPI-CUDA Bi-Directional Bandwidth Test v5.6.1
# Send Buffer on DEVICE (D) and Receive Buffer on DEVICE (D)
# Size Bandwidth (MB/s) Bandwidth (MB/s)
# with patch without patch
1 1.29 1.48
2 2.66 3.04
4 5.34 5.93
8 10.68 11.86
16 21.39 23.71
32 42.78 49.15
64 85.43 97.67
128 170.82 196.64
256 385.47 383.02
512 774.68 755.54
1024 1535.14 1495.30
2048 2599.31 2561.60
4096 5192.31 5092.47
8192 9930.30 9566.90
16384 18189.81 16803.42
32768 24671.48 21383.57
65536 28977.71 24104.50
131072 31110.55 25858.95
262144 32180.64 26470.61
524288 32842.23 26961.93
1048576 33184.87 27217.38
2097152 33342.67 27338.08
Signed-off-by: Frederic Barrat <fbarrat at linux.ibm.com>
---
hw/phb4.c | 92 +++++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 76 insertions(+), 16 deletions(-)
diff --git a/hw/phb4.c b/hw/phb4.c
index ed7f4e5c..59c04b9f 100644
--- a/hw/phb4.c
+++ b/hw/phb4.c
@@ -809,20 +809,88 @@ static int64_t phb4_pcicfg_no_dstate(void *dev __unused,
return OPAL_PARTIAL;
}
-static void phb4_check_device_quirks(struct pci_device *dev)
+static void phb4_pec2_dma_engine_realloc(struct phb *phb)
{
+ struct phb4 *p = phb_to_phb4(phb);
+ uint64_t reg;
+
+ /*
+ * Allocate 16 extra dma read engines to stack 0, to boost dma
+ * performance for devices on stack 0 of PEC2, i.e PHB3. It
+ * comes at a price of reduced read engine allocation for
+ * devices on stack 1 and 2. The engine allocation becomes
+ * 48/8/8 instead of the default 32/16/16.
+ *
+ * The reallocation magic value should be 0xffff0000ff008000,
+ * but per the PCI designers, dma engine 32 (bit 0) has a
+ * quirk, and 0x7fff80007F008000 has the same effect (engine
+ * 32 goes to PHB4).
+ */
+ if (p->index != 3) /* shared slot on PEC2 */
+ return;
+
+ PHBINF(p, "Allocating extra dma read engines on PEC2 stack0\n");
+ reg = 0x7fff80007F008000ULL;
+ xscom_write(p->chip_id,
+ p->pci_xscom + XPEC_PCI_PRDSTKOVR, reg);
+ xscom_write(p->chip_id,
+ p->pe_xscom + XPEC_NEST_READ_STACK_OVERRIDE, reg);
+}
+
+struct pci_card_id {
+ uint16_t vendor;
+ uint16_t device;
+};
+
+#define VENDOR(vdid) ((vdid) & 0xffff)
+#define DEVICE(vdid) (((vdid) >> 16) & 0xffff)
+
+static struct pci_card_id dma_eng_realloc_whitelist[] = {
+ { 0x15b3, 0x1017 }, /* Mellanox ConnectX-5 */
+ { 0x15b3, 0x1019 }, /* Mellanox ConnectX-5 Ex */
+ { 0x15b3, 0x101b }, /* Mellanox ConnectX-6 */
+ { 0x15b3, 0x101d }, /* Mellanox ConnectX-6 Dx */
+ { 0x15b3, 0x101f }, /* Mellanox ConnectX-6 Lx */
+ { 0x15b3, 0x1021 }, /* Mellanox ConnectX-7 */
+};
+
+static bool phb4_adapter_need_dma_engine_realloc(uint32_t vdid)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dma_eng_realloc_whitelist); i++)
+ if (dma_eng_realloc_whitelist[i].vendor == VENDOR(vdid) &&
+ dma_eng_realloc_whitelist[i].device == DEVICE(vdid))
+ return true;
+ return false;
+}
+
+static void phb4_check_device_quirks(struct phb *phb, struct pci_device *dev)
+{
+ struct phb4 *p = phb_to_phb4(phb);
+
/* Some special adapter tweaks for devices directly under the PHB */
if (dev->primary_bus != 1)
return;
/* PM quirk */
- if (!pci_has_cap(dev, PCI_CFG_CAP_ID_PM, false))
- return;
+ if (pci_has_cap(dev, PCI_CFG_CAP_ID_PM, false)) {
+ pci_add_cfg_reg_filter(dev,
+ pci_cap(dev, PCI_CFG_CAP_ID_PM, false), 8,
+ PCI_REG_FLAG_WRITE,
+ phb4_pcicfg_no_dstate);
+ }
- pci_add_cfg_reg_filter(dev,
- pci_cap(dev, PCI_CFG_CAP_ID_PM, false), 8,
- PCI_REG_FLAG_WRITE,
- phb4_pcicfg_no_dstate);
+ /*
+ * PEC2 dma engine reallocation for Mellanox cards.
+ * Only on witherspoon when the card is on the shared slot.
+ * It improves GPU direct performance.
+ */
+ if (p->index == 3 && phb->slot->peer_slot &&
+ phb4_adapter_need_dma_engine_realloc(dev->vdid)) {
+ if (PCI_FUNC(dev->bdfn) == 0) // once per adapter
+ phb4_pec2_dma_engine_realloc(phb);
+ }
}
static int phb4_device_init(struct phb *phb, struct pci_device *dev,
@@ -831,7 +899,7 @@ static int phb4_device_init(struct phb *phb, struct pci_device *dev,
int ecap, aercap;
/* Setup special device quirks */
- phb4_check_device_quirks(dev);
+ phb4_check_device_quirks(phb, dev);
/* Common initialization for the device */
pci_device_init(phb, dev);
@@ -2581,11 +2649,6 @@ static bool phb4_chip_retry_workaround(void)
return false;
}
-struct pci_card_id {
- uint16_t vendor;
- uint16_t device;
-};
-
static struct pci_card_id retry_whitelist[] = {
{ 0x1000, 0x005d }, /* LSI Logic MegaRAID SAS-3 3108 */
{ 0x1000, 0x00c9 }, /* LSI MPT SAS-3 */
@@ -2602,9 +2665,6 @@ static struct pci_card_id retry_whitelist[] = {
{ 0x9005, 0x028d }, /* MicroSemi PM8069 */
};
-#define VENDOR(vdid) ((vdid) & 0xffff)
-#define DEVICE(vdid) (((vdid) >> 16) & 0xffff)
-
static bool phb4_adapter_in_whitelist(uint32_t vdid)
{
int i;
--
2.24.1
More information about the Skiboot
mailing list