iommu/amd: Fix performance counter initialization

Certain AMD platforms enable power gating feature for IOMMU PMC,
which prevents the IOMMU driver from updating the counter while
trying to validate the PMC functionality in the init_iommu_perf_ctr().
This results in disabling PMC support and the following error message:

    "AMD-Vi: Unable to read/write to IOMMU perf counter"

To workaround this issue, disable power gating temporarily by programming
the counter source to non-zero value while validating the counter,
and restore the prior state afterward.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Tested-by: Tj (Elloe Linux) <ml.linux@elloe.vision>
Link: https://lore.kernel.org/r/20210208122712.5048-1-suravee.suthikulpanit@amd.com
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201753
Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 5a6c511e91d1b40eab3501c68e6d42edb9f937ea..5a0762377de599701b2cc1913278e55d1fffbfb8 100644 (file)
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -12,6 +12,7 @@
 #include <linux/acpi.h>
 #include <linux/list.h>
 #include <linux/bitmap.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
@@ -256,6 +257,8 @@ static enum iommu_init_state init_state = IOMMU_START_STATE;
 static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
 static void init_device_table_dma(void);
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+                               u8 fxn, u64 *value, bool is_write);
 
 static bool amd_iommu_pre_enabled = true;
 
@@ -1697,13 +1700,11 @@ static int __init init_iommu_all(struct acpi_table_header *table)
        return 0;
 }
 
-static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
-                               u8 fxn, u64 *value, bool is_write);
-
-static void init_iommu_perf_ctr(struct amd_iommu *iommu)
+static void __init init_iommu_perf_ctr(struct amd_iommu *iommu)
 {
+       int retry;
        struct pci_dev *pdev = iommu->dev;
-       u64 val = 0xabcd, val2 = 0, save_reg = 0;
+       u64 val = 0xabcd, val2 = 0, save_reg, save_src;
 
        if (!iommu_feature(iommu, FEATURE_PC))
                return;
@@ -1711,17 +1712,39 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
        amd_iommu_pc_present = true;
 
        /* save the value to restore, if writable */
-       if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false))
+       if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false) ||
+           iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, false))
                goto pc_false;
 
-       /* Check if the performance counters can be written to */
-       if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
-           (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
-           (val != val2))
+       /*
+        * Disable power gating by programing the performance counter
+        * source to 20 (i.e. counts the reads and writes from/to IOMMU
+        * Reserved Register [MMIO Offset 1FF8h] that are ignored.),
+        * which never get incremented during this init phase.
+        * (Note: The event is also deprecated.)
+        */
+       val = 20;
+       if (iommu_pc_get_set_reg(iommu, 0, 0, 8, &val, true))
                goto pc_false;
 
+       /* Check if the performance counters can be written to */
+       val = 0xabcd;
+       for (retry = 5; retry; retry--) {
+               if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true) ||
+                   iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false) ||
+                   val2)
+                       break;
+
+               /* Wait about 20 msec for power gating to disable and retry. */
+               msleep(20);
+       }
+
        /* restore */
-       if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true))
+       if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true) ||
+           iommu_pc_get_set_reg(iommu, 0, 0, 8, &save_src, true))
+               goto pc_false;
+
+       if (val != val2)
                goto pc_false;
 
        pci_info(pdev, "IOMMU performance counters supported\n");