igc: Reinstate IGC_REMOVED logic and implement it properly

The initially merged version of the igc driver code (via commit
146740f9abc4, "igc: Add support for PF") contained the following
IGC_REMOVED checks in the igc_rd32/wr32() MMIO accessors:

	u32 igc_rd32(struct igc_hw *hw, u32 reg)
	{
		u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
		u32 value = 0;

		if (IGC_REMOVED(hw_addr))
			return ~value;

		value = readl(&hw_addr[reg]);

		/* reads should not return all F's */
		if (!(~value) && (!reg || !(~readl(hw_addr))))
			hw->hw_addr = NULL;

		return value;
	}

And:

	#define wr32(reg, val) \
	do { \
		u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
		if (!IGC_REMOVED(hw_addr)) \
			writel((val), &hw_addr[(reg)]); \
	} while (0)

E.g. igb has similar checks in its MMIO accessors, and has a similar
macro E1000_REMOVED, which is implemented as follows:

	#define E1000_REMOVED(h) unlikely(!(h))

These checks serve to detect and take note of an 0xffffffff MMIO read
return from the device, which can be caused by a PCIe link flap or some
other kind of PCI bus error, and to avoid performing MMIO reads and
writes from that point onwards.

However, the IGC_REMOVED macro was not originally implemented:

	#ifndef IGC_REMOVED
	#define IGC_REMOVED(a) (0)
	#endif /* IGC_REMOVED */

This led to the IGC_REMOVED logic to be removed entirely in a
subsequent commit (commit 3c215fb18e70, "igc: remove IGC_REMOVED
function"), with the rationale that such checks matter only for
virtualization and that igc does not support virtualization -- but a
PCIe device can become detached even without virtualization being in
use, and without proper checks, a PCIe bus error affecting an igc
adapter will lead to various NULL pointer dereferences, as the first
access after the error will set hw->hw_addr to NULL, and subsequent
accesses will blindly dereference this now-NULL pointer.

This patch reinstates the IGC_REMOVED checks in igc_rd32/wr32(), and
implements IGC_REMOVED the way it is done for igb, by checking for the
unlikely() case of hw_addr being NULL.  This change prevents the oopses
seen when a PCIe link flap occurs on an igc adapter.

Fixes: 146740f9abc4 ("igc: Add support for PF")
Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ae17af4..a5ebee7 100644 (file)
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6171,6 +6171,9 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
        u8 __iomem *hw_addr = READ_ONCE(hw->hw_addr);
        u32 value = 0;
 
+       if (IGC_REMOVED(hw_addr))
+               return ~value;
+
        value = readl(&hw_addr[reg]);
 
        /* reads should not return all F's */

diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index e197a33..026c3b6 100644 (file)
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -306,7 +306,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg);
 #define wr32(reg, val) \
 do { \
        u8 __iomem *hw_addr = READ_ONCE((hw)->hw_addr); \
-       writel((val), &hw_addr[(reg)]); \
+       if (!IGC_REMOVED(hw_addr)) \
+               writel((val), &hw_addr[(reg)]); \
 } while (0)
 
 #define rd32(reg) (igc_rd32(hw, reg))
@@ -318,4 +319,6 @@ do { \
 
 #define array_rd32(reg, offset) (igc_rd32(hw, (reg) + ((offset) << 2)))
 
+#define IGC_REMOVED(h) unlikely(!(h))
+
 #endif